Related Experiment Video
Updated: Jul 12, 2026
06:46
3D Imaging of the Liver Extracellular Matrix in a Mouse Model of Non-Alcoholic Steatohepatitis
Published on: February 25, 2022
Deep Learning Reveals Liver MRI Features Associated With PNPLA3 I148M in Steatotic Liver Disease
Yazhou Chen1, Benjamin P M Laevens1, Teresa Lemainque2
1Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany.
Summary
This study uses deep learning on MRI images to non-invasively detect PNPLA3 I148M homozygosity, a key genetic factor in fatty liver disease. This approach could help identify at-risk individuals for personalized care.
Area of Science:
- Hepatology and Medical Imaging
- Genetics and Precision Medicine
- Artificial Intelligence in Healthcare
Background:
- Steatotic liver disease (SLD) is a prevalent global health issue, strongly linked to genetic and lifestyle factors.
- The PNPLA3 I148M variant significantly increases SLD heritability but is not routinely identified in clinical practice.
- Lack of carrier identification hinders personalized care for individuals at higher risk of SLD.
Purpose of the Study:
- To develop and evaluate a deep learning model for non-invasively detecting PNPLA3 I148M homozygosity using MRI data.
- To assess the predictive performance of the model in differentiating homozygous PNPLA3 I148M carriers from non-carriers in a large cohort.
- To explore how the PNPLA3 I148M variant influences liver fat distribution as visualized through MRI.
Main Methods:
- Analysis of MRI images and genetic variants (PNPLA3, TM6SF2, MTARC1, HSD17B13, GCKR) in 45,603 UK Biobank participants.
- Generation of proton density fat fraction (PDFF) maps from MRI data and segmentation of the liver using a U-Net model.
- Training and validation of a Vision Transformer classification model to differentiate PNPLA3 I148M homozygous carriers from non-carriers, excluding heterozygotes.
Main Results:
- The PNPLA3 I148M variant showed the best predictive performance (AUROC 0.68 in SLD patients, 0.57 in non-SLD patients) compared to other tested variants.
- Predictive performance was generally higher in SLD patients than in non-SLD patients.
- Attention maps indicated that fat deposition near hepatic vessels and the liver hilum is crucial for predicting the PNPLA3 I148M variant.
Conclusions:
- Deep learning models applied to MRI images enable novel non-invasive detection of PNPLA3 I148M homozygosity.
- PNPLA3 I148M may alter liver fat distribution, aiding in the prediction of PNPLA3 variants in fatty liver patients.
- Integration into clinical practice, alongside other data, can enhance accuracy for identifying at-risk individuals and developing tailored interventions.
