针对脑肿瘤分割中模态缺失和预测过自信问题，提出自适应融合与贝叶斯校准新框架。
BMDS-Net:Deployment-aware multi-modal brain tumor segmentation with adaptive fusion,decoder regularization,and Bayesian calibration
- 分两阶段设计：先自适应融合多模态信息，再用贝叶斯层估算不确定性
- 在BraTS 2021上实现WT/TC/ET Dice达0.9293/0.9098/0.8675，边界误差低于3.3mm
- 仅增少量训练成本即逼近三模型集成的校准效果，适合临床部署
多模态MRI可实现脑肿瘤亚区精细分割，但临床部署受模态缺失、边界错误和过自信预测影响。本文提出BMDS-Net，一种双阶段Swin UNETR框架，结合自适应模态融合、边界感知解码器正则化与高效贝叶斯校准。确定性阶段引入零初始化多模态上下文融合（MMCF）与残差门控深度解码器监督（DDS），调节模态贡献并正则化层级边界重建。第二阶段仅替换最后卷积层为贝叶斯层，以低额外训练成本实现蒙特卡洛不确定性估计。在BraTS 2021（1,251例）上，BMDS-Net取得WT、TC、ET的Dice分数分别为0.9293、0.9098、0.8675，HD95值为2.27、2.22、3.27 mm。配置对比显示，辅助监督利于全模态分割，而完整MMCF+门控DDS配置在单模态缺失下最鲁棒。贝叶斯版本预期校准误差为0.0037，接近三模型集成（0.0035）且训练成本降低约60%。在BraTS 2020上，相同协议下完整配置仍保持五种Swin UNETR变体中的领先内部排名。代码已开源：https://github.com/RyanZhou168/BMDS-Net。
原文摘要 · Abstract (English)
Multi-modal MRI enables detailed brain tumor sub-region segmentation, but clinical deployment remains affected by missing sequences,boundary errors, and overconfident predictions. We present BMDS-Net, a two-stage Swin UNETR framework that combines adaptivemodality fusion, boundary-aware decoder regularization, and efficient Bayesian calibration. The deterministic stage adds zero-initializedmultimodal contextual fusion (MMCF) and residual-gated deep decoder supervision (DDS) to modulate modality contributions andregularize hierarchical boundary reconstruction. The second stage replaces only the final convolutional layer with a Bayesian layer,enabling Monte Carlo uncertainty estimates with limited additional training cost. On BraTS 2021 (1,251 cases), BMDS-Net achieved Dice scores of 0.9293, 0.9098, and 0.8675 for WT, TC, and ET, with HD95 values of 2.27, 2.22, and 3.27 mm. Configuration comparisons showed that auxiliary supervision favored complete-input segmentation, whereas the complete MMCF+gated-DDS configuration was most robust under single-modality removal. Bayesian BMDS-Net achieved an expected calibration error of 0.0037, close to a three-model ensemble (0.0035) at approximately 60% lower training cost. On BraTS 2020, the same protocol preserved the leading internal ranking of the complete configuration among five Swin UNETR-controlled variants. The implementation code is available at https://github.com/RyanZhou168/BMDS-Net.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。