1
|
Turco F, Capiglioni M, Weng G, Slotboom J. TensorFit: A torch-based tool for ultrafast metabolite fitting of large MRSI data sets. Magn Reson Med 2024; 92:447-458. [PMID: 38469890 DOI: 10.1002/mrm.30084] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2023] [Revised: 02/21/2024] [Accepted: 02/26/2024] [Indexed: 03/13/2024]
Abstract
PURPOSE To introduce a tool (TensorFit) for ultrafast and robust metabolite fitting of MRSI data based on Torch's auto-differentiation and optimization framework. METHODS TensorFit was implemented in Python based on Torch's auto-differentiation to fit individual metabolites in MRS spectra. The underlying time domain and/or frequency domain fitting model is based on a linear combination of metabolite spectroscopic response. The computational time efficiency and accuracy of TensorFit were tested on simulated and in vivo MRS data and compared against TDFDFit and QUEST. RESULTS TensorFit demonstrates a significant improvement in computation speed, achieving a 165-times acceleration compared with TDFDFit and 115 times against QUEST. TensorFit showed smaller percentual errors on simulated data compared with TDFDFit and QUEST. When tested on in vivo data, it performed similarly to TDFDFit with a 2% better fit in terms of mean squared error while obtaining a 169-fold speedup. CONCLUSION TensorFit enables fast and robust metabolite fitting in large MRSI data sets compared with conventional metabolite fitting methods. This tool could boost the clinical applicability of large 3D MRSI by enabling the fitting of large MRSI data sets within computation times acceptable in a clinical environment.
Collapse
Affiliation(s)
- Federico Turco
- Support Center for Advanced Neuroimaging, Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland
- Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland
| | - Milena Capiglioni
- Support Center for Advanced Neuroimaging, Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland
- Graduate School for Cellular and Biomedical Sciences, University of Bern, Bern, Switzerland
| | - Guodong Weng
- Support Center for Advanced Neuroimaging, Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland
| | - Johannes Slotboom
- Support Center for Advanced Neuroimaging, Institute for Diagnostic and Interventional Neuroradiology, University of Bern, Bern, Switzerland
| |
Collapse
|
2
|
Kaiser L, Quach S, Zounek AJ, Wiestler B, Zatcepin A, Holzgreve A, Bollenbacher A, Bartos LM, Ruf VC, Böning G, Thon N, Herms J, Riemenschneider MJ, Stöcklein S, Brendel M, Rupprecht R, Tonn JC, Bartenstein P, von Baumgarten L, Ziegler S, Albert NL. Enhancing predictability of IDH mutation status in glioma patients at initial diagnosis: a comparative analysis of radiomics from MRI, [ 18F]FET PET, and TSPO PET. Eur J Nucl Med Mol Imaging 2024; 51:2371-2381. [PMID: 38396261 DOI: 10.1007/s00259-024-06654-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/13/2023] [Accepted: 02/10/2024] [Indexed: 02/25/2024]
Abstract
PURPOSE According to the World Health Organization classification for tumors of the central nervous system, mutation status of the isocitrate dehydrogenase (IDH) genes has become a major diagnostic discriminator for gliomas. Therefore, imaging-based prediction of IDH mutation status is of high interest for individual patient management. We compared and evaluated the diagnostic value of radiomics derived from dual positron emission tomography (PET) and magnetic resonance imaging (MRI) data to predict the IDH mutation status non-invasively. METHODS Eighty-seven glioma patients at initial diagnosis who underwent PET targeting the translocator protein (TSPO) using [18F]GE-180, dynamic amino acid PET using [18F]FET, and T1-/T2-weighted MRI scans were examined. In addition to calculating tumor-to-background ratio (TBR) images for all modalities, parametric images quantifying dynamic [18F]FET PET information were generated. Radiomic features were extracted from TBR and parametric images. The area under the receiver operating characteristic curve (AUC) was employed to assess the performance of logistic regression (LR) classifiers. To report robust estimates, nested cross-validation with five folds and 50 repeats was applied. RESULTS TBRGE-180 features extracted from TSPO-positive volumes had the highest predictive power among TBR images (AUC 0.88, with age as co-factor 0.94). Dynamic [18F]FET PET reached a similarly high performance (0.94, with age 0.96). The highest LR coefficients in multimodal analyses included TBRGE-180 features, parameters from kinetic and early static [18F]FET PET images, age, and the features from TBRT2 images such as the kurtosis (0.97). CONCLUSION The findings suggest that incorporating TBRGE-180 features along with kinetic information from dynamic [18F]FET PET, kurtosis from TBRT2, and age can yield very high predictability of IDH mutation status, thus potentially improving early patient management.
Collapse
Affiliation(s)
- Lena Kaiser
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany.
| | - S Quach
- Department of Neurosurgery, University Hospital, LMU Munich, 81377, Munich, Germany
| | - A J Zounek
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
| | - B Wiestler
- Department of Neuroradiology, Klinikum Rechts der Isar, Technical University of Munich, Munich, Germany
- Bavarian Cancer Research Center (BZKF), 91054, Erlangen, Germany
| | - A Zatcepin
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
- German Center for Neurodegenerative Diseases (DZNE), 81377, Munich, Germany
| | - A Holzgreve
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
| | - A Bollenbacher
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
| | - L M Bartos
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
| | - V C Ruf
- Center for Neuropathology and Prion Research, Faculty of Medicine, LMU Munich, Munich, Germany
| | - G Böning
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
| | - N Thon
- Department of Neurosurgery, University Hospital, LMU Munich, 81377, Munich, Germany
| | - J Herms
- Center for Neuropathology and Prion Research, Faculty of Medicine, LMU Munich, Munich, Germany
| | - M J Riemenschneider
- Department of Neuropathology, University Hospital Regensburg, 93053, Regensburg, Germany
- Bavarian Cancer Research Center (BZKF), 91054, Erlangen, Germany
| | - S Stöcklein
- Department of Radiology, University Hospital, LMU Munich, 81377, Munich, Germany
| | - M Brendel
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
- German Center for Neurodegenerative Diseases (DZNE), 81377, Munich, Germany
- Munich Cluster for Systems Neurology (SyNergy), 81377, Munich, Germany
| | - R Rupprecht
- Department of Psychiatry and Psychotherapy, University of Regensburg, 93053, Regensburg, Germany
| | - J C Tonn
- Department of Neurosurgery, University Hospital, LMU Munich, 81377, Munich, Germany
- Bavarian Cancer Research Center (BZKF), 91054, Erlangen, Germany
| | - P Bartenstein
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
- German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), 69120, Heidelberg, Germany
| | - L von Baumgarten
- Department of Neurosurgery, University Hospital, LMU Munich, 81377, Munich, Germany
- German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), 69120, Heidelberg, Germany
- Bavarian Cancer Research Center (BZKF), 91054, Erlangen, Germany
| | - S Ziegler
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
| | - N L Albert
- Department of Nuclear Medicine, University Hospital, LMU Munich, Marchioninistr. 15, 81377, Munich, Germany
- German Cancer Consortium (DKTK), Partner Site Munich, German Cancer Research Center (DKFZ), 69120, Heidelberg, Germany
- Bavarian Cancer Research Center (BZKF), 91054, Erlangen, Germany
| |
Collapse
|
3
|
Beser-Robles M, Castellá-Malonda J, Martínez-Gironés PM, Galiana-Bordera A, Ferrer-Lozano J, Ribas-Despuig G, Teruel-Coll R, Cerdá-Alberich L, Martí-Bonmatí L. Deep learning automatic semantic segmentation of glioblastoma multiforme regions on multimodal magnetic resonance images. Int J Comput Assist Radiol Surg 2024:10.1007/s11548-024-03205-z. [PMID: 38849632 DOI: 10.1007/s11548-024-03205-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2023] [Accepted: 05/30/2024] [Indexed: 06/09/2024]
Abstract
OBJECTIVES In patients having naïve glioblastoma multiforme (GBM), this study aims to assess the efficacy of Deep Learning algorithms in automating the segmentation of brain magnetic resonance (MR) images to accurately determine 3D masks for 4 distinct regions: enhanced tumor, peritumoral edema, non-enhanced/necrotic tumor, and total tumor. MATERIAL AND METHODS A 3D U-Net neural network algorithm was developed for semantic segmentation of GBM. The training dataset was manually delineated by a group of expert neuroradiologists on MR images from the Brain Tumor Segmentation Challenge 2021 (BraTS2021) image repository, as ground truth labels for diverse glioma (GBM and low-grade glioma) subregions across four MR sequences (T1w, T1w-contrast enhanced, T2w, and FLAIR) in 1251 patients. The in-house test was performed on 50 GBM patients from our cohort (PerProGlio project). By exploring various hyperparameters, the network's performance was optimized, and the most optimal parameter configuration was identified. The assessment of the optimized network's performance utilized Dice scores, precision, and sensitivity metrics. RESULTS Our adaptation of the 3D U-net with additional residual blocks demonstrated reliable performance on both the BraTS2021 dataset and the in-house PerProGlio cohort, employing only T1w-ce sequences for enhancement and non-enhanced/necrotic tumor models and T1w-ce + T2w + FLAIR for peritumoral edema and total tumor. The mean Dice scores (training and test) were 0.89 and 0.75; 0.75 and 0.64; 0.79 and 0.71; and 0.60 and 0.55, for total tumor, edema, enhanced tumor, and non-enhanced/necrotic tumor, respectively. CONCLUSIONS The results underscore the high precision with which our network can effectively segment GBM tumors and their distinct subregions. The level of accuracy achieved agrees with the coefficients recorded in previous GBM studies. In particular, our approach allows model specialization for each of the different tumor subregions employing only those MR sequences that provide value for segmentation.
Collapse
Affiliation(s)
- Maria Beser-Robles
- Biomedical Imaging Research Group (GIBI230), Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106, 46026, Valencia, Spain.
| | | | - Pedro Miguel Martínez-Gironés
- Biomedical Imaging Research Group (GIBI230), Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106, 46026, Valencia, Spain
| | - Adrián Galiana-Bordera
- Biomedical Imaging Research Group (GIBI230), Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106, 46026, Valencia, Spain
| | - Jaime Ferrer-Lozano
- Department of Pathology, Hospital Universitario y Politécnico de La Fe, Valencia, Spain
| | - Gloria Ribas-Despuig
- Biomedical Imaging Research Group (GIBI230), Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106, 46026, Valencia, Spain
| | - Regina Teruel-Coll
- Department of Radiology, Hospital Universitario y Politécnico de La Fe, Valencia, Spain
| | - Leonor Cerdá-Alberich
- Biomedical Imaging Research Group (GIBI230), Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106, 46026, Valencia, Spain
| | - Luis Martí-Bonmatí
- Biomedical Imaging Research Group (GIBI230), Instituto de Investigación Sanitaria La Fe, Avenida Fernando Abril Martorell, 106, 46026, Valencia, Spain
- Department of Radiology, Hospital Universitario y Politécnico de La Fe, Valencia, Spain
| |
Collapse
|
4
|
El Hachimy I, Kabelma D, Echcharef C, Hassani M, Benamar N, Hajji N. A comprehensive survey on the use of deep learning techniques in glioblastoma. Artif Intell Med 2024; 154:102902. [PMID: 38852314 DOI: 10.1016/j.artmed.2024.102902] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Revised: 04/28/2024] [Accepted: 06/02/2024] [Indexed: 06/11/2024]
Abstract
Glioblastoma, characterized as a grade 4 astrocytoma, stands out as the most aggressive brain tumor, often leading to dire outcomes. The challenge of treating glioblastoma is exacerbated by the convergence of genetic mutations and disruptions in gene expression, driven by alterations in epigenetic mechanisms. The integration of artificial intelligence, inclusive of machine learning algorithms, has emerged as an indispensable asset in medical analyses. AI is becoming a necessary tool in medicine and beyond. Current research on Glioblastoma predominantly revolves around non-omics data modalities, prominently including magnetic resonance imaging, computed tomography, and positron emission tomography. Nonetheless, the assimilation of omic data-encompassing gene expression through transcriptomics and epigenomics-offers pivotal insights into patients' conditions. These insights, reciprocally, hold significant value in refining diagnoses, guiding decision- making processes, and devising efficacious treatment strategies. This survey's core objective encompasses a comprehensive exploration of noteworthy applications of machine learning methodologies in the domain of glioblastoma, alongside closely associated research pursuits. The study accentuates the deployment of artificial intelligence techniques for both non-omics and omics data, encompassing a range of tasks. Furthermore, the survey underscores the intricate challenges posed by the inherent heterogeneity of Glioblastoma, delving into strategies aimed at addressing its multifaceted nature.
Collapse
Affiliation(s)
| | | | | | - Mohamed Hassani
- Cancer Division, Faculty of medicine, Department of Biomolecular Medicine, Imperial College, London, United Kingdom
| | - Nabil Benamar
- Moulay Ismail University of Meknes, Meknes, Morocco; Al Akhawayn University in Ifrane, Ifrane, Morocco.
| | - Nabil Hajji
- Cancer Division, Faculty of medicine, Department of Biomolecular Medicine, Imperial College, London, United Kingdom; Department of Medical Biochemistry, Molecular Biology and Immunology, School of Medicine, Virgen Macarena University Hospital, University of Seville, Seville, Spain
| |
Collapse
|
5
|
Batool A, Byun YC. Brain tumor detection with integrating traditional and computational intelligence approaches across diverse imaging modalities - Challenges and future directions. Comput Biol Med 2024; 175:108412. [PMID: 38691914 DOI: 10.1016/j.compbiomed.2024.108412] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Revised: 03/18/2024] [Accepted: 04/02/2024] [Indexed: 05/03/2024]
Abstract
Brain tumor segmentation and classification play a crucial role in the diagnosis and treatment planning of brain tumors. Accurate and efficient methods for identifying tumor regions and classifying different tumor types are essential for guiding medical interventions. This study comprehensively reviews brain tumor segmentation and classification techniques, exploring various approaches based on image processing, machine learning, and deep learning. Furthermore, our study aims to review existing methodologies, discuss their advantages and limitations, and highlight recent advancements in this field. The impact of existing segmentation and classification techniques for automated brain tumor detection is also critically examined using various open-source datasets of Magnetic Resonance Images (MRI) of different modalities. Moreover, our proposed study highlights the challenges related to segmentation and classification techniques and datasets having various MRI modalities to enable researchers to develop innovative and robust solutions for automated brain tumor detection. The results of this study contribute to the development of automated and robust solutions for analyzing brain tumors, ultimately aiding medical professionals in making informed decisions and providing better patient care.
Collapse
Affiliation(s)
- Amreen Batool
- Department of Electronic Engineering, Institute of Information Science & Technology, Jeju National University, Jeju, 63243, South Korea
| | - Yung-Cheol Byun
- Department of Computer Engineering, Major of Electronic Engineering, Jeju National University, Institute of Information Science Technology, Jeju, 63243, South Korea.
| |
Collapse
|
6
|
Pang JHW, Saffari SE, Lee GR, Yu WY, Lim CCT, Lim KC, Lee CC, Koh WY, Chia WTD, Chua KLM, Tham CK, Low YYS, Ng WH, Low CYD, Lin X. Tumour growth rate predicts overall survival in patients with recurrent WHO grade 4 glioma. BMC Med Imaging 2024; 24:125. [PMID: 38802734 PMCID: PMC11131225 DOI: 10.1186/s12880-024-01263-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/02/2022] [Accepted: 03/27/2024] [Indexed: 05/29/2024] Open
Abstract
PURPOSE Accurate prognostication may aid in the selection of patients who will benefit from surgery at recurrent WHO grade 4 glioma. This study aimed to evaluate the role of serial tumour volumetric measurements for prognostication at first tumour recurrence. METHODS We retrospectively analyzed patients with histologically-diagnosed WHO grade 4 glioma at initial and at first tumour recurrence at a tertiary hospital between May 2000 and September 2018. We performed auto-segmentation using ITK-SNAP software, followed by manual adjustment to measure serial contrast-enhanced T1W (CE-T1W) and T2W lesional volume changes on all MRI images performed between initial resection and repeat surgery. RESULTS Thirty patients met inclusion criteria; the median overall survival using Kaplan-Meier analysis from second surgery was 10.5 months. Seventeen (56.7%) patients received treatment post second surgery. Univariate cox regression analysis showed that greater rate of increase in lesional volume on CE-T1W (HR = 2.57; 95% CI [1.18, 5.57]; p = 0.02) in the last 2 MRI scans leading up to the second surgery was associated with a higher mortality likelihood. Patients with higher Karnofsky Performance Score (KPS) (HR = 0.97; 95% CI [0.95, 0.99]; p = 0.01) and who received further treatment following second surgery (HR = 0.43; 95% CI [0.19, 0.98]; p = 0.04) were shown to have a better survival. CONCLUSION Higher rate of CE-T1W lesional growth on the last 2 MRI images prior to surgery at recurrence was associated with increase mortality risk. A larger prospective study is required to determine and validate the threshold to distinguish rapidly progressive tumour with poor prognosis.
