1
|
Lewis D, Li KL, Waqar M, Coope DJ, Pathmanaban ON, King AT, Djoukhadar I, Zhao S, Cootes TF, Jackson A, Zhu X. Low-dose GBCA administration for brain tumour dynamic contrast enhanced MRI: a feasibility study. Sci Rep 2024; 14:4905. [PMID: 38418818 PMCID: PMC10902320 DOI: 10.1038/s41598-024-53871-x] [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: 02/06/2024] [Indexed: 03/02/2024] Open
Abstract
A key limitation of current dynamic contrast enhanced (DCE) MRI techniques is the requirement for full-dose gadolinium-based contrast agent (GBCA) administration. The purpose of this feasibility study was to develop and assess a new low GBCA dose protocol for deriving high-spatial resolution kinetic parameters from brain DCE-MRI. Nineteen patients with intracranial skull base tumours were prospectively imaged at 1.5 T using a single-injection, fixed-volume low GBCA dose, dual temporal resolution interleaved DCE-MRI acquisition. The accuracy of kinetic parameters (ve, Ktrans, vp) derived using this new low GBCA dose technique was evaluated through both Monte-Carlo simulations (mean percent deviation, PD, of measured from true values) and an in vivo study incorporating comparison with a conventional full-dose GBCA protocol and correlation with histopathological data. The mean PD of data from the interleaved high-temporal-high-spatial resolution approach outperformed use of high-spatial, low temporal resolution datasets alone (p < 0.0001, t-test). Kinetic parameters derived using the low-dose interleaved protocol correlated significantly with parameters derived from a full-dose acquisition (p < 0.001) and demonstrated a significant association with tissue markers of microvessel density (p < 0.05). Our results suggest accurate high-spatial resolution kinetic parameter mapping is feasible with significantly reduced GBCA dose.
Collapse
Affiliation(s)
- Daniel Lewis
- Department of Neurosurgery, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Manchester Academic Health Science Centre, Manchester, UK.
- Geoffrey Jefferson Brain Research Centre, University of Manchester, Manchester, UK.
- Division of Neuroscience and Experimental Psychology, School of Biological Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK.
- Department of Neurosurgery, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Stott Lane, Salford, Greater Manchester, M6 8HD, UK.
| | - Ka-Loh Li
- Geoffrey Jefferson Brain Research Centre, University of Manchester, Manchester, UK
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Mueez Waqar
- Department of Neurosurgery, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Manchester Academic Health Science Centre, Manchester, UK
- Geoffrey Jefferson Brain Research Centre, University of Manchester, Manchester, UK
- Division of Cancer Sciences, School of Medical Sciences, Faculty of Biology Medicine and Health, University of Manchester, Manchester, UK
| | - David J Coope
- Department of Neurosurgery, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Manchester Academic Health Science Centre, Manchester, UK
- Geoffrey Jefferson Brain Research Centre, University of Manchester, Manchester, UK
- Division of Neuroscience and Experimental Psychology, School of Biological Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Omar N Pathmanaban
- Department of Neurosurgery, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Manchester Academic Health Science Centre, Manchester, UK
- Geoffrey Jefferson Brain Research Centre, University of Manchester, Manchester, UK
- Division of Cell Matrix Biology and Regenerative Medicine, School of Biological Sciences, Faculty of Biology Medicine and Health, University of Manchester, Manchester, UK
| | - Andrew T King
- Department of Neurosurgery, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Manchester Academic Health Science Centre, Manchester, UK
- Geoffrey Jefferson Brain Research Centre, University of Manchester, Manchester, UK
- Division of Cardiovascular Sciences, School of Medical Sciences, Faculty of Biology Medicine and Health, University of Manchester, Manchester, UK
| | - Ibrahim Djoukhadar
- Department of Neuroradiology, Manchester Centre for Clinical Neurosciences, Salford Royal NHS Foundation Trust, Manchester Academic Health Science Centre, Manchester, UK
| | - Sha Zhao
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Timothy F Cootes
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Alan Jackson
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| | - Xiaoping Zhu
- Division of Informatics, Imaging and Data Sciences, School of Health Sciences, Faculty of Biology, Medicine and Health, University of Manchester, Manchester, UK
| |
Collapse
|
2
|
