1
|
Di Salle G, Tumminello L, Laino ME, Shalaby S, Aghakhanyan G, Fanni SC, Febi M, Shortrede JE, Miccoli M, Faggioni L, Cosottini M, Neri E. Accuracy of Radiomics in Predicting IDH Mutation Status in Diffuse Gliomas: A Bivariate Meta-Analysis. Radiol Artif Intell 2024; 6:e220257. [PMID: 38231039 PMCID: PMC10831518 DOI: 10.1148/ryai.220257] [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: 11/22/2022] [Revised: 09/12/2023] [Accepted: 10/24/2023] [Indexed: 01/18/2024]
Abstract
Purpose To perform a systematic review and meta-analysis assessing the predictive accuracy of radiomics in the noninvasive determination of isocitrate dehydrogenase (IDH) status in grade 4 and lower-grade diffuse gliomas. Materials and Methods A systematic search was performed in the PubMed, Scopus, Embase, Web of Science, and Cochrane Library databases for relevant articles published between January 1, 2010, and July 7, 2021. Pooled sensitivity and specificity across studies were estimated. Risk of bias was evaluated using Quality Assessment of Diagnostic Accuracy Studies-2, and methods were evaluated using the radiomics quality score (RQS). Additional subgroup analyses were performed according to tumor grade, RQS, and number of sequences used (PROSPERO ID: CRD42021268958). Results Twenty-six studies that included 3280 patients were included for analysis. The pooled sensitivity and specificity of radiomics for the detection of IDH mutation were 79% (95% CI: 76, 83) and 80% (95% CI: 76, 83), respectively. Low RQS scores were found overall for the included works. Subgroup analyses showed lower false-positive rates in very low RQS studies (RQS < 6) (meta-regression, z = -1.9; P = .02) compared with adequate RQS studies. No substantial differences were found in pooled sensitivity and specificity for the pure grade 4 gliomas group compared with the all-grade gliomas group (81% and 86% vs 79% and 79%, respectively) and for studies using single versus multiple sequences (80% and 77% vs 79% and 82%, respectively). Conclusion The pooled data showed that radiomics achieved good accuracy performance in distinguishing IDH mutation status in patients with grade 4 and lower-grade diffuse gliomas. The overall methodologic quality (RQS) was low and introduced potential bias. Keywords: Neuro-Oncology, Radiomics, Integration, Application Domain, Glioblastoma, IDH Mutation, Radiomics Quality Scoring Supplemental material is available for this article. Published under a CC BY 4.0 license.
Collapse
Affiliation(s)
- Gianfranco Di Salle
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Lorenzo Tumminello
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Maria Elena Laino
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Sherif Shalaby
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Gayane Aghakhanyan
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Salvatore Claudio Fanni
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Maria Febi
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Jorge Eduardo Shortrede
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Mario Miccoli
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Lorenzo Faggioni
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Mirco Cosottini
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| | - Emanuele Neri
- From Academic Radiology, Department of Translational Research on New
Technologies in Medicine and Surgery (G.D.S., L.T., G.A., S.C.F., M.F., J.E.S.,
L.F., E.N.), Department of Clinical and Experimental Medicine (M.M.), and
Neuroradiology Unit, Department of Translational Research on New Technologies in
Medicine and Surgery (M.C.), University of Pisa, Via Roma 67, 56126 Pisa, Italy;
Artificial Intelligence Center, IRCCS Humanitas Research Hospital, Rozzano,
Milan, Italy (M.E.L.); The Shrewsbury and Telford Hospital NHS Trust,
Shrewsbury, England (S.S.); and Italian Society of Medical and Interventional
Radiology, SIRM Foundation, Milan, Italy (E.N.)
