1
|
Bathla G, Dhruba DD, Liu Y, Le NH, Soni N, Zhang H, Mohan S, Roberts-Wolfe D, Rathore S, Sonka M, Priya S, Agarwal A. Differentiation Between Glioblastoma and Metastatic Disease on Conventional MRI Imaging Using 3D-Convolutional Neural Networks: Model Development and Validation. Acad Radiol 2024; 31:2041-2049. [PMID: 37977889 DOI: 10.1016/j.acra.2023.10.044] [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: 08/13/2023] [Revised: 10/24/2023] [Accepted: 10/25/2023] [Indexed: 11/19/2023]
Abstract
RATIONALE AND OBJECTIVES Imaging-based differentiation between glioblastoma (GB) and brain metastases (BM) remains challenging. Our aim was to evaluate the performance of 3D-convolutional neural networks (CNN) to address this binary classification problem. MATERIALS AND METHODS T1-CE, T2WI, and FLAIR 3D-segmented masks of 307 patients (157 GB and 150 BM) were generated post resampling, co-registration normalization and semi-automated 3D-segmentation and used for internal model development. Subsequent external validation was performed on 59 cases (27 GB and 32 BM) from another institution. Four different mask-sequence combinations were evaluated using area under the curve (AUC), precision, recall and F1-scores. Diagnostic performance of a neuroradiologist and a general radiologist, both without and with the model output available, was also assessed. RESULTS 3D-model using the T1-CE tumor mask (TM) showed the highest performance [AUC 0.93 (95% CI 0.858-0.995)] on the external test set, followed closely by the model using T1-CE TM and FLAIR mask of peri-tumoral region (PTR) [AUC of 0.91 (95% CI 0.834-0.986)]. Models using T2WI masks showed robust performance on the internal dataset but lower performance on the external set. Both neuroradiologist and general radiologist showed improved performance with model output provided [AUC increased from 0.89 to 0.968 (p = 0.06) and from 0.78 to 0.965 (p = 0.007) respectively], the latter being statistically significant. CONCLUSION 3D-CNNs showed robust performance for differentiating GB from BMs, with T1-CE TM, either alone or combined with FLAIR-PTR masks. Availability of model output significantly improved the accuracy of the general radiologist.
Collapse
Affiliation(s)
- Girish Bathla
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA (G.B., N.S., S.P.); Department of Radiology, Mayo Clinic, Rochester, Minnesota, USA (G.B.)
| | - Durjoy Deb Dhruba
- Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa, USA (D.D.D.).
| | - Yanan Liu
- College of Engineering, University of Iowa, Iowa City, Iowa, USA (Y.L., N.H.L., H.Z., M.S.)
| | - Nam H Le
- College of Engineering, University of Iowa, Iowa City, Iowa, USA (Y.L., N.H.L., H.Z., M.S.)
| | - Neetu Soni
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA (G.B., N.S., S.P.); Department of Radiology, Mayo Clinic, Jacksonville, Florida, USA (N.S., A.A.)
| | - Honghai Zhang
- College of Engineering, University of Iowa, Iowa City, Iowa, USA (Y.L., N.H.L., H.Z., M.S.)
| | - Suyash Mohan
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Pennsylvania, USA (S.M., D.R.W.)
| | - Douglas Roberts-Wolfe
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Pennsylvania, USA (S.M., D.R.W.)
| | - Saima Rathore
- Senior research scientist, Avid Radiopharmaceuticals, Philadelphia, Pennsylvania, USA (S.R.)
| | - Milan Sonka
- College of Engineering, University of Iowa, Iowa City, Iowa, USA (Y.L., N.H.L., H.Z., M.S.)
| | - Sarv Priya
- Department of Radiology, University of Iowa Hospitals and Clinics, Iowa City, Iowa, USA (G.B., N.S., S.P.)
| | - Amit Agarwal
- Department of Radiology, Mayo Clinic, Jacksonville, Florida, USA (N.S., A.A.)
