A Hierarchical Geometry-guided Transformer for Histological Subtyping of Primary Liver Cancer

2025-10-07

AI Summary

To address performance bottlenecks in hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) subtyping—stemming from complex tissue morphology and insufficient exploitation of multi-scale information in whole-slide images (WSIs)—this paper proposes ARGUS, a novel Transformer-based framework. ARGUS jointly models tumor microenvironment features across macro-, meso-, and micro-scales by integrating nucleus-level geometric graph representation with hierarchical field-of-view alignment. It further introduces geometric prior-guided multimodal self-supervised representation learning. By explicitly encoding cellular spatial configurations and the WSI pyramid structure, ARGUS achieves superior subtype discrimination. Evaluated on multiple public and private cohorts, it attains state-of-the-art accuracy, significantly outperforming existing methods. ARGUS thus provides an interpretable, robust AI-assisted tool for precision pathological diagnosis of liver cancer.

Technology Category

• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Argumentation
• Machine Learning: Multi-instance/Multi-view Learning

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Primary liver malignancies are widely recognized as the most heterogeneous and prognostically diverse cancers of the digestive system. Among these, hepatocellular carcinoma (HCC) and intrahepatic cholangiocarcinoma (ICC) emerge as the two principal histological subtypes, demonstrating significantly greater complexity in tissue morphology and cellular architecture than other common tumors. The intricate representation of features in Whole Slide Images (WSIs) encompasses abundant crucial information for liver cancer histological subtyping, regarding hierarchical pyramid structure, tumor microenvironment (TME), and geometric representation. However, recent approaches have not adequately exploited these indispensable effective descriptors, resulting in a limited understanding of histological representation and suboptimal subtyping performance. To mitigate these limitations, ARGUS is proposed to advance histological subtyping in liver cancer by capturing the macro-meso-micro hierarchical information within the TME. Specifically, we first construct a micro-geometry feature to represent fine-grained cell-level pattern via a geometric structure across nuclei, thereby providing a more refined and precise perspective for delineating pathological images. Then, a Hierarchical Field-of-Views (FoVs) Alignment module is designed to model macro- and meso-level hierarchical interactions inherent in WSIs. Finally, the augmented micro-geometry and FoVs features are fused into a joint representation via present Geometry Prior Guided Fusion strategy for modeling holistic phenotype interactions. Extensive experiments on public and private cohorts demonstrate that our ARGUS achieves state-of-the-art (SOTA) performance in histological subtyping of liver cancer, which provide an effective diagnostic tool for primary liver malignancies in clinical practice.

Problem

• Automating histological subtyping of primary liver cancer
• Capturing hierarchical tissue structures in whole slide images
• Improving classification of hepatocellular carcinoma and cholangiocarcinoma

Innovation

• Hierarchical geometry-guided Transformer for liver cancer subtyping
• Micro-geometry features capture cell-level patterns via nuclei structure
• FoVs alignment models macro-meso hierarchical interactions in WSIs