| |
Collapse
|
2
|
Ponsiglione AM, Angelone F, Amato F, Sansone M. A Statistical Approach to Assess the Robustness of Radiomics Features in the Discrimination of Mammographic Lesions. J Pers Med 2023; 13:1104. [PMID: 37511717 PMCID: PMC10381882 DOI: 10.3390/jpm13071104] [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: 05/30/2023] [Revised: 07/01/2023] [Accepted: 07/05/2023] [Indexed: 07/30/2023] Open
Abstract
Despite mammography (MG) being among the most widespread techniques in breast cancer screening, tumour detection and classification remain challenging tasks due to the high morphological variability of the lesions. The extraction of radiomics features has proved to be a promising approach in MG. However, radiomics features can suffer from dependency on factors such as acquisition protocol, segmentation accuracy, feature extraction and engineering methods, which prevent the implementation of robust and clinically reliable radiomics workflow in MG. In this study, the variability and robustness of radiomics features is investigated as a function of lesion segmentation in MG images from a public database. A statistical analysis is carried out to assess feature variability and a radiomics robustness score is introduced based on the significance of the statistical tests performed. The obtained results indicate that variability is observable not only as a function of the abnormality type (calcification and masses), but also among feature categories (first-order and second-order), image view (craniocaudal and medial lateral oblique), and the type of lesions (benign and malignant). Furthermore, through the proposed approach, it is possible to identify those radiomics characteristics with a higher discriminative power between benign and malignant lesions and a lower dependency on segmentation, thus suggesting the most appropriate choice of robust features to be used as inputs to automated classification algorithms.
Collapse
Affiliation(s)
- Alfonso Maria Ponsiglione
- Department of Information Technology and Electrical Engineering, University of Naples Federico II, 80125 Naples, Italy
| | - Francesca Angelone
- Department of Information Technology and Electrical Engineering, University of Naples Federico II, 80125 Naples, Italy
| | - Francesco Amato
- Department of Information Technology and Electrical Engineering, University of Naples Federico II, 80125 Naples, Italy
| | - Mario Sansone
- Department of Information Technology and Electrical Engineering, University of Naples Federico II, 80125 Naples, Italy
| |
Collapse
|
3
|
Kandalgaonkar P, Sahu A, Saju AC, Joshi A, Mahajan A, Thakur M, Sahay A, Epari S, Sinha S, Dasgupta A, Chatterjee A, Shetty P, Moiyadi A, Agarwal J, Gupta T, Goda JS. Predicting IDH subtype of grade 4 astrocytoma and glioblastoma from tumor radiomic patterns extracted from multiparametric magnetic resonance images using a machine learning approach. Front Oncol 2022; 12:879376. [PMID: 36276136 PMCID: PMC9585657 DOI: 10.3389/fonc.2022.879376] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/19/2022] [Accepted: 09/09/2022] [Indexed: 01/06/2023] Open
Abstract
Background and purposeSemantic imaging features have been used for molecular subclassification of high-grade gliomas. Radiomics-based prediction of molecular subgroups has the potential to strategize and individualize therapy. Using MRI texture features, we propose to distinguish between IDH wild type and IDH mutant type high grade gliomas.MethodsBetween 2013 and 2020, 100 patients were retrospectively analyzed for the radiomics study. Immunohistochemistry of the pathological specimen was used to initially identify patients for the IDH mutant/wild phenotype and was then confirmed by Sanger’s sequencing. Image texture analysis was performed on contrast-enhanced T1 (T1C) and T2 weighted (T2W) MR images. Manual segmentation was performed on MR image slices followed by single-slice multiple sampling image augmentation. Both whole tumor multislice segmentation and single-slice multiple sampling approaches were used to arrive at the best model. Radiomic features were extracted, which included first-order features, second-order (GLCM—Grey level co-occurrence matrix), and shape features. Feature enrichment was done using LASSO (Least Absolute Shrinkage and Selection Operator) regression, followed by radiomic classification using Support Vector Machine (SVM) and a 10-fold cross-validation strategy for model development. The area under the Receiver Operator Characteristic (ROC) curve and predictive accuracy were used as diagnostic metrics to evaluate the model to classify IDH mutant and wild-type subgroups.ResultsMultislice analysis resulted in a better model compared to the single-slice multiple-sampling approach. A total of 164 MR-based texture features were extracted, out of which LASSO regression identified 14 distinctive GLCM features for the endpoint, which were used for further model development. The best model was achieved by using combined T1C and T2W MR images using a Quadratic Support Vector Machine Classifier and a 10-fold internal cross-validation approach, which demonstrated a predictive accuracy of 89% with an AUC of 0.89 for each IDH mutant and IDH wild subgroup.ConclusionA machine learning classifier of radiomic features extracted from multiparametric MRI images (T1C and T2w) provides important diagnostic information for the non-invasive prediction of the IDH mutant or wild-type phenotype of high-grade gliomas and may have potential use in either escalating or de-escalating adjuvant therapy for gliomas or for using targeted agents in the future.