| |
Collapse
|
2
|
Shen S, Li C, Fan Y, Lu S, Yan Z, Liu H, Zhou H, Zhang Z. Development and validation of a multi-modality fusion deep learning model for differentiating glioblastoma from solitary brain metastases. ZHONG NAN DA XUE XUE BAO. YI XUE BAN = JOURNAL OF CENTRAL SOUTH UNIVERSITY. MEDICAL SCIENCES 2024; 49:58-67. [PMID: 38615167 PMCID: PMC11017031 DOI: 10.11817/j.issn.1672-7347.2024.230248] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Received: 06/14/2023] [Indexed: 04/15/2024]
Abstract
OBJECTIVES Glioblastoma (GBM) and brain metastases (BMs) are the two most common malignant brain tumors in adults. Magnetic resonance imaging (MRI) is a commonly used method for screening and evaluating the prognosis of brain tumors, but the specificity and sensitivity of conventional MRI sequences in differential diagnosis of GBM and BMs are limited. In recent years, deep neural network has shown great potential in the realization of diagnostic classification and the establishment of clinical decision support system. This study aims to apply the radiomics features extracted by deep learning techniques to explore the feasibility of accurate preoperative classification for newly diagnosed GBM and solitary brain metastases (SBMs), and to further explore the impact of multimodality data fusion on classification tasks. METHODS Standard protocol cranial MRI sequence data from 135 newly diagnosed GBM patients and 73 patients with SBMs confirmed by histopathologic or clinical diagnosis were retrospectively analyzed. First, structural T1-weight, T1C-weight, and T2-weight were selected as 3 inputs to the entire model, regions of interest (ROIs) were manually delineated on the registered three modal MR images, and multimodality radiomics features were obtained, dimensions were reduced using a random forest (RF)-based feature selection method, and the importance of each feature was further analyzed. Secondly, we used the method of contrast disentangled to find the shared features and complementary features between different modal features. Finally, the response of each sample to GBM and SBMs was predicted by fusing 2 features from different modalities. RESULTS The radiomics features using machine learning and the multi-modal fusion method had a good discriminatory ability for GBM and SBMs. Furthermore, compared with single-modal data, the multimodal fusion models using machine learning algorithms such as support vector machine (SVM), Logistic regression, RF, adaptive boosting (AdaBoost), and gradient boosting decision tree (GBDT) achieved significant improvements, with area under the curve (AUC) values of 0.974, 0.978, 0.943, 0.938, and 0.947, respectively; our comparative disentangled multi-modal MR fusion method performs well, and the results of AUC, accuracy (ACC), sensitivity (SEN) and specificity(SPE) in the test set were 0.985, 0.984, 0.900, and 0.990, respectively. Compared with other multi-modal fusion methods, AUC, ACC, and SEN in this study all achieved the best performance. In the ablation experiment to verify the effects of each module component in this study, AUC, ACC, and SEN increased by 1.6%, 10.9% and 15.0%, respectively after 3 loss functions were used simultaneously. CONCLUSIONS A deep learning-based contrast disentangled multi-modal MR radiomics feature fusion technique helps to improve GBM and SBMs classification accuracy.
Collapse
Affiliation(s)
- Shanshan Shen
- Department of Oncology, Second Hospital of Jiaxing, Jiaxing Zhejiang 314000.
- Information Engineering School of Nanchang University, Nanchang 330031.
| | - Chunquan Li
- Information Engineering School of Nanchang University, Nanchang 330031
| | - Yaohua Fan
- Department of Oncology, Second Hospital of Jiaxing, Jiaxing Zhejiang 314000
| | - Shanfu Lu
- Perception Vision Medical Technologies Co., Ltd., Guangzhou 510530
| | - Ziye Yan
- Perception Vision Medical Technologies Co., Ltd., Guangzhou 510530
| | - Hu Liu
- Department of Radiology, Second Hospital of Jiaxing, Jiaxing Zhejiang 314000
| | - Haihang Zhou
- Department of Neurosurgery, Second Hospital of Jiaxing, Jiaxing Zhejiang 314000
| | - Zijian Zhang
- Department of Oncology, Xiangya Hospital, Central South University, Changsha 410008, China.
