基于分层监督的上下文扩展分割
Scaling In-Context Segmentation with Hierarchical Supervision
AI总结：
本文提出PatchICL框架，通过选择性图像分块与多级监督实现高效上下文学习，提升医学图像分割性能并降低计算开销。
摘要：
上下文学习（ICL）使医学图像分割模型能够从有限示例中适应新解剖结构，减少临床标注负担。然而，标准ICL方法通常依赖密集的全局交叉注意力，其图像分辨率扩展性差。近期方法引入了局部注意力机制，但缺乏对选择过程的显式监督，导致非信息区域计算冗余。我们提出PatchICL，一种结合选择性图像分块与多级监督的分层框架。我们的方法学习主动识别并关注最具信息量的解剖区域。与UniverSeg相比，PatchICL在512×512分辨率下计算量减少44%，在35个跨领域数据集上，其在6个模态类别中表现优于基线，尤其在OCT和皮肤病学等局部病理主导的模态中表现突出。训练和评估代码可在https://github.com/tidiane-camaret/ic_segmentation获取。
英文摘要：
In-context learning (ICL) enables medical image segmentation models to adapt to new anatomical structures from limited examples, reducing the clinical annotation burden. However, standard ICL methods typically rely on dense, global cross-attention, which scales poorly with image resolution. While recent approaches have introduced localized attention mechanisms, they often lack explicit supervision on the selection process, leading to redundant computation in non-informative regions. We propose PatchICL, a hierarchical framework that combines selective image patching with multi-level supervision. Our approach learns to actively identify and attend only to the most informative anatomical regions. Compared to UniverSeg, a strong global-attention baseline, PatchICL achieves competitive in-domain CT segmentation accuracy while reducing compute by 44\% at $512\times512$ resolution. On 35 out-of-domain datasets spanning diverse imaging modalities, PatchICL outperforms the baseline on 6 of 13 modality categories, with particular strength on modalities dominated by localized pathology such as OCT and dermoscopy. Training and evaluation code are available at https://github.com/tidiane-camaret/ic_segmentation
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