Collapse
Affiliation(s)
- Jeffer Hann Wei Pang
- Department of Neurology, National Neuroscience Institute, 11 Jalan Tan Tock Seng, 308433, Singapore, Singapore
| | - Seyed Ehsan Saffari
- Department of Neurology, National Neuroscience Institute, 11 Jalan Tan Tock Seng, 308433, Singapore, Singapore
- Centre of Quantitative Medicine, Duke-NUS Medical School, National University of Singapore, Singapore, Singapore
| | - Guan Rong Lee
- Department of Neurology, National Neuroscience Institute, 11 Jalan Tan Tock Seng, 308433, Singapore, Singapore
| | - Wai-Yung Yu
- Department of Neuroradiology, National Neuroscience Institute, Singapore, Singapore
| | | | - Kheng Choon Lim
- Department of Diagnostic Radiology, Singapore General Hospital, Singapore, Singapore
| | - Chia Ching Lee
- Division of Radiation Oncology, National University Cancer Institute, Singapore, Singapore
| | - Wee Yao Koh
- Division of Radiation Oncology, National University Cancer Institute, Singapore, Singapore
| | - Wei Tsau David Chia
- Division of Radiation Oncology, National University Cancer Institute, Singapore, Singapore
| | - Kevin Lee Min Chua
- Department of Radiation Oncology, National Cancer Centre Singapore, Singapore, Singapore
| | - Chee Kian Tham
- Department of Medical Oncology, National Cancer Centre Singapore, Singapore, Singapore
| | - Yin Yee Sharon Low
- Department of Neurosurgery, National Neuroscience Institute, Singapore, Singapore
| | - Wai Hoe Ng
- Department of Neurosurgery, National Neuroscience Institute, Singapore, Singapore
| | - Chyi Yeu David Low
- Department of Neurosurgery, National Neuroscience Institute, Singapore, Singapore
| | - Xuling Lin
- Department of Neurology, National Neuroscience Institute, 11 Jalan Tan Tock Seng, 308433, Singapore, Singapore.
| |
Collapse
|
7
|
Xie Y, Zaccagna F, Rundo L, Testa C, Zhu R, Tonon C, Lodi R, Manners DN. IMPA-Net: Interpretable Multi-Part Attention Network for Trustworthy Brain Tumor Classification from MRI. Diagnostics (Basel) 2024; 14:997. [PMID: 38786294 PMCID: PMC11119919 DOI: 10.3390/diagnostics14100997] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Revised: 05/08/2024] [Accepted: 05/09/2024] [Indexed: 05/25/2024] Open
Abstract
Deep learning (DL) networks have shown attractive performance in medical image processing tasks such as brain tumor classification. However, they are often criticized as mysterious "black boxes". The opaqueness of the model and the reasoning process make it difficult for health workers to decide whether to trust the prediction outcomes. In this study, we develop an interpretable multi-part attention network (IMPA-Net) for brain tumor classification to enhance the interpretability and trustworthiness of classification outcomes. The proposed model not only predicts the tumor grade but also provides a global explanation for the model interpretability and a local explanation as justification for the proffered prediction. Global explanation is represented as a group of feature patterns that the model learns to distinguish high-grade glioma (HGG) and low-grade glioma (LGG) classes. Local explanation interprets the reasoning process of an individual prediction by calculating the similarity between the prototypical parts of the image and a group of pre-learned task-related features. Experiments conducted on the BraTS2017 dataset demonstrate that IMPA-Net is a verifiable model for the classification task. A percentage of 86% of feature patterns were assessed by two radiologists to be valid for representing task-relevant medical features. The model shows a classification accuracy of 92.12%, of which 81.17% were evaluated as trustworthy based on local explanations. Our interpretable model is a trustworthy model that can be used for decision aids for glioma classification. Compared with black-box CNNs, it allows health workers and patients to understand the reasoning process and trust the prediction outcomes.
Collapse
Affiliation(s)
- Yuting Xie
- Department of Biomedical and Neuromotor Sciences, University of Bologna, 40126 Bologna, Italy; (Y.X.); (C.T.); (R.L.)
- Functional and Molecular Neuroimaging Unit, IRCCS Istituto delle Scienze Neurologiche di Bologna, Bellaria Hospital, 40139 Bologna, Italy
| | - Fulvio Zaccagna
- Department of Imaging, Cambridge University Hospitals NHS Foundation Trust, Cambridge Biomedical Campus, Cambridge CB2 0SL, UK;
- Department of Radiology, University of Cambridge, Cambridge CB2 0QQ, UK
| | - Leonardo Rundo
- Department of Information and Electrical Engineering and Applied Mathematics, University of Salerno, 84084 Fisciano, Italy;
| | - Claudia Testa
- INFN Bologna Division, Viale C. Berti Pichat, 6/2, 40127 Bologna, Italy
- Department of Physics and Astronomy, University of Bologna, 40127 Bologna, Italy
| | - Ruifeng Zhu
- Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 41125 Modena, Italy;
| | - Caterina Tonon
- Department of Biomedical and Neuromotor Sciences, University of Bologna, 40126 Bologna, Italy; (Y.X.); (C.T.); (R.L.)
- Functional and Molecular Neuroimaging Unit, IRCCS Istituto delle Scienze Neurologiche di Bologna, Bellaria Hospital, 40139 Bologna, Italy
| | - Raffaele Lodi
- Department of Biomedical and Neuromotor Sciences, University of Bologna, 40126 Bologna, Italy; (Y.X.); (C.T.); (R.L.)
- Functional and Molecular Neuroimaging Unit, IRCCS Istituto delle Scienze Neurologiche di Bologna, Bellaria Hospital, 40139 Bologna, Italy
| | - David Neil Manners
- Functional and Molecular Neuroimaging Unit, IRCCS Istituto delle Scienze Neurologiche di Bologna, Bellaria Hospital, 40139 Bologna, Italy
- Department for Life Quality Studies, University of Bologna, 40126 Bologna, Italy
| |
Collapse
|
8
|
Jacobs L, Mandija S, Liu H, van den Berg CAT, Sbrizzi A, Maspero M. Generalizable synthetic MRI with physics-informed convolutional networks. Med Phys 2024; 51:3348-3359. [PMID: 38063208 DOI: 10.1002/mp.16884] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/14/2023] [Revised: 11/20/2023] [Accepted: 11/28/2023] [Indexed: 05/08/2024] Open
Abstract
BACKGROUND Magnetic resonance imaging (MRI) provides state-of-the-art image quality for neuroimaging, consisting of multiple separately acquired contrasts. Synthetic MRI aims to accelerate examinations by synthesizing any desirable contrast from a single acquisition. PURPOSE We developed a physics-informed deep learning-based method to synthesize multiple brain MRI contrasts from a single 5-min acquisition and investigate its ability to generalize to arbitrary contrasts. METHODS A dataset of 55 subjects acquired with a clinical MRI protocol and a 5-min transient-state sequence was used. The model, based on a generative adversarial network, maps data acquired from the five-minute scan to "effective" quantitative parameter maps (q*-maps), feeding the generated PD, T1, and T2 maps into a signal model to synthesize four clinical contrasts (proton density-weighted, T1-weighted, T2-weighted, and T2-weighted fluid-attenuated inversion recovery), from which losses are computed. The synthetic contrasts are compared to an end-to-end deep learning-based method proposed by literature. The generalizability of the proposed method is investigated for five volunteers by synthesizing three contrasts unseen during training and comparing these to ground truth acquisitions via qualitative assessment and contrast-to-noise ratio (CNR) assessment. RESULTS The physics-informed method matched the quality of the end-to-end method for the four standard contrasts, with structural similarity metrics above0.75 ± 0.08 $0.75\pm 0.08$ ( ± $\pm$ std), peak signal-to-noise ratios above22.4 ± 1.9 $22.4\pm 1.9$ , representing a portion of compact lesions comparable to standard MRI. Additionally, the physics-informed method enabled contrast adjustment, and similar signal contrast and comparable CNRs to the ground truth acquisitions for three sequences unseen during model training. CONCLUSIONS The study demonstrated the feasibility of physics-informed, deep learning-based synthetic MRI to generate high-quality contrasts and generalize to contrasts beyond the training data. This technology has the potential to accelerate neuroimaging protocols.
Collapse
Affiliation(s)
- Luuk Jacobs
- Department of Radiotherapy, UMC Utrecht, Utrecht, The Netherlands
- Computational Imaging Group for MR Diagnostics and Therapy, UMC Utrecht, Utrecht, The Netherlands
| | - Stefano Mandija
- Department of Radiotherapy, UMC Utrecht, Utrecht, The Netherlands
- Computational Imaging Group for MR Diagnostics and Therapy, UMC Utrecht, Utrecht, The Netherlands
| | - Hongyan Liu
- Department of Radiotherapy, UMC Utrecht, Utrecht, The Netherlands
- Computational Imaging Group for MR Diagnostics and Therapy, UMC Utrecht, Utrecht, The Netherlands
| | - Cornelis A T van den Berg
- Department of Radiotherapy, UMC Utrecht, Utrecht, The Netherlands
- Computational Imaging Group for MR Diagnostics and Therapy, UMC Utrecht, Utrecht, The Netherlands
| | - Alessandro Sbrizzi
- Department of Radiotherapy, UMC Utrecht, Utrecht, The Netherlands
- Computational Imaging Group for MR Diagnostics and Therapy, UMC Utrecht, Utrecht, The Netherlands
| | - Matteo Maspero
- Department of Radiotherapy, UMC Utrecht, Utrecht, The Netherlands
- Computational Imaging Group for MR Diagnostics and Therapy, UMC Utrecht, Utrecht, The Netherlands
| |
Collapse
|
9
|
Wang M, Ma Y, Li L, Pan X, Wen Y, Qiu Y, Guo D, Zhu Y, Lian J, Tong D. Compressed Sensitivity Encoding Artificial Intelligence Accelerates Brain Metastasis Imaging by Optimizing Image Quality and Reducing Scan Time. AJNR Am J Neuroradiol 2024; 45:444-452. [PMID: 38485196 DOI: 10.3174/ajnr.a8161] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/11/2023] [Accepted: 12/25/2023] [Indexed: 04/10/2024]
Abstract
BACKGROUND AND PURPOSE Accelerating the image acquisition speed of MR imaging without compromising the image quality is challenging. This study aimed to evaluate the feasibility of contrast-enhanced (CE) 3D T1WI and CE 3D-FLAIR sequences reconstructed with compressed sensitivity encoding artificial intelligence (CS-AI) for detecting brain metastases (BM) and explore the optimal acceleration factor (AF) for clinical BM imaging. MATERIALS AND METHODS Fifty-one patients with cancer with suspected BM were included. Fifty participants underwent different customized CE 3D-T1WI or CE 3D-FLAIR sequence scans. Compressed SENSE encoding acceleration 6 (CS6), a commercially available standard sequence, was used as the reference standard. Quantitative and qualitative methods were used to evaluate image quality. The SNR and contrast-to-noise ratio (CNR) were calculated, and qualitative evaluations were independently conducted by 2 neuroradiologists. After exploring the optimal AF, sample images were obtained from 1 patient by using both optimized sequences. RESULTS Quantitatively, the CNR of the CS-AI protocol for CE 3D-T1WI and CE 3D-FLAIR sequences was superior to that of the CS protocol under the same AF (P < .05). Compared with reference CS6, the CS-AI groups had higher CNR values (all P < .05), with the CS-AI10 scan having the highest value. The SNR of the CS-AI group was better than that of the reference for both CE 3D-T1WI and CE 3D-FLAIR sequences (all P < .05). Qualitatively, the CS-AI protocol produced higher image quality scores than did the CS protocol with the same AF (all P < .05). In contrast to the reference CS6, the CS-AI group showed good image quality scores until an AF of up to 10 (all P < .05). The CS-AI10 scan provided the optimal images, improving the delineation of normal gray-white matter boundaries and lesion areas (P < .05). Compared with the reference, CS-AI10 showed reductions in scan time of 39.25% and 39.93% for CE 3D-T1WI and CE 3D-FLAIR sequences, respectively. CONCLUSIONS CE 3D-T1WI and CE 3D-FLAIR sequences reconstructed with CS-AI for the detection of BM may provide a more effective alternative reconstruction approach than CS. CS-AI10 is suitable for clinical applications, providing optimal image quality and a shortened scan time.
Collapse
Affiliation(s)
- Mengmeng Wang
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Yue Ma
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Linna Li
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Xingchen Pan
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Yafei Wen
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Ying Qiu
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Dandan Guo
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| | - Yi Zhu
- Philips Healthcare (Y.Z., J.L., D.T.), Beijing, China
| | - Jianxiu Lian
- Philips Healthcare (Y.Z., J.L., D.T.), Beijing, China
| | - Dan Tong
- From the Department of Radiology (M.W., Y.M., L.L., X.P., Y.W., Y.Q., D.G., D.T.), The First Hospital of Jilin University, Changchun, China
| |
Collapse
|
10
|
Khalighi S, Reddy K, Midya A, Pandav KB, Madabhushi A, Abedalthagafi M. Artificial intelligence in neuro-oncology: advances and challenges in brain tumor diagnosis, prognosis, and precision treatment. NPJ Precis Oncol 2024; 8:80. [PMID: 38553633 PMCID: PMC10980741 DOI: 10.1038/s41698-024-00575-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/19/2023] [Accepted: 03/13/2024] [Indexed: 04/02/2024] Open
Abstract
This review delves into the most recent advancements in applying artificial intelligence (AI) within neuro-oncology, specifically emphasizing work on gliomas, a class of brain tumors that represent a significant global health issue. AI has brought transformative innovations to brain tumor management, utilizing imaging, histopathological, and genomic tools for efficient detection, categorization, outcome prediction, and treatment planning. Assessing its influence across all facets of malignant brain tumor management- diagnosis, prognosis, and therapy- AI models outperform human evaluations in terms of accuracy and specificity. Their ability to discern molecular aspects from imaging may reduce reliance on invasive diagnostics and may accelerate the time to molecular diagnoses. The review covers AI techniques, from classical machine learning to deep learning, highlighting current applications and challenges. Promising directions for future research include multimodal data integration, generative AI, large medical language models, precise tumor delineation and characterization, and addressing racial and gender disparities. Adaptive personalized treatment strategies are also emphasized for optimizing clinical outcomes. Ethical, legal, and social implications are discussed, advocating for transparency and fairness in AI integration for neuro-oncology and providing a holistic understanding of its transformative impact on patient care.
Collapse
Affiliation(s)
- Sirvan Khalighi
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA
| | - Kartik Reddy
- Department of Radiology, Emory University, Atlanta, GA, USA
| | - Abhishek Midya
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA
| | - Krunal Balvantbhai Pandav
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA
| | - Anant Madabhushi
- Wallace H. Coulter Department of Biomedical Engineering, Georgia Institute of Technology and Emory University, Atlanta, GA, USA.
- Atlanta Veterans Administration Medical Center, Atlanta, GA, USA.
| | - Malak Abedalthagafi
- Department of Pathology and Laboratory Medicine, Emory University, Atlanta, GA, USA.
- The Cell and Molecular Biology Program, Winship Cancer Institute, Atlanta, GA, USA.
| |
Collapse
|
11
|
Ullah MS, Khan MA, Almujally NA, Alhaisoni M, Akram T, Shabaz M. BrainNet: a fusion assisted novel optimal framework of residual blocks and stacked autoencoders for multimodal brain tumor classification. Sci Rep 2024; 14:5895. [PMID: 38467755 PMCID: PMC10928185 DOI: 10.1038/s41598-024-56657-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Accepted: 03/08/2024] [Indexed: 03/13/2024] Open
Abstract
A significant issue in computer-aided diagnosis (CAD) for medical applications is brain tumor classification. Radiologists could reliably detect tumors using machine learning algorithms without extensive surgery. However, a few important challenges arise, such as (i) the selection of the most important deep learning architecture for classification (ii) an expert in the field who can assess the output of deep learning models. These difficulties motivate us to propose an efficient and accurate system based on deep learning and evolutionary optimization for the classification of four types of brain modalities (t1 tumor, t1ce tumor, t2 tumor, and flair tumor) on a large-scale MRI database. Thus, a CNN architecture is modified based on domain knowledge and connected with an evolutionary optimization algorithm to select hyperparameters. In parallel, a Stack Encoder-Decoder network is designed with ten convolutional layers. The features of both models are extracted and optimized using an improved version of Grey Wolf with updated criteria of the Jaya algorithm. The improved version speeds up the learning process and improves the accuracy. Finally, the selected features are fused using a novel parallel pooling approach that is classified using machine learning and neural networks. Two datasets, BraTS2020 and BraTS2021, have been employed for the experimental tasks and obtained an improved average accuracy of 98% and a maximum single-classifier accuracy of 99%. Comparison is also conducted with several classifiers, techniques, and neural nets; the proposed method achieved improved performance.
Collapse
Affiliation(s)
| | - Muhammad Attique Khan
- Department of Computer Science and Mathematics, Lebanese American University, Beirut, Lebanon
- Department of Computer Science, HITEC University, Taxila, 47080, Pakistan
| | - Nouf Abdullah Almujally
- Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, PO Box 84428, 11671, Riyadh, Saudi Arabia
| | - Majed Alhaisoni
- Computer Sciences Department, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia
| | - Tallha Akram
- Department of ECE, COMSATS University Islamabad, Wah Campus, Rawalpindi, Pakistan
| | - Mohammad Shabaz
- Model Institute of Engineering and Technology, Jammu, J&K, India.
| |
Collapse
|
12
|
Murugesan G, Yu FF, Achilleos M, DeBevits J, Nalawade S, Ganesh C, Wagner B, Madhuranthakam AJ, Maldjian JA. Synthesizing Contrast-Enhanced MR Images from Noncontrast MR Images Using Deep Learning. AJNR Am J Neuroradiol 2024; 45:312-319. [PMID: 38453408 DOI: 10.3174/ajnr.a8107] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/27/2022] [Accepted: 12/01/2023] [Indexed: 03/09/2024]
Abstract
BACKGROUND AND PURPOSE Recent developments in deep learning methods offer a potential solution to the need for alternative imaging methods due to concerns about the toxicity of gadolinium-based contrast agents. The purpose of the study was to synthesize virtual gadolinium contrast-enhanced T1-weighted MR images from noncontrast multiparametric MR images in patients with primary brain tumors by using deep learning. MATERIALS AND METHODS We trained and validated a deep learning network by using MR images from 335 subjects in the Brain Tumor Segmentation Challenge 2019 training data set. A held out set of 125 subjects from the Brain Tumor Segmentation Challenge 2019 validation data set was used to test the generalization of the model. A residual inception DenseNet network, called T1c-ET, was developed and trained to simultaneously synthesize virtual contrast-enhanced T1-weighted (vT1c) images and segment the enhancing portions of the tumor. Three expert neuroradiologists independently scored the synthesized vT1c images by using a 3-point Likert scale, evaluating image quality and contrast enhancement against ground truth T1c images (1 = poor, 2 = good, 3 = excellent). RESULTS The synthesized vT1c images achieved structural similarity index, peak signal-to-noise ratio, and normalized mean square error scores of 0.91, 64.35, and 0.03, respectively. There was moderate interobserver agreement between the 3 raters, regarding the algorithm's performance in predicting contrast enhancement, with a Fleiss kappa value of 0.61. Our model was able to accurately predict contrast enhancement in 88.8% of the cases (scores of 2 to 3 on the 3-point scale). CONCLUSIONS We developed a novel deep learning architecture to synthesize virtual postcontrast enhancement by using only conventional noncontrast brain MR images. Our results demonstrate the potential of deep learning methods to reduce the need for gadolinium contrast in the evaluation of primary brain tumors.
Collapse
Affiliation(s)
- Gowtham Murugesan
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Fang F Yu
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Michael Achilleos
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - John DeBevits
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Sahil Nalawade
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Chandan Ganesh
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | - Ben Wagner
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| | | | - Joseph A Maldjian
- Department of Radiology, University of Texas Southwestern Medical Center, Dallas, Texas
| |
Collapse
|
13
|
Saluja S, Trivedi MC, Saha A. Deep CNNs for glioma grading on conventional MRIs: Performance analysis, challenges, and future directions. MATHEMATICAL BIOSCIENCES AND ENGINEERING : MBE 2024; 21:5250-5282. [PMID: 38872535 DOI: 10.3934/mbe.2024232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/15/2024]
Abstract
The increasing global incidence of glioma tumors has raised significant healthcare concerns due to their high mortality rates. Traditionally, tumor diagnosis relies on visual analysis of medical imaging and invasive biopsies for precise grading. As an alternative, computer-assisted methods, particularly deep convolutional neural networks (DCNNs), have gained traction. This research paper explores the recent advancements in DCNNs for glioma grading using brain magnetic resonance images (MRIs) from 2015 to 2023. The study evaluated various DCNN architectures and their performance, revealing remarkable results with models such as hybrid and ensemble based DCNNs achieving accuracy levels of up to 98.91%. However, challenges persisted in the form of limited datasets, lack of external validation, and variations in grading formulations across diverse literature sources. Addressing these challenges through expanding datasets, conducting external validation, and standardizing grading formulations can enhance the performance and reliability of DCNNs in glioma grading, thereby advancing brain tumor classification and extending its applications to other neurological disorders.