| |
Collapse
|
3
|
Koga SF, Hodges WB, Adamyan H, Hayes T, Fecci PE, Tsvankin V, Pradilla G, Hoang KB, Lee IY, Sankey EW, Codd PJ, Huie D, Zacharia BE, Verma R, Baboyan VG. Preoperative validation of edema-corrected tractography in neurosurgical practice: translating surgeon insights into novel software implementation. Front Neurol 2024; 14:1322815. [PMID: 38259649 PMCID: PMC10801029 DOI: 10.3389/fneur.2023.1322815] [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: 10/16/2023] [Accepted: 12/19/2023] [Indexed: 01/24/2024] Open
Abstract
Background Peritumoral edema alters diffusion anisotropy, resulting in false negatives in tractography reconstructions negatively impacting surgical decision-making. With supratotal resections tied to survival benefit in glioma patients, advanced diffusion modeling is critical to visualize fibers within the peritumoral zone to prevent eloquent fiber transection thereafter. A preoperative assessment paradigm is therefore warranted to systematically evaluate multi-subject tractograms along clinically meaningful parameters. We propose a novel noninvasive surgically-focused survey to evaluate the benefits of a tractography algorithm for preoperative planning, subsequently applied to Synaptive Medical's free-water correction algorithm developed for clinically feasible single-shell DTI data. Methods Ten neurosurgeons participated in the study and were presented with patient datasets containing histological lesions of varying degrees of edema. They were asked to compare standard (uncorrected) tractography reconstructions overlaid onto anatomical images with enhanced (corrected) reconstructions. The raters assessed the datasets in terms of overall data quality, tract alteration patterns, and the impact of the correction on lesion definition, brain-tumor interface, and optimal surgical pathway. Inter-rater reliability coefficients were calculated, and statistical comparisons were made. Results Standard tractography was perceived as problematic in areas proximal to the lesion, presenting with significant tract reduction that challenged assessment of the brain-tumor interface and of tract infiltration. With correction applied, significant reduction in false negatives were reported along with additional insight into tract infiltration. Significant positive correlations were shown between favorable responses to the correction algorithm and the lesion-to-edema ratio, such that the correction offered further clarification in increasingly edematous and malignant lesions. Lastly, the correction was perceived to introduce false tracts in CSF spaces and - to a lesser degree - the grey-white matter interface, highlighting the need for noise mitigation. As a result, the algorithm was modified by free-water-parameterizing the tractography dataset and introducing a novel adaptive thresholding tool for customizable correction guided by the surgeon's discretion. Conclusion Here we translate surgeon insights into a clinically deployable software implementation capable of recovering peritumoral tracts in edematous zones while mitigating artifacts through the introduction of a novel and adaptive case-specific correction tool. Together, these advances maximize tractography's clinical potential to personalize surgical decisions when faced with complex pathologies.
Collapse
Affiliation(s)
- Sebastian F. Koga
- Franciscan Missionaries of Our Lady Health System, Baton Rouge, LA, United States
| | | | | | - Tim Hayes
- Synaptive Medical Inc., Toronto, ON, Canada
| | - Peter E. Fecci
- Department of Neurosurgery, Duke University Medical Center, Durham, NC, United States
| | - Vadim Tsvankin
- Colorado Brain and Spine Institute, Englewood, CO, United States
| | - Gustavo Pradilla
- Department of Neurosurgery, Emory University School of Medicine, Atlanta, GA, United States
| | - Kimberly B. Hoang
- Department of Neurosurgery, Emory University School of Medicine, Atlanta, GA, United States
| | - Ian Y. Lee
- Department of Neurosurgery, Henry Ford Health System, Detroit, MI, United States
| | - Eric W. Sankey
- Department of Neurosurgery, Duke University Medical Center, Durham, NC, United States
| | - Patrick J. Codd
- Department of Neurosurgery, Duke University Medical Center, Durham, NC, United States
| | - David Huie
- Department of Neurosurgery, Duke University Medical Center, Durham, NC, United States
| | - Brad E. Zacharia
- Department of Neurosurgery, Penn State Hershey Medical Center, Hershey, PA, United States
| | - Ragini Verma
- Department of Radiology, University of Pennsylvania, Philadelphia, PA, United States
- Cohen Veterans Bioscience, New York, NY, United States
| | | |
Collapse
|
4
|
Zhu FY, Sun YF, Yin XP, Zhang Y, Xing LH, Ma ZP, Xue LY, Wang JN. Using machine learning-based radiomics to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes. Discov Oncol 2023; 14:224. [PMID: 38055122 DOI: 10.1007/s12672-023-00837-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/03/2023] [Accepted: 11/22/2023] [Indexed: 12/07/2023] Open
Abstract