Collapse
Affiliation(s)
- Pashmina Kandalgaonkar
- Department of Radiodiagnosis, Tata Memorial Center, Mumbai, India
- Homi Bhabha National Institute, Mumbai, India
| | - Arpita Sahu
- Department of Radiodiagnosis, Tata Memorial Center, Mumbai, India
- Homi Bhabha National Institute, Mumbai, India
- *Correspondence: Arpita Sahu, ; Jayant S. Goda, ;
| | - Ann Christy Saju
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
| | - Akanksha Joshi
- Department of Radiodiagnosis, Tata Memorial Center, Mumbai, India
- Homi Bhabha National Institute, Mumbai, India
| | - Abhishek Mahajan
- Department of Radiodiagnosis, Tata Memorial Center, Mumbai, India
- Homi Bhabha National Institute, Mumbai, India
| | - Meenakshi Thakur
- Department of Radiodiagnosis, Tata Memorial Center, Mumbai, India
- Homi Bhabha National Institute, Mumbai, India
| | - Ayushi Sahay
- Homi Bhabha National Institute, Mumbai, India
- Department of Pathology, Tata Memorial Center, Mumbai, India
| | - Sridhar Epari
- Homi Bhabha National Institute, Mumbai, India
- Department of Pathology, Tata Memorial Center, Mumbai, India
| | - Shwetabh Sinha
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
| | - Archya Dasgupta
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
| | - Abhishek Chatterjee
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
| | - Prakash Shetty
- Homi Bhabha National Institute, Mumbai, India
- Department of Neurosurgery, Tata Memorial Center, Mumbai, India
| | - Aliasgar Moiyadi
- Homi Bhabha National Institute, Mumbai, India
- Department of Neurosurgery, Tata Memorial Center, Mumbai, India
| | - Jaiprakash Agarwal
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
| | - Tejpal Gupta
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
| | - Jayant S. Goda
- Homi Bhabha National Institute, Mumbai, India
- Department of Radiation Oncology, Tata Memorial Center, Mumbai, India
- *Correspondence: Arpita Sahu, ; Jayant S. Goda, ;
| |
Collapse
|
4
|
Lo CM, Hung PH. Computer-aided diagnosis of ischemic stroke using multi-dimensional image features in carotid color Doppler. Comput Biol Med 2022; 147:105779. [DOI: 10.1016/j.compbiomed.2022.105779] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/05/2022] [Revised: 05/24/2022] [Accepted: 06/19/2022] [Indexed: 11/17/2022]
|
5
|
Hagiwara A, Tatekawa H, Yao J, Raymond C, Everson R, Patel K, Mareninov S, Yong WH, Salamon N, Pope WB, Nghiemphu PL, Liau LM, Cloughesy TF, Ellingson BM. Visualization of tumor heterogeneity and prediction of isocitrate dehydrogenase mutation status for human gliomas using multiparametric physiologic and metabolic MRI. Sci Rep 2022; 12:1078. [PMID: 35058510 PMCID: PMC8776874 DOI: 10.1038/s41598-022-05077-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/13/2021] [Accepted: 12/10/2021] [Indexed: 01/19/2023] Open
Abstract
This study aimed to differentiate isocitrate dehydrogenase (IDH) mutation status with the voxel-wise clustering method of multiparametric magnetic resonance imaging (MRI) and to discover biological underpinnings of the clusters. A total of 69 patients with treatment-naïve diffuse glioma were scanned with pH-sensitive amine chemical exchange saturation transfer MRI, diffusion-weighted imaging, fluid-attenuated inversion recovery, and contrast-enhanced T1-weighted imaging at 3 T. An unsupervised two-level clustering approach was used for feature extraction from acquired images. The logarithmic ratio of the labels in each class within tumor regions was applied to a support vector machine to differentiate IDH status. The highest performance to predict IDH mutation status was found for 10-class clustering, with a mean area under the curve, accuracy, sensitivity, and specificity of 0.94, 0.91, 0.90, and 0.91, respectively. Targeted biopsies revealed that the tissues with labels 7-10 showed high expression levels of hypoxia-inducible factor 1-alpha, glucose transporter 3, and hexokinase 2, which are typical of IDH wild-type glioma, whereas those with labels 1 showed low expression of these proteins. In conclusion, A machine learning model successfully predicted the IDH mutation status of gliomas, and the resulting clusters properly reflected the metabolic status of the tumors.
