DLiPath: A Benchmark for the Comprehensive Assessment of Donor Liver Based on Histopathological Image Dataset

2025-05-30

AI Summary

Current histopathological assessment of donor livers via biopsy is time-consuming, highly subjective, and suffers from substantial inter-observer variability. Method: We introduce DLiPath—the first benchmark dataset for donor liver pathology assessment—comprising 636 whole-slide images (WSIs) with expert annotations across six critical pathological features. We propose the first standardized annotation protocol specifically designed for donor livers and develop a weakly supervised, spatially disentangled quantitative evaluation framework for pathological feature assessment. Using multi-instance learning (MIL), we systematically benchmark nine state-of-the-art models on DLiPath. Results: Our evaluation achieves an average AUC exceeding 0.92, significantly improving diagnostic consistency and reproducibility. Both the dataset and source code are publicly released to advance clinically deployable, trustworthy AI in organ transplantation decision-making.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Pathologists comprehensive evaluation of donor liver biopsies provides crucial information for accepting or discarding potential grafts. However, rapidly and accurately obtaining these assessments intraoperatively poses a significant challenge for pathologists. Features in donor liver biopsies, such as portal tract fibrosis, total steatosis, macrovesicular steatosis, and hepatocellular ballooning are correlated with transplant outcomes, yet quantifying these indicators suffers from substantial inter- and intra-observer variability. To address this, we introduce DLiPath, the first benchmark for comprehensive donor liver assessment based on a histopathology image dataset. We collected and publicly released 636 whole slide images from 304 donor liver patients at the Department of Pathology, the Third Xiangya Hospital, with expert annotations for key pathological features (including cholestasis, portal tract fibrosis, portal inflammation, total steatosis, macrovesicular steatosis, and hepatocellular ballooning). We selected nine state-of-the-art multiple-instance learning (MIL) models based on the DLiPath dataset as baselines for extensive comparative analysis. The experimental results demonstrate that several MIL models achieve high accuracy across donor liver assessment indicators on DLiPath, charting a clear course for future automated and intelligent donor liver assessment research. Data and code are available at https://github.com/panliangrui/ACM_MM_2025.

Problem

• Assessing donor liver biopsies rapidly and accurately intraoperatively
• Reducing variability in quantifying key pathological liver features
• Establishing a benchmark for automated donor liver assessment

Innovation

• First benchmark for donor liver assessment
• Uses multiple-instance learning models
• Public histopathology dataset with expert annotations