JMIR Publications

ABSTRACT

Background:

Liver fibrosis is a pathological outcome of chronic liver injury and a hallmark of multiple chronic liver diseases. Magnetic resonance elastography (MRE) provides a non-invasive modality for evaluating the severity of liver fibrosis.

Objective:

This study aimed to develop and evaluate deep learning–based segmentation models for the automated assessment of liver fibrosis using MRE images, with a focus on comparing the performance of a conventional U-Net and a UNet-ResNet50-32x4d architecture.

Methods:

A retrospective analysis was conducted on 319 patients enrolled between January 2018 and December 2020. MRE images were processed and segmented using two U-Net–based models. Model performance was assessed through correlation coefficients, Intersection over Union (IoU), and additional segmentation metrics.

Results:

The UNet-ResNet50-32x4d model demonstrated strong agreement with ground truth annotations, achieving correlation coefficients of 0.952 in the training phase and 0.943 in the validation phase, along with an IoU score of 85.68%, confirming its high segmentation accuracy. By contrast, the conventional U-Net failed to generate clinically meaningful predictions.

Conclusions:

The UNet-ResNet50-32x4d model exhibited robust performance and may serve as a reliable tool for rapid and accurate assessment of liver fibrosis severity. The integration of automated segmentation into MRE analysis has the potential to improve clinical workflows and support timely decision-making in the management of chronic liver disease.