Staging Liver Fibrosis with Hepatic Perivascular Adipose Tissue as a CT Biomarker

Skylar Chan, Tejas Sudharshan Mathai, Praveen T.S. Balamuralikrishna, Vivek Batheja, Jianfei Liu, Meghan G Lubner, Perry J Pickhardt, Ronald Summers
Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, PMLR 301:183-194, 2026.

Abstract

Cirrhosis is the 12th leading cause of death in the US. There are several CT imaging signs of late fibrosis, such as redistribution of liver segment volume, increased liver nodularity, and periportal space widening. Timely intervention can reverse the progression of early hepatic fibrosis, but later stages are irreversible. We hypothesize that the perivascular adipose tissue (PVAT) around the portal vein arising from periportal space widening may also be predictive of liver fibrosis. In this work, a fully automated pipeline was developed to segment the liver, spleen, portal vein and its branches. The PVAT in the vicinity of the portal vein was identified. From these structures, CT imaging biomarkers (volume, attenuation, fat fraction) were computed. They were used to build uni- and multivariate logistic regression models for diagnosing advanced fibrosis and cirrhosis. The best multivariate model for cirrhosis achieved 93.3% AUC, 78.9% sensitivity, and 93.4% specificity. For advanced fibrosis, the multivariate model obtained 88.7% AUC, 84.2% sensitivity, and 73.7% specificity. The automated approach may be useful for population-based studies of metabolic disease and opportunistic screening.

Cite this Paper

BibTeX
@InProceedings{pmlr-v301-chan26a, title = {Staging Liver Fibrosis with Hepatic Perivascular Adipose Tissue as a CT Biomarker}, author = {Chan, Skylar and Mathai, Tejas Sudharshan and Balamuralikrishna, Praveen T.S. and Batheja, Vivek and Liu, Jianfei and Lubner, Meghan G and Pickhardt, Perry J and Summers, Ronald}, booktitle = {Proceedings of The 8th International Conference on Medical Imaging with Deep Learning}, pages = {183--194}, year = {2026}, editor = {Tasdizen, Tolga and Elhabian, Shireen and Summers, Ronald and Chen, Chen and Koch, Lisa and Zhuang, Yan}, volume = {301}, series = {Proceedings of Machine Learning Research}, month = {09--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v301/main/assets/chan26a/chan26a.pdf}, url = {https://proceedings.mlr.press/v301/chan26a.html}, abstract = {Cirrhosis is the 12th leading cause of death in the US. There are several CT imaging signs of late fibrosis, such as redistribution of liver segment volume, increased liver nodularity, and periportal space widening. Timely intervention can reverse the progression of early hepatic fibrosis, but later stages are irreversible. We hypothesize that the perivascular adipose tissue (PVAT) around the portal vein arising from periportal space widening may also be predictive of liver fibrosis. In this work, a fully automated pipeline was developed to segment the liver, spleen, portal vein and its branches. The PVAT in the vicinity of the portal vein was identified. From these structures, CT imaging biomarkers (volume, attenuation, fat fraction) were computed. They were used to build uni- and multivariate logistic regression models for diagnosing advanced fibrosis and cirrhosis. The best multivariate model for cirrhosis achieved 93.3% AUC, 78.9% sensitivity, and 93.4% specificity. For advanced fibrosis, the multivariate model obtained 88.7% AUC, 84.2% sensitivity, and 73.7% specificity. The automated approach may be useful for population-based studies of metabolic disease and opportunistic screening.} }
Endnote
%0 Conference Paper %T Staging Liver Fibrosis with Hepatic Perivascular Adipose Tissue as a CT Biomarker %A Skylar Chan %A Tejas Sudharshan Mathai %A Praveen T.S. Balamuralikrishna %A Vivek Batheja %A Jianfei Liu %A Meghan G Lubner %A Perry J Pickhardt %A Ronald Summers %B Proceedings of The 8th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Tolga Tasdizen %E Shireen Elhabian %E Ronald Summers %E Chen Chen %E Lisa Koch %E Yan Zhuang %F pmlr-v301-chan26a %I PMLR %P 183--194 %U https://proceedings.mlr.press/v301/chan26a.html %V 301 %X Cirrhosis is the 12th leading cause of death in the US. There are several CT imaging signs of late fibrosis, such as redistribution of liver segment volume, increased liver nodularity, and periportal space widening. Timely intervention can reverse the progression of early hepatic fibrosis, but later stages are irreversible. We hypothesize that the perivascular adipose tissue (PVAT) around the portal vein arising from periportal space widening may also be predictive of liver fibrosis. In this work, a fully automated pipeline was developed to segment the liver, spleen, portal vein and its branches. The PVAT in the vicinity of the portal vein was identified. From these structures, CT imaging biomarkers (volume, attenuation, fat fraction) were computed. They were used to build uni- and multivariate logistic regression models for diagnosing advanced fibrosis and cirrhosis. The best multivariate model for cirrhosis achieved 93.3% AUC, 78.9% sensitivity, and 93.4% specificity. For advanced fibrosis, the multivariate model obtained 88.7% AUC, 84.2% sensitivity, and 73.7% specificity. The automated approach may be useful for population-based studies of metabolic disease and opportunistic screening.
APA
Chan, S., Mathai, T.S., Balamuralikrishna, P.T., Batheja, V., Liu, J., Lubner, M.G., Pickhardt, P.J. & Summers, R.. (2026). Staging Liver Fibrosis with Hepatic Perivascular Adipose Tissue as a CT Biomarker. Proceedings of The 8th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 301:183-194 Available from https://proceedings.mlr.press/v301/chan26a.html.

Related Material