Machine Learning Identifies Histologic Features Associated With Regression of Cirrhosis in Treatment for Chronic Hepatitis B

♦ Hepatitis B virus (HBV) infection is associated with progression to
cirrhosis, development of hepatocellular carcinoma, and liver-related
mortality

♦ Although most patients with HBV on suppressive antiviral therapy
achieve regression of cirrhosis, a subset do not; histologic features
associated with regression of cirrhosis are not well understood

♦ Image analysis methods have been applied to evaluate liver histology
in HBV; a machine learning (ML) approach leveraging convolutional
neural networks (CNNs) could facilitate characterization of histologic
features associated with regression of cirrhosis