BMDS-Net: A Bayesian Multi-Modal Deep Supervision Network for Robust Brain Tumor Segmentation

TL;DR

BMDS-Net is a robust brain tumor segmentation model that incorporates Bayesian uncertainty estimation, improving clinical reliability especially when some MRI modalities are missing, outperforming existing methods in stability and safety.

Contribution

The paper introduces a Bayesian framework integrated into a multi-modal deep network, enhancing robustness and uncertainty calibration for brain tumor segmentation.

Findings

Maintains competitive accuracy on BraTS 2021 dataset.

Exhibits superior stability in missing-modality scenarios.

Provides voxel-wise uncertainty maps for clinical trustworthiness.

Abstract

Accurate brain tumor segmentation from multi-modal magnetic resonance imaging (MRI) is a prerequisite for precise radiotherapy planning and surgical navigation. While recent Transformer-based models such as Swin UNETR have achieved impressive benchmark performance, their clinical utility is often compromised by two critical issues: sensitivity to missing modalities (common in clinical practice) and a lack of confidence calibration. Merely chasing higher Dice scores on idealized data fails to meet the safety requirements of real-world medical deployment. In this work, we propose BMDS-Net, a unified framework that prioritizes clinical robustness and trustworthiness over simple metric maximization. Our contribution is three-fold. First, we construct a robust deterministic backbone by integrating a Zero-Init Multimodal Contextual Fusion (MMCF) module and a Residual-Gated Deep Decoder Supervision (DDS) mechanism, enabling stable feature learning and precise boundary delineation with significantly reduced Hausdorff Distance, even under modality corruption. Second, and most importantly, we introduce a memory-efficient Bayesian fine-tuning strategy that transforms the network into a probabilistic predictor, providing voxel-wise uncertainty maps to highlight potential errors for clinicians. Third, comprehensive experiments on the BraTS 2021 dataset demonstrate that BMDS-Net not only maintains competitive accuracy but, more importantly, exhibits superior stability in missing-modality scenarios where baseline models fail. The source code is publicly available at https://github.com/RyanZhou168/BMDS-Net.