Collapse
Affiliation(s)
- Sonam Saluja
- Department of Computer Science and Engineering, National Institute of Technology Agartala, Tripura 799046, India
| | - Munesh Chandra Trivedi
- Department of Computer Science and Engineering, National Institute of Technology Agartala, Tripura 799046, India
| | - Ashim Saha
- Department of Computer Science and Engineering, National Institute of Technology Agartala, Tripura 799046, India
| |
Collapse
|
14
|
Li D, Kirberger M, Qiao J, Gui Z, Xue S, Pu F, Jiang J, Xu Y, Tan S, Salarian M, Ibhagui O, Hekmatyar K, Yang JJ. Protein MRI Contrast Agents as an Effective Approach for Precision Molecular Imaging. Invest Radiol 2024; 59:170-186. [PMID: 38180819 DOI: 10.1097/rli.0000000000001057] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/07/2024]
Abstract
ABSTRACT Cancer and other acute and chronic diseases are results of perturbations of common molecular determinants in key biological and signaling processes. Imaging is critical for characterizing dynamic changes in tumors and metastases, the tumor microenvironment, tumor-stroma interactions, and drug targets, at multiscale levels. Magnetic resonance imaging (MRI) has emerged to be a primary imaging modality for both clinical and preclinical applications due to its advantages over other modalities, including sensitivity to soft tissues, nondepth limitations, and the use of nonionizing radiation. However, extending the application of MRI to achieve both qualitative and quantitative precise molecular imaging with the capability to quantify molecular biomarkers for early detection, staging, and monitoring therapeutic treatment requires the capacity to overcome several major challenges including the trade-off between metal-binding affinity and relaxivity, which is an issue frequently associated with small chelator contrast agents. In this review, we will introduce the criteria of ideal contrast agents for precision molecular imaging and discuss the relaxivity of current contrast agents with defined first shell coordination water molecules. We will then report our advances in creating a new class of protein-targeted MRI contrast agents (ProCAs) with contributions to relaxivity largely derived from the secondary sphere and correlation time. We will summarize our rationale, design strategy, and approaches to the development and optimization of our pioneering ProCAs with desired high relaxivity, metal stability, and molecular biomarker-targeting capability, for precision MRI. From first generation (ProCA1) to third generation (ProCA32), we have achieved dual high r1 and r2 values that are 6- to 10-fold higher than clinically approved contrast agents at magnetic fields of 1.5 T, and their relaxivity values at high field are also significantly higher, which enables high resolution during small animal imaging. Further engineering of multiple targeting moieties enables ProCA32 agents that have strong biomarker-binding affinity and specificity for an array of key molecular biomarkers associated with various chronic diseases, while maintaining relaxation and exceptional metal-binding and selectivity, serum stability, and resistance to transmetallation, which are critical in mitigating risks associated with metal toxicity. Our leading product ProCA32.collagen has enabled the first early detection of liver metastasis from multiple cancers at early stages by mapping the tumor environment and early stage of fibrosis from liver and lung in vivo, with strong translational potential to extend to precision MRI for preclinical and clinical applications for precision diagnosis and treatment.
Collapse
Affiliation(s)
- Dongjun Li
- From the Center for Diagnostics and Therapeutics, Advanced Translational Imaging Facility, Department of Chemistry, Georgia State University, Atlanta, GA (D.L., M.K., J.Q., Z.G., S.X., P.F., J.J., S.T., M.S., O.I., K.H., J.J.Y.); and InLighta BioSciences, LLC, Marietta, GA (Y.X., J.J.Y)
| | | | | | | | | | | | | | | | | | | | | | | | | |
Collapse
|
15
|
Dhabalia R, Kashikar SV, Parihar PS, Mishra GV. Unveiling the Intricacies: A Comprehensive Review of Magnetic Resonance Imaging (MRI) Assessment of T2-Weighted Hyperintensities in the Neuroimaging Landscape. Cureus 2024; 16:e54808. [PMID: 38529430 PMCID: PMC10961652 DOI: 10.7759/cureus.54808] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2023] [Accepted: 02/24/2024] [Indexed: 03/27/2024] Open
Abstract
T2-weighted hyperintensities in neuroimaging represent areas of heightened signal intensity on magnetic resonance imaging (MRI) scans, holding crucial importance in neuroimaging. This comprehensive review explores the T2-weighted hyperintensities, providing insights into their definition, characteristics, clinical relevance, and underlying causes. It highlights the significance of these hyperintensities as sensitive markers for neurological disorders, including multiple sclerosis, vascular dementia, and brain tumors. The review also delves into advanced neuroimaging techniques, such as susceptibility-weighted and diffusion tensor imaging, and the application of artificial intelligence and machine learning in hyperintensities analysis. Furthermore, it outlines the challenges and pitfalls associated with their assessment and emphasizes the importance of standardized protocols and a multidisciplinary approach. The review discusses future directions for research and clinical practice, including the development of biomarkers, personalized medicine, and enhanced imaging techniques. Ultimately, the review underscores the profound impact of T2-weighted hyperintensities in shaping the landscape of neurological diagnosis, prognosis, and treatment, contributing to a deeper understanding of complex neurological conditions and guiding more informed and effective patient care.
Collapse
Affiliation(s)
- Rishabh Dhabalia
- Radiodiagnosis, Jawaharlal Nehru Medical College, Datta Meghe Institute of Higher Education & Research, Wardha, IND
| | - Shivali V Kashikar
- Radiodiagnosis, Jawaharlal Nehru Medical College, Datta Meghe Institute of Higher Education & Research, Wardha, IND
| | - Pratap S Parihar
- Radiodiagnosis, Jawaharlal Nehru Medical College, Datta Meghe Institute of Higher Education & Research, Wardha, IND
| | - Gaurav V Mishra
- Radiodiagnosis, Jawaharlal Nehru Medical College, Datta Meghe Institute of Higher Education & Research, Wardha, IND
| |
Collapse
|
16
|
Aumiller M, Arazar A, Sroka R, Dietrich O, Rühm A. Investigations on correlations between changes of optical tissue properties and NMR relaxation times. Photodiagnosis Photodyn Ther 2024; 45:103968. [PMID: 38215958 DOI: 10.1016/j.pdpdt.2024.103968] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 01/03/2024] [Accepted: 01/09/2024] [Indexed: 01/14/2024]
Abstract
BACKGROUND Accurate light dosimetry is a complex remaining challenge in interstitial photodynamic therapy (iPDT) for malignant gliomas. The light dosimetry should ideally be based on the tissue morphology and the individual optical tissue properties of each tissue type in the target region. First investigations are reported on using NMR information to estimate changes of individual optical tissue properties. METHODS Porcine brain tissue and optical tissue phantoms were investigated. To the porcine brain, supplements were added to simulate an edema or high blood content. The tissue phantoms were based on agar, Lipoveneous, ink, blood and gadobutrol (Gd-based MRI contrast agent). The concentrations of phantom ingredients and tissue additives are varied to compare concentration-dependent effects on optical and NMR properties. A 3-tesla whole-body MRI system was used to determine T1 and T2 relaxation times. Optical tissue properties, i.e., the spectrally resolved absorption and reduced scattering coefficient, were obtained using a single integrating sphere setup. The observed changes of NMR and optical properties were compared to each other. RESULTS By adjusting the NMR relaxation times and optical tissue properties of the tissue phantoms to literature values, recipes for human brain tumor, white matter and grey matter tissue phantoms were obtained that mimic these brain tissues simultaneously in both properties. For porcine brain tissue, it was observed that with increasing water concentration in the tissue, both NMR-relaxation times increased, while µa decreased and µs' increased at 635 nm. The addition of blood to porcine brain samples showed a constant T1, while T2 shortened and the absorption coefficient at 635 nm increased. CONCLUSIONS In this investigation, by changing sample contents, notable changes of both NMR relaxation times and optical tissue properties have been observed and their relations examined. The developed dual NMR/optical tissue phantoms can be used in iPDT research, clinical training and demonstrations.
Collapse
Affiliation(s)
- Maximilian Aumiller
- Laser-Forschungslabor, LIFE Center, LMU University Hospital, LMU Munich, Planegg 82152, Germany; Department of Urology, LMU University Hospital, LMU Munich, Munich 81377, Germany.
| | - Asmerom Arazar
- Laser-Forschungslabor, LIFE Center, LMU University Hospital, LMU Munich, Planegg 82152, Germany
| | - Ronald Sroka
- Laser-Forschungslabor, LIFE Center, LMU University Hospital, LMU Munich, Planegg 82152, Germany; Department of Urology, LMU University Hospital, LMU Munich, Munich 81377, Germany
| | - Olaf Dietrich
- Department of Radiology, LMU University Hospital, LMU Munich, Munich 81377, Germany
| | - Adrian Rühm
- Laser-Forschungslabor, LIFE Center, LMU University Hospital, LMU Munich, Planegg 82152, Germany; Department of Urology, LMU University Hospital, LMU Munich, Munich 81377, Germany
| |
Collapse
|
17
|
Raut P, Baldini G, Schöneck M, Caldeira L. Using a generative adversarial network to generate synthetic MRI images for multi-class automatic segmentation of brain tumors. FRONTIERS IN RADIOLOGY 2024; 3:1336902. [PMID: 38304344 PMCID: PMC10830800 DOI: 10.3389/fradi.2023.1336902] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/11/2023] [Accepted: 12/28/2023] [Indexed: 02/03/2024]
Abstract
Challenging tasks such as lesion segmentation, classification, and analysis for the assessment of disease progression can be automatically achieved using deep learning (DL)-based algorithms. DL techniques such as 3D convolutional neural networks are trained using heterogeneous volumetric imaging data such as MRI, CT, and PET, among others. However, DL-based methods are usually only applicable in the presence of the desired number of inputs. In the absence of one of the required inputs, the method cannot be used. By implementing a generative adversarial network (GAN), we aim to apply multi-label automatic segmentation of brain tumors to synthetic images when not all inputs are present. The implemented GAN is based on the Pix2Pix architecture and has been extended to a 3D framework named Pix2PixNIfTI. For this study, 1,251 patients of the BraTS2021 dataset comprising sequences such as T1w, T2w, T1CE, and FLAIR images equipped with respective multi-label segmentation were used. This dataset was used for training the Pix2PixNIfTI model for generating synthetic MRI images of all the image contrasts. The segmentation model, namely DeepMedic, was trained in a five-fold cross-validation manner for brain tumor segmentation and tested using the original inputs as the gold standard. The inference of trained segmentation models was later applied to synthetic images replacing missing input, in combination with other original images to identify the efficacy of generated images in achieving multi-class segmentation. For the multi-class segmentation using synthetic data or lesser inputs, the dice scores were observed to be significantly reduced but remained similar in range for the whole tumor when compared with evaluated original image segmentation (e.g. mean dice of synthetic T2w prediction NC, 0.74 ± 0.30; ED, 0.81 ± 0.15; CET, 0.84 ± 0.21; WT, 0.90 ± 0.08). A standard paired t-tests with multiple comparison correction were performed to assess the difference between all regions (p < 0.05). The study concludes that the use of Pix2PixNIfTI allows us to segment brain tumors when one input image is missing.
Collapse
Affiliation(s)
- P. Raut
- Department of Pediatric Pulmonology, Erasmus Medical Center, Rotterdam, Netherlands
- Department of Radiology & Nuclear Medicine, Erasmus Medical Center, Rotterdam, Netherlands
- Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany
| | - G. Baldini
- Institute of Interventional and Diagnostic Radiology and Neuroradiology, University Hospital Essen, Essen, Germany
| | - M. Schöneck
- Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany
| | - L. Caldeira
- Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany
| |
Collapse
|
18
|
Herr J, Stoyanova R, Mellon EA. Convolutional Neural Networks for Glioma Segmentation and Prognosis: A Systematic Review. Crit Rev Oncog 2024; 29:33-65. [PMID: 38683153 DOI: 10.1615/critrevoncog.2023050852] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/01/2024]
Abstract
Deep learning (DL) is poised to redefine the way medical images are processed and analyzed. Convolutional neural networks (CNNs), a specific type of DL architecture, are exceptional for high-throughput processing, allowing for the effective extraction of relevant diagnostic patterns from large volumes of complex visual data. This technology has garnered substantial interest in the field of neuro-oncology as a promising tool to enhance medical imaging throughput and analysis. A multitude of methods harnessing MRI-based CNNs have been proposed for brain tumor segmentation, classification, and prognosis prediction. They are often applied to gliomas, the most common primary brain cancer, to classify subtypes with the goal of guiding therapy decisions. Additionally, the difficulty of repeating brain biopsies to evaluate treatment response in the setting of often confusing imaging findings provides a unique niche for CNNs to help distinguish the treatment response to gliomas. For example, glioblastoma, the most aggressive type of brain cancer, can grow due to poor treatment response, can appear to grow acutely due to treatment-related inflammation as the tumor dies (pseudo-progression), or falsely appear to be regrowing after treatment as a result of brain damage from radiation (radiation necrosis). CNNs are being applied to separate this diagnostic dilemma. This review provides a detailed synthesis of recent DL methods and applications for intratumor segmentation, glioma classification, and prognosis prediction. Furthermore, this review discusses the future direction of MRI-based CNN in the field of neuro-oncology and challenges in model interpretability, data availability, and computation efficiency.
Collapse
Affiliation(s)
| | - Radka Stoyanova
- Department of Radiation Oncology, University of Miami Miller School of Medicine, Sylvester Comprehensive Cancer Center, Miami, Fl 33136, USA
| | - Eric Albert Mellon
- Department of Radiation Oncology, University of Miami Miller School of Medicine, Sylvester Comprehensive Cancer Center, Miami, Fl 33136, USA
| |
Collapse
|
19
|
Jung AY. Basics for Pediatric Brain Tumor Imaging: Techniques and Protocol Recommendations. Brain Tumor Res Treat 2024; 12:1-13. [PMID: 38317484 PMCID: PMC10864130 DOI: 10.14791/btrt.2023.0037] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2023] [Revised: 11/24/2023] [Accepted: 11/28/2023] [Indexed: 02/07/2024] Open
Abstract
This review provides an overview of the current state of pediatric brain tumor imaging, emphasizing the role of various imaging sequences and highlighting the advantages of standardizing protocols for pediatric brain tumor imaging in diagnosis and treatment response evaluation. Basic anatomical sequences such as pre- and post-contrast 3D T1-weighted, T2-weighted, fluid-attenuated inversion recovery, T2*-weighted, and diffusion-weighted imaging (DWI), are fundamental for assessing tumor location, extent, and characteristics. Advanced techniques like DWI, diffusion tensor imaging, perfusion imaging, magnetic resonance spectroscopy, and functional MRI offer insights into cellularity, vascularity, metabolism, and function. To enhance consistency and quality, standardized protocols for pediatric brain tumor imaging have been recommended by expert groups. Special considerations for pediatric patients, including the minimization of anesthesia exposure and gadolinium contrast agent usage, are essential to ensure patient safety and comfort. Staying up-to-date with diagnostic imaging techniques can contribute to improved communication, outcomes, and patient care in the field of pediatric neurooncology.
Collapse
Affiliation(s)
- Ah Young Jung
- Department of Radiology, Asan Medical Center, Seoul, Korea.
| |
Collapse
|
20
|
El-Ghandour NMF. Commentary: Awake Craniotomy for a Ruptured Arteriovenous Malformation With Preoperative Navigated Transcranial Magnetic Stimulation for Language Mapping: 2-Dimensional Operative Video. Oper Neurosurg (Hagerstown) 2024; 26:111-112. [PMID: 37815232 DOI: 10.1227/ons.0000000000000912] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/05/2023] [Accepted: 08/08/2023] [Indexed: 10/11/2023] Open
|
21
|
Kopřivová T, Keřkovský M, Jůza T, Vybíhal V, Rohan T, Kozubek M, Dostál M. Possibilities of Using Multi-b-value Diffusion Magnetic Resonance Imaging for Classification of Brain Lesions. Acad Radiol 2024; 31:261-272. [PMID: 37932166 DOI: 10.1016/j.acra.2023.10.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/13/2023] [Revised: 09/25/2023] [Accepted: 10/03/2023] [Indexed: 11/08/2023]
Abstract
In contrast to conventional diffusion magnetic resonance imaging (MRI), multi-b-value diffusion MRI methods are able to separate the signal from free water, pseudo-diffusion, and non-Gaussian components of water molecule diffusion. These approaches can then be utilised in so-called intravoxel incoherent motion imaging and diffusion kurtosis imaging. Various parameters provided by these methods can describe additional characteristics of the tissue microstructure and potentially help in the diagnosis and classification of various pathological processes. In this review, we present the basic principles and methods of analysing multi-b-value diffusion imaging data and specifically focus on the known possibilities for its use in the diagnosis of brain lesions. We also suggest possible directions for further research.
