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.

翻译：从多模态磁共振成像中准确分割脑肿瘤是精确放疗规划和手术导航的前提。尽管近期基于Transformer的模型（如Swin UNETR）在基准测试中取得了令人印象深刻的性能，但其临床应用常受两个关键问题影响：对缺失模态的敏感性（临床实践中常见）以及置信度校准的缺乏。仅在理想化数据上追求更高的Dice分数无法满足真实世界医疗部署的安全性要求。本研究提出BMDS-Net，一个将临床鲁棒性和可信度置于简单指标最大化之上的统一框架。我们的贡献包含三个方面。首先，我们通过集成零初始化多模态上下文融合模块和残差门控深度解码器监督机制，构建了一个鲁棒的确定性主干网络，即使在模态损坏情况下也能实现稳定的特征学习和精确的边界描绘，并显著降低豪斯多夫距离。其次，也是最重要的，我们引入了一种内存高效的贝叶斯微调策略，将网络转化为概率预测器，提供体素级不确定性图谱以向临床医生提示潜在错误。第三，在BraTS 2021数据集上的综合实验表明，BMDS-Net不仅保持了有竞争力的准确性，更重要的是在基线模型失效的缺失模态场景中表现出卓越的稳定性。源代码公开于https://github.com/RyanZhou168/BMDS-Net。