OBJECTIVE To establish a machine learning-based radiomics model to differentiate between glioma and solitary brain metastasis from lung cancer and its subtypes, thereby achieving accurate preoperative classification. MATERIALS AND METHODS A retrospective analysis was conducted on MRI T1WI-enhanced images of 105 patients with glioma and 172 patients with solitary brain metastasis from lung cancer, which were confirmed pathologically. The patients were divided into the training group and validation group in an 8:2 ratio for image segmentation, extraction, and filtering; multiple layer perceptron (MLP), support vector machine (SVM), random forest (RF), and logistic regression (LR) were used for modeling; fivefold cross-validation was used to train the model; the validation group was used to evaluate and assess the predictive performance of the model, ROC curve was used to calculate the accuracy, sensitivity, and specificity of the model, and the area under curve (AUC) was used to assess the predictive performance of the model. RESULTS The accuracy and AUC of the MLP differentiation model for high-grade glioma and solitary brain metastasis in the validation group was 0.992, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.968, respectively. The accuracy and AUC for the MLP and SVM differentiation model for high-grade glioma and small cell lung cancer brain metastasis in the validation group was 0.966, 1.000, respectively, while the sensitivity and specificity were 1.000, 0.929, respectively. The accuracy and AUC for the MLP differentiation model for high-grade glioma and non-small cell lung cancer brain metastasis in the validation group was 0.982, 0.999, respectively, while the sensitivity and specificity were 0.958, 1.000, respectively. CONCLUSION The application of machine learning-based radiomics has a certain clinical value in differentiating glioma from solitary brain metastasis from lung cancer and its subtypes. In the HGG/SBM and HGG/NSCLC SBM validation groups, the MLP model had the best diagnostic performance, while in the HGG/SCLC SBM validation group, the MLP and SVM models had the best diagnostic performance.
Collapse
Affiliation(s)
- Feng-Ying Zhu
- Department of Radiology, Affiliated Hospital of Hebei University, No.212 of Yuhua Road, Lianchi District, Baoding, 071000, China
| | - Yu-Feng Sun
- College of Electronic Information Engineering, Hebei University, Baoding, 071002, China
| | - Xiao-Ping Yin
- Department of Radiology, Affiliated Hospital of Hebei University, No.212 of Yuhua Road, Lianchi District, Baoding, 071000, China
| | - Yu Zhang
- Department of Radiology, Affiliated Hospital of Hebei University, No.212 of Yuhua Road, Lianchi District, Baoding, 071000, China
| | - Li-Hong Xing
- Department of Radiology, Affiliated Hospital of Hebei University, No.212 of Yuhua Road, Lianchi District, Baoding, 071000, China
| | - Ze-Peng Ma
- Department of Radiology, Affiliated Hospital of Hebei University, No.212 of Yuhua Road, Lianchi District, Baoding, 071000, China
| | - Lin-Yan Xue
- College of Quality and Technical Supervision, Hebei University, No.180 of Wusi Road, Lianchi District, Baoding, 071002, China.
| | - Jia-Ning Wang
- Department of Radiology, Affiliated Hospital of Hebei University, No.212 of Yuhua Road, Lianchi District, Baoding, 071000, China.
| |
Collapse
|
5
|
Okada T. Editorial for "Glioblastoma and Solitary Brain Metastasis: Differentiation by Integrating Demographic-MRI and Deep-Learning Radiomics Signatures". J Magn Reson Imaging 2023. [PMID: 37974516 DOI: 10.1002/jmri.29126] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Accepted: 10/02/2023] [Indexed: 11/19/2023] Open
Affiliation(s)
- Tomohisa Okada
- Human Brain Research Center, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| |
Collapse
|
6
|
Raghavendra U, Gudigar A, Paul A, Goutham TS, Inamdar MA, Hegde A, Devi A, Ooi CP, Deo RC, Barua PD, Molinari F, Ciaccio EJ, Acharya UR. Brain tumor detection and screening using artificial intelligence techniques: Current trends and future perspectives. Comput Biol Med 2023; 163:107063. [PMID: 37329621 DOI: 10.1016/j.compbiomed.2023.107063] [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: 12/26/2022] [Revised: 05/16/2023] [Accepted: 05/19/2023] [Indexed: 06/19/2023]
Abstract
A brain tumor is an abnormal mass of tissue located inside the skull. In addition to putting pressure on the healthy parts of the brain, it can lead to significant health problems. Depending on the region of the brain tumor, it can cause a wide range of health issues. As malignant brain tumors grow rapidly, the mortality rate of individuals with this cancer can increase substantially with each passing week. Hence it is vital to detect these tumors early so that preventive measures can be taken at the initial stages. Computer-aided diagnostic (CAD) systems, in coordination with artificial intelligence (AI) techniques, have a vital role in the early detection of this disorder. In this review, we studied 124 research articles published from 2000 to 2022. Here, the challenges faced by CAD systems based on different modalities are highlighted along with the current requirements of this domain and future prospects in this area of research.
