基于弱监督学习的全病理切片分类
The Whole Pathological Slide Classification via Weakly Supervised Learning
AI总结：
针对全切片病理图像分类，本文融合核异质性与图块空间相关性两种病理先验，构建含染色分离对比增强和邻接空间建模的MIL框架，在Camelyon16与TCGA-NSCLC上优于现有方法。
摘要：
由于在利用标注和处理千兆像素级图像方面具有卓越效率，多示例学习（MIL）作为数字病理诊断中全切片图像（WSI）分类的框架已展现出巨大前景。然而，现有方法往往聚焦于具有不同结构的高级聚合器，却常常忽视H&E病理切片的内在特征。为解决这一局限，我们引入了两个病理先验：病变细胞的核异质性以及病理图块的空间相关性。利用前者，我们提出了一种数据增强方法，该方法在提取器训练过程中通过对比学习策略利用染色分离，以获得示例级表征。随后，我们使用邻接矩阵描述图块之间的空间关系。通过整合这两个视角，我们基于病理归纳偏置设计了一个用于分析H&E染色组织图像的多示例框架，涵盖特征提取、过滤和聚合。在Camelyon16乳腺数据集和TCGA-NSCLC肺部数据集上的大量实验表明，我们提出的框架能够有效处理癌症检测和亚型区分相关任务，性能优于基于MIL的最先进医学图像分类方法。代码将于稍后发布。
英文摘要：
Due to its superior efficiency in utilizing annotations and addressing gigapixel-sized images, multiple instance learning (MIL) has shown great promise as a framework for whole slide image (WSI) classification in digital pathology diagnosis. However, existing methods tend to focus on advanced aggregators with different structures, often overlooking the intrinsic features of H\&E pathological slides. To address this limitation, we introduced two pathological priors: nuclear heterogeneity of diseased cells and spatial correlation of pathological tiles. Leveraging the former, we proposed a data augmentation method that utilizes stain separation during extractor training via a contrastive learning strategy to obtain instance-level representations. We then described the spatial relationships between the tiles using an adjacency matrix. By integrating these two views, we designed a multi-instance framework for analyzing H\&E-stained tissue images based on pathological inductive bias, encompassing feature extraction, filtering, and aggregation. Extensive experiments on the Camelyon16 breast dataset and TCGA-NSCLC Lung dataset demonstrate that our proposed framework can effectively handle tasks related to cancer detection and differentiation of subtypes, outperforming state-of-the-art medical image classification methods based on MIL. The code will be released later.
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。
