arXiv 2308.127372023-08-24cs.CVcs.AI

用于组织病理学图像分类的结合可解释细胞图集成的非对称协同训练

Asymmetric Co-Training with Explainable Cell Graph Ensembling for Histopathological Image Classification

Xi’an Jiaotong University（西安交通大学）；Fujian Medical University（福建医科大学）；University of Electronic Science and Technology of China（电子科技大学）；Hunan Frontline Medical Technology Co., Ltd.（湖南前沿医疗科技有限公司）

Ziqi Yang, Zhongyu Li, Chen Liu, Xiangde Luo, Xingguang Wang, Dou Xu, Chaoqun Li, Xiaoying Qin, Meng Yang, Long Jin

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对卷积神经网络可解释性不足、图卷积网络在多类别组织病理学图像分类中表现欠佳的问题，提出结合深度图卷积网络与卷积神经网络的非对称协同训练框架，在私有和公开数据集上验证了其优越性能、可解释性与泛化性。

摘要：

卷积神经网络在组织病理学图像分类中表现出色，但其对像素级的关注阻碍了可解释性。相反，新兴的图卷积网络则聚焦于细胞级特征及医学意义。然而，受限于自身深度较浅以及对高维像素数据的利用不够优化，GCN在多类别组织病理学图像分类中表现不佳。为了动态地充分利用像素级和细胞级特征，我们提出了一种非对称协同训练框架，该框架结合深度图卷积网络与卷积神经网络，用于多类别组织病理学图像分类。为了通过嵌入细胞的形态和拓扑分布来提升整个框架的可解释性，我们构建了一个14层的深度图卷积网络来处理细胞图数据。为了进一步利用像素级与细胞级信息并实现二者的动态交互，我们还设计了一种协同训练策略来整合这两个非对称分支。值得注意的是，我们收集了一个名为LUAD7C的临床采集私有数据集，包含7种肺腺癌亚型，这类数据集较为稀缺且分类难度更高。我们在私有LUAD7C数据集和公开结直肠癌数据集上评估了所提方法，结果表明该方法在多类别组织病理学图像分类中具备优越的性能、可解释性和泛化能力。

英文摘要：

Convolutional neural networks excel in histopathological image classification, yet their pixel-level focus hampers explainability. Conversely, emerging graph convolutional networks spotlight cell-level features and medical implications. However, limited by their shallowness and suboptimal use of high-dimensional pixel data, GCNs underperform in multi-class histopathological image classification. To make full use of pixel-level and cell-level features dynamically, we propose an asymmetric co-training framework combining a deep graph convolutional network and a convolutional neural network for multi-class histopathological image classification. To improve the explainability of the entire framework by embedding morphological and topological distribution of cells, we build a 14-layer deep graph convolutional network to handle cell graph data. For the further utilization and dynamic interactions between pixel-level and cell-level information, we also design a co-training strategy to integrate the two asymmetric branches. Notably, we collect a private clinically acquired dataset termed LUAD7C, including seven subtypes of lung adenocarcinoma, which is rare and more challenging. We evaluated our approach on the private LUAD7C and public colorectal cancer datasets, showcasing its superior performance, explainability, and generalizability in multi-class histopathological image classification.

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。