Histopathology‐validated machine learning radiographic biomarker for noninvasive discrimination between true progression and pseudo‐progression in glioblastoma. Issue 11 (4th March 2020)

• Record Type: Journal Article
• Authors: Akbari, Hamed; Rathore, Saima; Bakas, Spyridon; Nasrallah, MacLean P.; Shukla, Gaurav; Mamourian, Elizabeth; Rozycki, Martin; Bagley, Stephen J.; Rudie, Jeffrey D.; Flanders, Adam E.; Dicker, Adam P.; Desai, Arati S.; O'Rourke, Donald M.; Brem, Steven; Lustig, Robert; Mohan, Suyash; Wolf, Ronald L.; Bilello, Michel; Martinez‐Lage, Maria; Davatzikos, Christos
• Is Part Of: Cancer. Volume 126:Issue 11(2020)
• Page Start: 2625
• Page End: 2636
• Publication Date: 2020-03-04
• Subjects: glioblastoma -- machine learning -- pseudo‐progression -- radiographic biomarker -- true progression; Cancer -- Periodicals; Cancer -- Cytopathology -- Periodicals; 616.99405
• DOI: 10.1002/cncr.32790
• Languages: English
• ISSNs: 0008-543X

Abstract

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. Abstract : Artificial intelligence methods can accurately predict pseudo‐progression in glioblastoma. The histopathologic characteristics of glioblastoma progression correlate with radiomic features.