Non-invasive liver fibrosis screening on CT images using radiomics.
Authors
Affiliations (16)
Affiliations (16)
- Institute of Medical Science, University of Toronto, 1 King's College Circle, Toronto, ON, M5S 1A8, Canada.
- Department of Diagnostic Imaging & Interventional Radiology, The Hospital for Sick Children, 555 University Avenue, Toronto, ON, M5G 1X8, Canada.
- Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON, M5S 2E4, Canada.
- Vector Institute, 661 University Avenue, Toronto, ON, M5G 1M1, Canada.
- Joint Department of Medical Imaging, University of Toronto, Toronto General Hospital, 585 University Avenue, Toronto, ON, M5G 2N2, Canada.
- Laboratory Medicine & Pathobiology - Anatomic Pathology, University of Toronto, Toronto General Hospital, 585 University Avenue, Toronto, ON, M5G 2N2, Canada.
- Department of Medical Biophysics, University of Toronto, 101 College Street, Toronto, ON, M5G 1L7, Canada.
- Techna Institute, University Health Network, 190 Elizabeth Street, Toronto, ON, M5G 2C4, Canada.
- Radiation Medicine Program, Princess Margaret Cancer Centre, 610 University Avenue, Toronto, ON, M5G 2C4, Canada.
- Peter Munk Cardiac Center, University Health Network, 585 University Avenue, Toronto, ON, M5G 2N2, Canada.
- Institute of Medical Science, University of Toronto, 1 King's College Circle, Toronto, ON, M5S 1A8, Canada. [email protected].
- Department of Diagnostic Imaging & Interventional Radiology, The Hospital for Sick Children, 555 University Avenue, Toronto, ON, M5G 1X8, Canada. [email protected].
- Department of Medical Imaging, University of Toronto, 263 McCaul Street, Toronto, ON, M5T 1W7, Canada. [email protected].
- Department of Computer Science, University of Toronto, 40 St. George Street, Toronto, ON, M5S 2E4, Canada. [email protected].
- Department of Mechanical and Industrial Engineering, University of Toronto, 5 King's College Road, Toronto, ON, M5S 3G8, Canada. [email protected].
- Vector Institute, 661 University Avenue, Toronto, ON, M5G 1M1, Canada. [email protected].
Abstract
To develop a radiomics machine learning model for detecting liver fibrosis on CT images of the liver. 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. 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). 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 .