Collapse
Affiliation(s)
- U Raghavendra
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, India
| | - Anjan Gudigar
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, India.
| | - Aritra Paul
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, India
| | - T S Goutham
- Department of Instrumentation and Control Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, India
| | - Mahesh Anil Inamdar
- Department of Mechatronics, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, 576104, India
| | - Ajay Hegde
- Consultant Neurosurgeon Manipal Hospitals, Sarjapur Road, Bangalore, India
| | - Aruna Devi
- School of Education and Tertiary Access, University of the Sunshine Coast, Caboolture Campus, Australia
| | - Chui Ping Ooi
- School of Science and Technology, Singapore University of Social Sciences, Singapore, 599494, Singapore
| | - Ravinesh C Deo
- School of Mathematics, Physics, and Computing, University of Southern Queensland, Springfield, QLD, 4300, Australia
| | - Prabal Datta Barua
- Cogninet Brain Team, Cogninet Australia, Sydney, NSW, 2010, Australia; School of Business (Information Systems), Faculty of Business, Education, Law & Arts, University of Southern Queensland, Toowoomba, QLD, 4350, Australia; Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, NSW, 2007, Australia
| | - Filippo Molinari
- Department of Electronics and Telecommunications, Politecnico di Torino, 10129, Torino, Italy
| | - Edward J Ciaccio
- Department of Medicine, Columbia University Medical Center, New York, NY, 10032, USA
| | - U Rajendra Acharya
- School of Mathematics, Physics, and Computing, University of Southern Queensland, Springfield, QLD, 4300, Australia; International Research Organization for Advanced Science and Technology (IROAST), Kumamoto University, Kumamoto, 860-8555, Japan
| |
Collapse
|
7
|
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
|
8
|
Tabassum M, Suman AA, Suero Molina E, Pan E, Di Ieva A, Liu S. Radiomics and Machine Learning in Brain Tumors and Their Habitat: A Systematic Review. Cancers (Basel) 2023; 15:3845. [PMID: 37568660 PMCID: PMC10417709 DOI: 10.3390/cancers15153845] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2023] [Accepted: 07/24/2023] [Indexed: 08/13/2023] Open
Abstract
Radiomics is a rapidly evolving field that involves extracting and analysing quantitative features from medical images, such as computed tomography or magnetic resonance images. Radiomics has shown promise in brain tumor diagnosis and patient-prognosis prediction by providing more detailed and objective information about tumors' features than can be obtained from the visual inspection of the images alone. Radiomics data can be analyzed to determine their correlation with a tumor's genetic status and grade, as well as in the assessment of its recurrence vs. therapeutic response, among other features. In consideration of the multi-parametric and high-dimensional space of features extracted by radiomics, machine learning can further improve tumor diagnosis, treatment response, and patients' prognoses. There is a growing recognition that tumors and their microenvironments (habitats) mutually influence each other-tumor cells can alter the microenvironment to increase their growth and survival. At the same time, habitats can also influence the behavior of tumor cells. In this systematic review, we investigate the current limitations and future developments in radiomics and machine learning in analysing brain tumors and their habitats.
Collapse
Affiliation(s)
- Mehnaz Tabassum
- Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, Australia;
- Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW 2109, Australia; (A.A.S.); (E.S.M.); (E.P.)
| | - Abdulla Al Suman
- Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW 2109, Australia; (A.A.S.); (E.S.M.); (E.P.)
| | - Eric Suero Molina
- Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW 2109, Australia; (A.A.S.); (E.S.M.); (E.P.)
- Department of Neurosurgery, University Hospital of Münster, 48149 Münster, Germany
| | - Elizabeth Pan
- Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW 2109, Australia; (A.A.S.); (E.S.M.); (E.P.)