Collapse
Affiliation(s)
- Tereza Kopřivová
- Department of Radiology and Nuclear Medicine, Faculty of Medicine, Masaryk University, Brno and University Hospital Brno, Jihlavská 20, 625 00, Brno, Czech Republic (T.K., M.K., T.J., T.R., M.D.)
| | - Miloš Keřkovský
- Department of Radiology and Nuclear Medicine, Faculty of Medicine, Masaryk University, Brno and University Hospital Brno, Jihlavská 20, 625 00, Brno, Czech Republic (T.K., M.K., T.J., T.R., M.D.).
| | - Tomáš Jůza
- Department of Radiology and Nuclear Medicine, Faculty of Medicine, Masaryk University, Brno and University Hospital Brno, Jihlavská 20, 625 00, Brno, Czech Republic (T.K., M.K., T.J., T.R., M.D.); Department of Biophysics, Faculty of Medicine, Masaryk University, Brno, Czech Republic (T.J., M.D.)
| | - Václav Vybíhal
- Department of Neurosurgery, Faculty of Medicine, Masaryk University Brno and University Hospital Brno, 625 00, Brno, Czech Republic (V.V.)
| | - Tomáš Rohan
- Department of Radiology and Nuclear Medicine, Faculty of Medicine, Masaryk University, Brno and University Hospital Brno, Jihlavská 20, 625 00, Brno, Czech Republic (T.K., M.K., T.J., T.R., M.D.)
| | - Michal Kozubek
- Centre for Biomedical Image Analysis, Faculty of Informatics, Masaryk University, Šumavská, Brno, Czech Republic (M.K.)
| | - Marek Dostál
- Department of Radiology and Nuclear Medicine, Faculty of Medicine, Masaryk University, Brno and University Hospital Brno, Jihlavská 20, 625 00, Brno, Czech Republic (T.K., M.K., T.J., T.R., M.D.); Department of Biophysics, Faculty of Medicine, Masaryk University, Brno, Czech Republic (T.J., M.D.)
| |
Collapse
|
22
|
Gharbaran R. Insights into the molecular roles of FOXR2 in the pathology of primary pediatric brain tumors. Crit Rev Oncol Hematol 2023; 192:104188. [PMID: 37879492 DOI: 10.1016/j.critrevonc.2023.104188] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2023] [Revised: 08/23/2023] [Accepted: 10/16/2023] [Indexed: 10/27/2023] Open
Abstract
Forkhead box gene R2 (FOXR2) belongs to the family of FOX genes which codes for highly conserved transcription factors (TFs) with critical roles in biological processes ranging from development to organogenesis to metabolic and immune regulation to cellular homeostasis. A number of FOX genes are associated with cancer development and progression and poor prognosis. A growing body of evidence suggests that FOXR2 is an oncogene. Studies suggested important roles for FOXR2 in cancer cell growth, metastasis, and drug resistance. Recent studies showed that FOXR2 is overexpressed by a subset of newly identified entities of embryonal tumors. This review discusses the role(s) FOXR2 plays in the pathology of pediatric brain cancers and its potential as a therapeutic target.
Collapse
Affiliation(s)
- Rajendra Gharbaran
- Biological Sciences Department, Bronx Community College/City University of New York, 2155 University Avenue, Bronx, NY 10453, USA.
| |
Collapse
|
23
|
Hu JY, Vaziri S, Bøgh N, Kim Y, Autry AW, Bok RA, Li Y, Laustsen C, Xu D, Larson PEZ, Chang S, Vigneron DB, Gordon JW. Investigating cerebral perfusion with high resolution hyperpolarized [1- 13 C]pyruvate MRI. Magn Reson Med 2023; 90:2233-2241. [PMID: 37665726 PMCID: PMC10543485 DOI: 10.1002/mrm.29844] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2023] [Revised: 08/08/2023] [Accepted: 08/10/2023] [Indexed: 09/06/2023]
Abstract
PURPOSE To investigate high-resolution hyperpolarized (HP) 13 C pyruvate MRI for measuring cerebral perfusion in the human brain. METHODS HP [1-13 C]pyruvate MRI was acquired in five healthy volunteers with a multi-resolution EPI sequence with 7.5 × 7.5 mm2 resolution for pyruvate. Perfusion parameters were calculated from pyruvate MRI using block-circulant singular value decomposition and compared to relative cerebral blood flow calculated from arterial spin labeling (ASL). To examine regional perfusion patterns, correlations between pyruvate and ASL perfusion were performed for whole brain, gray matter, and white matter voxels. RESULTS High resolution 7.5 × 7.5 mm2 pyruvate images were used to obtain relative cerebral blood flow (rCBF) values that were significantly positively correlated with ASL rCBF values (r = 0.48, 0.20, 0.28 for whole brain, gray matter, and white matter voxels respectively). Whole brain voxels exhibited the highest correlation between pyruvate and ASL perfusion, and there were distinct regional patterns of relatively high ASL and low pyruvate normalized rCBF found across subjects. CONCLUSION Acquiring HP 13 C pyruvate metabolic images at higher resolution allows for finer spatial delineation of brain structures and can be used to obtain cerebral perfusion parameters. Pyruvate perfusion parameters were positively correlated to proton ASL perfusion values, indicating a relationship between the two perfusion measures. This HP 13 C study demonstrated that hyperpolarized pyruvate MRI can assess cerebral metabolism and perfusion within the same study.
Collapse
Affiliation(s)
- Jasmine Y. Hu
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
- UC Berkeley-UCSF Graduate Program in Bioengineering,
University of California, San Francisco and University of California, Berkeley,
California, USA
| | - Sana Vaziri
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
| | - Nikolaj Bøgh
- MR Research Center, Department of Clinical Medicine, Aarhus
University, Aarhus, Denmark
| | - Yaewon Kim
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
| | - Adam W. Autry
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
| | - Robert A. Bok
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
| | - Yan Li
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
- UC Berkeley-UCSF Graduate Program in Bioengineering,
University of California, San Francisco and University of California, Berkeley,
California, USA
| | - Christoffer Laustsen
- MR Research Center, Department of Clinical Medicine, Aarhus
University, Aarhus, Denmark
| | - Duan Xu
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
- UC Berkeley-UCSF Graduate Program in Bioengineering,
University of California, San Francisco and University of California, Berkeley,
California, USA
| | - Peder E. Z. Larson
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
- UC Berkeley-UCSF Graduate Program in Bioengineering,
University of California, San Francisco and University of California, Berkeley,
California, USA
| | - Susan Chang
- Department of Neurological Surgery, University of
California San Francisco, San Francisco, California, USA
| | - Daniel B. Vigneron
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
- UC Berkeley-UCSF Graduate Program in Bioengineering,
University of California, San Francisco and University of California, Berkeley,
California, USA
| | - Jeremy W. Gordon
- Department of Radiology and Biomedical Imaging, University
of California San Francisco, San Francisco, California, USA
| |
Collapse
|
24
|
Patil V, Malik R, Sarawagi R. Comparative study between dynamic susceptibility contrast magnetic resonance imaging and arterial spin labelling perfusion in differentiating low-grade from high-grade brain tumours. Pol J Radiol 2023; 88:e521-e528. [PMID: 38125817 PMCID: PMC10731442 DOI: 10.5114/pjr.2023.132889] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2023] [Accepted: 10/06/2023] [Indexed: 12/23/2023] Open
Abstract
Purpose Our aim was to distinguish between low-grade and high-grade brain tumours on the basis of dynamic susceptibility contrast (DSC) magnetic resonance imaging (MRI) perfusion and arterial spin labelling (ASL) perfusion and to compare DSC and ASL techniques. Material and methods Forty-one patients with brain tumours were evaluated by 3-Tesla MRI. Conventional and perfusion MRI imaging with a 3D pseudo-continuous ASL (PCASL) and DSC perfusion maps were evaluated. Three ROIs were placed to obtain cerebral blood value (CBV) and cerebral blood flow (CBF) in areas of maximum perfusion in brain tumour and normal grey matter. Histopathological diagnosis was considered as the reference. ROC analysis was performed to compare the diagnostic performance and to obtain a feasible cut-off value of perfusion parameters to differentiate low-grade and high-grade brain tumours. Results Normalised perfusion parameters with grey matter (rCBF or rCBV lesion/NGM) of malignant lesions were significantly higher than those of benign lesions in both DSC (normalised rCBF of 2.16 and normalised rCBV of 2.63) and ASL (normalised rCBF of 2.22) perfusion imaging. The normalised cut-off values of DSC (rCBF of 1.1 and rCBV of 1.4) and ASL (rCBF of 1.3) showed similar specificity and near similar sensitivity in distinguishing low-grade and high-grade brain tumours. Conclusions Quantitative analysis of perfusion parameters obtained by both DSC and ASL perfusion techniques can be reliably used to distinguish low-grade and high-grade brain tumours. Normalisation of these values by grey matter gives us more reliable parameters, eliminating the different technical parameters involved in both the techniques.
Collapse
Affiliation(s)
- Vaibhav Patil
- All India Institute of Medical Sciences, Bhopal, India
| | - Rajesh Malik
- All India Institute of Medical Sciences, Bhopal, India
| | | |
Collapse
|
25
|
Sun W, Wang C, Tian C, Li X, Hu X, Liu S. Nanotechnology for brain tumor imaging and therapy based on π-conjugated materials: state-of-the-art advances and prospects. Front Chem 2023; 11:1301496. [PMID: 38025074 PMCID: PMC10663370 DOI: 10.3389/fchem.2023.1301496] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/25/2023] [Accepted: 10/26/2023] [Indexed: 12/01/2023] Open
Abstract
In contemporary biomedical research, the development of nanotechnology has brought forth numerous possibilities for brain tumor imaging and therapy. Among these, π-conjugated materials have garnered significant attention as a special class of nanomaterials in brain tumor-related studies. With their excellent optical and electronic properties, π-conjugated materials can be tailored in structure and nature to facilitate applications in multimodal imaging, nano-drug delivery, photothermal therapy, and other related fields. This review focuses on presenting the cutting-edge advances and application prospects of π-conjugated materials in brain tumor imaging and therapeutic nanotechnology.
Collapse
Affiliation(s)
- Wenshe Sun
- Department of Interventional Medical Center, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
- Qingdao Cancer Institute, Qingdao University, Qingdao, China
| | - Congxiao Wang
- Department of Interventional Medical Center, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Chuan Tian
- Department of Interventional Medical Center, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Xueda Li
- Department of Interventional Medical Center, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Xiaokun Hu
- Department of Interventional Medical Center, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| | - Shifeng Liu
- Department of Interventional Medical Center, Affiliated Hospital of Qingdao University, Qingdao, Shandong, China
| |
Collapse
|
26
|
Zhang W, Oh JH, Zhang W, Rathi S, Le J, Talele S, Sarkaria JN, Elmquist WF. How Much is Enough? Impact of Efflux Transporters on Drug delivery Leading to Efficacy in the Treatment of Brain Tumors. Pharm Res 2023; 40:2731-2746. [PMID: 37589827 PMCID: PMC10841221 DOI: 10.1007/s11095-023-03574-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Accepted: 07/19/2023] [Indexed: 08/18/2023]
Abstract
The lack of effective chemotherapeutic agents for the treatment of brain tumors is a serious unmet medical need. This can be attributed, in part, to inadequate delivery through the blood-brain barrier (BBB) and the tumor-cell barrier, both of which have active efflux transporters that can restrict the transport of many potentially effective agents for both primary and metastatic brain tumors. This review briefly summarizes the components and function of the normal BBB with respect to drug penetration into the brain and the alterations in the BBB due to brain tumor that could influence drug delivery. Depending on what is rate-limiting a compound's distribution, the limited permeability across the BBB and the subsequent delivery into the tumor cell can be greatly influenced by efflux transporters and these are discussed in some detail. Given these complexities, it is necessary to quantify the extent of brain distribution of the active (unbound) drug to compare across compounds and to inform potential for use against brain tumors. In this regard, the metric, Kp,uu, a brain-to-plasma unbound partition coefficient, is examined and its current use is discussed. However, the extent of active drug delivery is not the only determinant of effective therapy. In addition to Kp,uu, drug potency is an important parameter that should be considered alongside drug delivery in drug discovery and development processes. In other words, to answer the question - How much is enough? - one must consider how much can be delivered with how much needs to be delivered.
Collapse
Affiliation(s)
- Wenjuan Zhang
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA
| | - Ju-Hee Oh
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA
| | - Wenqiu Zhang
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA
| | - Sneha Rathi
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA
| | - Jiayan Le
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA
| | - Surabhi Talele
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA
| | - Jann N Sarkaria
- Department of Radiation Oncology, Mayo Clinic, Rochester, MN, USA
| | - William F Elmquist
- Brain Barriers Research Center, Department of Pharmaceutics, College of Pharmacy, University of Minnesota, Minneapolis, MN, USA.
| |
Collapse
|
27
|
Barry N, Francis RJ, Ebert MA, Koh ES, Rowshanfarzad P, Hassan GM, Kendrick J, Gan HK, Lee ST, Lau E, Moffat BA, Fitt G, Moore A, Thomas P, Pattison DA, Akhurst T, Alipour R, Thomas EL, Hsiao E, Schembri GP, Lin P, Ly T, Yap J, Kirkwood I, Vallat W, Khan S, Krishna D, Ngai S, Yu C, Beuzeville S, Yeow TC, Bailey D, Cook O, Whitehead A, Dykyj R, Rossi A, Grose A, Scott AM. Delineation and agreement of FET PET biological volumes in glioblastoma: results of the nuclear medicine credentialing program from the prospective, multi-centre trial evaluating FET PET In Glioblastoma (FIG) study-TROG 18.06. Eur J Nucl Med Mol Imaging 2023; 50:3970-3981. [PMID: 37563351 PMCID: PMC10611835 DOI: 10.1007/s00259-023-06371-5] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/27/2023] [Accepted: 07/28/2023] [Indexed: 08/12/2023]
Abstract
PURPOSE The O-(2-[18F]-fluoroethyl)-L-tyrosine (FET) PET in Glioblastoma (FIG) trial is an Australian prospective, multi-centre study evaluating FET PET for glioblastoma patient management. FET PET imaging timepoints are pre-chemoradiotherapy (FET1), 1-month post-chemoradiotherapy (FET2), and at suspected progression (FET3). Before participant recruitment, site nuclear medicine physicians (NMPs) underwent credentialing of FET PET delineation and image interpretation. METHODS Sites were required to complete contouring and dynamic analysis by ≥ 2 NMPs on benchmarking cases (n = 6) assessing biological tumour volume (BTV) delineation (3 × FET1) and image interpretation (3 × FET3). Data was reviewed by experts and violations noted. BTV definition includes tumour-to-background ratio (TBR) threshold of 1.6 with crescent-shaped background contour in the contralateral normal brain. Recurrence/pseudoprogression interpretation (FET3) required assessment of maximum TBR (TBRmax), dynamic analysis (time activity curve [TAC] type, time to peak), and qualitative assessment. Intraclass correlation coefficient (ICC) assessed volume agreement, coefficient of variation (CoV) compared maximum/mean TBR (TBRmax/TBRmean) across cases, and pairwise analysis assessed spatial (Dice similarity coefficient [DSC]) and boundary agreement (Hausdorff distance [HD], mean absolute surface distance [MASD]). RESULTS Data was accrued from 21 NMPs (10 centres, n ≥ 2 each) and 20 underwent review. The initial pass rate was 93/119 (78.2%) and 27/30 requested resubmissions were completed. Violations were found in 25/72 (34.7%; 13/12 minor/major) of FET1 and 22/74 (29.7%; 14/8 minor/major) of FET3 reports. The primary reasons for resubmission were as follows: BTV over-contour (15/30, 50.0%), background placement (8/30, 26.7%), TAC classification (9/30, 30.0%), and image interpretation (7/30, 23.3%). CoV median and range for BTV, TBRmax, and TBRmean were 21.53% (12.00-30.10%), 5.89% (5.01-6.68%), and 5.01% (3.37-6.34%), respectively. BTV agreement was moderate to excellent (ICC = 0.82; 95% CI, 0.63-0.97) with good spatial (DSC = 0.84 ± 0.09) and boundary (HD = 15.78 ± 8.30 mm; MASD = 1.47 ± 1.36 mm) agreement. CONCLUSION The FIG study credentialing program has increased expertise across study sites. TBRmax and TBRmean were robust, with considerable variability in BTV delineation and image interpretation observed.
Collapse
Affiliation(s)
- Nathaniel Barry
- School of Physics, Mathematics and Computing, University of Western Australia, WA, Crawley, Australia.
- Centre for Advanced Technologies in Cancer Research (CATCR), WA, Perth, Australia.
