CT-fibrosis score: development and internal validation for identifying advanced fibrosis in metabolic dysfunction-associated steatotic liver disease.
Authors
Affiliations (6)
Affiliations (6)
- Department of Radiology, University of Pittsburgh, Pittsburgh, USA.
- Department of Medicine, University of Pittsburgh, Pittsburgh, USA.
- Department of Bioengineering, University of Pittsburgh, Pittsburgh, USA.
- Department of Research, University of Miami, Coral Gables, USA.
- Pittsburgh Liver Research Center, University of Pittsburgh, Pittsburgh, USA. [email protected].
- Department of Radiology, University of Pittsburgh, Pittsburgh, USA. [email protected].
Abstract
Advanced fibrosis in metabolic dysfunction-associated steatotic liver disease (MASLD) involves metabolic and anatomic remodeling beyond the liver. We developed and internally validated an interpretable CT-based score integrating abdominal body-composition and organ measurements and compared it with the Fibrosis-4 (FIB-4) index. We retrospectively studied 151 patients with biopsy-confirmed MASLD (86 advanced [F3-F4], 65 early-stage [F0-F2] fibrosis). Deep learning-based segmentation quantified abdominal adipose tissue, skeletal muscle, bone, liver, and spleen measurements. The CT-Fibrosis Score was developed using repeated (50×) stratified 5-fold cross-validation, with imputation, standardization, and feature selection confined to each training fold and inner 5-fold cross-validation for hyperparameter selection. Performance was based on out-of-fold predictions and compared with FIB-4 using the DeLong test. Sensitivity analyses addressed missing data, age dependence, and ascites. Four features were consistently selected: age, bone-to-abdominal-cavity volume ratio, visceral adipose tissue (VAT) density, and spleen index. The CT-Fibrosis Score achieved an out-of-fold AUC of 0.77 (95% CI 0.69-0.85). Among 141 patients with an available FIB-4 score, no significant difference was detected between the CT-Fibrosis Score (AUC 0.76) and FIB-4 (AUC 0.79; difference - 0.03, 95% CI - 0.11 to + 0.04; p = 0.37); this comparison was not powered for non-inferiority. Adding the CT-Fibrosis Score to FIB-4 did not improve discrimination (AUC 0.80 vs. 0.79; difference + 0.003, 95% CI - 0.04 to + 0.05; p = 0.90), with the confidence interval excluding an improvement greater than approximately 0.05. The CT-Fibrosis Score achieved moderate discrimination for advanced fibrosis but did not improve discrimination when added to FIB-4. External validation in an unselected population undergoing CT for non-hepatic indications is required before any opportunistic application.