Kalisvaart GM, van der Heijden L, Navas Cañete A, van de Sande MAJ, Gelderblom H, van Langevelde K. Characterization of denosumab treatment response in giant cell tumors of bone with dynamic contrast-enhanced MRI. Eur J Radiol 2023; 167:111070. [PMID: 37683333 DOI: 10.1016/j.ejrad.2023.111070] [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: 08/02/2023] [Revised: 08/23/2023] [Accepted: 08/28/2023] [Indexed: 09/10/2023]
Abstract
RATIONALE AND OBJECTIVES Denosumab is a monoclonal antibody used neo-adjuvantly in giant cell tumor of bone (GCTB) to facilitate surgery, or long term for axial tumors where surgery comes with high morbidity. Time intervals for treatment effects to occur are unclear and monitoring tools are limited, complicating optimal drug dose titration. We assessed changes in time intensity curve (TIC) - derived perfusion features on DCE-MRI in GCTB during denosumab treatment and evaluated the duration of treatment effects on tumor perfusion. MATERIALS AND METHODS Patients with GCTB who underwent dynamic contrast enhanced (DCE) MRI before (t = 0) and after 3 (t = 3), 6 (t = 6) or 12 (t = 12) months of denosumab treatment were retrospectively included in a single center. Regions of interest were placed on tumor compartments with visually most intense enhancement and TICs were created. Time-to-enhancement (TTE), wash-in rate (WIR), maximal relative enhancement (MRE), and area-under-the-curve (AUC) were calculated. Differences in perfusion features were calculated with the Wilcoxon signed-rank test. RESULTS In all 24 patients decreased perfusion on DCE-MRI after start of denosumab treatment was seen. TTE increased between t = 0 and t = 3 (p < 0.001). WIR, MRE and AUC decreased between t = 0 and t = 3 (p < 0.001, p = 0.01 and p = 0.02, respectively). No significant differences in features were found between t = 3 and t = 6 or t = 6 and t = 12. No significant perfusion differences in primary versus recurrent, or axial versus appendicular tumors, were found. CONCLUSION MRI perfusion significantly changed in GCTB within 3 months of denosumab treatment compared to baseline. No further significant change occurred between 3 and 6, and 6 and 12 months of treatment. These findings suggest that evaluation of treatment response and subsequent consideration of maintenance with lower doses of denosumab, may already be indicated after 3 months. In cases where long term denosumab is the preferred therapy, monitoring change in tumor characteristics on DCE-MRI may aid optimal drug dose titration, minimizing side effects.
Collapse
Affiliation(s)
- G M Kalisvaart
- Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands.
| | - L van der Heijden
- Department of Orthopedics, Princess Maxima Center for Pediatric Oncology, Heidelberglaan 25, 3584 CS Utrecht, the Netherlands
| | - A Navas Cañete
- Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands
| | - M A J van de Sande
- Department of Orthopedics, Princess Maxima Center for Pediatric Oncology, Heidelberglaan 25, 3584 CS Utrecht, the Netherlands; Department of Orthopedics, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands
| | - H Gelderblom
- Department of Medical Oncology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands
| | - K van Langevelde
- Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands
| |
Collapse
|
3
|
Wang H, Xu S, Fang KB, Dai ZS, Wei GZ, Chen LF. Contrast-enhanced magnetic resonance image segmentation based on improved U-Net and Inception-ResNet in the diagnosis of spinal metastases. J Bone Oncol 2023; 42:100498. [PMID: 37670740 PMCID: PMC10475503 DOI: 10.1016/j.jbo.2023.100498] [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: 02/17/2023] [Revised: 07/18/2023] [Accepted: 07/26/2023] [Indexed: 09/07/2023] Open
Abstract
Objective The objective of this study was to investigate the use of contrast-enhanced magnetic resonance imaging (CE-MRI) combined with radiomics and deep learning technology for the identification of spinal metastases and primary malignant spinal bone tumor. Methods The region growing algorithm was utilized to segment the lesions, and two parameters were defined based on the region of interest (ROI). Deep learning algorithms were employed: improved U-Net, which utilized CE-MRI parameter maps as input, and used 10 layers of CE images as input. Inception-ResNet model was used to extract relevant features for disease identification and construct a diagnosis classifier. Results The diagnostic accuracy of radiomics was 0.74, while the average diagnostic accuracy of improved U-Net was 0.98, respectively. the PA of our model is as high as 98.001%. The findings indicate that CE-MRI based radiomics and deep learning have the potential to assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor. Conclusion CE-MRI combined with radiomics and deep learning technology can potentially assist in the differential diagnosis of spinal metastases and primary malignant spinal bone tumor, providing a promising approach for clinical diagnosis.
