A Digital Pathology Resource for Liver Cancer Quantification with Datasets, Benchmarks, and Tools

2026-04-22

AI Summary

Current digital pathology research in hepatocellular carcinoma lacks fine-grained annotations of tissue components, hindering the development of reproducible models and quantitative analysis. To address this gap, this work introduces HepatoBench, the first patch-level dataset annotated with seven key histological tissue classes. We propose HepatoQuant, an end-to-end analytical framework that integrates whole-slide tumor segmentation with patch-level tissue classification to enable a unified pipeline for quantitative tissue composition analysis—from tumor localization at the whole-slide level to detailed component characterization at the patch level. The project publicly releases the dataset, benchmarking protocols, and associated toolchain, establishing a foundation for automated, region-specific quantitative pathology in hepatocellular carcinoma and enabling fair algorithmic evaluation.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Computer Vision: Segmentation
• Knowledge Representation and Reasoning: Qualitative Reasoning

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Liver cancer, especially hepatocellular carcinoma (HCC), imposes a substantial global disease burden. Accurate diagnosis and prognostic assessment directly influence treatment selection and patient survival, and pathological examination remains the gold standard for liver cancer diagnosis. Identifying diverse tissue components and pathological subtypes on histopathology slides is crucial for estimating postoperative recurrence risk and overall prognosis. However, most publicly available resources are still provided at the whole-slide image (WSI) level, and well-annotated datasets for fine-grained tissue component identification in liver cancer are scarce, which hinders reproducible model development and the deployment of quantitative analysis tools. To address this gap, we release HepatoBench, a patch-level image database for liver cancer with annotations for seven key tissue categories. Based on HepatoBench, we train and open-source a deep learning classification model as a tissue recognition tool. Furthermore, we train a WSI-level tumor/non-tumor segmentation model to automatically localize lesion regions across entire slides. By integrating the patch-level tissue classifier with the WSI-level segmentation model, we build HepatoQuant, an end-to-end, disease-specific regional quantification tool for liver cancer, enabling a unified workflow from WSIs to tissue composition parsing and quantitative statistics. We also open-source HepatoBench, the benchmarking protocol, and supporting tools, providing a solid foundation for automated regional quantification and fair method comparison in liver cancer pathology.

Problem

• liver cancer
• histopathology
• tissue component identification
• quantitative analysis
• dataset scarcity

Innovation

• HepatoBench
• patch-level annotation
• deep learning classification
• WSI-level segmentation
• HepatoQuant