Liver Fibrosis Quantification and Analysis: The LiQA Dataset and Baseline Method
Yuanye Liu, Hanxiao Zhang, Jiyao Liu, Nannan Shi, Yuxin Shi, Arif Mahmood, Murtaza Taj, Xiahai Zhuang
TL;DR
LiQA tackles robust, non-invasive liver fibrosis quantification from multi-phase MRI in real-world settings by introducing a large, multi-center dataset and two tasks: LiSeg for liver segmentation and LiFS for fibrosis staging. The winning approach combines semi-supervised segmentation with external data and a multi-view, CAM-regularized staging pipeline that copes with missing modalities and misalignments. Key findings show that external data and VOI-guided attention improve segmentation robustness, while multi-view fusion provides resilience for LiFS across heterogeneous sequences, though OOD domains challenge AUC. The work establishes a practical benchmark for clinical deployment and points to directions in interpretable fusion and multi-modal data integration.
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.