Collapse
Affiliation(s)
- Akifumi Hagiwara
- grid.19006.3e0000 0000 9632 6718UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, 924 Westwood Blvd., Suite 615, Los Angeles, CA 90024 USA ,grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA ,grid.258269.20000 0004 1762 2738Department of Radiology, Juntendo University School of Medicine, Tokyo, Japan
| | - Hiroyuki Tatekawa
- grid.19006.3e0000 0000 9632 6718UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, 924 Westwood Blvd., Suite 615, Los Angeles, CA 90024 USA ,grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA ,grid.261445.00000 0001 1009 6411Department of Diagnostic and Interventional Radiology, Osaka City University Graduate School of Medicine, Osaka, Japan
| | - Jingwen Yao
- grid.19006.3e0000 0000 9632 6718UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, 924 Westwood Blvd., Suite 615, Los Angeles, CA 90024 USA ,grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA ,grid.19006.3e0000 0000 9632 6718Department of Bioengineering, Henry Samueli School of Engineering and Applied Science, University of California Los Angeles, Los Angeles, CA USA
| | - Catalina Raymond
- grid.19006.3e0000 0000 9632 6718UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, 924 Westwood Blvd., Suite 615, Los Angeles, CA 90024 USA ,grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA
| | - Richard Everson
- grid.19006.3e0000 0000 9632 6718Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA
| | - Kunal Patel
- grid.19006.3e0000 0000 9632 6718Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA
| | - Sergey Mareninov
- grid.19006.3e0000 0000 9632 6718Department of Pathology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA USA
| | - William H. Yong
- grid.19006.3e0000 0000 9632 6718Department of Pathology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA USA
| | - Noriko Salamon
- grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA
| | - Whitney B. Pope
- grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA
| | - Phioanh L. Nghiemphu
- grid.19006.3e0000 0000 9632 6718UCLA Neuro-Oncology Program, University of California, Los Angeles, Los Angeles, CA USA ,grid.19006.3e0000 0000 9632 6718Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA USA
| | - Linda M. Liau
- grid.19006.3e0000 0000 9632 6718Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA
| | - Timothy F. Cloughesy
- grid.19006.3e0000 0000 9632 6718UCLA Neuro-Oncology Program, University of California, Los Angeles, Los Angeles, CA USA ,grid.19006.3e0000 0000 9632 6718Department of Neurology, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA USA
| | - Benjamin M. Ellingson
- grid.19006.3e0000 0000 9632 6718UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, 924 Westwood Blvd., Suite 615, Los Angeles, CA 90024 USA ,grid.19006.3e0000 0000 9632 6718Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA USA ,grid.19006.3e0000 0000 9632 6718Department of Bioengineering, Henry Samueli School of Engineering and Applied Science, University of California Los Angeles, Los Angeles, CA USA ,grid.19006.3e0000 0000 9632 6718UCLA Neuro-Oncology Program, University of California, Los Angeles, Los Angeles, CA USA ,grid.19006.3e0000 0000 9632 6718Department of Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California Los Angeles, Los Angeles, CA USA
| |
Collapse
|
6
|
Liang CW, Fang PW, Huang HY, Lo CM. Deep Convolutional Neural Networks Detect Tumor Genotype from Pathological Tissue Images in Gastrointestinal Stromal Tumors. Cancers (Basel) 2021; 13:5787. [PMID: 34830948 PMCID: PMC8616403 DOI: 10.3390/cancers13225787] [Citation(s) in RCA: 7] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/20/2021] [Revised: 11/07/2021] [Accepted: 11/16/2021] [Indexed: 11/17/2022] Open
Abstract
Gastrointestinal stromal tumors (GIST) are common mesenchymal tumors, and their effective treatment depends upon the mutational subtype of the KIT/PDGFRA genes. We established deep convolutional neural network (DCNN) models to rapidly predict drug-sensitive mutation subtypes from images of pathological tissue. A total of 5153 pathological images of 365 different GISTs from three different laboratories were collected and divided into training and validation sets. A transfer learning mechanism based on DCNN was used with four different network architectures, to identify cases with drug-sensitive mutations. The accuracy ranged from 87% to 75%. Cross-institutional inconsistency, however, was observed. Using gray-scale images resulted in a 7% drop in accuracy (accuracy 80%, sensitivity 87%, specificity 73%). Using images containing only nuclei (accuracy 81%, sensitivity 87%, specificity 73%) or cytoplasm (accuracy 79%, sensitivity 88%, specificity 67%) produced 6% and 8% drops in accuracy rate, respectively, suggesting buffering effects across subcellular components in DCNN interpretation. The proposed DCNN model successfully inferred cases with drug-sensitive mutations with high accuracy. The contribution of image color and subcellular components was also revealed. These results will help to generate a cheaper and quicker screening method for tumor gene testing.
