Hamed Akbari1,2, Saima Rathore1,2, Spyridon Bakas1,2,3, MacLean P Nasrallah3, Gaurav Shukla1,2,4,5, Elizabeth Mamourian1,2, Martin Rozycki1,2, Stephen J Bagley6, Jeffrey D Rudie2, Adam E Flanders7, Adam P Dicker8, Arati S Desai6, Donald M O'Rourke9, Steven Brem9, Robert Lustig4, Suyash Mohan2, Ronald L Wolf2, Michel Bilello1,2, Maria Martinez-Lage10, Christos Davatzikos1,2. 1. Center for Biomedical Image Computing and Analytics, University of Pennsylvania, Philadelphia, Pennsylvania. 2. Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 3. Department of Pathology and Laboratory Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 4. Department of Radiation Oncology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 5. Helen F. Graham Cancer Center and Research Institute, ChristianaCare, Newark, Delaware. 6. Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 7. Department of Radiology, Thomas Jefferson University Hospital, Philadelphia, Pennsylvania. 8. Department of Radiation Oncology, Sidney Kimmel Medical College and Cancer Center, Thomas Jefferson University, Philadelphia, Pennsylvania. 9. Department of Neurosurgery, Perelman School of Medicine, University of Pennsylvania, Philadelphia, Pennsylvania. 10. Department of Pathology, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts.
Abstract
BACKGROUND: Imaging of glioblastoma patients after maximal safe resection and chemoradiation commonly demonstrates new enhancements that raise concerns about tumor progression. However, in 30% to 50% of patients, these enhancements primarily represent the effects of treatment, or pseudo-progression (PsP). We hypothesize that quantitative machine learning analysis of clinically acquired multiparametric magnetic resonance imaging (mpMRI) can identify subvisual imaging characteristics to provide robust, noninvasive imaging signatures that can distinguish true progression (TP) from PsP. METHODS: We evaluated independent discovery (n = 40) and replication (n = 23) cohorts of glioblastoma patients who underwent second resection due to progressive radiographic changes suspicious for recurrence. Deep learning and conventional feature extraction methods were used to extract quantitative characteristics from the mpMRI scans. Multivariate analysis of these features revealed radiophenotypic signatures distinguishing among TP, PsP, and mixed response that compared with similar categories blindly defined by board-certified neuropathologists. Additionally, interinstitutional validation was performed on 20 new patients. RESULTS: Patients who demonstrate TP on neuropathology are significantly different (P < .0001) from those with PsP, showing imaging features reflecting higher angiogenesis, higher cellularity, and lower water concentration. The accuracy of the proposed signature in leave-one-out cross-validation was 87% for predicting PsP (area under the curve [AUC], 0.92) and 84% for predicting TP (AUC, 0.83), whereas in the discovery/replication cohort, the accuracy was 87% for predicting PsP (AUC, 0.84) and 78% for TP (AUC, 0.80). The accuracy in the interinstitutional cohort was 75% (AUC, 0.80). CONCLUSION: Quantitative mpMRI analysis via machine learning reveals distinctive noninvasive signatures of TP versus PsP after treatment of glioblastoma. Integration of the proposed method into clinical studies can be performed using the freely available Cancer Imaging Phenomics Toolkit.
BACKGROUND: Imaging of glioblastomapatients after maximal safe resection and chemoradiation commonly demonstrates new enhancements that raise concerns about tumor progression. However, in 30% to 50% of patients, these enhancements primarily represent the effects of treatment, or pseudo-progression (PsP). We hypothesize that quantitative machine learning analysis of clinically acquired multiparametric magnetic resonance imaging (mpMRI) can identify subvisual imaging characteristics to provide robust, noninvasive imaging signatures that can distinguish true progression (TP) from PsP. METHODS: We evaluated independent discovery (n = 40) and replication (n = 23) cohorts of glioblastomapatients who underwent second resection due to progressive radiographic changes suspicious for recurrence. Deep learning and conventional feature extraction methods were used to extract quantitative characteristics from the mpMRI scans. Multivariate analysis of these features revealed radiophenotypic signatures distinguishing among TP, PsP, and mixed response that compared with similar categories blindly defined by board-certified neuropathologists. Additionally, interinstitutional validation was performed on 20 new patients. RESULTS:Patients who demonstrate TP on neuropathology are significantly different (P < .0001) from those with PsP, showing imaging features reflecting higher angiogenesis, higher cellularity, and lower water concentration. The accuracy of the proposed signature in leave-one-out cross-validation was 87% for predicting PsP (area under the curve [AUC], 0.92) and 84% for predicting TP (AUC, 0.83), whereas in the discovery/replication cohort, the accuracy was 87% for predicting PsP (AUC, 0.84) and 78% for TP (AUC, 0.80). The accuracy in the interinstitutional cohort was 75% (AUC, 0.80). CONCLUSION: Quantitative mpMRI analysis via machine learning reveals distinctive noninvasive signatures of TP versus PsP after treatment of glioblastoma. Integration of the proposed method into clinical studies can be performed using the freely available Cancer Imaging Phenomics Toolkit.
Authors: Saima Rathore; Suyash Mohan; Spyridon Bakas; Chiharu Sako; Chaitra Badve; Sarthak Pati; Ashish Singh; Dimitrios Bounias; Phuc Ngo; Hamed Akbari; Aimilia Gastounioti; Mark Bergman; Michel Bilello; Russell T Shinohara; Paul Yushkevich; Donald M O'Rourke; Andrew E Sloan; Despina Kontos; MacLean P Nasrallah; Jill S Barnholtz-Sloan; Christos Davatzikos Journal: Neurooncol Adv Date: 2021-01-23
Authors: Hamed Akbari; Anahita Fathi Kazerooni; Jeffrey B Ware; Elizabeth Mamourian; Hannah Anderson; Samantha Guiry; Chiharu Sako; Catalina Raymond; Jingwen Yao; Steven Brem; Donald M O'Rourke; Arati S Desai; Stephen J Bagley; Benjamin M Ellingson; Christos Davatzikos; Ali Nabavizadeh Journal: Sci Rep Date: 2021-07-22 Impact factor: 4.379