用随机丢弃学习平滑先验，提升脑肿瘤分割边界清晰度。
Variance-Penalized MC-Dropout as a Learned Smoothing Prior for Brain Tumour Segmentation
- 通过蒙特卡洛丢弃学习数据驱动的平滑先验，减少预测噪声。
- 在BraTS2023/2024上提升Dice达3.3%/4.5%，IoU提升2.7%/4.0%。
- 减少42.5%计算量，适合高效高精度医学图像分割场景。
脑肿瘤分割对诊断和治疗规划至关重要，但许多基于CNN和U-Net的方法在肿瘤浸润区域会产生噪声边界。本文提出UAMSA-UNet，一种不确定性感知的多尺度注意力贝叶斯U-Net，利用蒙特卡洛丢弃学习数据驱动的平滑先验，同时融合多尺度特征与注意力图以捕捉细粒度细节与全局上下文。其平滑正则化损失在二值交叉熵基础上加入随机前向传播间的方差惩罚，抑制虚假波动，生成空间连贯的分割掩码。在BraTS2023上，相比U-Net，Dice相似系数最高提升3.3%，平均IoU提升2.7%；在BraTS2024上，相较最佳基线，Dice最高提升4.5%，IoU提升4.0%。尤为显著的是，该模型相比U-Net++降低42.5%的浮点运算量（FLOPs）且保持更高精度。结果表明，结合多尺度注意力与学习式平滑先验，UAMSA-UNet实现了更优的分割质量与计算效率，为未来与基于Transformer模块集成提供灵活基础。
原文摘要 · Abstract (English)
Brain tumor segmentation is essential for diagnosis and treatment planning, yet many CNN and U-Net based approaches produce noisy boundaries in regions of tumor infiltration. We introduce UAMSA-UNet, an Uncertainty-Aware Multi-Scale Attention-based Bayesian U-Net that in- stead leverages Monte Carlo Dropout to learn a data-driven smoothing prior over its predictions, while fusing multi-scale features and attention maps to capture both fine details and global context. Our smoothing-regularized loss augments binary cross-entropy with a variance penalty across stochas- tic forward passes, discouraging spurious fluctuations and yielding spatially coherent masks. On BraTS2023, UAMSA- UNet improves Dice Similarity Coefficient by up to 3.3% and mean IoU by up to 2.7% over U-Net; on BraTS2024, it delivers up to 4.5% Dice and 4.0% IoU gains over the best baseline. Remarkably, it also reduces FLOPs by 42.5% rel- ative to U-Net++ while maintaining higher accuracy. These results demonstrate that, by combining multi-scale attention with a learned smoothing prior, UAMSA-UNet achieves both better segmentation quality and computational efficiency, and provides a flexible foundation for future integration with transformer-based modules for further enhanced segmenta- tion results.
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。