Deep Learning for Liver Disease Stratification: Findings from UKBB MRI

Rami Al-Belmpeisi, Josefine Vilsb ll Sundgaard, Peter Hj rringgaard Larsen, Anders Bjorholm Dahl
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:4384-4400, 2026.

Abstract

Metabolic dysfunction-associated steatotic liver disease (MASLD) and its progressive form, metabolic dysfunction-associated steatohepatitis (MASH), have become more prevalent, spurring interest in using magnetic resonance imaging (MRI) sequences for diagnosis. In this study, we propose a method that uses deep learning to diagnose MASLD and MASH with significant fibrosis from single-slice (2D) and volumetric (3D) MRI sequences that originate from the UK Biobank. In this paper, we focus on transparent decision-making. Our study shows that imposing anatomically informed constraints by using a liver segmentation mask on the network’s input has minimal impact on diagnostic performance. Still, it redirects attention to clinically relevant liver regions, preventing shortcut learning from extrahepatic features, such as subcutaneous fat. These constraints shift the focus of the model toward proton density fat fraction (PDFF) maps for healthy liver assessment, $T_1$ maps for MASLD diagnosis, and both sequences to identify MASH with significant fibrosis. Our top-performing models achieve AUCs of 0.89/0.96/0.79 for the diagnosis of the healthy/MASLD/MASH groups with significant fibrosis, respectively. Despite label noise and limited sequence specificity, which primarily hinder predictive performance in cases of MASH with significant fibrosis, the identified indicators are frequently located in liver regions consistent with prior understanding of disease progression. In conclusion, we find that 2D MRI sequences are sufficient for diagnosing MASLD/MASH with significant fibrosis, as performance decreases and computation time increases when using 3D volumes.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-al-belmpeisi26a, title = {Deep Learning for Liver Disease Stratification: Findings from UKBB MRI}, author = {Al-Belmpeisi, Rami and Sundgaard, Josefine Vilsb ll and Larsen, Peter Hj rringgaard and Dahl, Anders Bjorholm}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {4384--4400}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/al-belmpeisi26a/al-belmpeisi26a.pdf}, url = {https://proceedings.mlr.press/v315/al-belmpeisi26a.html}, abstract = {Metabolic dysfunction-associated steatotic liver disease (MASLD) and its progressive form, metabolic dysfunction-associated steatohepatitis (MASH), have become more prevalent, spurring interest in using magnetic resonance imaging (MRI) sequences for diagnosis. In this study, we propose a method that uses deep learning to diagnose MASLD and MASH with significant fibrosis from single-slice (2D) and volumetric (3D) MRI sequences that originate from the UK Biobank. In this paper, we focus on transparent decision-making. Our study shows that imposing anatomically informed constraints by using a liver segmentation mask on the network’s input has minimal impact on diagnostic performance. Still, it redirects attention to clinically relevant liver regions, preventing shortcut learning from extrahepatic features, such as subcutaneous fat. These constraints shift the focus of the model toward proton density fat fraction (PDFF) maps for healthy liver assessment, $T_1$ maps for MASLD diagnosis, and both sequences to identify MASH with significant fibrosis. Our top-performing models achieve AUCs of 0.89/0.96/0.79 for the diagnosis of the healthy/MASLD/MASH groups with significant fibrosis, respectively. Despite label noise and limited sequence specificity, which primarily hinder predictive performance in cases of MASH with significant fibrosis, the identified indicators are frequently located in liver regions consistent with prior understanding of disease progression. In conclusion, we find that 2D MRI sequences are sufficient for diagnosing MASLD/MASH with significant fibrosis, as performance decreases and computation time increases when using 3D volumes.} }
Endnote
%0 Conference Paper %T Deep Learning for Liver Disease Stratification: Findings from UKBB MRI %A Rami Al-Belmpeisi %A Josefine Vilsb ll Sundgaard %A Peter Hj rringgaard Larsen %A Anders Bjorholm Dahl %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-al-belmpeisi26a %I PMLR %P 4384--4400 %U https://proceedings.mlr.press/v315/al-belmpeisi26a.html %V 315 %X Metabolic dysfunction-associated steatotic liver disease (MASLD) and its progressive form, metabolic dysfunction-associated steatohepatitis (MASH), have become more prevalent, spurring interest in using magnetic resonance imaging (MRI) sequences for diagnosis. In this study, we propose a method that uses deep learning to diagnose MASLD and MASH with significant fibrosis from single-slice (2D) and volumetric (3D) MRI sequences that originate from the UK Biobank. In this paper, we focus on transparent decision-making. Our study shows that imposing anatomically informed constraints by using a liver segmentation mask on the network’s input has minimal impact on diagnostic performance. Still, it redirects attention to clinically relevant liver regions, preventing shortcut learning from extrahepatic features, such as subcutaneous fat. These constraints shift the focus of the model toward proton density fat fraction (PDFF) maps for healthy liver assessment, $T_1$ maps for MASLD diagnosis, and both sequences to identify MASH with significant fibrosis. Our top-performing models achieve AUCs of 0.89/0.96/0.79 for the diagnosis of the healthy/MASLD/MASH groups with significant fibrosis, respectively. Despite label noise and limited sequence specificity, which primarily hinder predictive performance in cases of MASH with significant fibrosis, the identified indicators are frequently located in liver regions consistent with prior understanding of disease progression. In conclusion, we find that 2D MRI sequences are sufficient for diagnosing MASLD/MASH with significant fibrosis, as performance decreases and computation time increases when using 3D volumes.
APA
Al-Belmpeisi, R., Sundgaard, J.V.l., Larsen, P.H.r. & Dahl, A.B.. (2026). Deep Learning for Liver Disease Stratification: Findings from UKBB MRI. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:4384-4400 Available from https://proceedings.mlr.press/v315/al-belmpeisi26a.html.

Related Material