Related Experiment Video
Updated: Oct 21, 2025

Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
Liver fibrosis staging by computed tomography: Prospective randomized multicentric evaluation of image analyses
Carole Vitellius1, Anita Paisant2, Adrien Lannes1
1Hepato-gastroenterology department, Angers University Hospital, Angers, France; HIFIH Laboratory UPRES EA3859, SFR 4208, Angers University, Angers, France.
Aim:
Liver fibrosis staging is essential. We prospectively evaluated the liver fibrosis staging performance of computed tomography (CT).
Methods:
70 hepato-gastroenterology clinicians were randomized into three stratified groups with different image analyses of radiological semiology, i.e., on raw images (group 1) and on expert-annotated (group 2) and computerized-morphometry-enriched (group 3) images. Radiological fibrosis staging based on seven simple descriptors into four stages equivalent to Metavir stages (F0/1, F2, F3, F4=cirrhosis) was determined at baseline and after image analyses in 10 patients with chronic liver diseases (two per F) concordant for four independent fibrosis stagings including Metavir. 23,800 CT images were analysed, providing 1400 fibrosis stagings.
Results:
Fibrosis staging: overall (3 groups) accuracy (correct classification rate) was, baseline: 43%, post-analysis: 60% (p < 0.001) without significant progression in group 1 (6%, p = 0.207) contrary to groups 2 (34%, p < 0.001) and 3 (13%, p = 0.007). Cirrhosis diagnosis: overall accuracy was, baseline: 84%, post-analysis: 89% (p < 0.001) without significant progression in group 1 (0%, p = 1) contrary to groups 2 (8%, p = 0.009) and 3 (7%, p = 0.015). Baseline AUROCs were good (≥0.83) for marked fibrosis (F≥3 or cirrhosis) in all groups. Post-analysis AUROCs became excellent (≥0.89) in group 2 for all diagnostic targets (≥0.98 for F≥3 and cirrhosis) and in group 3 for cirrhosis. In post-analysis group 2, discrimination between all F was excellent (especially, F1 from F0) with an Obuchowski index at 0.87. Negative and positive predictive values for marked fibrosis were 98% and 95%, respectively.
Conclusion:
Simple CT descriptors accurately discriminate all Metavir liver fibrosis stages.
More Related Videos
08:41Novel In Vivo Micro-Computed Tomography Imaging Techniques for Assessing the Progression of Non-Alcoholic Fatty Liver Disease
Published on: March 24, 2023
09:23Author Spotlight: Enhancing Transplantation Research Through MicroCT Angiography in Murine Models
Published on: September 22, 2023