Collapse
Affiliation(s)
- Hai Wang
- Department of Orthopedics, The First Affiliated Hospital, Fujian Medical University, Fuzhou 350005, China
- Department of Orthopedics, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou 350212,China
| | - Shaohua Xu
- Department of Hepatobiliary and Pancreatic Surgery, Clinical Oncology School of Fujian Medical University, Fujian Cancer Hospital, Fuzhou 350014, China
| | - Kai-bin Fang
- Department of Orthopedics, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China
| | - Zhang-Sheng Dai
- Department of Orthopedics, The Second Affiliated Hospital of Fujian Medical University, Quanzhou 362000, China
| | - Guo-Zhen Wei
- Department of Orthopedics, The First Affiliated Hospital, Fujian Medical University, Fuzhou 350005, China
- Department of Orthopedics, National Regional Medical Center, Binhai Campus of the First Affiliated Hospital, Fujian Medical University, Fuzhou 350212,China
| | - Lu-Feng Chen
- Department of Thoracic and Cardiovascular Surgery, The Second Affiliated Hospital of Fujian Medical University, Quanzhou, Fujian 362000, China
| |
Collapse
|
4
|
Bone marrow MR perfusion imaging and potential for tumor evaluation. Skeletal Radiol 2023; 52:477-491. [PMID: 36271181 DOI: 10.1007/s00256-022-04202-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Revised: 09/19/2022] [Accepted: 10/04/2022] [Indexed: 02/02/2023]
Abstract
The physiology of bone perfusion is reviewed outlining how it can be measured with dynamic contrast-enhanced MRI as well as intravoxel incoherent imaging. Evaluation of bone perfusion provides a potential means of assessing tumor activity and treatment response beyond that possible with standard MR imaging.
Collapse
|
5
|
A Computed Tomography Radiomics Nomogram in Differentiating Chordoma From Giant Cell Tumor in the Axial Skeleton. J Comput Assist Tomogr 2023; 47:453-459. [PMID: 36728104 DOI: 10.1097/rct.0000000000001436] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/03/2023]
Abstract
OBJECTIVE The aim of the study is to develop and validate a computed tomography (CT) radiomics nomogram for preoperatively differentiating chordoma from giant cell tumor (GCT) in the axial skeleton. METHODS Seventy-three chordomas and 38 GCTs in axial skeleton were retrospectively included and were divided into a training cohort (n = 63) and a test cohort (n = 48). The radiomics features were extracted from CT images. A radiomics signature was developed by using the least absolute shrinkage and selection operator model, and a radiomics score (Rad-score) was acquired. By combining the Rad-score with independent clinical risk factors using multivariate logistic regression model, a radiomics nomogram was established. Calibration and receiver operator characteristic curves were used to assess the performance of the nomogram. RESULTS Five features were selected to construct the radiomics signature. The radiomics signature showed favorable discrimination in the training cohort (area under the curve [AUC], 0.860; 95% confidence interval [CI], 0.760-0.960) and the test cohort (AUC, 0.830; 95% CI, 0.710-0.950). Age and location were the independent clinical factors. The radiomics nomogram combining the Rad-score with independent clinical factors showed good discrimination capability in the training cohort (AUC, 0.930; 95% CI, 0.880-0.990) and the test cohort (AUC, 0.980; 95% CI, 0.940-1.000) and outperformed the radiomics signature (z = 2.768, P = 0.006) in the test cohort. CONCLUSIONS The CT radiomics nomogram shows good predictive efficacy in differentiating chordoma from GCT in the axial skeleton, which might facilitate clinical decision making.
Collapse
|
6
|
Mark IT, Van Gompel JJ, Inwards CY, Ball MK, Morris JM, Carr CM. MRI enhancement patterns in 28 cases of clival chordomas. J Clin Neurosci 2022; 99:117-122. [PMID: 35278932 DOI: 10.1016/j.jocn.2022.02.037] [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: 01/26/2021] [Revised: 02/09/2022] [Accepted: 02/27/2022] [Indexed: 10/18/2022]
Abstract
Clival chordomas are classically thought of as locally aggressive tumors of the skull base and differentiate themselves from their benign counterparts by demonstrating moderate to marked contrast enhancement, reported as 95-100% in prior studies. The purpose of this review was to evaluate the imaging characteristics of lesions from a single institution classified as clival chordomas with an emphasis of highlighting lesions that do not follow the prevalent current description for chordoma. We searched our institutional databases for all patients with pathologically proven clival chordomas from 1997 to 2017 who had pre-operative imaging available. The images were evaluated for degree of contrast enhancement, MRI signal characteristics, osseous involvement, location, aggressiveness of appearance, and presence of calcifications. 28 cases were identified that had preoperative imaging available for review. Over half of the patients demonstrated either no/minimal (11/28, 39%) or mild enhancement (7/28, 25%). The remaining cases demonstrated moderate (4/28, 14%) and marked enhancement (6/28, 21%). The 4 lesions measuring less than 20 mm all had mild to minimal/no enhancement and lacked aggressive features on CT. Our experience finds that over half (64%) of clival chordomas will demonstrate mild or no enhancement at all. These findings suggest that the lack of MRI contrast enhancement should not be synonymous with a benign clival mass.
