Liver fibrosis phenotyping and severity scoring by quantitative image analysis of biopsy slides

Abstract

Background & Aims: Digital pathology image analysis can phenotype liver fibrosis using histological traits that reflect collagen content, morphometry and architecture. Here, we aimed to calculate fibrosis severity scores to quantify these traits. Methods: Liver biopsy slides were categorised by Ishak stage and aetiology. We used a digital pathology technique to calculate four fibrosis severity scores: Architecture Composite Score (ACS), Collagen Composite Score (CCS), Morphometric Composite Score (MCS) and Phenotypic Fibrosis Composite Score (PH-FCS). We compared how these scores varied according to disease stage and aetiology. Results: We included 80 patients (40% female, mean age 59.0 years, mean collagen proportionate area 17.1%) with mild (F0-2, n = 28), moderate (F3-4, n = 17) or severe (F5-6, n = 35) fibrosis. All four aetiology independent scores corelated with collagen proportionate area (ACS: rp =.512, CCS: rp =.727, MCS: rp =.777, PFCS: r =.772, p