Collapse
Affiliation(s)
- Cher-Wei Liang
- Department of Pathology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 243, Taiwan; (C.-W.L.); (P.-W.F.)
- School of Medicine, College of Medicine, Fu Jen Catholic University, New Taipei City 242, Taiwan
- Graduate Institute of Pathology, College of Medicine, National Taiwan University, Taipei 100, Taiwan
| | - Pei-Wei Fang
- Department of Pathology, Fu Jen Catholic University Hospital, Fu Jen Catholic University, New Taipei City 243, Taiwan; (C.-W.L.); (P.-W.F.)
| | - Hsuan-Ying Huang
- Department of Anatomic Pathology, Chang Gung Memorial Hospital, College of Medicine, Chang Gung University, Kaohsiung 833, Taiwan;
| | - Chung-Ming Lo
- Graduate Institute of Library, Information and Archival Studies, National Chengchi University, Taipei 116, Taiwan
| |
Collapse
|
7
|
Zhang M, Tong E, Hamrick F, Lee EH, Tam LT, Pendleton C, Smith BW, Hug NF, Biswal S, Seekins J, Mattonen SA, Napel S, Campen CJ, Spinner RJ, Yeom KW, Wilson TJ, Mahan MA. Machine-Learning Approach to Differentiation of Benign and Malignant Peripheral Nerve Sheath Tumors: A Multicenter Study. Neurosurgery 2021; 89:509-517. [PMID: 34131749 PMCID: PMC8364819 DOI: 10.1093/neuros/nyab212] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2020] [Accepted: 04/27/2021] [Indexed: 12/13/2022] Open
Abstract
BACKGROUND Clinicoradiologic differentiation between benign and malignant peripheral nerve sheath tumors (PNSTs) has important management implications. OBJECTIVE To develop and evaluate machine-learning approaches to differentiate benign from malignant PNSTs. METHODS We identified PNSTs treated at 3 institutions and extracted high-dimensional radiomics features from gadolinium-enhanced, T1-weighted magnetic resonance imaging (MRI) sequences. Training and test sets were selected randomly in a 70:30 ratio. A total of 900 image features were automatically extracted using the PyRadiomics package from Quantitative Imaging Feature Pipeline. Clinical data including age, sex, neurogenetic syndrome presence, spontaneous pain, and motor deficit were also incorporated. Features were selected using sparse regression analysis and retained features were further refined by gradient boost modeling to optimize the area under the curve (AUC) for diagnosis. We evaluated the performance of radiomics-based classifiers with and without clinical features and compared performance against human readers. RESULTS A total of 95 malignant and 171 benign PNSTs were included. The final classifier model included 21 imaging and clinical features. Sensitivity, specificity, and AUC of 0.676, 0.882, and 0.845, respectively, were achieved on the test set. Using imaging and clinical features, human experts collectively achieved sensitivity, specificity, and AUC of 0.786, 0.431, and 0.624, respectively. The AUC of the classifier was statistically better than expert humans (P = .002). Expert humans were not statistically better than the no-information rate, whereas the classifier was (P = .001). CONCLUSION Radiomics-based machine learning using routine MRI sequences and clinical features can aid in evaluation of PNSTs. Further improvement may be achieved by incorporating additional imaging sequences and clinical variables into future models.
