59. A RADIOMICS-BASED MACHINE LEARNING MODEL FOR DISTINGUISHING RADIATION NECROSIS FROM PROGRESSION OF BRAIN METASTASES TREATED WITH STEREOTACTIC RADIOSURGERY (SRS). (4th August 2020)

• Record Type: Journal Article
• Authors: Chen, Xuguang; Parekh, Vishwa; Peng, Luke; Chan, Michael; Soike, Michael; McTyre, Emory; Jacobs, Michael; Kleinberg, Lawrence
• Is Part Of: Neuro-oncology advances. Volume 2(2020)Supplement 2
• Page Start: ii12
• Page End: ii12
• Publication Date: 2020-08-04
• Subjects: 616.99481
• DOI: 10.1093/noajnl/vdaa073.047
• Languages: English
• ISSNs: 2632-2498

Abstract

Abstract: PURPOSE: This study aims to test whether MRI radiomic signatures can distinguish radiation necrosis (RN) from tumor progression (TP) in a multi-institution dataset using machine learning. METHODS: Brain metastases treated with SRS were followed by serial MRI, and those showing evidence of RN or TP underwent pathologic confirmation. Radiomic features were extracted from T1 post-contrast (T1c) and T2 fluid attenuated inversion recovery (T2 FLAIR) MRI. High dimensional radiomic feature space was visualized in a two-dimensional space using t-distributed stochastic neighbor embedding (t-SNE). Cases from 2 institutions were combined and randomly assigned to training (2/3) and testing (1/3) cohorts. Backward elimination was used for feature selection, followed by random forest algorithm for predictive modeling. RESULTS: A total of 135 individual lesions (37 RN and 98 TP) were included. The majority (72.6%) received single-fraction SRS to a median dose of 18Gy. Clear clustering of cases around the institutional origin was observed on t-SNE analysis. 21 T1c and 4 FLAIR features were excluded from subsequent modeling due to significant correlation with the institutional origin. Backward elimination yielded 6 T1c and 6 FLAIR features used for model construction. A random forest model based on the 6 FLAIR features (cluster shade, neighborhood gray tone difference matrix (NGTDM) coarseness, NGTDM texture strength, run length nonuniformity, run percentage, and short run high gray-level emphasis) achieved sensitivity of 76% and specificity of 70% on the training cohort (AUC 0.74, 95% CI 0.60–0.88), and sensitivity of 67% and specificity of 83% on the testing cohort (AUC 0.75, 95% CI 0.59–0.93). Addition of the T1c features resulted in overfitting of the training cohort (AUC 1.00), but did not improve model performance on the testing cohort (AUC 0.69, 95% CI 0.51–0.87). CONCLUSION: MRI radiomics based machine learning can distinguish RN from TP after brain SRS in a heterogeneous image dataset.