提出解耦掩码与类别预测的新架构，提升医学图像分割精度。
MaskMed: Decoupled Mask and Class Prediction for Medical Image Segmentation
- 用共享查询分离掩码和类别预测，增强特征复用
- 在AMOS2022上比nnUNet高2.0% Dice，BTCV上高6.9% Dice
- 适合追求高精度的医学图像分割研究者
医学图像分割通常采用逐点卷积分割头，每个输出通道固定对应一个类别，这种刚性设计限制了特征共享与语义泛化。本文提出统一的解耦分割头，将多类别预测拆分为无类别的掩码预测与类别标签预测，利用共享对象查询实现。此外，引入全尺度感知可变形Transformer模块，使低分辨率编码器特征通过可变形注意力机制关注全分辨率特征，实现内存高效且空间对齐的全尺度融合。所提方法MaskMed在AMOS2022上超越nnUNet达+2.0% Dice，在BTCV上达+6.9% Dice，性能达到当前最优。
原文摘要 · Abstract (English)
Medical image segmentation typically adopts a point-wise convolutional segmentation head to predict dense labels, where each output channel is heuristically tied to a specific class. This rigid design limits both feature sharing and semantic generalization. In this work, we propose a unified decoupled segmentation head that separates multi-class prediction into class-agnostic mask prediction and class label prediction using shared object queries. Furthermore, we introduce a Full-Scale Aware Deformable Transformer module that enables low-resolution encoder features to attend across full-resolution encoder features via deformable attention, achieving memory-efficient and spatially aligned full-scale fusion. Our proposed method, named MaskMed, achieves state-of-the-art performance, surpassing nnUNet by +2.0% Dice on AMOS 2022 and +6.9% Dice on BTCV.
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。