Collapse
Affiliation(s)
- Michael Zhang
- Department of Neurosurgery, Stanford University, Stanford, California, USA
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Elizabeth Tong
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Forrest Hamrick
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
| | - Edward H Lee
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Lydia T Tam
- Stanford School of Medicine, Stanford University, Stanford, California, USA
| | | | - Brandon W Smith
- Department of Neurosurgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Nicholas F Hug
- Stanford School of Medicine, Stanford University, Stanford, California, USA
| | - Sandip Biswal
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Jayne Seekins
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Sarah A Mattonen
- Department of Medical Biophysics, Western University, London, Canada
| | - Sandy Napel
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Cynthia J Campen
- Department of Neurology and Neurological Sciences, Stanford University, Stanford, California, USA
| | - Robert J Spinner
- Department of Neurosurgery, Mayo Clinic, Rochester, Minnesota, USA
| | - Kristen W Yeom
- Department of Radiology, Stanford University, Stanford, California, USA
| | - Thomas J Wilson
- Department of Neurosurgery, Stanford University, Stanford, California, USA
| | - Mark A Mahan
- Department of Neurosurgery, Clinical Neurosciences Center, University of Utah, Salt Lake City, Utah, USA
| |
Collapse
|
8
|
Safai A, Shinde S, Jadhav M, Chougule T, Indoria A, Kumar M, Santosh V, Jabeen S, Beniwal M, Konar S, Saini J, Ingalhalikar M. Developing a Radiomics Signature for Supratentorial Extra-Ventricular Ependymoma Using Multimodal MR Imaging. Front Neurol 2021; 12:648092. [PMID: 34367044 PMCID: PMC8339322 DOI: 10.3389/fneur.2021.648092] [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: 12/31/2020] [Accepted: 06/14/2021] [Indexed: 11/25/2022] Open
Abstract
Rationale and Objectives: To build a machine learning-based diagnostic model that can accurately distinguish adult supratentorial extraventricular ependymoma (STEE) from similarly appearing high-grade gliomas (HGG) using quantitative radiomic signatures from a multi-parametric MRI framework. Materials and Methods: We computed radiomic features on the preprocessed and segmented tumor masks from a pre-operative multimodal MRI dataset [contrast-enhanced T1 (T1ce), T2, fluid-attenuated inversion recovery (FLAIR), apparent diffusion coefficient (ADC)] from STEE (n = 15), HGG-Grade IV (HGG-G4) (n = 24), and HGG-Grade III (HGG-G3) (n = 36) patients, followed by an optimum two-stage feature selection and multiclass classification. Performance of multiple classifiers were evaluated on both unimodal and multimodal feature sets and most discriminative radiomic features involved in classification of STEE from HGG subtypes were obtained. Results: Multimodal features demonstrated higher classification performance over unimodal feature set in discriminating STEE and HGG subtypes with an accuracy of 68% on test data and above 80% on cross validation, along with an overall above 90% specificity. Among unimodal feature sets, those extracted from FLAIR demonstrated high classification performance in delineating all three tumor groups. Texture-based radiomic features particularly from FLAIR were most important in discriminating STEE from HGG-G4, whereas first-order features from T2 and ADC consistently ranked higher in differentiating multiple tumor groups. Conclusions: This study illustrates the utility of radiomics-based multimodal MRI framework in accurately discriminating similarly appearing adult STEE from HGG subtypes. Radiomic features from multiple MRI modalities could capture intricate and complementary information for a robust and highly accurate multiclass tumor classification.