| | - Roslyn J Francis
- Department of Nuclear Medicine, Sir Charles Gairdner Hospital, Nedlands, WA, Australia
- Australian Centre for Quantitative Imaging, Medical School, University of Western Australia, Crawley, WA, Australia
| | - Martin A Ebert
- School of Physics, Mathematics and Computing, University of Western Australia, WA, Crawley, Australia
- Centre for Advanced Technologies in Cancer Research (CATCR), WA, Perth, Australia
- Australian Centre for Quantitative Imaging, Medical School, University of Western Australia, Crawley, WA, Australia
- Department of Radiation Oncology, Sir Charles Gairdner Hospital, Nedlands, WA, Australia
| | - Eng-Siew Koh
- Department of Radiation Oncology, Liverpool and Macarthur Cancer Therapy Centres, Liverpool, NSW, Australia
- South Western Sydney Clinical School, UNSW Medicine, University of New South Wales, Liverpool, NSW, Australia
| | - Pejman Rowshanfarzad
- School of Physics, Mathematics and Computing, University of Western Australia, WA, Crawley, Australia
- Centre for Advanced Technologies in Cancer Research (CATCR), WA, Perth, Australia
| | - Ghulam Mubashar Hassan
- School of Physics, Mathematics and Computing, University of Western Australia, WA, Crawley, Australia
| | - Jake Kendrick
- School of Physics, Mathematics and Computing, University of Western Australia, WA, Crawley, Australia
- Centre for Advanced Technologies in Cancer Research (CATCR), WA, Perth, Australia
| | - Hui K Gan
- Department of Medical Oncology, Austin Hospital, Melbourne, VIC, Australia
- Olivia Newton-John Cancer Research Institute, Melbourne, VIC, Australia
- Department of Medicine, University of Melbourne, Melbourne, VIC, Australia
- School of Cancer Medicine, La Trobe University, Melbourne, VIC, Australia
| | - Sze T Lee
- Olivia Newton-John Cancer Research Institute, Melbourne, VIC, Australia
- Department of Medicine, University of Melbourne, Melbourne, VIC, Australia
- School of Cancer Medicine, La Trobe University, Melbourne, VIC, Australia
- Department of Molecular Imaging and Therapy, Austin Health, Melbourne, VIC, Australia
| | - Eddie Lau
- Department of Molecular Imaging and Therapy, Austin Health, Melbourne, VIC, Australia
- Department of Radiology, Austin Health, Melbourne, VIC, Australia
- Department of Radiology, University of Melbourne, Melbourne, VIC, Australia
| | - Bradford A Moffat
- Department of Radiology, University of Melbourne, Melbourne, VIC, Australia
| | - Greg Fitt
- Department of Radiology, Austin Health, Melbourne, VIC, Australia
| | - Alisha Moore
- Trans Tasman Radiation Oncology Group (TROG Cancer Research), University of Newcastle, Callaghan, NSW, Australia
| | - Paul Thomas
- Department of Nuclear Medicine, Royal Brisbane and Women's Hospital, Herston, QLD, Australia
- Faculty of Medicine, University of Queensland, St Lucia, QLD, Australia
| | - David A Pattison
- Department of Nuclear Medicine, Royal Brisbane and Women's Hospital, Herston, QLD, Australia
- Faculty of Medicine, University of Queensland, St Lucia, QLD, Australia
| | - Tim Akhurst
- Department of Medicine, University of Melbourne, Melbourne, VIC, Australia
- The Sir Peter MacCallum Department of Oncology, Melbourne, VIC, Australia
| | - Ramin Alipour
- Department of Medicine, University of Melbourne, Melbourne, VIC, Australia
- The Sir Peter MacCallum Department of Oncology, Melbourne, VIC, Australia
| | - Elizabeth L Thomas
- Department of Nuclear Medicine, Sir Charles Gairdner Hospital, Nedlands, WA, Australia
| | - Edward Hsiao
- Department of Nuclear Medicine, Royal North Shore Hospital, St Leonards, NSW, Australia
| | - Geoffrey P Schembri
- Department of Nuclear Medicine, Royal North Shore Hospital, St Leonards, NSW, Australia
| | - Peter Lin
- South Western Sydney Clinical School, UNSW Medicine, University of New South Wales, Liverpool, NSW, Australia
- Department of Nuclear Medicine, Liverpool Hospital, Liverpool, NSW, Australia
| | - Tam Ly
- Department of Nuclear Medicine, Liverpool Hospital, Liverpool, NSW, Australia
| | - June Yap
- Department of Nuclear Medicine, Liverpool Hospital, Liverpool, NSW, Australia
| | - Ian Kirkwood
- Department of Nuclear Medicine, Royal Adelaide Hospital, Adelaide, SA, Australia
- Faculty of Health and Medical Sciences, The University of Adelaide, Adelaide, SA, Australia
| | - Wilson Vallat
- Department of Nuclear Medicine, Royal Adelaide Hospital, Adelaide, SA, Australia
| | - Shahroz Khan
- Department of Nuclear Medicine, Canberra Hospital, Woden, ACT, Australia
| | - Dayanethee Krishna
- Department of Nuclear Medicine, Canberra Hospital, Woden, ACT, Australia
| | - Stanley Ngai
- Department of Nuclear Medicine, Princess Alexandra Hospital, Woolloongabba, QLD, Australia
| | - Chris Yu
- Department of Nuclear Medicine, Princess Alexandra Hospital, Woolloongabba, QLD, Australia
| | - Scott Beuzeville
- Department of Nuclear Medicine, St George Hospital, Kogarah, NSW, Australia
| | - Tow C Yeow
- Department of Nuclear Medicine, St George Hospital, Kogarah, NSW, Australia
| | - Dale Bailey
- Department of Nuclear Medicine, Royal North Shore Hospital, St Leonards, NSW, Australia
- Faculty of Medicine 7 Health, University of Sydney, Sydney, NSW, Australia
| | - Olivia Cook
- Trans Tasman Radiation Oncology Group (TROG Cancer Research), University of Newcastle, Callaghan, NSW, Australia
| | - Angela Whitehead
- Trans Tasman Radiation Oncology Group (TROG Cancer Research), University of Newcastle, Callaghan, NSW, Australia
| | - Rachael Dykyj
- Trans Tasman Radiation Oncology Group (TROG Cancer Research), University of Newcastle, Callaghan, NSW, Australia
| | - Alana Rossi
- Trans Tasman Radiation Oncology Group (TROG Cancer Research), University of Newcastle, Callaghan, NSW, Australia
| | - Andrew Grose
- Trans Tasman Radiation Oncology Group (TROG Cancer Research), University of Newcastle, Callaghan, NSW, Australia
| | - Andrew M Scott
- Olivia Newton-John Cancer Research Institute, Melbourne, VIC, Australia
- Department of Medicine, University of Melbourne, Melbourne, VIC, Australia
- School of Cancer Medicine, La Trobe University, Melbourne, VIC, Australia
- Department of Molecular Imaging and Therapy, Austin Health, Melbourne, VIC, Australia
| |
Collapse
|
28
|
Kim E, Fortoul MC, Weimer D, Meggyesy M, Demory Beckler M. Co-occurrence of glioma and multiple sclerosis: Prevailing theories and emerging therapies. Mult Scler Relat Disord 2023; 79:105027. [PMID: 37801959 DOI: 10.1016/j.msard.2023.105027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Revised: 09/01/2023] [Accepted: 09/23/2023] [Indexed: 10/08/2023]
Abstract
Though the concurrence of primary brain tumors and multiple sclerosis (MS) is exceedingly rare, instances have been noted in the literature as early as 1949. Given these observations, researchers have proposed various ideas as to how these malignancies may be linked to MS. Due to insufficient data, none have gained traction or been widely accepted amongst neurologists or neuro-oncologists. What is abundantly clear, however, is the mounting uncertainty faced by clinicians when caring for these individuals. Concerns persist about the potential for disease modifying therapies (DMTs) to initiate or promote tumor growth and progression, and to date, there are no approved treatments capable of mitigating both MS disease activity and tumor growth, let alone established guidelines that clinicians may refer to. Collectively, these gaps in the literature impose limitations to optimizing the care and management of this population. As such, our hope is to stimulate further discussion of this topic and prompt future investigations to explore novel treatment options and advance our understanding of these concurrent disease processes. To this end, the chief objective of this article is to evaluate proposed ideas of how the diseases may be linked, outline emerging therapies for both MS and brain tumors, and describe evidence-based approaches to diagnosing and treating this patient population.
Collapse
Affiliation(s)
- Enoch Kim
- Dr. Kiran C. Patel College of Allopathic Medicine, Nova Southeastern University, 3200 S University Drive, Fort Lauderdale, FL 33328, United States
| | - Marla C Fortoul
- Dr. Kiran C. Patel College of Allopathic Medicine, Nova Southeastern University, 3200 S University Drive, Fort Lauderdale, FL 33328, United States
| | - Derek Weimer
- Dr. Kiran C. Patel College of Allopathic Medicine, Nova Southeastern University, 3200 S University Drive, Fort Lauderdale, FL 33328, United States
| | - Michael Meggyesy
- Department of Neurosurgery, Johns Hopkins University School of Medicine, Baltimore, MD, United States
| | - Michelle Demory Beckler
- Dr. Kiran C. Patel College of Allopathic Medicine, Nova Southeastern University, 3200 S University Drive, Fort Lauderdale, FL 33328, United States.
| |
Collapse
|
29
|
Sollmann N, Zhang H, Kloth C, Zimmer C, Wiestler B, Rosskopf J, Kreiser K, Schmitz B, Beer M, Krieg SM. Modern preoperative imaging and functional mapping in patients with intracranial glioma. ROFO-FORTSCHR RONTG 2023; 195:989-1000. [PMID: 37224867 DOI: 10.1055/a-2083-8717] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/26/2023]
Abstract
Magnetic resonance imaging (MRI) in therapy-naïve intracranial glioma is paramount for neuro-oncological diagnostics, and it provides images that are helpful for surgery planning and intraoperative guidance during tumor resection, including assessment of the involvement of functionally eloquent brain structures. This study reviews emerging MRI techniques to depict structural information, diffusion characteristics, perfusion alterations, and metabolism changes for advanced neuro-oncological imaging. In addition, it reflects current methods to map brain function close to a tumor, including functional MRI and navigated transcranial magnetic stimulation with derived function-based tractography of subcortical white matter pathways. We conclude that modern preoperative MRI in neuro-oncology offers a multitude of possibilities tailored to clinical needs, and advancements in scanner technology (e. g., parallel imaging for acceleration of acquisitions) make multi-sequence protocols increasingly feasible. Specifically, advanced MRI using a multi-sequence protocol enables noninvasive, image-based tumor grading and phenotyping in patients with glioma. Furthermore, the add-on use of preoperatively acquired MRI data in combination with functional mapping and tractography facilitates risk stratification and helps to avoid perioperative functional decline by providing individual information about the spatial location of functionally eloquent tissue in relation to the tumor mass. KEY POINTS:: · Advanced preoperative MRI allows for image-based tumor grading and phenotyping in glioma.. · Multi-sequence MRI protocols nowadays make it possible to assess various tumor characteristics (incl. perfusion, diffusion, and metabolism).. · Presurgical MRI in glioma is increasingly combined with functional mapping to identify and enclose individual functional areas.. · Advancements in scanner technology (e. g., parallel imaging) facilitate increasing application of dedicated multi-sequence imaging protocols.. CITATION FORMAT: · Sollmann N, Zhang H, Kloth C et al. Modern preoperative imaging and functional mapping in patients with intracranial glioma. Fortschr Röntgenstr 2023; 195: 989 - 1000.
Collapse
Affiliation(s)
- Nico Sollmann
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, München, Germany
- TUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, München, Germany
- Department of Radiology and Biomedical Imaging, University of California San Francisco, San Francisco, United States
| | - Haosu Zhang
- Department of Neurosurgery, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, München, Germany
| | - Christopher Kloth
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
| | - Claus Zimmer
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, München, Germany
- TUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, München, Germany
| | - Benedikt Wiestler
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, München, Germany
- TranslaTUM - Central Institute for Translational Cancer Research, Klinikum rechts der Isar, Technical University of Munich, München, Germany
| | - Johannes Rosskopf
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
- Section of Neuroradiology, Bezirkskrankenhaus Günzburg, Günzburg, Germany
| | - Kornelia Kreiser
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
- Department of Radiology and Neuroradiology, Universitäts- und Rehabilitationskliniken Ulm, Ulm, Germany
| | - Bernd Schmitz
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
- Section of Neuroradiology, Bezirkskrankenhaus Günzburg, Günzburg, Germany
| | - Meinrad Beer
- Department of Diagnostic and Interventional Radiology, University Hospital Ulm, Ulm, Germany
| | - Sandro M Krieg
- TUM-Neuroimaging Center, Klinikum rechts der Isar, Technical University of Munich, München, Germany
- Department of Neurosurgery, School of Medicine, Klinikum rechts der Isar, Technical University of Munich, München, Germany
| |
Collapse
|
30
|
Moshe YH, Buchsweiler Y, Teicher M, Artzi M. Handling Missing MRI Data in Brain Tumors Classification Tasks: Usage of Synthetic Images vs. Duplicate Images and Empty Images. J Magn Reson Imaging 2023. [PMID: 37864370 DOI: 10.1002/jmri.29072] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Revised: 09/30/2023] [Accepted: 10/02/2023] [Indexed: 10/22/2023] Open
Abstract
BACKGROUND Deep-learning is widely used for lesion classification. However, in the clinic patient data often has missing images. PURPOSE To evaluate the use of generated, duplicate and empty(black) images for replacing missing MRI data in AI brain tumor classification tasks. STUDY TYPE Retrospective. POPULATION 224 patients (local-dataset; low-grade-glioma (LGG) = 37, high-grade-glioma (HGG) = 187) and 335 patients (public-dataset (BraTS); LGG = 76, HGG = 259). The local-dataset was divided into training (64), validation (16), and internal-test-data (20), while the public-dataset was an independent test-set. FIELD STRENGTH/SEQUENCE T1WI, T1WI+C, T2WI, and FLAIR images (1.5T/3.0T-MR), obtained from different suppliers. ASSESSMENT Three image-to-image translation generative-adversarial-network (Pix2Pix-GAN) models were trained on the local-dataset, to generate T1WI, T2WI, and FLAIR images. The rating-and-preference-judgment assessment was performed by three human-readers (radiologist (MD) and two MRI-technicians). Resnet152 was used for classification, and inference was performed on both datasets, with baseline input, and with missing data replaced by 1) generated images; 2) duplication of existing images; and 3) black images. STATISTICAL TESTS The similarity between the generated and the original images was evaluated using the peak-signal-to-noise-ratio (PSNR) and the structural-similarity-index-measure (SSIM). Classification results were evaluated using accuracy, F1-score and the Kolmogorov-Smirnov test and distance. RESULTS For baseline-state, the classification model reached to accuracy = 0.93,0.82 on the local and public-datasets. For the missing-data methods, high similarity was obtained between the generated and the original images with mean PSNR = 35.65,32.94 and SSIM = 0.87,0.91 on the local and public-datasets; 39% of the generated-images were labeled as real images by the human-readers. The classification model using generated-images to replace missing images produced the highest results with mean accuracy = 0.91,0.82 compared to 0.85,0.79 for duplicated and 0.77,0.68 for use of black images; DATA CONCLUSION: The feasibility for inference classification model on an MRI dataset with missing images using the Pix2pix-GAN generated images, was shown. The stability and generalization ability of the model was demonstrated by producing consistent results on two independent datasets. LEVEL OF EVIDENCE 3 TECHNICAL EFFICACY: Stage 5.
Collapse
Affiliation(s)
- Yael H Moshe
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
- Department of Mathematics, Bar Ilan University, Ramat Gan, Israel
| | - Yuval Buchsweiler
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
- The Iby and Aladar Fleischman Faculty of Engineering, Tel Aviv University, Tel Aviv, Israel
| | - Mina Teicher
- Department of Mathematics, Bar Ilan University, Ramat Gan, Israel
- Gonda Brain Research Center, Bar-Ilan University, Ramat Gan, Israel
| | - Moran Artzi
- Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, Israel
- Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel
- Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel
| |
Collapse
|
31
|
Karmakar DK, Badhe PV, Mhatre P, Shrivastava S, Sultan M, Shankar G, Tekriwal K, Moharkar S. Utility of Diffusion Tensor Imaging in Assessing Corticospinal Tracts for the Management of Brain Tumors: A Cross-Sectional Observational Study. Cureus 2023; 15:e47811. [PMID: 38021806 PMCID: PMC10679788 DOI: 10.7759/cureus.47811] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/27/2023] [Indexed: 12/01/2023] Open
Abstract
Introduction Intra-axial brain tumors are a significant health problem and present several diagnostic and treatment challenges. Conventional magnetic resonance imaging (MRI) has posed several limitations, such as the inability to delineate the detailed anatomy of fibers in structures like the brainstem and the inability to accurately judge the extent of tumor infiltration. Diffusion tensor imaging (DTI), based on the concepts of isotropic and anisotropic diffusion, is capable of visualizing and segmenting white fiber bundles in high detail and providing crucial information about tumor boundaries, extent, neighboring tracts, and more. This information can be very useful in initial non-invasive diagnosis, preoperative tumor grading, biopsy planning, surgical planning, and prognosis. Methods and materials This is a cross-sectional observational study in a tertiary care setup, conducted over a one-year period. The study was performed in Seth Gordhandas Sunderdas Medical College (Seth G.S. Medical College) and King Edward VII Memorial Hospital (K.E.M. Hospital), a tertiary care hospital located in Mumbai, India. Fiber tractography was performed and was used to visualize the corticospinal tracts passing through the length of the brainstem. Changes in the degree of infiltration, destruction, and displacement of the corticospinal tracts were observed carefully. Adult patients who were diagnosed with brain tumors, willing to participate in the study, and capable of providing written informed consent prior to study registration were included. The DTI findings along with information from other investigations were used to decide the best course of management for each case. Results The study included 30 participants with a mean age of 46.0 ± 17.1 years, 63.3% and 37.7% being male and female, respectively. According to the lesion's location, the pons was found to be the most often affected area in 23.33% of cases, followed by the temporo-parietal region (13.3%) and the frontal region (13.3%). These lesions had heterogenous enhancement in 63.3% of the instances and homogeneous enhancement in 36.7% of the cases, according to a contrast study. According to their consistency, the lesions were further divided into two categories: solid lesions, which were present in 66.7% of instances, and cystic lesions, which were present in 90% of cases. Results from the diffusion tensor technique revealed that infiltration accounted for 40.0% of cases, displacement for 76.7%, and loss of white fiber tracts for 20.0%. DTI findings were significantly associated with the type of planned management and with the presence of post-management neurological deficit. Conclusion DTI played a complementary role in the assessment of tumors and can be used to improve surgical planning and therapeutic decision making. Preservation of corticospinal tracts is vital to prevent motor impairment. Availability of qualitative data with the depiction of corticospinal tracts in a three-dimensional projection and their relation with the brain tumors by DTI greatly helps in preoperative decision making and surgical approach.
Collapse
Affiliation(s)
- Deepmala K Karmakar
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| | - Padma V Badhe
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| | - Pauras Mhatre
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| | - Shashwat Shrivastava
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| | | | - Gautham Shankar
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| | - Khushboo Tekriwal
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| | - Swapnil Moharkar
- Radiology, Seth Gordhandas Sunderdas Medical College and King Edward Memorial Hospital, Mumbai, IND
| |
Collapse
|
32
|
Andrijauskis D, Woolf G, Kuehne A, Al-Dasuqi K, Silva CT, Payabvash S, Malhotra A. Utility of Gadolinium-Based Contrast in Initial Evaluation of Seizures in Children Presenting Emergently. AJNR Am J Neuroradiol 2023; 44:1208-1211. [PMID: 37652579 PMCID: PMC10549952 DOI: 10.3174/ajnr.a7976] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/16/2023] [Accepted: 08/02/2023] [Indexed: 09/02/2023]
Abstract
BACKGROUND AND PURPOSE The frequency and utility of gadolinium in evaluation of acute pediatric seizure presentation is not well known. The purpose of this study was to assess the utility of gadolinium-based contrast agents in MR imaging performed for the evaluation of acute pediatric seizure presentation. MATERIALS AND METHODS We identified consecutive pediatric patients with new-onset seizures from October 1, 2016, to September 30, 2021, who presented to the emergency department and/or were admitted to the inpatient unit and had an MR imaging of the brain for the evaluation of seizures. The clinical and imaging data were recorded, including the patient's age and sex, the use of IV gadolinium, and the underlying cause of epilepsy when available. RESULTS A total of 1884 patients were identified for inclusion. Five hundred twenty-four (28%) patients had potential epileptogenic findings on brain MR imaging, while 1153 (61%) patients had studies with normal findings and 207 (11%) patients had nonspecific signal changes. Epileptogenic findings were subclassified as the following: neurodevelopmental lesions, 142 (27%); intracranial hemorrhage (traumatic or germinal matrix), 89 (17%); ischemic/hypoxic, 62 (12%); hippocampal sclerosis, 44 (8%); neoplastic, 38 (7%); immune/infectious, 20 (4%); phakomatoses, 19 (4%); vascular anomalies, 17 (3%); metabolic, 3 (<1%); and other, 90 (17%). Eight hundred seventy-four (46%) patients received IV gadolinium. Of those, only 48 (5%) cases were retrospectively deemed to have necessitated the use of IV gadolinium: Fifteen of 48 (31%) cases were subclassified as immune/infectious, while 33 (69%) were neoplastic. Of the 1010 patients with an initial noncontrast study, 15 (1.5%) required repeat MR imaging with IV contrast to further evaluate the findings. CONCLUSIONS Gadolinium contrast is of limited additive benefit in the imaging of patients with an acute onset of pediatric seizures in most instances.