- Faculty of Medicine and Health Sciences, Macquarie University, Sydney, NSW 2109, Australia
| | - Antonio Di Ieva
- Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW 2109, Australia; (A.A.S.); (E.S.M.); (E.P.)
| | - Sidong Liu
- Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Sydney, NSW 2109, Australia;
- Computational NeuroSurgery (CNS) Lab, Macquarie Medical School, Macquarie University, Sydney, NSW 2109, Australia; (A.A.S.); (E.S.M.); (E.P.)
| |
Collapse
|
9
|
Chen L, Li T, Li Y, Zhang J, Li S, Zhu L, Qin J, Tang L, Zeng Z. Combining amide proton transfer-weighted and arterial spin labeling imaging to differentiate solitary brain metastases from glioblastomas. Magn Reson Imaging 2023; 102:96-102. [PMID: 37172748 DOI: 10.1016/j.mri.2023.05.004] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/26/2023] [Revised: 05/03/2023] [Accepted: 05/09/2023] [Indexed: 05/15/2023]
Abstract
PURPOSE To evaluate the clinical utility of amide proton transfer-weighted imaging (APTw) and arterial spin labeling (ASL) in differentiating solitary brain metastases (SBMs) from glioblastomas (GBMs). METHODS Forty-eight patients diagnosed with brain tumors were enrolled. All patients underwent conventional MRI, APTw, and ASL scans on a 3.0 T MRI system. The mean APTw value and mean cerebral blood flow (CBF) value were measured. The differences in various parameters between GBMs and SBMs were assessed using the independent-samples t-test. The quantitative performance of these MRI parameters in distinguishing between GBMs and SBMs was evaluated using receiver operating characteristic (ROC) curve analysis. RESULTS GBMs exhibited significantly higher APTw and CBF values in peritumoral regions compared with SBMs (P < 0.05). There was no significant difference between SBMs and GBMs in tumor cores. APTw MRI had a higher diagnostic efficiency in differentiating SBMs from GBMs (area under the curve [AUC]: 0.864; 75.0% sensitivity and 81.8% specificity). Combined use of APTw and CBF value increased the AUC to 0.927. CONCLUSION APTw may be superior to ASL for distinguishing between SBMs and GBMs. Combination of APTw and ASL showed better discrimination and a superior diagnostic performance.
Collapse
Affiliation(s)
- Ling Chen
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No.6, Shuangyong Road, Nanning, Guangxi 530021, China; Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Tao Li
- Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Yao Li
- Department of Neurosurgery, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Jinhuan Zhang
- Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Shuanghong Li
- Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Li Zhu
- Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Jianli Qin
- Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Lifang Tang
- Department of Medical Imaging Center, The Fourth Affiliated Hospital, Guangxi Medical University, Heping Road No.156, Liunan District, Liuzhou, Guangxi 545007, China
| | - Zisan Zeng
- Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, No.6, Shuangyong Road, Nanning, Guangxi 530021, China.
| |
Collapse
|
10
|
Petinrin OO, Saeed F, Toseef M, Liu Z, Basurra S, Muyide IO, Li X, Lin Q, Wong KC. Machine Learning in Metastatic Cancer Research: Potentials, Possibilities, and Prospects. Comput Struct Biotechnol J 2023; 21:2454-2470. [PMID: 37077177 PMCID: PMC10106342 DOI: 10.1016/j.csbj.2023.03.046] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Revised: 03/26/2023] [Accepted: 03/27/2023] [Indexed: 03/31/2023] Open
Abstract
Cancer has received extensive recognition for its high mortality rate, with metastatic cancer being the top cause of cancer-related deaths. Metastatic cancer involves the spread of the primary tumor to other body organs. As much as the early detection of cancer is essential, the timely detection of metastasis, the identification of biomarkers, and treatment choice are valuable for improving the quality of life for metastatic cancer patients. This study reviews the existing studies on classical machine learning (ML) and deep learning (DL) in metastatic cancer research. Since the majority of metastatic cancer research data are collected in the formats of PET/CT and MRI image data, deep learning techniques are heavily involved. However, its black-box nature and expensive computational cost are notable concerns. Furthermore, existing models could be overestimated for their generality due to the non-diverse population in clinical trial datasets. Therefore, research gaps are itemized; follow-up studies should be carried out on metastatic cancer using machine learning and deep learning tools with data in a symmetric manner.
