Liver Cirrhosis Stage Estimation from MRI with Deep Learning

2025-02-23

AI Summary

Addressing the clinical challenge of difficult and frequently missed early diagnosis of liver cirrhosis—leading to severe complications—this study proposes the first end-to-end deep learning framework for automatic MRI-based staging using multi-sequence (T1-weighted/T2-weighted) scans. Methodologically, it introduces a novel architecture integrating multi-scale feature extraction with sequence-specific attention mechanisms to precisely model subtle tissue alterations associated with hepatic fibrosis progression. We construct and publicly release CirrMRI600+, the first large-scale, expert-annotated MRI benchmark dataset for liver cirrhosis staging. In a three-stage classification task (compensated, decompensated, end-stage), our model achieves accuracies of 72.8% (T1W) and 63.8% (T2W), significantly surpassing conventional radiomics approaches and establishing a new state-of-the-art. This work provides a generalizable, non-invasive, and interpretable technical paradigm—underpinned by robust data—for precise, automated cirrhosis staging.

Technology Category

• Machine Learning: Multi-instance/Multi-view Learning
• Computer Vision: Multi-modal Vision
• Humans and AI: Human-in-the-loop Machine Learning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

We present an end-to-end deep learning framework for automated liver cirrhosis stage estimation from multi-sequence MRI. Cirrhosis is the severe scarring (fibrosis) of the liver and a common endpoint of various chronic liver diseases. Early diagnosis is vital to prevent complications such as decompensation and cancer, which significantly decreases life expectancy. However, diagnosing cirrhosis in its early stages is challenging, and patients often present with life-threatening complications. Our approach integrates multi-scale feature learning with sequence-specific attention mechanisms to capture subtle tissue variations across cirrhosis progression stages. Using CirrMRI600+, a large-scale publicly available dataset of 628 high-resolution MRI scans from 339 patients, we demonstrate state-of-the-art performance in three-stage cirrhosis classification. Our best model achieves 72.8% accuracy on T1W and 63.8% on T2W sequences, significantly outperforming traditional radiomics-based approaches. Through extensive ablation studies, we show that our architecture effectively learns stage-specific imaging biomarkers. We establish new benchmarks for automated cirrhosis staging and provide insights for developing clinically applicable deep learning systems. The source code will be available at https://github.com/JunZengz/CirrhosisStage.

Problem

• Automated liver cirrhosis stage estimation
• Multi-sequence MRI analysis
• Deep learning framework for early diagnosis

Innovation

• End-to-end deep learning framework
• Multi-scale feature learning
• Sequence-specific attention mechanisms