Collapse
Affiliation(s)
- Denas Andrijauskis
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| | - Graham Woolf
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| | - Alexander Kuehne
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| | - Khalid Al-Dasuqi
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| | - Cicero T Silva
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| | - Seyedmehdi Payabvash
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| | - Ajay Malhotra
- From the Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, Connecticut
| |
Collapse
|
33
|
Grudzień K, Klimeczek-Chrapusta M, Kwiatkowski S, Milczarek O. Predicting the WHO Grading of Pediatric Brain Tumors Based on Their MRI Appearance: A Retrospective Study. Cureus 2023; 15:e47333. [PMID: 38021610 PMCID: PMC10657198 DOI: 10.7759/cureus.47333] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/19/2023] [Indexed: 12/01/2023] Open
Abstract
The treatment of central nervous system (CNS) tumors constitutes a significant part of a pediatric neurosurgeon's workload. The classification of such neoplasms spans many entities. These include low- and high-grade lesions, with both occurring in the population of patients under 18 years of age. Magnetic resonance imaging serves as the imaging method of choice for neoplastic lesions of the brain. Through its different modalities, such as T1, T2, T1 C+, apparent diffusion coefficient (ADC), diffusion-weighted imaging (DWI), susceptibility-weighted imaging (SWI), fluid-attenuated inversion recovery (FLAIR), etc., it allows the medical team to plan the therapeutic process accordingly while also possibly suggesting the specific tumor subtype prior to obtaining a definitive histological diagnosis. We conducted a retrospective study spanning 32 children treated surgically for brain tumors between July 2021 and January 2023 who had a precise histological diagnosis determined by using the 2021 WHO Classification of Tumors of the Central Nervous System. We divided them into two groups (high-grade and low-grade tumors, i.e., WHO grades 1 and 2, and grades 3 and 4, respectively) and analyzed their demographic data and preoperative MRI results. This was done using the following criteria: sub or supratentorial location of the tumor; lesion is circumscribed or infiltrating; solid, cystic, or mixed solid and cystic character of the tumor; number of compartments in cystic lesions; signal intensity (hypo-, iso-, hyperintensity sequences: T1, T2, T1 C+); presence of restricted diffusion; the largest diameter of the solid component and/or the largest diameter of the largest cyst in the transverse section. Then, we examined the results to find any correlation between the lesions' morphologies and their final assigned degree of malignancy. We found that the only radiological criteria correlating with the final WHO grade of the tumor were an infiltrative pattern of growth (25% of low-grade lesions, 75% of high-grade; p = 0.006) and the presence of a cystic component in the tumor (in 68.75% of low-grade tumors and 43.75% of high-grade tumors; p = 0.041). The only other feature close to attaining statistical significance was diffusion restriction (33.3% of low-grade tumors, 66.7% high-grade; p = 0.055). Older children tended to present with tumors of lower degrees of malignancy, and there was a predominance of female patients (21 female, 11 male).
Collapse
Affiliation(s)
- Kacper Grudzień
- Neurosurgery, University Children's Hospital, Kraków, POL
- Medicine, Jagiellonian University Medical College, Kraków, POL
| | - Maria Klimeczek-Chrapusta
- Neurosurgery, University Children's Hospital, Kraków, POL
- Medicine, Jagiellonian University Medical College, Kraków, POL
| | - Stanisław Kwiatkowski
- Neurosurgery, University Children's Hospital, Kraków, POL
- Medicine, Jagiellonian University Medical College, Kraków, POL
| | - Olga Milczarek
- Neurosurgery, University Children's Hospital, Kraków, POL
- Medicine, Jagiellonian University Medical College, Kraków, POL
| |
Collapse
|
34
|
Chen P, Scarpelli ML, Healey DR, Mehta S, Quarles CC. MRI and amino acid PET detection of whole-brain tumor burden. Front Oncol 2023; 13:1248249. [PMID: 37810983 PMCID: PMC10558180 DOI: 10.3389/fonc.2023.1248249] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/26/2023] [Accepted: 08/30/2023] [Indexed: 10/10/2023] Open
Abstract
Background [18F]fluciclovine amino acid PET has shown promise for detecting brain tumor regions undetected on conventional anatomic MRI scans. However, it remains unclear which of these modalities provides a better assessment of the whole brain tumor burden. This study quantifies the performance of [18F]fluciclovine PET and MRI for detecting the whole brain tumor burden. Methods Thirteen rats were orthotopically implanted with fluorescently transduced human glioblastoma cells. Rats underwent MRI (T1- and T2-weighted) and [18F]fluciclovine PET. Next brains were excised, optically cleared, and scanned ex vivo with fluorescence imaging. All images were co-registered using a novel landmark-based registration to enable a spatial comparison. The tumor burden identified on the fluorescent images was considered the ground truth for comparison with the in vivo imaging. Results Across all cases, the PET sensitivity for detecting tumor burden (median 0.67) was not significantly different than MRI (combined T1+T2-weighted) sensitivity (median 0.61; p=0.85). However, the combined PET+MRI sensitivity (median 0.86) was significantly higher than MRI alone (41% higher; p=0.004) or PET alone (28% higher; p=0.0002). The specificity of combined PET+MRI (median=0.91) was significantly lower compared with MRI alone (6% lower; p=0.004) or PET alone (2% lower; p=0.002). Conclusion In these glioblastoma xenografts, [18F]fluciclovine PET did not provide a significant increase in tumor burden detection relative to conventional anatomic MRI. However, a combined PET and MRI assessment did significantly improve detection sensitivity relative to either modality alone, suggesting potential value in a combined assessment for some tumors.
Collapse
Affiliation(s)
- Peng Chen
- School of Health Sciences, Purdue University, West Lafayette, IN, United States
| | | | - Debbie R. Healey
- Department of Cancer Systems Imaging, The University of Texas (UT) MD Anderson Cancer Center, Houston, TX, United States
| | - Shwetal Mehta
- Ivy Brain Tumor Center, Barrow Neurological Institute, Phoenix, AZ, United States
| | - C. Chad Quarles
- Department of Cancer Systems Imaging, The University of Texas (UT) MD Anderson Cancer Center, Houston, TX, United States
| |
Collapse
|
35
|
Meister RL, Groth M, Zhang S, Buhk JH, Herrmann J. Evaluation of Artifact Appearance and Burden in Pediatric Brain Tumor MR Imaging with Compressed Sensing in Comparison to Conventional Parallel Imaging Acceleration. J Clin Med 2023; 12:5732. [PMID: 37685799 PMCID: PMC10489124 DOI: 10.3390/jcm12175732] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2023] [Revised: 08/25/2023] [Accepted: 08/30/2023] [Indexed: 09/10/2023] Open
Abstract
Clinical magnetic resonance imaging (MRI) aims for the highest possible image quality, while balancing the need for acceptable examination time, reasonable signal-to-noise ratio (SNR), and lowest artifact burden. With a recently introduced imaging acceleration technique, compressed sensing, the acquisition speed and image quality of pediatric brain tumor exams can be improved. However, little attention has been paid to its impact on method-related artifacts in pediatric brain MRI. This study assessed the overall artifact burden and artifact appearances in a standardized pediatric brain tumor MRI by comparing conventional parallel imaging acceleration with compressed sensing. This showed that compressed sensing resulted in fewer physiological artifacts in the FLAIR sequence, and a reduction in technical artifacts in the 3D T1 TFE sequences. Only a slight difference was noted in the T2 TSE sequence. A relatively new range of artifacts, which are likely technique-related, was noted in the 3D T1 TFE sequences. In conclusion, by equipping a basic pediatric brain tumor protocol for 3T MRI with compressed sensing, the overall burden of common artifacts can be reduced. However, attention should be paid to novel compressed-sensing-specific artifacts.
Collapse
Affiliation(s)
- Rieke Lisa Meister
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, Section of Pediatric Radiology, University Medical Center Hamburg-Eppendorf, 20251 Hamburg, Germany
- Department of Medical Imaging, Southland Hospital, Invercargill 9812, New Zealand
| | - Michael Groth
- Department of Radiology, St. Marienhospital Vechta, 49377 Vechta, Germany
| | - Shuo Zhang
- Philips Healthcare, 22335 Hamburg, Germany;
| | - Jan-Hendrik Buhk
- Department of Neuroradiology, Asklepios Kliniken St. Georg und Wandsbek, 22043 Hamburg, Germany
| | - Jochen Herrmann
- Department of Diagnostic and Interventional Radiology and Nuclear Medicine, Section of Pediatric Radiology, University Medical Center Hamburg-Eppendorf, 20251 Hamburg, Germany
| |
Collapse
|
36
|
Abe D, Kanaya K, Kiuchi T, Kobayashi S, Horiuchi T. The Importance of Intratumoral Venous Drainage Preservation in Two-Stage Surgery of Large Hypervascular Choroid Plexus Papilloma: A Case Report. Cureus 2023; 15:e45796. [PMID: 37872942 PMCID: PMC10590673 DOI: 10.7759/cureus.45796] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/22/2023] [Indexed: 10/25/2023] Open
Abstract
Two-stage surgery may be necessary when total tumor removal cannot be accomplished in the first surgery; however, the extent and condition in which the remaining tumor should be before the next surgery have not yet been established. There is a risk of postoperative hemorrhage in the residual tumor, especially in hypervascular tumors. We report a case of hypervascular choroid plexus papilloma (CPP) in a 22-year-old male patient where the preservation of intratumoral venous drainage was considered important to avoid hemorrhagic complications during a two-stage surgery. In the first surgery, it was difficult to control the bleeding from the debulked tumor, and the surgery was terminated due to severe blood loss. Large draining veins running in the tumor were preserved as it was suspected that these were important drainage routes of the bloodstream of the tumor. The preserved draining red veins changed to normal venous color in the second surgery performed after one week. The residual tumor was not vascularized during the second surgery and underwent gross total resection with less blood loss. The patient was discharged without sequelae. There was no recurrence of the tumor and no neurological deficit during the three-year follow-up. To prevent postoperative hemorrhage associated with a residual tumor, it may be important to preserve venous drainage of the tumor in hypervascular tumor resection.
Collapse
Affiliation(s)
- Daishiro Abe
- Neurosurgery, Shinshu University School of Medicine, Matsumoto, JPN
| | - Kohei Kanaya
- Neurosurgery, Shinshu University School of Medicine, Matsumoto, JPN
| | | | | | | |
Collapse
|
37
|
Bronte G, Cosi DM, Magri C, Frassoldati A, Crinò L, Calabrò L. Immune Checkpoint Inhibitors in "Special" NSCLC Populations: A Viable Approach? Int J Mol Sci 2023; 24:12622. [PMID: 37628803 PMCID: PMC10454231 DOI: 10.3390/ijms241612622] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2023] [Revised: 07/23/2023] [Accepted: 08/04/2023] [Indexed: 08/27/2023] Open
Abstract
Over the last decade, the therapeutic scenario for advanced non-small-cell lung cancer (NSCLC) has undergone a major paradigm shift. Immune checkpoint inhibitors (ICIs) have shown a meaningful clinical and survival improvement in different settings of the disease. However, the real benefit of this therapeutic approach remains controversial in selected NSCLC subsets, such as those of the elderly with active brain metastases or oncogene-addicted mutations. This is mainly due to the exclusion or underrepresentation of these patient subpopulations in most pivotal phase III studies; this precludes the generalization of ICI efficacy in this context. Moreover, no predictive biomarkers of ICI response exist that can help with patient selection for this therapeutic approach. Here, we critically summarize the current state of ICI efficacy in the most common "special" NSCLC subpopulations.
Collapse
Affiliation(s)
- Giuseppe Bronte
- Department of Clinical and Molecular Sciences (DISCLIMO), Università Politecnica Delle Marche, Via Tronto 10/A, 60121 Ancona, Italy
- Clinic of Laboratory and Precision Medicine, National Institute of Health and Sciences on Ageing (IRCCS INRCA), 60124 Ancona, Italy
| | | | - Chiara Magri
- Department of Oncology, University Hospital of Ferrara, 44124 Cona, Italy
| | | | - Lucio Crinò
- Department of Medical Oncology, IRCCS Istituto Romagnolo Per Lo Studio Dei Tumori (IRST) “Dino Amadori”, 47014 Meldola, Italy
| | - Luana Calabrò
- Department of Oncology, University Hospital of Ferrara, 44124 Cona, Italy
- Department of Translational Medicine, University of Ferrara, 44121 Ferrara, Italy
| |
Collapse
|
38
|
Yan Q, Li F, Cui Y, Wang Y, Wang X, Jia W, Liu X, Li Y, Chang H, Shi F, Xia Y, Zhou Q, Zeng Q. Discrimination Between Glioblastoma and Solitary Brain Metastasis Using Conventional MRI and Diffusion-Weighted Imaging Based on a Deep Learning Algorithm. J Digit Imaging 2023; 36:1480-1488. [PMID: 37156977 PMCID: PMC10406764 DOI: 10.1007/s10278-023-00838-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Revised: 04/13/2023] [Accepted: 04/18/2023] [Indexed: 05/10/2023] Open
Abstract
This study aims to develop and validate a deep learning (DL) model to differentiate glioblastoma from single brain metastasis (BM) using conventional MRI combined with diffusion-weighted imaging (DWI). Preoperative conventional MRI and DWI of 202 patients with solitary brain tumor (104 glioblastoma and 98 BM) were retrospectively obtained between February 2016 and September 2022. The data were divided into training and validation sets in a 7:3 ratio. An additional 32 patients (19 glioblastoma and 13 BM) from a different hospital were considered testing set. Single-MRI-sequence DL models were developed using the 3D residual network-18 architecture in tumoral (T model) and tumoral + peritumoral regions (T&P model). Furthermore, the combination model based on conventional MRI and DWI was developed. The area under the receiver operating characteristic curve (AUC) was used to assess the classification performance. The attention area of the model was visualized as a heatmap by gradient-weighted class activation mapping technique. For the single-MRI-sequence DL model, the T2WI sequence achieved the highest AUC in the validation set with either T models (0.889) or T&P models (0.934). In the combination models of the T&P model, the model of DWI combined with T2WI and contrast-enhanced T1WI showed increased AUC of 0.949 and 0.930 compared with that of single-MRI sequences in the validation set, respectively. And the highest AUC (0.956) was achieved by combined contrast-enhanced T1WI, T2WI, and DWI. In the heatmap, the central region of the tumoral was hotter and received more attention than other areas and was more important for differentiating glioblastoma from BM. A conventional MRI-based DL model could differentiate glioblastoma from solitary BM, and the combination models improved classification performance.
Collapse
Affiliation(s)
- Qingqing Yan
- Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China
- Shandong First Medical University, Jinan, China
| | - Fuyan Li
- Department of Radiology, Shandong Provincial Hospital affiliated to Shandong First Medical University, Jinan, China
| | - Yi Cui
- Department of Radiology, Qilu Hospital of Shandong University, Jinan, China
| | - Yong Wang
- Shandong Cancer Hospital and Institute, Shandong First Medical University, Shandong Academy of Medical Sciences, Jinan, China
| | - Xiao Wang
- Department of Radiology, Jining NO.1 People's Hospital, Jining, China
| | - Wenjing Jia
- Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China
| | - Xinhui Liu
- Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China
| | - Yuting Li
- Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China
| | - Huan Chang
- Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China
| | - Feng Shi
- Shanghai United Imaging Intelligence, Shanghai, China
| | - Yuwei Xia
- Shanghai United Imaging Intelligence, Shanghai, China
| | - Qing Zhou
- Shanghai United Imaging Intelligence, Shanghai, China
| | - Qingshi Zeng
- Department of Radiology, The First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital, Jinan, China.
| |
Collapse
|
39
|
Sugii N, Matsuda M, Tsurubuchi T, Ishikawa E. Hemorrhagic Complications After Brain Tumor Biopsy: Risk-Reduction Strategies Based on Safer Biopsy Targets and Techniques. World Neurosurg 2023; 176:e254-e264. [PMID: 37207726 DOI: 10.1016/j.wneu.2023.05.046] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/23/2023] [Revised: 05/09/2023] [Accepted: 05/10/2023] [Indexed: 05/21/2023]
Abstract
OBJECTIVE Brain tumor biopsies are essential for pathologic diagnosis. However, hemorrhagic complications after biopsies may occur, leading to suboptimal outcomes. This study aimed to evaluate the associated factors of hemorrhagic complications after brain tumor biopsies and propose countermeasures. METHODS We retrospectively collected data on 208 consecutive patients with brain tumors (malignant lymphoma or glioma) who underwent a biopsy from 2011-2020. We evaluated factors and microbleeds (MBs) in the tumor plus relative cerebral/tumoral blood flow (rCBF) at the biopsy site on preoperative magnetic resonance imaging (MRI). RESULTS Postoperative all and symptomatic hemorrhage occurred in 21.6% and 9.6% of patients. In univariate analysis, a needle biopsy was significantly associated with the risk of all and symptomatic hemorrhages compared to techniques that allow adequate hemostatic manipulation (i.e., open and endoscopic biopsies). Multivariate analyses revealed that a needle biopsy and gliomas of World Health Organization (WHO) grade III/IV were significantly associated with postoperative all and symptomatic hemorrhages. Multiple lesions were also an independent risk factor for symptomatic hemorrhages. On preoperative MRI, abundant MBs in the tumor and MBs at the biopsy sites, in addition to high rCBF, were significantly associated with postoperative all and symptomatic hemorrhages. CONCLUSIONS We recommend the following measures to prevent hemorrhagic complications: consider biopsy techniques that allow adequate hemostatic manipulation preferentially; perform more careful hemostasis in cases of suspected gliomas of WHO grade III/IV, multiple lesions, and abundant MBs in the tumors; and, if there are multiple candidate biopsy sites, select areas with lower rCBF and no MBs as a biopsy target.
Collapse
Affiliation(s)
- Narushi Sugii
- Department of Neurosurgery, Faculty of Medicine, University of Tsukuba, Tsukuba, Ibaraki, Japan
| | - Masahide Matsuda
- Department of Neurosurgery, Faculty of Medicine, University of Tsukuba, Tsukuba, Ibaraki, Japan.
| | - Takao Tsurubuchi
- Department of Neurosurgery, Faculty of Medicine, University of Tsukuba, Tsukuba, Ibaraki, Japan
| | - Eiichi Ishikawa
- Department of Neurosurgery, Faculty of Medicine, University of Tsukuba, Tsukuba, Ibaraki, Japan
| |
Collapse
|
40
|
Dong W, Wang N, Qi Z. Advances in the application of neuroinflammatory molecular imaging in brain malignancies. Front Immunol 2023; 14:1211900. [PMID: 37533851 PMCID: PMC10390727 DOI: 10.3389/fimmu.2023.1211900] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2023] [Accepted: 06/27/2023] [Indexed: 08/04/2023] Open
Abstract
The prevalence of brain cancer has been increasing in recent decades, posing significant healthcare challenges. The introduction of immunotherapies has brought forth notable diagnostic imaging challenges for brain tumors. The tumor microenvironment undergoes substantial changes in induced immunosuppression and immune responses following the development of primary brain tumor and brain metastasis, affecting the progression and metastasis of brain tumors. Consequently, effective and accurate neuroimaging techniques are necessary for clinical practice and monitoring. However, patients with brain tumors might experience radiation-induced necrosis or other neuroinflammation. Currently, positron emission tomography and various magnetic resonance imaging techniques play a crucial role in diagnosing and evaluating brain tumors. Nevertheless, differentiating between brain tumors and necrotic lesions or inflamed tissues remains a significant challenge in the clinical diagnosis of the advancements in immunotherapeutics and precision oncology have underscored the importance of clinically applicable imaging measures for diagnosing and monitoring neuroinflammation. This review summarizes recent advances in neuroimaging methods aimed at enhancing the specificity of brain tumor diagnosis and evaluating inflamed lesions.