Collapse
|
11
|
Riahi Samani Z, Parker D, Akbari H, Wolf RL, Brem S, Bakas S, Verma R. Artificial intelligence-based locoregional markers of brain peritumoral microenvironment. Sci Rep 2023; 13:963. [PMID: 36653382 PMCID: PMC9849348 DOI: 10.1038/s41598-022-26448-9] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/23/2022] [Accepted: 12/14/2022] [Indexed: 01/19/2023] Open
Abstract
In malignant primary brain tumors, cancer cells infiltrate into the peritumoral brain structures which results in inevitable recurrence. Quantitative assessment of infiltrative heterogeneity in the peritumoral region, the area where biopsy or resection can be hazardous, is important for clinical decision making. Here, we derive a novel set of Artificial intelligence (AI)-based markers capturing the heterogeneity of tumor infiltration, by characterizing free water movement restriction in the peritumoral region using Diffusion Tensor Imaging (DTI)-based free water volume fraction maps. We leverage the differences in the peritumoral region of metastasis and glioblastomas, the former consisting of vasogenic versus the latter containing infiltrative edema, to extract a voxel-wise deep learning-based peritumoral microenvironment index (PMI). Descriptive characteristics of locoregional hubs of uniformly high PMI values are then extracted as AI-based markers to capture distinct aspects of infiltrative heterogeneity. The proposed markers are utilized to stratify patients' survival and IDH1 mutation status on a population of 275 adult-type diffuse gliomas (CNS WHO grade 4). Our results show significant differences in the proposed markers between patients with different overall survival and IDH1 mutation status (t test, Wilcoxon rank sum test, linear regression; p < 0.01). Clustering of patients using the proposed markers reveals distinct survival groups (logrank; p < 10-5, Cox hazard ratio = 1.82; p < 0.005). Our findings provide a panel of markers as surrogates of infiltration that might capture novel insight about underlying biology of peritumoral microstructural heterogeneity, providing potential biomarkers of prognosis pertaining to survival and molecular stratification, with applicability in clinical decision making.
Collapse
Affiliation(s)
- Zahra Riahi Samani
- Diffusion & Connectomics In Precision Healthcare Research (DiCIPHR) Lab, University of Pennsylvania, Philadelphia, PA, 19104, USA.
- Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, 19104, USA.
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA.
| | - Drew Parker
- Diffusion & Connectomics In Precision Healthcare Research (DiCIPHR) Lab, University of Pennsylvania, Philadelphia, PA, 19104, USA
- Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, 19104, USA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Hamed Akbari
- Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, 19104, USA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Ronald L Wolf
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Steven Brem
- Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Spyridon Bakas
- Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, 19104, USA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
- Department of Pathology & Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| | - Ragini Verma
- Diffusion & Connectomics In Precision Healthcare Research (DiCIPHR) Lab, University of Pennsylvania, Philadelphia, PA, 19104, USA
- Center for Biomedical Image Computing and Analytics (CBICA), University of Pennsylvania, Philadelphia, PA, 19104, USA
- Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, 19104, USA
| |
Collapse
|
12
|
Alshammari A. Construction of VGG16 Convolution Neural Network (VGG16_CNN) Classifier with NestNet-Based Segmentation Paradigm for Brain Metastasis Classification. SENSORS (BASEL, SWITZERLAND) 2022; 22:s22208076. [PMID: 36298426 PMCID: PMC9606896 DOI: 10.3390/s22208076] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/18/2022] [Revised: 09/24/2022] [Accepted: 10/11/2022] [Indexed: 06/01/2023]
Abstract
Brain metastases (BMs) happen often in patients with metastatic cancer (MC), requiring initial and precise diagnosis of BMs, which remains important for medical care preparation and radiotherapy prognostication. Nevertheless, the susceptibility of automated BM (ABMS) diagnosis is unfairly great for minute BMs, and integrating into medical exercises to distinguish true metastases (MtS) from false positives remains difficult. For enhancing BM classification execution, MtS localization is performed through the NestNet framework. Subsequent to segmentation, classification is performed by employing the VGG16 convolution neural network. A novel loss function is computed by employing the weighted softmax function (WSF) for enhancing minute MtS diagnosis and for calibrating susceptibility and particularity. The aim of this study was to merge temporal prior data for ABMS detection. The proffered VGG16_CNN is capable of differentiating positive MtS among MtS candidates with high confidence, which typically needs distinct specialist analysis or additional investigation, remaining specifically apt for specialist reinforcement in actual medical practice. The proffered VGG16_CNN framework can be correlated with three advanced methodologies (moU-Net, DSNet, and U-Net) concerning diverse criteria. It was observed that the proffered VGG16_CNN attained 93.74% accuracy, 92% precision, 92.1% recall, and 67.08% F1-score.