Collapse
Affiliation(s)
- Apoorva Safai
- Symbiosis Center for Medical Image Analysis, Symbiosis Institute of Technology, Symbiosis International University, Pune, India
| | - Sumeet Shinde
- Symbiosis Center for Medical Image Analysis, Symbiosis Institute of Technology, Symbiosis International University, Pune, India
| | - Manali Jadhav
- Symbiosis Center for Medical Image Analysis, Symbiosis Institute of Technology, Symbiosis International University, Pune, India
| | - Tanay Chougule
- Symbiosis Center for Medical Image Analysis, Symbiosis Institute of Technology, Symbiosis International University, Pune, India
| | - Abhilasha Indoria
- Department of Neuroimaging & Interventional Radiology, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Manoj Kumar
- Department of Neuroimaging & Interventional Radiology, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Vani Santosh
- Department of Neuropathology, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Shumyla Jabeen
- Department of Neuroimaging & Interventional Radiology, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Manish Beniwal
- Department of Neurosurgery, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Subhash Konar
- Department of Neurosurgery, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Jitender Saini
- Department of Neuroimaging & Interventional Radiology, National Institute of Mental Health & Neurosciences, Bangalore, India
| | - Madhura Ingalhalikar
- Symbiosis Center for Medical Image Analysis, Symbiosis Institute of Technology, Symbiosis International University, Pune, India
| |
Collapse
|
9
|
van Kempen EJ, Post M, Mannil M, Kusters B, ter Laan M, Meijer FJA, Henssen DJHA. Accuracy of Machine Learning Algorithms for the Classification of Molecular Features of Gliomas on MRI: A Systematic Literature Review and Meta-Analysis. Cancers (Basel) 2021; 13:cancers13112606. [PMID: 34073309 PMCID: PMC8198025 DOI: 10.3390/cancers13112606] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/06/2021] [Revised: 05/17/2021] [Accepted: 05/18/2021] [Indexed: 12/12/2022] Open
Abstract
Simple Summary Glioma prognosis and treatment are based on histopathological characteristics and molecular profile. Following the World Health Organization (WHO) guidelines (2016), the most important molecular diagnostic markers include IDH1/2-genotype and 1p/19q codeletion status, although more recent publications also include ARTX genotype and TERT- and MGMT promoter methylation. Machine learning algorithms (MLAs), however, were described to successfully determine these molecular characteristics non-invasively by using magnetic resonance imaging (MRI) data. The aim of this review and meta-analysis was to define the diagnostic accuracy of MLAs with regard to these different molecular markers. We found high accuracies of MLAs to predict each individual molecular marker, with IDH1/2-genotype being the most investigated and the most accurate. Radiogenomics could therefore be a promising tool for discriminating genetically determined gliomas in a non-invasive fashion. Although encouraging results are presented here, large-scale, prospective trials with external validation groups are warranted. Abstract Treatment planning and prognosis in glioma treatment are based on the classification into low- and high-grade oligodendroglioma or astrocytoma, which is mainly based on molecular characteristics (IDH1/2- and 1p/19q codeletion status). It would be of great value if this classification could be made reliably before surgery, without biopsy. Machine learning algorithms (MLAs) could play a role in achieving this by enabling glioma characterization on magnetic resonance imaging (MRI) data without invasive tissue sampling. The aim of this study is to provide a performance evaluation and meta-analysis of various MLAs for glioma characterization. Systematic literature search and meta-analysis were performed on the aggregated data, after which subgroup analyses for several target conditions were conducted. This study is registered with PROSPERO, CRD42020191033. We identified 724 studies; 60 and 17 studies were eligible to be included in the systematic review and meta-analysis, respectively. Meta-analysis showed excellent accuracy for all subgroups, with the classification of 1p/19q codeletion status scoring significantly poorer than other subgroups (AUC: 0.748, p = 0.132). There was considerable heterogeneity among some of the included studies. Although promising results were found with regard to the ability of MLA-tools to be used for the non-invasive classification of gliomas, large-scale, prospective trials with external validation are warranted in the future.
Collapse
Affiliation(s)
- Evi J. van Kempen
- Department of Medical Imaging, Radboud University Medical Center, Radboud University, 6500HB Nijmegen, The Netherlands; (E.J.v.K.); (M.P.); (F.J.A.M.)
| | - Max Post
- Department of Medical Imaging, Radboud University Medical Center, Radboud University, 6500HB Nijmegen, The Netherlands; (E.J.v.K.); (M.P.); (F.J.A.M.)
| | - Manoj Mannil
- Clinic of Radiology, University Hospital Münster, WWU University of Münster, 48149 Münster, Germany;
| | - Benno Kusters
- Department of Pathology, Radboud University Medical Center, Radboud University, 6500HB Nijmegen, The Netherlands;
| | - Mark ter Laan
- Department of Neurosurgery, Radboud University Medical Center, Radboud University, 6500HB Nijmegen, The Netherlands;
| | - Frederick J. A. Meijer
- Department of Medical Imaging, Radboud University Medical Center, Radboud University, 6500HB Nijmegen, The Netherlands; (E.J.v.K.); (M.P.); (F.J.A.M.)
| | - Dylan J. H. A. Henssen
- Department of Medical Imaging, Radboud University Medical Center, Radboud University, 6500HB Nijmegen, The Netherlands; (E.J.v.K.); (M.P.); (F.J.A.M.)