Collapse
Affiliation(s)
- Wenxia Dong
- Department of Radiology, The First People’s Hospital of Linping District, Hangzhou, China
| | - Ning Wang
- Department of Medical Imaging, Jining Third People’s Hospital, Jining, Shandong, China
| | - Zhe Qi
- Department of Radiology, Zibo Central Hospital, Zibo, Shandong, China
| |
Collapse
|
41
|
Solar P, Valekova H, Marcon P, Mikulka J, Barak M, Hendrych M, Stransky M, Siruckova K, Kostial M, Holikova K, Brychta J, Jancalek R. Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics. Sci Rep 2023; 13:11459. [PMID: 37454179 PMCID: PMC10349862 DOI: 10.1038/s41598-023-38542-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2023] [Accepted: 07/10/2023] [Indexed: 07/18/2023] Open
Abstract
Diffusion-weighted imaging (DWI) and its numerical expression via apparent diffusion coefficient (ADC) values are commonly utilized in non-invasive assessment of various brain pathologies. Although numerous studies have confirmed that ADC values could be pathognomic for various ring-enhancing lesions (RELs), their true potential is yet to be exploited in full. The article was designed to introduce an image analysis method allowing REL recognition independently of either absolute ADC values or specifically defined regions of interest within the evaluated image. For this purpose, the line of interest (LOI) was marked on each ADC map to cross all of the RELs' compartments. Using a machine learning approach, we analyzed the LOI between two representatives of the RELs, namely, brain abscess and glioblastoma (GBM). The diagnostic ability of the selected parameters as predictors for the machine learning algorithms was assessed using two models, the k-NN model and the SVM model with a Gaussian kernel. With the k-NN machine learning method, 80% of the abscesses and 100% of the GBM were classified correctly at high accuracy. Similar results were obtained via the SVM method. The proposed assessment of the LOI offers a new approach for evaluating ADC maps obtained from different RELs and contributing to the standardization of the ADC map assessment.
Collapse
Affiliation(s)
- Peter Solar
- Department of Neurosurgery, St. Anne's University Hospital, Pekarska 53, 656 91, Brno, Czech Republic
- Faculty of Medicine, Masaryk University, Brno, Czech Republic
| | - Hana Valekova
- Department of Neurosurgery, St. Anne's University Hospital, Pekarska 53, 656 91, Brno, Czech Republic
- Faculty of Medicine, Masaryk University, Brno, Czech Republic
| | - Petr Marcon
- Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka, 12, 616 00, Brno, Czech Republic
| | - Jan Mikulka
- Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka, 12, 616 00, Brno, Czech Republic
| | - Martin Barak
- Department of Neurosurgery, St. Anne's University Hospital, Pekarska 53, 656 91, Brno, Czech Republic
- Faculty of Medicine, Masaryk University, Brno, Czech Republic
| | - Michal Hendrych
- Faculty of Medicine, Masaryk University, Brno, Czech Republic
- First Department of Pathology, St. Anne's University Hospital, Brno, Czech Republic
| | - Matyas Stransky
- Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka, 12, 616 00, Brno, Czech Republic
| | - Katerina Siruckova
- Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka, 12, 616 00, Brno, Czech Republic
| | - Martin Kostial
- Faculty of Electrical Engineering and Communication, Brno University of Technology, Technicka, 12, 616 00, Brno, Czech Republic
| | - Klara Holikova
- Faculty of Medicine, Masaryk University, Brno, Czech Republic
- Department of Medical Imaging, St. Anne's University Hospital, Brno, Czech Republic
| | - Jindrich Brychta
- Department of Neurosurgery, St. Anne's University Hospital, Pekarska 53, 656 91, Brno, Czech Republic
| | - Radim Jancalek
- Department of Neurosurgery, St. Anne's University Hospital, Pekarska 53, 656 91, Brno, Czech Republic.
- Faculty of Medicine, Masaryk University, Brno, Czech Republic.
| |
Collapse
|
42
|
Chen T, Hu L, Lu Q, Xiao F, Xu H, Li H, Lu L. A computer-aided diagnosis system for brain tumors based on artificial intelligence algorithms. Front Neurosci 2023; 17:1120781. [PMID: 37483342 PMCID: PMC10360168 DOI: 10.3389/fnins.2023.1120781] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2022] [Accepted: 06/19/2023] [Indexed: 07/25/2023] Open
Abstract
The choice of treatment and prognosis evaluation depend on the accurate early diagnosis of brain tumors. Many brain tumors go undiagnosed or are overlooked by clinicians as a result of the challenges associated with manually evaluating magnetic resonance imaging (MRI) images in clinical practice. In this study, we built a computer-aided diagnosis (CAD) system for glioma detection, grading, segmentation, and knowledge discovery based on artificial intelligence algorithms. Neuroimages are specifically represented using a type of visual feature known as the histogram of gradients (HOG). Then, through a two-level classification framework, the HOG features are employed to distinguish between healthy controls and patients, or between different glioma grades. This CAD system also offers tumor visualization using a semi-automatic segmentation tool for better patient management and treatment monitoring. Finally, a knowledge base is created to offer additional advice for the diagnosis of brain tumors. Based on our proposed two-level classification framework, we train models for glioma detection and grading, achieving area under curve (AUC) of 0.921 and 0.806, respectively. Different from other systems, we integrate these diagnostic tools with a web-based interface, which provides the flexibility for system deployment.
Collapse
Affiliation(s)
- Tao Chen
- School of Information Technology, Shangqiu Normal University, Shangqiu, China
| | - Lianting Hu
- Medical Big Data Center, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China
- Guangdong Cardiovascular Institute, Guangzhou, China
| | - Quan Lu
- School of Information Management, Wuhan University, Wuhan, China
| | - Feng Xiao
- Department of Radiology, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Haibo Xu
- Department of Radiology, Zhongnan Hospital of Wuhan University, Wuhan, China
| | - Hongjun Li
- Department of Radiology, Beijing Youan Hospital, Capital Medical University, Beijing, China
| | - Long Lu
- School of Information Management, Wuhan University, Wuhan, China
- Big Data Institute, Wuhan University, Wuhan, China
- School of Public Health, Wuhan University, Wuhan, China
- Institute of Pediatrics, Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China
| |
Collapse
|
43
|
Du P, Liu X, Wu X, Chen J, Cao A, Geng D. Predicting Histopathological Grading of Adult Gliomas Based On Preoperative Conventional Multimodal MRI Radiomics: A Machine Learning Model. Brain Sci 2023; 13:912. [PMID: 37371390 DOI: 10.3390/brainsci13060912] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2023] [Revised: 05/13/2023] [Accepted: 05/30/2023] [Indexed: 06/29/2023] Open
Abstract
PURPOSE The accurate preoperative histopathological grade diagnosis of adult gliomas is of great significance for the formulation of a surgical plan and the implementation of a subsequent treatment. The aim of this study is to establish a predictive model for classifying adult gliomas into grades 2-4 based on preoperative conventional multimodal MRI radiomics. PATIENTS AND METHODS Patients with pathologically confirmed gliomas at Huashan Hospital, Fudan University, between February 2017 and July 2019 were retrospectively analyzed. Two regions of interest (ROIs), called the maximum anomaly region (ROI1) and the tumor region (ROI2), were delineated on the patients' preoperative MRIs utilizing the tool ITK-SNAP, and Pyradiomics 3.0 was applied to execute feature extraction. Feature selection was performed utilizing a least absolute shrinkage and selection operator (LASSO) filter. Six classifiers, including Gaussian naive Bayes (GNB), random forest (RF), K-nearest neighbor (KNN), support vector machine (SVM) with a linear kernel, adaptive boosting (AB), and multilayer perceptron (MLP) were used to establish predictive models, and the predictive performance of the six classifiers was evaluated through five-fold cross-validation. The performance of the predictive models was evaluated using the AUC and other metrics. After that, the model with the best predictive performance was tested using the external data from The Cancer Imaging Archive (TCIA). RESULTS According to the inclusion and exclusion criteria, 240 patients with gliomas were identified for inclusion in the study, including 106 grade 2, 68 grade 3, and 66 grade 4 gliomas. A total of 150 features was selected, and the MLP classifier had the best predictive performance among the six classifiers based on T2-FLAIR (mean AUC of 0.80 ± 0.07). The SVM classifier had the best predictive performance among the six classifiers based on DWI (mean AUC of 0.84 ± 0.05); the SVM classifier had the best predictive performance among the six classifiers based on CE-T1WI (mean AUC of 0.85 ± 0.06). Among the six classifiers, based on ROI1, the MLP classifier had the best prediction performance (mean AUC of 0.78 ± 0.07); among the six classifiers, based on ROI2, the SVM classifier had the best prediction performance (mean AUC of 0.82 ± 0.07). Among the six classifiers, based on the multimodal MRI of all the ROIs, the SVM classifier had the best prediction performance (average AUC of 0.85 ± 0.04). The SVM classifier, based on the multimodal MRI of all the ROIs, achieved an AUC of 0.81 using the external data from TCIA. CONCLUSIONS The prediction model, based on preoperative conventional multimodal MRI radiomics, established in this study can conveniently, accurately, and noninvasively classify adult gliomas into grades 2-4, providing certain assistance for the precise diagnosis and treatment of patients and optimizing their clinical management.
Collapse
Affiliation(s)
- Peng Du
- Department of Radiology, Huashan Hospital, Fudan University, Shanghai 200040, China
- Department of Radiology, the Second Affiliated Hospital of Xuzhou Medical University, Xuzhou 221000, China
| | - Xiao Liu
- School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China
| | - Xuefan Wu
- Department of Radiology, Shanghai Gamma Hospital, Shanghai 200040, China
| | - Jiawei Chen
- Department of Neurosurgery, Huashan Hospital, Fudan University, Shanghai 200040, China
| | - Aihong Cao
- Department of Radiology, the Second Affiliated Hospital of Xuzhou Medical University, Xuzhou 221000, China
| | - Daoying Geng
- Department of Radiology, Huashan Hospital, Fudan University, Shanghai 200040, China
| |
Collapse
|
44
|
Poojar P, Qian E, Fernandes TT, Nunes RG, Fung M, Quarterman P, Jambawalikar SR, Lignelli A, Geethanath S. Tailored magnetic resonance fingerprinting. Magn Reson Imaging 2023; 99:81-90. [PMID: 36764630 DOI: 10.1016/j.mri.2023.02.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/04/2021] [Revised: 01/27/2023] [Accepted: 02/06/2023] [Indexed: 02/11/2023]
Abstract
Neuroimaging of certain pathologies requires both multi-parametric qualitative and quantitative imaging. The role of the quantitative MRI (qMRI) is well accepted but suffers from long acquisition times leading to patient discomfort, especially in geriatric and pediatric patients. Previous studies show that synthetic MRI can be used in order to reduce the scan time and provide qMRI as well as multi-contrast data. However, this approach suffers from artifacts such as partial volume and flow. In order to increase the scan efficiency (the number of contrasts and quantitative maps acquired per unit time), we designed, simulated, and demonstrated rapid, simultaneous, multi-contrast qualitative (T1 weighted, T1 fluid attenuated inversion recovery (FLAIR), T2 weighted, water, and fat), and quantitative imaging (T1 and T2 maps) through the approach of tailored MR fingerprinting (TMRF) to cover whole-brain in approximately four minutes. We performed TMRF on in vivo four healthy human brains and in vitro ISMRM/NIST phantom and compared with vendor supplied gold standard (GS) and MRF sequences. All scans were performed on a 3 T GE Premier system and images were reconstructed offline using MATLAB. The reconstructed qualitative images were then subjected to custom DL denoising and gradient anisotropic diffusion denoising. The quantitative tissue parametric maps were reconstructed using a dense neural network to gain computational speed compared to dictionary matching. The grey matter and white matter tissues in qualitative and quantitative data for the in vivo datasets were segmented semi-automatically. The SNR and mean contrasts were plotted and compared across all three methods. The GS images show better SNR in all four subjects compared to MRF and TMRF (GS > TMRF>MRF). The T1 and T2 values of MRF are relatively overestimated as compared to GS and TMRF. The scan efficiency for TMRF is 1.72 min-1 which is higher compared to GS (0.32 min-1) and MRF (0.90 min-1).
Collapse
Affiliation(s)
- Pavan Poojar
- Icahn School of Medicine at Mt. Sinai, New York, NY, USA; Columbia Magnetic Resonance Research Center, Columbia University in the city of New York, NY, USA
| | - Enlin Qian
- Columbia Magnetic Resonance Research Center, Columbia University in the city of New York, NY, USA
| | - Tiago T Fernandes
- Institute for Systems and Robotics and Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
| | - Rita G Nunes
- Institute for Systems and Robotics and Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
| | - Maggie Fung
- GE Healthcare Applied Sciences Laboratory East, New York, NY, USA
| | | | - Sachin R Jambawalikar
- Department of Radiology, Columbia University Irving Medical Center, Columbia University in the city of New York, NY, USA
| | - Angela Lignelli
- Department of Radiology, Columbia University Irving Medical Center, Columbia University in the city of New York, NY, USA
| | - Sairam Geethanath
- Icahn School of Medicine at Mt. Sinai, New York, NY, USA; Columbia Magnetic Resonance Research Center, Columbia University in the city of New York, NY, USA.
| |
Collapse
|
45
|
Hirschler L, Sollmann N, Schmitz‐Abecassis B, Pinto J, Arzanforoosh F, Barkhof F, Booth T, Calvo‐Imirizaldu M, Cassia G, Chmelik M, Clement P, Ercan E, Fernández‐Seara MA, Furtner J, Fuster‐Garcia E, Grech‐Sollars M, Guven NT, Hatay GH, Karami G, Keil VC, Kim M, Koekkoek JAF, Kukran S, Mancini L, Nechifor RE, Özcan A, Ozturk‐Isik E, Piskin S, Schmainda K, Svensson SF, Tseng C, Unnikrishnan S, Vos F, Warnert E, Zhao MY, Jancalek R, Nunes T, Emblem KE, Smits M, Petr J, Hangel G. Advanced MR Techniques for Preoperative Glioma Characterization: Part 1. J Magn Reson Imaging 2023; 57:1655-1675. [PMID: 36866773 PMCID: PMC10946498 DOI: 10.1002/jmri.28662] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Revised: 02/08/2023] [Accepted: 02/09/2023] [Indexed: 03/04/2023] Open
Abstract
Preoperative clinical magnetic resonance imaging (MRI) protocols for gliomas, brain tumors with dismal outcomes due to their infiltrative properties, still rely on conventional structural MRI, which does not deliver information on tumor genotype and is limited in the delineation of diffuse gliomas. The GliMR COST action wants to raise awareness about the state of the art of advanced MRI techniques in gliomas and their possible clinical translation or lack thereof. This review describes current methods, limits, and applications of advanced MRI for the preoperative assessment of glioma, summarizing the level of clinical validation of different techniques. In this first part, we discuss dynamic susceptibility contrast and dynamic contrast-enhanced MRI, arterial spin labeling, diffusion-weighted MRI, vessel imaging, and magnetic resonance fingerprinting. The second part of this review addresses magnetic resonance spectroscopy, chemical exchange saturation transfer, susceptibility-weighted imaging, MRI-PET, MR elastography, and MR-based radiomics applications. Evidence Level: 3 Technical Efficacy: Stage 2.
