论文标题
使用图神经网络对组织病理学图像的表示
Representation Learning of Histopathology Images using Graph Neural Networks
论文作者
论文摘要
整个幻灯片图像（WSI）的表示学习对于开发基于图像的系统以达到诊断病理学的精度更高。我们为WSI表示学习提供了一个两阶段的框架。我们使用基于颜色的方法对相关的补丁进行了采样，并使用图形神经网络来学习采样贴片之间的关系，以将图像信息汇总为单个向量表示。我们通过图形池引入注意力，以自动推断具有更高相关性的斑块。我们证明了我们的方法可以区分肺癌，肺腺癌（LUAD）和肺鳞状细胞癌（LUSC）的两种亚类型的方法。我们收集了1,026个肺癌WSI，并从癌症基因组图集（TCGA）数据集中获得了40 $ \ times $放大倍数，该数据集是组织病理学图像的最大公共存储库，并通过从肺癌子类别中提取肺癌分类的0.89的最先进的准确性为88.8％，AUC为0.89，源自肺癌的分类，并具有从肺癌的分类中提取的预先分类。
Representation learning for Whole Slide Images (WSIs) is pivotal in developing image-based systems to achieve higher precision in diagnostic pathology. We propose a two-stage framework for WSI representation learning. We sample relevant patches using a color-based method and use graph neural networks to learn relations among sampled patches to aggregate the image information into a single vector representation. We introduce attention via graph pooling to automatically infer patches with higher relevance. We demonstrate the performance of our approach for discriminating two sub-types of lung cancers, Lung Adenocarcinoma (LUAD) & Lung Squamous Cell Carcinoma (LUSC). We collected 1,026 lung cancer WSIs with the 40$\times$ magnification from The Cancer Genome Atlas (TCGA) dataset, the largest public repository of histopathology images and achieved state-of-the-art accuracy of 88.8% and AUC of 0.89 on lung cancer sub-type classification by extracting features from a pre-trained DenseNet
