Related Experiment Video
Updated: Jul 12, 2026
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.
Background:
Steatotic liver disease (SLD) is the most common liver disease worldwide, affecting 30% of the global population. It is strongly associated with the interplay of genetic and lifestyle-related risk factors. The genetic variant accounting for the largest fraction of SLD heritability is PNPLA3 I148M, which is carried by 23% of the western population and increases the risk of SLD two to three-fold. However, identification of variant carriers is not part of routine clinical care and prevents patients from receiving personalised care.
Methods:
We analysed MRI images and common genetic variants in PNPLA3, TM6SF2, MTARC1, HSD17B13 and GCKR from a cohort of 45 603 individuals from the UK Biobank. Proton density fat fraction (PDFF) maps were generated using a water-fat separation toolbox, applied to the magnitude and phase MRI data. The liver region was segmented using a U-Net model trained on 600 manually segmented ground truth images. The resulting liver masks and PDFF maps were subsequently used to calculate liver PDFF values. Individuals with (PDFF ≥ 5%) and without SLD (PDFF < 5%) were selected as the study cohort and used to train and test a Vision Transformer classification model with five-fold cross validation. We aimed to differentiate individuals who are homozygous for the PNPLA3 I148M variant from non-carriers, as evaluated by the area under the receiver operating characteristic curve (AUROC). To ensure a clear genetic contrast, all heterozygous individuals were excluded. To interpret our model, we generated attention maps that highlight the regions that are most predictive of the outcomes.
Results:
Homozygosity for the PNPLA3 I148M variant demonstrated the best predictive performance among five variants with AUROC of 0.68 (95% CI: 0.64-0.73) in SLD patients and 0.57 (95% CI: 0.52-0.61) in non-SLD patients. The AUROCs for the other SNPs ranged from 0.54 to 0.57 in SLD patients and from 0.52 to 0.54 in non-SLD patients. The predictive performance was generally higher in SLD patients compared to non-SLD patients. Attention maps for PNPLA3 I148M carriers showed that fat deposition in regions adjacent to the hepatic vessels, near the liver hilum, plays an important role in predicting the presence of the I148M variant.
Conclusion:
Our study marks novel progress in the non-invasive detection of homozygosity for PNPLA3 I148M through the application of deep learning models on MRI images. Our findings suggest that PNPLA3 I148M might affect the liver fat distribution and could be used to predict the presence of PNPLA3 variants in patients with fatty liver. The findings of this research have the potential to be integrated into standard clinical practice, particularly when combined with clinical and biochemical data from other modalities to increase accuracy, enabling easier identification of at-risk individuals and facilitating the development of tailored interventions for PNPLA3 I148M-associated liver disease.
Insights
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.