Collapse
Affiliation(s)
- Ian T Mark
- Mayo Clinic, Department of Radiology. Rochester, MN, USA.
| | | | | | | | | | - Carrie M Carr
- Mayo Clinic, Department of Radiology. Rochester, MN, USA
| |
Collapse
|
7
|
Fan Y, Dong Y, Yang H, Chen H, Yu Y, Wang X, Wang X, Yu T, Luo Y, Jiang X. Subregional radiomics analysis for the detection of the EGFR mutation on thoracic spinal metastases from lung cancer. Phys Med Biol 2021; 66. [PMID: 34633298 DOI: 10.1088/1361-6560/ac2ea7] [Citation(s) in RCA: 17] [Impact Index Per Article: 5.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2021] [Accepted: 10/11/2021] [Indexed: 01/20/2023]
Abstract
The present study intended to use radiomic analysis of spinal metastasis subregions to detect epidermal growth factor receptor (EGFR) mutation. In total, 94 patients with thoracic spinal metastasis originated from primary lung adenocarcinoma (2017-2020) were studied. All patients underwent T1-weighted (T1W) and T2 fat-suppressed (T2FS) MRI scans. The spinal metastases (tumor region) were subdivided into phenotypically consistent subregions based on patient- and population-level clustering: Three subregions, S1, S2 and S3, and the total tumor region. Radiomics features were extracted from each subregion and from the whole tumor region as well. Least shrinkage and selection operator (LASSO) regression were used for feature selection and radiomics signature definition. Detection performance of S3 was better than all other regions using T1W (AUCs, S1 versus S2 versus S3 versus whole tumor, 0.720 versus 0.764 versus 0.786 versus 0.758) and T2FS (AUCs, S1 versus S2 versus S3 versus whole tumor, 0.791 versus 0.708 versus 0.838 versus 0.797) MRI. The multi-regional radiomics signature derived from the joint of inner subregion S3 from T1W and T2FS MRI achieved the best detection capabilities with AUCs of 0.879 (ACC = 0.774, SEN = 0.838, SPE = 0.840) and 0.777 (ACC = 0.688, SEN = 0.947, SPE = 0.615) in the training and test sets, respectively. Our study revealed that MRI-based radiomic analysis of spinal metastasis subregions has the potential to detect the EGFR mutation in patients with primary lung adenocarcinoma.
Collapse
Affiliation(s)
- Ying Fan
- Department of Biomedical Engineering, School of Intelligent Medicine, China Medical University, Shenyang, 110122, People's Republic of China
| | - Yue Dong
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, 110042, People's Republic of China
| | - Huazhe Yang
- Department of Biophysics, School of Intelligent Medicine, China Medical University, Shenyang, 110122, People's Republic of China
| | - Huanhuan Chen
- Department of Oncology, Shengjing Hospital of China Medical University, Shenyang, 110004, People's Republic of China
| | - Yalian Yu
- Department of Otorhinolaryngology, the First Affiliated Hospital of China Medical University, Shenyang, 110122, People's Republic of China
| | - Xiaoyu Wang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, 110042, People's Republic of China
| | - Xinling Wang
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, 110042, People's Republic of China
| | - Tao Yu
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, 110042, People's Republic of China
| | - Yahong Luo
- Department of Radiology, Cancer Hospital of China Medical University, Liaoning Cancer Hospital and Institute, Shenyang, 110042, People's Republic of China
| | - Xiran Jiang
- Department of Biomedical Engineering, School of Intelligent Medicine, China Medical University, Shenyang, 110122, People's Republic of China
| |
Collapse
|
8
|
Rajakulasingam R, Botchu R. Current progress and future trends in imaging of musculoskeletal bone tumours. J Clin Orthop Trauma 2021; 23:101622. [PMID: 34707971 PMCID: PMC8522479 DOI: 10.1016/j.jcot.2021.101622] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2021] [Revised: 10/01/2021] [Accepted: 10/04/2021] [Indexed: 10/20/2022] Open
Abstract
Plain radiographs and MRI remains the gold standard imaging modality for bone tumour and tumour like lesions. Several imaging techniques have been developed to be used in conjunction, but doubt remains over how much additional diagnostic information they provide over and above routine MRI bone tumour sequences. Given the plethora of new modalities, this review aims to highlight some of them and how they may help in the diagnostic assessment of musculoskeletal bone tumours.
