A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images

Liangliang Liu; Ying Wang; Jing Chang; Pei Zhang; Shufeng Xiong; Hebing Liu

doi:10.1016/j.isci.2023.106874

A correlation graph attention network for classifying chromosomal instabilities from histopathology whole-slide images

iScience. 2023 May 18;26(6):106874. doi: 10.1016/j.isci.2023.106874. eCollection 2023 Jun 16.

Authors

Liangliang Liu¹, Ying Wang¹, Jing Chang¹, Pei Zhang¹, Shufeng Xiong¹, Hebing Liu¹

Affiliation

¹ College of Information and Management Science, Henan Agricultural University, Zhengzhou, Henan 450046, P.R. China.

Abstract

The chromosome instability (CIN) is one of the hallmarks of cancer and is closely related to tumor metastasis. However, the sheer size and resolution of histopathology whole-slide images (WSIs) already challenges the capabilities of computational pathology. In this study, we propose a correlation graph attention network (MLP-GAT) that can construct graphs for classifying multi-type CINs from the WSIs of breast cancer. We construct a WSIs dataset of breast cancer from the Cancer Genome Atlas Breast Invasive Carcinoma (TCGA-BRCA). Extensive experiments show that MLP-GAT far outperforms accepted state-of-the-art methods and demonstrate the advantages of the constructed graph networks for analyzing WSI data. The visualization shows the difference among the tiles in a WSI. Furthermore, the generalization performance of the proposed method was verified on the stomach cancer. This study provides guidance for studying the relationship between CIN and cancer from the perspective of image phenotype.

Keywords: Histology; Interconnection network; Medical imaging.