Non-invasive liver fibrosis screening on CT images using radiomics

Abstract Purpose To develop a radiomics machine learning model for detecting liver fibrosis on CT images of the liver. Methods With Ethics Board approval, 169 patients (68 women, 101 men; mean age, 51.2 years ± 14.7 [SD]) underwent an ultrasound-guided liver biopsy with simultaneous CT acquisitions...

Full description

Saved in:
Bibliographic Details
Main Authors: Jay J. Yoo, Khashayar Namdar, Sean Carey, Sandra E. Fischer, Chris McIntosh, Farzad Khalvati, Patrik Rogalla
Format: Article
Language:English
Published: BMC 2025-07-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01823-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849738603915116544
author Jay J. Yoo
Khashayar Namdar
Sean Carey
Sandra E. Fischer
Chris McIntosh
Farzad Khalvati
Patrik Rogalla
author_facet Jay J. Yoo
Khashayar Namdar
Sean Carey
Sandra E. Fischer
Chris McIntosh
Farzad Khalvati
Patrik Rogalla
author_sort Jay J. Yoo
collection DOAJ
description Abstract Purpose To develop a radiomics machine learning model for detecting liver fibrosis on CT images of the liver. Methods With Ethics Board approval, 169 patients (68 women, 101 men; mean age, 51.2 years ± 14.7 [SD]) underwent an ultrasound-guided liver biopsy with simultaneous CT acquisitions without and following intravenous contrast material administration. Radiomic features were extracted from two regions of interest (ROIs) on the CT images, one placed at the biopsy site and another distant from the biopsy site. A development cohort, which was split further into training and validation cohorts across 100 trials, was used to determine the optimal combinations of contrast, normalization, machine learning model, and radiomic features for liver fibrosis detection based on their Area Under the Receiver Operating Characteristic curve (AUC) on the validation cohort. The optimal combinations were then used to develop one final liver fibrosis model which was evaluated on a test cohort. Results When averaging the AUC across all combinations, non-contrast enhanced (NC) CT (AUC, 0.6100; 95% CI: 0.5897, 0.6303) outperformed contrast-enhanced CT (AUC, 0.5680; 95% CI: 0.5471, 0.5890). The most effective model was found to be a logistic regression model with input features of maximum, energy, kurtosis, skewness, and small area high gray level emphasis extracted from non-contrast enhanced NC CT normalized using Gamma correction with γ = 1.5 (AUC, 0.7833; 95% CI: 0.7821, 0.7845). Conclusions The presented radiomics-based logistic regression model holds promise as a non-invasive detection tool for subclinical, asymptomatic liver fibrosis. The model may serve as an opportunistic liver fibrosis screening tool when operated in the background during routine CT examinations covering liver parenchyma. The final liver fibrosis detection model is made publicly available at: https://github.com/IMICSLab/RadiomicsLiverFibrosisDetection .
format Article
id doaj-art-efd8af34a5a443eda6b71d2f2a9a2d50
institution DOAJ
issn 1471-2342
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-efd8af34a5a443eda6b71d2f2a9a2d502025-08-20T03:06:31ZengBMCBMC Medical Imaging1471-23422025-07-0125111410.1186/s12880-025-01823-wNon-invasive liver fibrosis screening on CT images using radiomicsJay J. Yoo0Khashayar Namdar1Sean Carey2Sandra E. Fischer3Chris McIntosh4Farzad Khalvati5Patrik Rogalla6Institute of Medical Science, University of TorontoInstitute of Medical Science, University of TorontoJoint Department of Medical Imaging, University of Toronto, Toronto General HospitalLaboratory Medicine & Pathobiology - Anatomic Pathology, University of Toronto, Toronto General HospitalVector InstituteInstitute of Medical Science, University of TorontoJoint Department of Medical Imaging, University of Toronto, Toronto General HospitalAbstract Purpose To develop a radiomics machine learning model for detecting liver fibrosis on CT images of the liver. Methods With Ethics Board approval, 169 patients (68 women, 101 men; mean age, 51.2 years ± 14.7 [SD]) underwent an ultrasound-guided liver biopsy with simultaneous CT acquisitions without and following intravenous contrast material administration. Radiomic features were extracted from two regions of interest (ROIs) on the CT images, one placed at the biopsy site and another distant from the biopsy site. A development cohort, which was split further into training and validation cohorts across 100 trials, was used to determine the optimal combinations of contrast, normalization, machine learning model, and radiomic features for liver fibrosis detection based on their Area Under the Receiver Operating Characteristic curve (AUC) on the validation cohort. The optimal combinations were then used to develop one final liver fibrosis model which was evaluated on a test cohort. Results When averaging the AUC across all combinations, non-contrast enhanced (NC) CT (AUC, 0.6100; 95% CI: 0.5897, 0.6303) outperformed contrast-enhanced CT (AUC, 0.5680; 95% CI: 0.5471, 0.5890). The most effective model was found to be a logistic regression model with input features of maximum, energy, kurtosis, skewness, and small area high gray level emphasis extracted from non-contrast enhanced NC CT normalized using Gamma correction with γ = 1.5 (AUC, 0.7833; 95% CI: 0.7821, 0.7845). Conclusions The presented radiomics-based logistic regression model holds promise as a non-invasive detection tool for subclinical, asymptomatic liver fibrosis. The model may serve as an opportunistic liver fibrosis screening tool when operated in the background during routine CT examinations covering liver parenchyma. The final liver fibrosis detection model is made publicly available at: https://github.com/IMICSLab/RadiomicsLiverFibrosisDetection .https://doi.org/10.1186/s12880-025-01823-wMachine learningLiverFibrosisComputed tomographyRadiomics
spellingShingle Jay J. Yoo
Khashayar Namdar
Sean Carey
Sandra E. Fischer
Chris McIntosh
Farzad Khalvati
Patrik Rogalla
Non-invasive liver fibrosis screening on CT images using radiomics
BMC Medical Imaging
Machine learning
Liver
Fibrosis
Computed tomography
Radiomics
title Non-invasive liver fibrosis screening on CT images using radiomics
title_full Non-invasive liver fibrosis screening on CT images using radiomics
title_fullStr Non-invasive liver fibrosis screening on CT images using radiomics
title_full_unstemmed Non-invasive liver fibrosis screening on CT images using radiomics
title_short Non-invasive liver fibrosis screening on CT images using radiomics
title_sort non invasive liver fibrosis screening on ct images using radiomics
topic Machine learning
Liver
Fibrosis
Computed tomography
Radiomics
url https://doi.org/10.1186/s12880-025-01823-w
work_keys_str_mv AT jayjyoo noninvasiveliverfibrosisscreeningonctimagesusingradiomics
AT khashayarnamdar noninvasiveliverfibrosisscreeningonctimagesusingradiomics
AT seancarey noninvasiveliverfibrosisscreeningonctimagesusingradiomics
AT sandraefischer noninvasiveliverfibrosisscreeningonctimagesusingradiomics
AT chrismcintosh noninvasiveliverfibrosisscreeningonctimagesusingradiomics
AT farzadkhalvati noninvasiveliverfibrosisscreeningonctimagesusingradiomics
AT patrikrogalla noninvasiveliverfibrosisscreeningonctimagesusingradiomics