用于组织病理学全切片图像表示与分类的集成图-Transformer框架
Integrative Graph-Transformer Framework for Histopathology Whole Slide Image Representation and Classification
AI总结：
本文提出集成图-Transformer框架，通过结合图卷积网络与全局注意力模型的GTI模块，同时捕获局部相邻关系与全局依赖，有效提升了组织病理学全切片图像分类的准确率与AUROC。
摘要：
在数字病理学中，多示例学习（MIL）策略被广泛应用于弱监督组织病理学全切片图像（WSI）分类任务，其中千兆像素的WSI仅在切片级别进行标注。然而，现有的基于注意力的MIL方法常忽略上下文信息及相邻组织切片间的内在空间关系，而基于图的MIL框架在识别长距离依赖性方面能力有限。本文提出了一种集成图-Transformer框架，通过新颖的Graph Transformer Integration（GTI）模块同时捕获上下文感知的关系特征和全局WSI表示。具体而言，每个GTI模块由一个在局部实例层面建模相邻关系的图卷积网络（GCN）层和一个从广泛特征嵌入中捕获全面全局信息的高效全局注意力模型组成。在三个公开WSI数据集：TCGA-NSCLC、TCGA-RCC和BRIGHT上的大量实验表明，该方法优于当前最先进的MIL方法，准确率提升了1.0%至2.6%，AUROC提升了0.7%至1.6%。
英文摘要：
In digital pathology, the multiple instance learning (MIL) strategy is widely used in the weakly supervised histopathology whole slide image (WSI) classification task where giga-pixel WSIs are only labeled at the slide level. However, existing attention-based MIL approaches often overlook contextual information and intrinsic spatial relationships between neighboring tissue tiles, while graph-based MIL frameworks have limited power to recognize the long-range dependencies. In this paper, we introduce the integrative graph-transformer framework that simultaneously captures the context-aware relational features and global WSI representations through a novel Graph Transformer Integration (GTI) block. Specifically, each GTI block consists of a Graph Convolutional Network (GCN) layer modeling neighboring relations at the local instance level and an efficient global attention model capturing comprehensive global information from extensive feature embeddings. Extensive experiments on three publicly available WSI datasets: TCGA-NSCLC, TCGA-RCC and BRIGHT, demonstrate the superiority of our approach over current state-of-the-art MIL methods, achieving an improvement of 1.0% to 2.6% in accuracy and 0.7%-1.6% in AUROC.
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。