Collapse
Affiliation(s)
- R. Rajakulasingam
- Departments of Musculoskeletal Radiology, Royal National Orthopaedic Hospital, Stanmore, UK
| | - R. Botchu
- Departments of Musculoskeletal Radiology, Royal Orthopaedic Hospital, Birmingham, UK,Corresponding author. Department of Radiology, Royal Orthopaedic Hospital, Bristol Road South, Birmingham, B21 3AP, UK.
| |
Collapse
|
9
|
Xiong X, Wang J, Hu S, Dai Y, Zhang Y, Hu C. Differentiating Between Multiple Myeloma and Metastasis Subtypes of Lumbar Vertebra Lesions Using Machine Learning-Based Radiomics. Front Oncol 2021; 11:601699. [PMID: 33718148 PMCID: PMC7943866 DOI: 10.3389/fonc.2021.601699] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/01/2020] [Accepted: 01/11/2021] [Indexed: 12/15/2022] Open
Abstract
Objective To determine whether machine learning based on conventional magnetic resonance imaging (MRI) sequences have the potential for the differential diagnosis of multiple myeloma (MM), and different tumor metastasis lesions of the lumbar vertebra. Methods We retrospectively enrolled 107 patients newly diagnosed with MM and different metastasis of the lumbar vertebra. In total 60 MM lesions and 118 metastasis lesions were selected for training classifiers (70%) and subsequent validation (30%). Following segmentation, 282 texture features were extracted from both T1WI and T2WI images. Following regression analysis using the least absolute shrinkage and selection operator (LASSO) algorithm, the following machine learning models were selected: Support‐Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest (RF), Artificial Neural Networks (ANN), and Naïve Bayes (NB) using 10-fold cross validation, and the performances were evaluated using a confusion matrix. Matthews correlation coefficient (MCC), sensitivity, specificity, and accuracy of the models were also calculated. Results To differentiate MM and metastasis, 13 features in the T1WI images and 9 features in the T2WI images were obtained. Among the 10 classifiers, the ANN classifier from the T2WI images achieved the best performance (MCC = 0.605) with accuracy, sensitivity, and specificity of 0.815, 0.879, and 0.790, respectively, in the validation cohort. To differentiate MM and metastasis subtypes, eight features in the T1WI images and seven features in the T2WI images were obtained. Among the 10 classifiers, the ANN classifier from the T2WI images achieved the best performance (MCC = 0.560, 0.412, 0.449), respectively, with accuracy = 0.648; sensitivity 0.714, 0.821, 0.897 and specificity 0.775, 0.600, 0.640 for the MM, lung, and other metastases, respectively, in the validation cohort. Conclusions Machine learning–based classifiers showed a satisfactory performance in differentiating MM lesions from those of tumor metastasis. While their value for distinguishing myeloma from different metastasis subtypes was moderate.
Collapse
Affiliation(s)
- Xing Xiong
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Jia Wang
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Su Hu
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China.,Institute of Medical Imaging, Soochow University, Suzhou, China
| | - Yao Dai
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China
| | - Yu Zhang
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China.,Institute of Medical Imaging, Soochow University, Suzhou, China.,State Key Laboratory of Radiation Medicine and Protection, Soochow University, Suzhou, China
| | - Chunhong Hu
- Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China.,Institute of Medical Imaging, Soochow University, Suzhou, China
| |
Collapse
|
10
|
Use of monoexponential diffusion-weighted imaging and diffusion kurtosis imaging and dynamic contrast-enhanced-MRI for the differentiation of spinal tumors. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2020; 29:1112-1120. [DOI: 10.1007/s00586-020-06330-w] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/09/2019] [Revised: 11/22/2019] [Accepted: 02/01/2020] [Indexed: 12/26/2022]
|
11
|
Diagnosis of spinal lesions using perfusion parameters measured by DCE-MRI and metabolism parameters measured by PET/CT. EUROPEAN SPINE JOURNAL : OFFICIAL PUBLICATION OF THE EUROPEAN SPINE SOCIETY, THE EUROPEAN SPINAL DEFORMITY SOCIETY, AND THE EUROPEAN SECTION OF THE CERVICAL SPINE RESEARCH SOCIETY 2019; 29:1061-1070. [PMID: 31754820 DOI: 10.1007/s00586-019-06213-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.2] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 05/08/2019] [Revised: 05/08/2019] [Accepted: 11/07/2019] [Indexed: 12/13/2022]
Abstract
PURPOSE To investigate the correlation of parameters measured by dynamic-contrast-enhanced MRI (DCE-MRI) and 18F-FDG PET/CT in spinal tumors, and their role in differential diagnosis. METHODS A total of 49 patients with pathologically confirmed spinal tumors, including 38 malignant, six benign and five borderline tumors, were analyzed. The MRI and PET/CT were done within 3 days, before biopsy. On MRI, the ROI was manually placed on area showing the strongest enhancement to measure pharmacokinetic parameters Ktrans and kep. On PET, the maximum standardized uptake value SUVmax was measured. The parameters in different histological groups were compared. ROC was performed to differentiate between the two largest subtypes, metastases and plasmacytomas. Spearman rank correlation was performed to compare DCE-MRI and PET/CT parameters. RESULTS The Ktrans, kep and SUVmax were not statistically different among malignant, benign and borderline groups (P = 0.95, 0.50, 0.11). There was no significant correlation between Ktrans and SUVmax (r = - 0.20, P = 0.18), or between kep and SUVmax (r = - 0.16, P = 0.28). The kep was significantly higher in plasmacytoma than in metastasis (0.78 ± 0.17 vs. 0.61 ± 0.18, P = 0.02); in contrast, the SUVmax was significantly lower in plasmacytoma than in metastasis (5.58 ± 2.16 vs. 9.37 ± 4.26, P = 0.03). In differential diagnosis, the AUC of kep and SUVmax was 0.79 and 0.78, respectively. CONCLUSIONS The vascular parameters measured by DCE-MRI and glucose metabolism measured by PET/CT from the most aggressive tumor area did not show a significant correlation. The results suggest they provide complementary information reflecting different aspects of the tumor, which may aid in diagnosis of spinal lesions. These slides can be retrieved under Electronic Supplementary Material.
