3D Deep Learning for Brain Tumor Segmentation and Survival Prediction: A Comprehensive Multi-Modal Analysis Using the BraTS2020 Dataset
Authors:
- Vivek SankerVSVivek Sanker
- Dhanya MaheshDMDhanya Mahesh
- Zhikai LiZLZhikai Li
- Alexander ThallerAlexander Thaller
- Philip HeesenPhilip Heesen
- Linda LiveraniLLLinda Liverani
- David WangDWDavid Wang
- Maria Jose CavagnaroMCMaria Jose Cavagnaro
- Ravi Teja MedikondaRMRavi Teja Medikonda
- Laura ProloLPLaura Prolo
- Harminder SinghHSHarminder Singh
- John RatliffJRJohn Ratliff
Open Access
- 6 June 2026
- journal article
- research article
- Published by MDPI AG in Journal of Imaging
- Vol. 12 (6) , 251
Abstract
Introduction: Three-dimensional deep learning offers promise for automated accurate brain tumor segmentation and survival prediction but requires robust validation across multiple MRI modalities to be effectively implemented in clinical practice. Methods: This study presents a comprehensive 3D deep learning framework using 369 cases from the BraTS2020 dataset. A 3D U-Net architecture was developed for tumor segmentation utilizing combined imaging data and optimized for computational efficiency and memory. The final 3D U-Net model segmentations were used to build machine learning 6-month and 12-month survival classifiers. Segmentation models were evaluated using multiple metrics, including the Dice Similarity Coefficient, Hausdorff Distance, and Cohen’s d. The classification models were evaluated using AUC-ROC and balanced accuracy. Results: Segmentation achieved a modest, but promising, performance across 30 epochs and with 295 training patients, achieving the best mean validation Dice = 0.8388 and a final-epoch mean Dice of 0.8263. Survival classification with a hybrid clinical and imaging logistic regression showed promising results, with 12-month prediction achieving AUC = 0.746 and 69% accuracy. The top contributing features for the 12-month prediction classifier were extent of resection, T1 contrast-enhanced tumor median, and FLAIR tumor median. Conclusions: This comprehensive framework demonstrates that a multi-modal approach provides meaningful performance gains, while segmentation-derived features show a promising ability to enable survival prediction.Keywords
This publication has 33 references indexed in Scilit:
- Voxel-level Radiomics and Deep Learning Based on MRI for Predicting Microsatellite Instability in Endometrial Carcinoma: A Two-center StudyAcademic Radiology, 2025
- Explainable artificial intelligence for medical imaging systems using deep learning: a comprehensive reviewCluster Computing, 2025
- A review of deep learning for brain tumor analysis in MRInpj Precision Oncology, 2025
- A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIMEAdvanced Intelligent Systems, 2024
- Numerical calculation of streaming potential around osteocytes under human gait loadingComputers in Biology and Medicine, 2024
- Data leakage inflates prediction performance in connectome-based machine learning modelsNature Communications, 2024
- Detection of tumors on brain MRI images using the hybrid convolutional neural network architectureMedical Hypotheses, 2020
- Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networksNature Medicine, 2020
- Radiomics: the bridge between medical imaging and personalized medicineNature Reviews Clinical Oncology, 2017
- Multiparametric Tissue Characterization of Brain Neoplasms and Their Recurrence Using Pattern Classification of MR ImagesAcademic Radiology, 2008