HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis

TL;DR

HIGT introduces a hierarchical graph-transformer model that captures multi-resolution interactions in whole slide images, improving cancer diagnosis and prognosis accuracy by learning both local and global features.

Contribution

The paper proposes a novel Bidirectional Interaction block within a Hierarchical Interaction Graph-Transformer for comprehensive WSI analysis, enabling effective multi-resolution feature learning.

Findings

HIGT outperforms state-of-the-art methods on TCGA datasets.

Effective modeling of multi-resolution interactions improves tumor subtyping.

Model achieves higher accuracy in tumor staging tasks.

Abstract

In computation pathology, the pyramid structure of gigapixel Whole Slide Images (WSIs) has recently been studied for capturing various information from individual cell interactions to tissue microenvironments. This hierarchical structure is believed to be beneficial for cancer diagnosis and prognosis tasks. However, most previous hierarchical WSI analysis works (1) only characterize local or global correlations within the WSI pyramids and (2) use only unidirectional interaction between different resolutions, leading to an incomplete picture of WSI pyramids. To this end, this paper presents a novel Hierarchical Interaction Graph-Transformer (i.e., HIGT) for WSI analysis. With Graph Neural Network and Transformer as the building commons, HIGT can learn both short-range local information and long-range global representation of the WSI pyramids. Considering that the information from different resolutions is complementary and can benefit each other during the learning process, we further design a novel Bidirectional Interaction block to establish communication between different levels within the WSI pyramids. Finally, we aggregate both coarse-grained and fine-grained features learned from different levels together for slide-level prediction. We evaluate our methods on two public WSI datasets from TCGA projects, i.e., kidney carcinoma (KICA) and esophageal carcinoma (ESCA). Experimental results show that our HIGT outperforms both hierarchical and non-hierarchical state-of-the-art methods on both tumor subtyping and staging tasks.