Collapse
|
12
|
Lang N, Zhang Y, Zhang E, Zhang J, Chow D, Chang P, Yu HJ, Yuan H, Su MY. Differentiation of spinal metastases originated from lung and other cancers using radiomics and deep learning based on DCE-MRI. Magn Reson Imaging 2019; 64:4-12. [PMID: 30826448 DOI: 10.1016/j.mri.2019.02.013] [Citation(s) in RCA: 52] [Impact Index Per Article: 10.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/20/2018] [Revised: 02/06/2019] [Accepted: 02/28/2019] [Indexed: 02/08/2023]
Abstract
PURPOSE To differentiate metastatic lesions in the spine originated from primary lung cancer and other cancers using radiomics and deep learning, compared to traditional hot-spot ROI analysis. METHODS In a retrospective review of clinical spinal MRI database with a dynamic contrast enhanced (DCE) sequence, a total of 61 patients without prior cancer diagnosis and later confirmed to have metastases (30 lung; 31 non-lung cancers) were identified. For hot-spot analysis, a manual ROI was placed to calculate three heuristic parameters from the wash-in, maximum, and wash-out phases in the DCE kinetics. For each case, the 3D tumor mask was generated by using the normalized-cut algorithm. Radiomics analysis was performed to extract histogram and texture features from three DCE parametric maps. Deep learning was performed using these maps as inputs into a conventional convolutional neural network (CNN), as well as using all 12 sets of DCE images into a convolutional long short term memory (CLSTM) network. RESULTS For hot-spot ROI analysis, mean wash-out slope was 0.25 ± 10% for lung metastases and -9.8 ± 12.9% for other tumors. CHAID classification using a wash-out slope of -6.6% followed by wash-in enhancement ratio of 98% achieved a diagnostic accuracy of 0.79. Radiomics analysis using features representing tumor heterogeneity only reached the highest accuracy of 0.71. Classification using CNN achieved a mean accuracy of 0.71 ± 0.043, whereas a CLSTM improved accuracy to 0.81 ± 0.034. CONCLUSIONS DCE-MRI machine-learning analysis methods have potential to predict lung cancer metastases in the spine, which may be used to guide subsequent workup for confirmed diagnosis.
Collapse
Affiliation(s)
- Ning Lang
- Department of Radiology, Peking University Third Hospital, Beijing, China
| | - Yang Zhang
- Department of Radiological Sciences, University of California, Irvine, CA, USA
| | - Enlong Zhang
- Department of Radiology, Peking University Third Hospital, Beijing, China
| | - Jiahui Zhang
- Department of Radiology, Peking University Third Hospital, Beijing, China
| | - Daniel Chow
- Department of Radiological Sciences, University of California, Irvine, CA, USA
| | - Peter Chang
- Department of Radiological Sciences, University of California, Irvine, CA, USA
| | - Hon J Yu
- Department of Radiological Sciences, University of California, Irvine, CA, USA
| | - Huishu Yuan
- Department of Radiology, Peking University Third Hospital, Beijing, China.
| | - Min-Ying Su
- Department of Radiological Sciences, University of California, Irvine, CA, USA.