Collapse
Affiliation(s)
- Lydiane Hirschler
- C.J. Gorter MRI Center, Department of RadiologyLeiden University Medical CenterLeidenThe Netherlands
| | - Nico Sollmann
- Department of Diagnostic and Interventional RadiologyUniversity Hospital UlmUlmGermany
- Department of Diagnostic and Interventional Neuroradiology, School of Medicine, Klinikum rechts der IsarTechnical University of MunichMunichGermany
- TUM‐Neuroimaging Center, Klinikum rechts der IsarTechnical University of MunichMunichGermany
| | - Bárbara Schmitz‐Abecassis
- Department of RadiologyLeiden University Medical CenterLeidenThe Netherlands
- Medical Delta FoundationDelftThe Netherlands
| | - Joana Pinto
- Institute of Biomedical Engineering, Department of Engineering ScienceUniversity of OxfordOxfordUK
| | | | - Frederik Barkhof
- Department of Radiology & Nuclear MedicineAmsterdam UMC, Vrije UniversiteitAmsterdamThe Netherlands
- Queen Square Institute of Neurology and Centre for Medical Image ComputingUniversity College LondonLondonUK
| | - Thomas Booth
- School of Biomedical Engineering and Imaging SciencesKing's College LondonLondonUK
- Department of NeuroradiologyKing's College Hospital NHS Foundation TrustLondonUK
| | | | | | - Marek Chmelik
- Department of Technical Disciplines in Medicine, Faculty of Health CareUniversity of PrešovPrešovSlovakia
| | - Patricia Clement
- Department of Diagnostic SciencesGhent UniversityGhentBelgium
- Department of Medical ImagingGhent University HospitalGhentBelgium
| | - Ece Ercan
- Department of RadiologyLeiden University Medical CenterLeidenThe Netherlands
| | - Maria A. Fernández‐Seara
- Department of RadiologyClínica Universidad de NavarraPamplonaSpain
- IdiSNA, Instituto de Investigación Sanitaria de NavarraPamplonaSpain
| | - Julia Furtner
- Department of Biomedical Imaging and Image‐guided TherapyMedical University of ViennaViennaAustria
- Research Center of Medical Image Analysis and Artificial IntelligenceDanube Private UniversityKrems an der DonauAustria
| | - Elies Fuster‐Garcia
- Biomedical Data Science Laboratory, Instituto Universitario de Tecnologías de la Información y ComunicacionesUniversitat Politècnica de ValènciaValenciaSpain
| | - Matthew Grech‐Sollars
- Centre for Medical Image Computing, Department of Computer ScienceUniversity College LondonLondonUK
- Lysholm Department of Neuroradiology, National Hospital for Neurology and NeurosurgeryUniversity College London Hospitals NHS Foundation TrustLondonUK
| | - Nazmiye Tugay Guven
- Institute of Biomedical EngineeringBogazici University IstanbulIstanbulTurkey
| | - Gokce Hale Hatay
- Institute of Biomedical EngineeringBogazici University IstanbulIstanbulTurkey
| | - Golestan Karami
- School of Biomedical Engineering and Imaging SciencesKing's College LondonLondonUK
| | - Vera C. Keil
- Department of Radiology & Nuclear MedicineAmsterdam UMC, Vrije UniversiteitAmsterdamThe Netherlands
- Cancer Center AmsterdamAmsterdamThe Netherlands
| | - Mina Kim
- Centre for Medical Image Computing, Department of Medical Physics & Biomedical Engineering and Department of NeuroinflammationUniversity College LondonLondonUK
| | - Johan A. F. Koekkoek
- Department of NeurologyLeiden University Medical CenterLeidenThe Netherlands
- Department of NeurologyHaaglanden Medical CenterThe HagueThe Netherlands
| | - Simran Kukran
- Department of BioengineeringImperial College LondonLondonUK
- Department of Radiotherapy and ImagingInstitute of Cancer ResearchLondonUK
| | - Laura Mancini
- Lysholm Department of Neuroradiology, National Hospital for Neurology and NeurosurgeryUniversity College London Hospitals NHS Foundation TrustLondonUK
- Department of Brain Repair and Rehabilitation, Institute of NeurologyUniversity College LondonLondonUK
| | - Ruben Emanuel Nechifor
- Department of Clinical Psychology and PsychotherapyInternational Institute for the Advanced Studies of Psychotherapy and Applied Mental Health, Babes‐Bolyai UniversityCluj‐NapocaRomania
| | - Alpay Özcan
- Electrical and Electronics Engineering DepartmentBogazici University IstanbulIstanbulTurkey
| | - Esin Ozturk‐Isik
- Institute of Biomedical EngineeringBogazici University IstanbulIstanbulTurkey
| | - Senol Piskin
- Department of Mechanical Engineering, Faculty of Natural Sciences and EngineeringIstinye University IstanbulIstanbulTurkey
| | - Kathleen Schmainda
- Department of BiophysicsMedical College of WisconsinMilwaukeeWisconsinUSA
| | - Siri F. Svensson
- Department of Physics and Computational RadiologyOslo University HospitalOsloNorway
- Department of PhysicsUniversity of OsloOsloNorway
| | - Chih‐Hsien Tseng
- Medical Delta FoundationDelftThe Netherlands
- Department of Imaging PhysicsDelft University of TechnologyDelftThe Netherlands
| | - Saritha Unnikrishnan
- Faculty of Engineering and DesignAtlantic Technological University (ATU) SligoSligoIreland
- Mathematical Modelling and Intelligent Systems for Health and Environment (MISHE), ATU SligoSligoIreland
| | - Frans Vos
- Medical Delta FoundationDelftThe Netherlands
- Department of Radiology & Nuclear MedicineErasmus MCRotterdamThe Netherlands
- Department of Imaging PhysicsDelft University of TechnologyDelftThe Netherlands
| | - Esther Warnert
- Department of Radiology & Nuclear MedicineErasmus MCRotterdamThe Netherlands
| | - Moss Y. Zhao
- Department of RadiologyStanford UniversityStanfordCaliforniaUSA
- Stanford Cardiovascular InstituteStanford UniversityStanfordCaliforniaUSA
| | - Radim Jancalek
- Department of NeurosurgerySt. Anne's University Hospital, BrnoBrnoCzech Republic
- Faculty of Medicine, Masaryk UniversityBrnoCzech Republic
| | - Teresa Nunes
- Department of NeuroradiologyHospital Garcia de OrtaAlmadaPortugal
| | - Kyrre E. Emblem
- Department of Physics and Computational RadiologyOslo University HospitalOsloNorway
| | - Marion Smits
- Institute of Biomedical Engineering, Department of Engineering ScienceUniversity of OxfordOxfordUK
- Department of Radiology & Nuclear MedicineErasmus MCRotterdamThe Netherlands
- Brain Tumour CentreErasmus MC Cancer InstituteRotterdamThe Netherlands
| | - Jan Petr
- Helmholtz‐Zentrum Dresden‐RossendorfInstitute of Radiopharmaceutical Cancer ResearchDresdenGermany
| | - Gilbert Hangel
- Department of NeurosurgeryMedical University of ViennaViennaAustria
- High Field MR Centre, Department of Biomedical Imaging and Image‐guided TherapyMedical University of ViennaViennaAustria
- Christian Doppler Laboratory for MR Imaging BiomarkersViennaAustria
- Medical Imaging ClusterMedical University of ViennaViennaAustria
| |
Collapse
|
46
|
Scola E, Del Vecchio G, Busto G, Bianchi A, Desideri I, Gadda D, Mancini S, Carlesi E, Moretti M, Desideri I, Muscas G, Della Puppa A, Fainardi E. Conventional and Advanced Magnetic Resonance Imaging Assessment of Non-Enhancing Peritumoral Area in Brain Tumor. Cancers (Basel) 2023; 15:cancers15112992. [PMID: 37296953 DOI: 10.3390/cancers15112992] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/04/2023] [Revised: 05/24/2023] [Accepted: 05/26/2023] [Indexed: 06/12/2023] Open
Abstract
The non-enhancing peritumoral area (NEPA) is defined as the hyperintense region in T2-weighted and fluid-attenuated inversion recovery (FLAIR) images surrounding a brain tumor. The NEPA corresponds to different pathological processes, including vasogenic edema and infiltrative edema. The analysis of the NEPA with conventional and advanced magnetic resonance imaging (MRI) was proposed in the differential diagnosis of solid brain tumors, showing higher accuracy than MRI evaluation of the enhancing part of the tumor. In particular, MRI assessment of the NEPA was demonstrated to be a promising tool for distinguishing high-grade gliomas from primary lymphoma and brain metastases. Additionally, the MRI characteristics of the NEPA were found to correlate with prognosis and treatment response. The purpose of this narrative review was to describe MRI features of the NEPA obtained with conventional and advanced MRI techniques to better understand their potential in identifying the different characteristics of high-grade gliomas, primary lymphoma and brain metastases and in predicting clinical outcome and response to surgery and chemo-irradiation. Diffusion and perfusion techniques, such as diffusion tensor imaging (DTI), diffusional kurtosis imaging (DKI), dynamic susceptibility contrast-enhanced (DSC) perfusion imaging, dynamic contrast-enhanced (DCE) perfusion imaging, arterial spin labeling (ASL), spectroscopy and amide proton transfer (APT), were the advanced MRI procedures we reviewed.
Collapse
Affiliation(s)
- Elisa Scola
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Guido Del Vecchio
- Radiodiagnostic Unit N. 2, Department of Experimental and Clinical Biomedical Sciences, University of Florence, 50121 Florence, Italy
| | - Giorgio Busto
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Andrea Bianchi
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Ilaria Desideri
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Davide Gadda
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Sara Mancini
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Edoardo Carlesi
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Marco Moretti
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
| | - Isacco Desideri
- Radiation Oncology, Oncology Department, Careggi University Hospital, University of Florence, 50121 Florence, Italy
| | - Giovanni Muscas
- Neurosurgery Unit, Department of Neuroscience, Psychology, Pharmacology and Child Health, Careggi University Hospital, University of Florence, 50121 Florence, Italy
| | - Alessandro Della Puppa
- Neurosurgery Unit, Department of Neuroscience, Psychology, Pharmacology and Child Health, Careggi University Hospital, University of Florence, 50121 Florence, Italy
| | - Enrico Fainardi
- Neuroradiology Unit, Department of Radiology, Careggi University Hospital, 50134 Florence, Italy
- Neuroradiology Unit, Department of Experimental and Clinical Biomedical Sciences "Mario Serio", University of Florence, 50121 Florence, Italy
| |
Collapse
|
47
|
Figini M, Castellano A, Bailo M, Callea M, Cadioli M, Bouyagoub S, Palombo M, Pieri V, Mortini P, Falini A, Alexander DC, Cercignani M, Panagiotaki E. Comprehensive Brain Tumour Characterisation with VERDICT-MRI: Evaluation of Cellular and Vascular Measures Validated by Histology. Cancers (Basel) 2023; 15:2490. [PMID: 37173965 PMCID: PMC10177485 DOI: 10.3390/cancers15092490] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/27/2023] [Revised: 04/14/2023] [Accepted: 04/17/2023] [Indexed: 05/15/2023] Open
Abstract
The aim of this work was to extend the VERDICT-MRI framework for modelling brain tumours, enabling comprehensive characterisation of both intra- and peritumoural areas with a particular focus on cellular and vascular features. Diffusion MRI data were acquired with multiple b-values (ranging from 50 to 3500 s/mm2), diffusion times, and echo times in 21 patients with brain tumours of different types and with a wide range of cellular and vascular features. We fitted a selection of diffusion models that resulted from the combination of different types of intracellular, extracellular, and vascular compartments to the signal. We compared the models using criteria for parsimony while aiming at good characterisation of all of the key histological brain tumour components. Finally, we evaluated the parameters of the best-performing model in the differentiation of tumour histotypes, using ADC (Apparent Diffusion Coefficient) as a clinical standard reference, and compared them to histopathology and relevant perfusion MRI metrics. The best-performing model for VERDICT in brain tumours was a three-compartment model accounting for anisotropically hindered and isotropically restricted diffusion and isotropic pseudo-diffusion. VERDICT metrics were compatible with the histological appearance of low-grade gliomas and metastases and reflected differences found by histopathology between multiple biopsy samples within tumours. The comparison between histotypes showed that both the intracellular and vascular fractions tended to be higher in tumours with high cellularity (glioblastoma and metastasis), and quantitative analysis showed a trend toward higher values of the intracellular fraction (fic) within the tumour core with increasing glioma grade. We also observed a trend towards a higher free water fraction in vasogenic oedemas around metastases compared to infiltrative oedemas around glioblastomas and WHO 3 gliomas as well as the periphery of low-grade gliomas. In conclusion, we developed and evaluated a multi-compartment diffusion MRI model for brain tumours based on the VERDICT framework, which showed agreement between non-invasive microstructural estimates and histology and encouraging trends for the differentiation of tumour types and sub-regions.
Collapse
Affiliation(s)
- Matteo Figini
- Centre for Medical Image Computing and Department of Computer Science, University College London, London WC1V 6LJ, UK
| | - Antonella Castellano
- Neuroradiology Unit and CERMAC, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, 20132 Milan, Italy
| | - Michele Bailo
- Department of Neurosurgery and Gamma Knife Radiosurgery, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, 20132 Milan, Italy
| | - Marcella Callea
- Pathology Unit, IRCCS Ospedale San Raffaele, 20132 Milan, Italy
| | | | - Samira Bouyagoub
- Clinical Imaging Sciences Centre, Brighton and Sussex Medical School, Brighton BN1 9RR, UK
| | - Marco Palombo
- Centre for Medical Image Computing and Department of Computer Science, University College London, London WC1V 6LJ, UK
- Cardiff University Brain Research Imaging Centre (CUBRIC), School of Psychology, Cardiff University, Cardiff CF24 4HQ, UK
| | - Valentina Pieri
- Neuroradiology Unit and CERMAC, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, 20132 Milan, Italy
| | - Pietro Mortini
- Department of Neurosurgery and Gamma Knife Radiosurgery, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, 20132 Milan, Italy
| | - Andrea Falini
- Neuroradiology Unit and CERMAC, IRCCS Ospedale San Raffaele, Vita-Salute San Raffaele University, 20132 Milan, Italy
| | - Daniel C. Alexander
- Centre for Medical Image Computing and Department of Computer Science, University College London, London WC1V 6LJ, UK
| | - Mara Cercignani
- Clinical Imaging Sciences Centre, Brighton and Sussex Medical School, Brighton BN1 9RR, UK
- Cardiff University Brain Research Imaging Centre (CUBRIC), School of Psychology, Cardiff University, Cardiff CF24 4HQ, UK
| | - Eleftheria Panagiotaki
- Centre for Medical Image Computing and Department of Computer Science, University College London, London WC1V 6LJ, UK
| |
Collapse
|
48
|
Chen Z, Zhai X, Chen Z. Computed cancer magnetic susceptibility imaging (canχ): Computational inverse mappings of cancer MRI. Magn Reson Imaging 2023; 102:86-95. [PMID: 37075866 DOI: 10.1016/j.mri.2023.04.003] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/05/2023] [Revised: 03/31/2023] [Accepted: 04/16/2023] [Indexed: 04/21/2023]
Abstract
PURPOSE We report a new cancer imaging modality in the contrast of tissue intrinsic susceptibility property by computed inverse magnetic resonance imaging (CIMRI). METHODS In MRI physics, an MRI signal is formed from tissue magnetism source (primarily magnetic susceptibility χ) through a cascade of MRI-introduced transformations (e.g. dipole-convolved magnetization) involving MRI setting parameters (e.g. echo time). In two-step computational inverse mappings (from phase image to internal fieldmap to susceptibility source), we could remove the MRI transformations and imaging parameters, thereby obtaining χ-depicted cancer images (canχ) from MRI phase images. Canχ is computationally implemented from clinical cancer MRI phase image by CIMRI. RESULTS As a result of MRI effect removal through computational inverse mappings, the reconstructed χ map (canχ) could provide a new cancerous tissue depiction in contrast of tissue intrinsic magnetism property (i.e. diamagnetism vs paramagnetism) as in an off-scanner state (e.g. in absence of main field B0). CONCLUSION Through retrospective clinical cancer MRI data analysis, we reported on the canχ method in technical details and demonstrated its feasibility of innovating cancer imaging in the contrast of tissue intrinsic paramagnetism/diamagnetism property (in a cancer tissue state free from MRI effect).
Collapse
Affiliation(s)
- Zikuan Chen
- Diagnostic Radiology, City of Hope National Medical Center, Duarte, CA 91010, United States of America; Zinv LLC, Albuquerque, NM 87108, United States of America.
| | - Xiulan Zhai
- Zinv LLC, Albuquerque, NM 87108, United States of America
| | - Zeyuan Chen
- Department of Computer Sciences, University of California-Davis, Davis, CA 95616, United States of America; Microsoft Corporation, Seattle, WA 98052, United States of America.
| |
Collapse
|
49
|
Shi S, Zhong J, Peng W, Yin H, Zhong D, Cui H, Sun X. System analysis based on the migration- and invasion-related gene sets identifies the infiltration-related genes of glioma. Front Oncol 2023; 13:1075716. [PMID: 37091145 PMCID: PMC10117932 DOI: 10.3389/fonc.2023.1075716] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2022] [Accepted: 03/23/2023] [Indexed: 04/09/2023] Open
Abstract
The current database has no information on the infiltration of glioma samples. Here, we assessed the glioma samples' infiltration in The Cancer Gene Atlas (TCGA) through the single-sample Gene Set Enrichment Analysis (ssGSEA) with migration and invasion gene sets. The Weighted Gene Co-expression Network Analysis (WGCNA) and the differentially expressed genes (DEGs) were used to identify the genes most associated with infiltration. Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) were used to analyze the major biological processes and pathways. Protein-protein interaction (PPI) network analysis and the least absolute shrinkage and selection operator (LASSO) were used to screen the key genes. Furthermore, the nomograms and receiver operating characteristic (ROC) curve were used to evaluate the prognostic and predictive accuracy of this clinical model in patients in TCGA and the Chinese Glioma Genome Atlas (CGGA). The results showed that turquoise was selected as the hub module, and with the intersection of DEGs, we screened 104 common genes. Through LASSO regression, TIMP1, EMP3, IGFBP2, and the other nine genes were screened mostly in correlation with infiltration and prognosis. EMP3 was selected to be verified in vitro. These findings could help researchers better understand the infiltration of gliomas and provide novel therapeutic targets for the treatment of gliomas.
Collapse
Affiliation(s)
- Shuang Shi
- Department of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Jiacheng Zhong
- Department of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Wen Peng
- State Key Laboratory of Silkworm Genome Biology, Southwest University, Chongqing, China
- Cancer Center, Medical Research Institute, Southwest University, Chongqing, China
| | - Haoyang Yin
- Department of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Dong Zhong
- Department of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| | - Hongjuan Cui
- State Key Laboratory of Silkworm Genome Biology, Southwest University, Chongqing, China
- Cancer Center, Medical Research Institute, Southwest University, Chongqing, China
| | - Xiaochuan Sun
- Department of Neurosurgery, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China
| |
Collapse
|
50
|
Mengide JP, Berros MF, Turza ME, Liñares JM. Posterior fossa tumors in children: An update and new concepts. Surg Neurol Int 2023; 14:114. [PMID: 37151431 PMCID: PMC10159277 DOI: 10.25259/sni_43_2023] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/14/2023] [Accepted: 03/15/2023] [Indexed: 04/03/2023] Open
Abstract
Background:
Posterior fossa tumors account for approximately half of the central nervous system tumors in children. Major technological advances, mainly in the fields of molecular biology and neuroimaging, have modified their classification, leading to a more detailed description of these entities. Into the classic taxonomy, used for many years, new concepts have been incorporated at times eliminating or modifying former ones.
Methods:
A literature search was conducted in PubMed using the medical subject headings involving the five most common pediatric posterior fossa tumors: diffuse midline glioma, medulloblastoma, ependymoma, atypical teratoid/rhabdoid tumor, and pilocytic astrocytoma. Only English published articles in the past 11 years that provided technological, neuroimaging, and molecular biology insight into posterior fossa tumors in children were considered.
Results:
Substantial changes have been introduced in the nomenclature of pediatric posterior fossa tumors. Diffuse midline gliomas are named based on alterations in histone H3. Molecular rearrangements of medulloblastomas are more important in defining the prognosis than histological variants; therefore, these tumors are currently named based on their molecular subgroups. Posterior fossa ependymomas and atypical teratoid rhabdoid tumor classification have incorporated new groups based on different genetic profiles. Pilocytic astrocytoma has been placed in a new category that distinguishes circumscribed from diffuse entities.
Conclusion:
Advances in molecular biology and neuroimaging have substantially changed the way pediatric neoplasms are studied. The classical taxonomy has been modified leading to more accurate classifications that are based on the genetic alterations.
Collapse
Affiliation(s)
- Juan Pablo Mengide
- Division of Pediatric Neurosurgery, Hospital Provincial Neuquen Dr. Castro Rendon, Neuquen, Argentina
| | | | | | - Juan Manuel Liñares
- Division of Pediatric Neurosurgery, Hospital Provincial Neuquen Dr. Castro Rendon, Neuquen, Argentina
| |
Collapse
|