A machine learning based algorithm accurately stages liver disease by quantification of arteries

A major histologic feature of cirrhosis is the loss of liver architecture with collapse of tissue and vascular changes per unit. We developed qVessel to quantify the arterial density (AD) in liver biopsies with chronic disease of varied etiology and stage. 46 needle liver biopsy samples with chronic hepatitis B (CHB), 48 with primary biliary cholangitis (PBC) and 43 with metabolic dysfunction-associated steatotic liver disease (MASLD) were collected at the Shuguang Hospital. The METAVIR system was used to assess stage. The second harmonic generation (SHG)/two-photon images were generated from unstained slides. Collagen proportionate area (CPA) using SHG. AD was counted using qVessel (previously trained on manually labeled vessels by stained slides (CD34/a-SMA/CK19) and developed by a decision tree algorithm). As liver fibrosis progressed from F1 to F4, we observed that both AD and CPA gradually increases among the three etiologies (P < 0.05). However, at each stage of liver fibrosis, there was no significant difference in AD or CPA between CHB and PBC compared to MASLD (P > 0.05). AD and CPA performed similar diagnostic efficacy in liver cirrhosis (P > 0.05). Using the qVessel algorithm, we discovered a significant correlation between AD, CPA and METAVIR stages in all three etiologies. This suggests that AD could underpin a novel staging system.