| |
Collapse
|
13
|
Fukuda T, Wengler K, de Carvalho R, Boonsri P, Schweitzer ME. MRI biomarkers in osseous tumors. J Magn Reson Imaging 2019; 50:702-718. [PMID: 30701624 DOI: 10.1002/jmri.26672] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2018] [Revised: 01/15/2019] [Accepted: 01/15/2019] [Indexed: 12/12/2022] Open
Abstract
Although radiography continues to play a critical role in osseous tumor assessment, there have been remarkable advances in cross-sectional imaging. MRI has taken a lead in this assessment due to high tissue contrast and spatial resolution, which are well suited for bone lesion assessment. More recently, although somewhat lagging other organ systems, quantitative parameters have shown promising potential as biomarkers for osseous tumors. Among these sequences are chemical shift imaging (CSI), apparent diffusion coefficient (ADC), and intravoxel incoherent motion (IVIM) from diffusion-weighted imaging (DWI), quantitative dynamic contrast enhanced (DCE)-MRI, and magnetic resonance spectroscopy (MRS). In this article, we review the background and recent roles of these quantitative MRI biomarkers for osseous tumors. Level of Evidence: 3 Technical Efficacy Stage: 3 J. MAGN. RESON. IMAGING 2019. J. Magn. Reson. Imaging 2019;50:702-718.
Collapse
Affiliation(s)
- Takeshi Fukuda
- Department of Radiology, Stony Brook University, Stony Brook, New York, USA
| | - Kenneth Wengler
- Department of Biomedical Engineering, Stony Brook University, Stony Brook, New York, USA
| | - Ruben de Carvalho
- Department of Radiology, Stony Brook University, Stony Brook, New York, USA
| | - Pattira Boonsri
- Department of Radiology, Stony Brook University, Stony Brook, New York, USA
| | - Mark E Schweitzer
- Department of Radiology, Stony Brook University, Stony Brook, New York, USA
| |
Collapse
|
14
|
Lin E, Scognamiglio T, Zhao Y, Schwartz TH, Phillips CD. Prognostic Implications of Gadolinium Enhancement of Skull Base Chordomas. AJNR Am J Neuroradiol 2018; 39:1509-1514. [PMID: 29903925 DOI: 10.3174/ajnr.a5714] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2017] [Accepted: 05/11/2018] [Indexed: 12/16/2022]
Abstract
BACKGROUND AND PURPOSE Skull base chordomas often demonstrate variable MR imaging characteristics, and there has been limited prior research investigating the potential clinical relevance of this variability. The purpose of this retrospective study was to assess the prognostic implications of signal intensity on standard imaging techniques for the biologic behavior of skull base chordomas. MATERIALS AND METHODS Medical records were retrospectively reviewed for 22 patients with pathologically confirmed skull base chordomas. Clinical data were recorded, including the degree of surgical resection, the presence or absence of radiation therapy, and time to progression/recurrence of the tumor or time without progression/recurrence of the tumor following initial treatment. Pretreatment imaging was reviewed for the presence or absence of enhancement and the T2 signal characteristics. Tumor-to-brain stem signal intensity ratios on T2, precontrast T1, and postcontrast T1 spin-echo sequences were also calculated. Statistical analysis was then performed to assess correlations between imaging characteristics and tumor progression/recurrence. RESULTS Progression/recurrence of skull base chordomas was seen following surgical resection in 11 of 14 (78.6%) patients with enhancing tumors and in zero of 8 patients with nonenhancing tumors. There was a statistically significant correlation between skull base chordoma enhancement and subsequent tumor progression/recurrence (P < .001), which remained significant after controlling for differences in treatment strategy (P < .001). There was also a correlation between postcontrast T1 signal intensity (as measured by postcontrast T1 tumor-to-brain stem signal intensity ratios) and recurrence/progression (P = .02). While T2 signal intensity was higher in patients without tumor progression (median tumor-to-brain stem signal intensity ratios on T2 = 2.27) than in those with progression (median tumor-to-brain stem signal intensity ratios on T2 = 1.78), this association was not significant (P = .12). CONCLUSIONS Enhancement of skull base chordomas is a risk factor for tumor progression/recurrence following surgical resection.
Collapse
Affiliation(s)
- E Lin
- From the Departments of Radiology (E.L., C.D.P.)
| | | | - Y Zhao
- Healthcare Policy and Research (Y.Z.)
| | - T H Schwartz
- Neurological Surgery (T.H.S.), New York-Presbyterian Hospital/Weill Cornell Medical Center, New York, New York
| | - C D Phillips
- From the Departments of Radiology (E.L., C.D.P.)
| |
Collapse
|
15
|
Abstract
Purpose of Review Chordoma are rare tumours of the axial skeleton which occur most often at the base of the skull and in the sacrum. Although chordoma are generally slow-growing lesions, the recurrence rate is high and the location makes it often difficult to treat. Both computed tomography (CT) and magnetic resonance imaging (MRI) are crucial in the initial diagnosis, treatment planning and post-treatment follow-up. Recent Findings Basic MRI and CT characteristics of chordoma were described in the late 1980s and early 1990s. Since then, imaging techniques have evolved with increased resolution and new molecular imaging tools are rapidly evolving. New imaging tools have been developed not only to study anatomy, but also physiologic changes and characterization of tissue and assessment of tumour biology. Recent studies show the uptake of multiple PET tracers in chordoma, which may become an important aspect in the diagnosis, follow-up and personalized therapy. Summary This review gives an overview of skull base chordoma histopathology, classic imaging characteristics, radiomics and state-of-the-art imaging techniques that are now emerging in diagnosis, treatment planning and disease monitoring of skull base chordoma.