Collapse
Affiliation(s)
- Abdulaziz Alshammari
- College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia
| |
Collapse
|
13
|
Eckel-Passow JE, Lachance DH, Decker PA, Kollmeyer TM, Kosel ML, Drucker KL, Slager S, Wrensch M, Tobin WO, Jenkins RB. Inherited genetics of adult diffuse glioma and polygenic risk scores-a review. Neurooncol Pract 2022; 9:259-270. [PMID: 35859544 PMCID: PMC9290891 DOI: 10.1093/nop/npac017] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/14/2022] Open
Abstract
Knowledge about inherited and acquired genetics of adult diffuse glioma has expanded significantly over the past decade. Genomewide association studies (GWAS) stratified by histologic subtype identified six germline variants that were associated specifically with glioblastoma (GBM) and 12 that were associated with lower grade glioma. A GWAS performed using the 2016 WHO criteria, stratifying patients by IDH mutation and 1p/19q codeletion (as well as TERT promoter mutation), discovered that many of the known variants are associated with specific WHO glioma subtypes. In addition, the GWAS stratified by molecular group identified two additional novel regions: variants in D2HGDH that were associated with tumors that had an IDH mutation and a variant near FAM20C that was associated with tumors that had both IDH mutation and 1p/19q codeletion. The results of these germline associations have been used to calculate polygenic risk scores, from which to estimate relative and absolute risk of overall glioma and risk of specific glioma subtypes. We will review the concept of polygenic risk models and their potential clinical utility, as well as discuss the published adult diffuse glioma polygenic risk models. To date, these prior genetic studies have been done on European populations. Using the published glioma polygenic risk model, we show that the genetic associations published to date do not generalize across genetic ancestries, demonstrating that genetic studies need to be done on more diverse populations.
Collapse
Affiliation(s)
- Jeanette E Eckel-Passow
- Corresponding Author: Jeanette E. Eckel-Passow, PhD, Department of Quantitative Health Sciences, Mayo Clinic, 200 First Street SW, Rochester, MN 55905, USA ()
| | - Daniel H Lachance
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota, USA
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Paul A Decker
- Department of Quantitative Health Sciences, Mayo Clinic, Rochester, Minnesota, USA
| | - Thomas M Kollmeyer
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota, USA
| | - Matthew L Kosel
- Department of Quantitative Health Sciences, Mayo Clinic, Rochester, Minnesota, USA
| | - Kristen L Drucker
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota, USA
| | - Susan Slager
- Department of Quantitative Health Sciences, Mayo Clinic, Rochester, Minnesota, USA
| | - Margaret Wrensch
- Department of Neurological Surgery, Institute of Human Genetics, University of California, San Francisco, San Francisco, California, USA
| | | | | |
Collapse
|
14
|
Machine Learning Applications for Differentiation of Glioma from Brain Metastasis-A Systematic Review. Cancers (Basel) 2022; 14:cancers14061369. [PMID: 35326526 PMCID: PMC8946855 DOI: 10.3390/cancers14061369] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/19/2022] [Revised: 02/22/2022] [Accepted: 03/01/2022] [Indexed: 12/19/2022] Open
Abstract
Simple Summary We present a systematic review of published reports on machine learning (ML) applications for the differentiation of gliomas from brain metastases by summarizing study characteristics, strengths, and pitfalls. Based on these findings, we present recommendations for future research in this field. Abstract Glioma and brain metastasis can be difficult to distinguish on conventional magnetic resonance imaging (MRI) due to the similarity of imaging features in specific clinical circumstances. Multiple studies have investigated the use of machine learning (ML) models for non-invasive differentiation of glioma from brain metastasis. Many of the studies report promising classification results, however, to date, none have been implemented into clinical practice. After a screening of 12,470 studies, we included 29 eligible studies in our systematic review. From each study, we aggregated data on model design, development, and best classifiers, as well as quality of reporting according to the TRIPOD statement. In a subset of eligible studies, we conducted a meta-analysis of the reported AUC. It was found that data predominantly originated from single-center institutions (n = 25/29) and only two studies performed external validation. The median TRIPOD adherence was 0.48, indicating insufficient quality of reporting among surveyed studies. Our findings illustrate that despite promising classification results, reliable model assessment is limited by poor reporting of study design and lack of algorithm validation and generalizability. Therefore, adherence to quality guidelines and validation on outside datasets is critical for the clinical translation of ML for the differentiation of glioma and brain metastasis.
Collapse
|