Saved in:
Bibliographic Details
Main Authors: Zhou, Yan, Huang, Zhen, Li, Yingqiu, Ouyang, Yue, Xiang, Suncheng, Wang, Zehua
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.17504
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912845726220288
author Zhou, Yan
Huang, Zhen
Li, Yingqiu
Ouyang, Yue
Xiang, Suncheng
Wang, Zehua
author_facet Zhou, Yan
Huang, Zhen
Li, Yingqiu
Ouyang, Yue
Xiang, Suncheng
Wang, Zehua
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_17504
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BMDS-Net: A Bayesian Multi-Modal Deep Supervision Network for Robust Brain Tumor Segmentation
Zhou, Yan
Huang, Zhen
Li, Yingqiu
Ouyang, Yue
Xiang, Suncheng
Wang, Zehua
Computer Vision and Pattern Recognition
Quantitative Methods
92C55 (Primary), 68T07 (Secondary)
I.4.6
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.
title BMDS-Net: A Bayesian Multi-Modal Deep Supervision Network for Robust Brain Tumor Segmentation
topic Computer Vision and Pattern Recognition
Quantitative Methods
92C55 (Primary), 68T07 (Secondary)
I.4.6
url https://arxiv.org/abs/2601.17504