Purpose To develop and validate a deep learning (DL) method to detect and segment enhancing and nonenhancing cellular tumor on pre- and posttreatment MRI scans in patients with glioblastoma and to predict overall survival (OS) and progression-free survival (PFS). Materials and Methods This retrospective study included 1397 MRI scans in 1297 patients with glioblastoma, including an internal set of 243 MRI scans (January 2010 to June 2022) for model training and cross-validation and four external test cohorts. Cellular tumor maps were segmented by two radiologists on the basis of imaging, clinical history, and pathologic findings. Multimodal MRI data with perfusion and multishell diffusion imaging were inputted into a nnU-Net DL model to segment cellular tumor. Segmentation performance (Dice score) and performance in distinguishing recurrent tumor from posttreatment changes (area under the receiver operating characteristic curve [AUC]) were quantified. Model performance in predicting OS and PFS was assessed using Cox multivariable analysis. Results A cohort of 178 patients (mean age, 56 years ± 13 [SD]; 116 male, 62 female) with 243 MRI timepoints, as well as four external datasets with 55, 70, 610, and 419 MRI timepoints, respectively, were evaluated. The median Dice score was 0.79 (IQR, 0.53-0.89), and the AUC for detecting residual or recurrent tumor was 0.84 (95% CI: 0.79, 0.89). In the internal test set, estimated cellular tumor volume was significantly associated with OS (hazard ratio [HR] = 1.04 per milliliter; P < .001) and PFS (HR = 1.04 per milliliter; P < .001) after adjustment for age, sex, and gross total resection (GTR) status. In the external test sets, estimated cellular tumor volume was significantly associated with OS (HR = 1.01 per milliliter; P < .001) after adjustment for age, sex, and GTR status. Conclusion A DL model incorporating advanced imaging could accurately segment enhancing and nonenhancing cellular tumor, distinguish recurrent or residual tumor from posttreatment changes, and predict OS and PFS in patients with glioblastoma. Keywords: Segmentation, Glioblastoma, Multishell Diffusion MRI Supplemental material is available for this article. © RSNA, 2024.

BACKGROUND: Evaluating longitudinal changes in gliomas is a time-intensive process with significant interrater variability. Automated segmentation could reduce interrater variability and increase workflow efficiency for assessment of treatment response. We sought to evaluate whether neural networks would be comparable to expert assessment of pre- and posttreatment diffuse gliomas tissue subregions including resection cavities. METHODS: A retrospective cohort of 647 MRIs of patients with diffuse gliomas (average 55.1 years; 29%/36%/34% female/male/unknown; 396 pretreatment and 251 posttreatment, median 237 days post-surgery) from 7 publicly available repositories in The Cancer Imaging Archive were split into training (536) and test/generalization (111) samples. T1, T1-post-contrast, T2, and FLAIR images were used as inputs into a 3D nnU-Net to predict 3 tumor subregions and resection cavities. We evaluated the performance of networks trained on pretreatment training cases (Pre-Rx network), posttreatment training cases (Post-Rx network), and both pre- and posttreatment cases (Combined networks). RESULTS: Segmentation performance was as good as or better than interrater reliability with median dice scores for main tumor subregions ranging from 0.82 to 0.94 and strong correlations between manually segmented and predicted total lesion volumes (0.94 < R 2 values < 0.98). The Combined network performed similarly to the Pre-Rx network on pretreatment cases and the Post-Rx network on posttreatment cases with fewer false positive resection cavities (7% vs 59%). CONCLUSIONS: Neural networks that accurately segment pre- and posttreatment diffuse gliomas have the potential to improve response assessment in clinical trials and reduce provider burden and errors in measurement.