Liver Fibrosis Quantification and Analysis: The LiQA Dataset and Baseline Method

2025-12-08

AI Summary

To address unstable liver segmentation and fibrosis staging caused by missing MRI modalities in clinical practice and domain shifts across multi-center data, this work introduces LiQA—a multi-center, multi-phase MRI dataset comprising 440 patients—and proposes a semi-supervised liver segmentation framework leveraging external data. For fibrosis staging, we innovatively integrate class activation map (CAM)-regularized multi-view consensus learning with anatomically constrained modeling. Our method significantly improves model generalizability: on multi-center testing, liver segmentation achieves a 4.2% Dice score improvement, while fibrosis staging attains a weighted Kappa of 0.81 (a +0.13 gain over baseline). These results validate the critical role of synergistic multi-source data utilization and anatomy-informed prior integration in robust medical image analysis.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Liver fibrosis represents a significant global health burden, necessitating accurate staging for effective clinical management. This report introduces the LiQA (Liver Fibrosis Quantification and Analysis) dataset, established as part of the CARE 2024 challenge. Comprising $440$ patients with multi-phase, multi-center MRI scans, the dataset is curated to benchmark algorithms for Liver Segmentation (LiSeg) and Liver Fibrosis Staging (LiFS) under complex real-world conditions, including domain shifts, missing modalities, and spatial misalignment. We further describe the challenge's top-performing methodology, which integrates a semi-supervised learning framework with external data for robust segmentation, and utilizes a multi-view consensus approach with Class Activation Map (CAM)-based regularization for staging. Evaluation of this baseline demonstrates that leveraging multi-source data and anatomical constraints significantly enhances model robustness in clinical settings.

Problem

• Introduces the LiQA dataset for liver fibrosis quantification and analysis
• Benchmarks algorithms for liver segmentation and fibrosis staging
• Addresses domain shifts, missing modalities, and spatial misalignment challenges

Innovation

• Semi-supervised learning with external data for segmentation
• Multi-view consensus approach with CAM-based regularization
• Leveraging multi-source data and anatomical constraints