Collapse
|
16
|
Multifocal metastatic chordoma to the soft tissues of the fingertips: a case report including sonographic features and a review of the literature. Skeletal Radiol 2018; 47:401-406. [PMID: 28986658 DOI: 10.1007/s00256-017-2785-4] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/28/2017] [Revised: 09/25/2017] [Accepted: 09/27/2017] [Indexed: 02/02/2023]
Abstract
Chordoma is a rare, locally aggressive tumor which commonly metastasizes, most often to the lung, liver, and spine. In this case report, a 59-year-old male with history of sacral chordoma and pulmonary metastases presented to the emergency department with swelling and discoloration of multiple left fingertips. The initial radiographs led to a presumptive diagnosis of gout, which did not respond to medical therapy. An ultrasound demonstrated multiple solid masses with vascular hyperechoic septations which were subsequently biopsied and proven to be metastatic chordoma. Metastatic disease to the hand is a well documented but rare manifestation of many malignancies. The clinical presentation and radiographic features of multifocal hand metastases may mimic entities such as systemic deposition and granulomatous diseases. To the best of our knowledge, this is the first case report of soft tissue chordoma metastases to the fingertips as well as the first reported sonographic description of chordoma metastases.
Collapse
|
17
|
Santos P, Peck KK, Arevalo-Perez J, Karimi S, Lis E, Yamada Y, Holodny AI, Lyo J. T1-Weighted Dynamic Contrast-Enhanced MR Perfusion Imaging Characterizes Tumor Response to Radiation Therapy in Chordoma. AJNR Am J Neuroradiol 2017; 38:2210-2216. [PMID: 28912284 DOI: 10.3174/ajnr.a5383] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.9] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2017] [Accepted: 06/15/2017] [Indexed: 11/07/2022]
Abstract
BACKGROUND AND PURPOSE Chordomas notoriously demonstrate a paucity of changes following radiation therapy on conventional MR imaging. We hypothesized that dynamic contrast-enhanced MR perfusion imaging parameters of chordomas would change significantly following radiation therapy. MATERIALS AND METHODS Eleven patients with pathology-proved chordoma who completed dynamic contrast-enhanced MR perfusion imaging pre- and postradiation therapy were enrolled. Quantitative tumor measurements were obtained by 2 attending neuroradiologists. ROIs were used to calculate vascular permeability and plasma volume and generate dynamic contrast-enhancement curves. Quantitative analysis was performed to determine mean and maximum plasma volume and vascular permeability values, while semiquantitative analysis on averaged concentration curves was used to determine the area under the curve. A Mann-Whitney U test at a significance level of P < .05 was used to assess differences of the above parameters between pre- and postradiation therapy. RESULTS Plasma volume mean (pretreatment mean = 0.82; posttreatment mean = 0.42), plasma volume maximum (pretreatment mean = 3.56; posttreatment mean = 2.27), and vascular permeability mean (pretreatment mean = 0.046; posttreatment mean = 0.028) in the ROIs significantly decreased after radiation therapy (P < .05); this change thereby demonstrated the potential for assessing tumor response. Area under the curve values also demonstrated significant differences (P < .05). CONCLUSIONS Plasma volume and vascular permeability decreased after radiation therapy, suggesting that these dynamic contrast-enhanced MR perfusion parameters may be useful for monitoring chordoma growth and response to radiation therapy. Additionally, the characteristic dynamic MR signal intensity-time curve of chordoma may provide a radiographic means of distinguishing chordoma from other spinal lesions.
Collapse
Affiliation(s)
- P Santos
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.)
| | - K K Peck
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.) .,Medical Physics (K.K.P.)
| | - J Arevalo-Perez
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.)
| | - S Karimi
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.)
| | - E Lis
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.)
| | - Y Yamada
- Radiation Oncology (Y.Y.), Memorial Sloan Kettering Cancer Center, New York, New York
| | - A I Holodny
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.)
| | - J Lyo
- From the Departments of Radiology (P.S., K.K.P., J.A.-P., S.K., E.L., A.I.H., J.L.)
| |
Collapse
|