- Correspondence:
| |
Collapse
|
10
|
Patel SH, Batchala PP, Muttikkal TJE, Ferrante SS, Patrie JT, Fadul CE, Schiff D, Lopes MB, Jain R. Fluid attenuation in non-contrast-enhancing tumor (nCET): an MRI Marker for Isocitrate Dehydrogenase (IDH) mutation in Glioblastoma. J Neurooncol 2021; 152:523-531. [PMID: 33661425 DOI: 10.1007/s11060-021-03720-y] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2020] [Revised: 02/12/2021] [Accepted: 02/15/2021] [Indexed: 11/29/2022]
Abstract
PURPOSE The WHO 2016 update classifies glioblastomas (WHO grade IV) according to isocitrate dehydrogenase (IDH) gene mutation status. We aimed to determine MRI-based metrics for predicting IDH mutation in glioblastoma. METHODS This retrospective study included glioblastoma cases (n = 199) with known IDH mutation status and pre-operative MRI (T1WI, T2WI, FLAIR, contrast-enhanced T1W1 at minimum). Two neuroradiologists determined the following MRI metrics: (1) primary lobe of involvement (frontal or non-frontal); (2) presence/absence of contrast-enhancement; (3) presence/absence of necrosis; (4) presence/absence of fluid attenuation in the non-contrast-enhancing tumor (nCET); (5) maximum width of peritumoral edema (cm); (6) presence/absence of multifocal disease. Inter-reader agreement was determined. After resolving discordant measurements, multivariate association between consensus MRI metrics/patient age and IDH mutation status was determined. RESULTS Among 199 glioblastomas, 16 were IDH-mutant. Inter-reader agreement was calculated for contrast-enhancement (ĸ = 0.49 [- 0.11-1.00]), necrosis (ĸ = 0.55 [0.34-0.76]), fluid attenuation in nCET (ĸ = 0.83 [0.68-0.99]), multifocal disease (ĸ = 0.55 [0.39-0.70]), and primary lobe (ĸ = 0.85 [0.80-0.91]). Mean difference for peritumoral edema width between readers was 0.3 cm [0.2-0.5], p < 0.001. Multivariate analysis uncovered significant associations between IDH-mutation and fluid attenuation in nCET (OR 82.9 [19.22, ∞], p < 0.001), younger age (OR 0.93 [0.86, 0.98], p = 0.009), frontal lobe location (OR 11.08 [1.14, 352.97], p = 0.037), and less peritumoral edema (OR 0.15 [0, 0.65], p = 0.044). CONCLUSIONS Conventional MRI metrics and patient age predict IDH-mutation status in glioblastoma. Among MRI markers, fluid attenuation in nCET represents a novel marker with high inter-reader agreement that is strongly associated with Glioblastoma, IDH-mutant.
Collapse
Affiliation(s)
- Sohil H Patel
- Department of Radiology and Medical Imaging, University of Virginia Health System, PO Box 800170, Charlottesville, VA, 22908, USA.
| | - Prem P Batchala
- Department of Radiology and Medical Imaging, University of Virginia Health System, PO Box 800170, Charlottesville, VA, 22908, USA
| | - Thomas J Eluvathingal Muttikkal
- Department of Radiology and Medical Imaging, University of Virginia Health System, PO Box 800170, Charlottesville, VA, 22908, USA
| | - Sergio S Ferrante
- Department of Radiology and Medical Imaging, University of Virginia Health System, PO Box 800170, Charlottesville, VA, 22908, USA
| | - James T Patrie
- Department of Public Health Sciences, University of Virginia Health System, Charlottesville, VA, USA
| | - Camilo E Fadul
- Division of Neuro-Oncology, Department of Neurology, University of Virginia Health System, Charlottesville, VA, USA
| | - David Schiff
- Division of Neuro-Oncology, Department of Neurology, University of Virginia Health System, Charlottesville, VA, USA
| | - M Beatriz Lopes
- Department of Pathology, Divisions of Neuropathology and Molecular Diagnostics, University of Virginia Health System, Charlottesville, VA, USA
| | - Rajan Jain
- Department of Radiology, New York University School of Medicine, 550 1st Avenue, New York, NY, 10016, USA.,Department of Neurosurgery, New York University School of Medicine, 550 1st Avenue, New York, NY, 10016, USA
| |
Collapse
|