基于图的可解释全切片图像分析框架
A Graph-Based Framework for Interpretable Whole Slide Image Analysis
AI总结：
提出将全切片图像转化为生物信息图表示的可解释框架，通过自适应图粗化与图注意力网络，以极少参数和数据实现与基础模型相当的癌症分期与生存预测性能。
摘要：
全切片图像的组织病理学分析是癌症诊断的基础，但这一过程耗时且依赖专家经验。尽管深度学习方法展现出可喜的成果，但主流的基于补丁的方法人为地分割组织，忽略了生物学边界，并产生黑箱预测。我们通过一个新颖的框架克服了这些局限，该框架将十亿像素级的全切片图像转化为具有生物学意义的图表示，并且设计上就是可解释的。我们的方法从尊重自然结构而非任意网格的组织区域构建图节点。我们引入了一种由学习到的嵌入引导的自适应图粗化技术，以高效合并同质区域，同时在异质区域保留诊断关键细节。每个节点都配备了一个紧凑、可解释的特征集，捕捉临床动机的先验知识。随后，一个图注意力网络基于这一紧凑表示进行诊断。我们在具有挑战性的癌症分期和生存预测任务上展示了强大的性能。关键在于，我们资源高效的模型（参数减少超过13倍，数据减少超过300倍）在结果上与大规模基础模型相当，同时通过特征归因提供了完全的可解释性。我们的代码公开于 https://github.com/HistoGraph31/pix2pathology。
英文摘要：
The histopathological analysis of whole-slide images (WSIs) is fundamental to cancer diagnosis but is a time-consuming and expert-driven process. While deep learning methods show promising results, dominant patch-based methods artificially fragment tissue, ignore biological boundaries, and produce black-box predictions. We overcome these limitations with a novel framework that transforms gigapixel WSIs into biologically-informed graph representations and is interpretable by design. Our approach builds graph nodes from tissue regions that respect natural structures, not arbitrary grids. We introduce an adaptive graph coarsening technique, guided by learned embeddings, to efficiently merge homogeneous regions while preserving diagnostically critical details in heterogeneous areas. Each node is enriched with a compact, interpretable feature set capturing clinically-motivated priors. A graph attention network then performs diagnosis on this compact representation. We demonstrate strong performance on challenging cancer staging and survival prediction tasks. Crucially, our resource-efficient model ($>$13x fewer parameters and $>$300x less data) achieves results competitive with a massive foundation model, while offering full interpretability through feature attribution. Our code is publicly available at https://github.com/HistoGraph31/pix2pathology.
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。
