BaCKgRoUND aND aIMS: Manual histological assessment is currently the accepted standard for diagnosing and monitoring disease progression in NASH, but is limited by variability in interpretation and insensitivity to change. Thus, there is a critical need for improved tools to assess liver pathology in order to risk stratify NASH patients and monitor treatment response. appRoaCH aND ReSUltS: Here, we describe a machine learning (ML)-based approach to liver histology assessment, which accurately characterizes disease severity and heterogeneity, and sensitively quantifies treatment response in NASH. We use samples from three randomized controlled trials to build and then validate deep convolutional neural networks to measure key histological features in NASH, including steatosis, inflammation, hepatocellular ballooning, and fibrosis. The ML-based predictions showed strong correlations with expert pathologists and were prognostic of progression to cirrhosis and liver-related clinical events. We developed a heterogeneity-sensitive metric of fibrosis response, the Deep Learning Treatment Assessment Liver Fibrosis score, which measured antifibrotic treatment effects that went undetected by manual pathological staging and was concordant with histological disease progression. CoNClUSIoNS:Our ML method has shown reproducibility and sensitivity and was prognostic for disease progression, demonstrating the power of ML to advance our understanding of disease heterogeneity in NASH, risk stratify affected patients, and facilitate the development of therapies. (Hepatology 2021;74:133-147). G lobal prevalence of NAFLD is rising rapidly. (1,2) NAFLD represents a continuum of disease of varying severity, with milder forms consisting of simple steatosis, whereas the progressive form, NASH, can progress to cirrhosis and end-stage liver disease. NASH-related cirrhosis is now the fastest growing indication for liver transplantation (LT) in the USA. (3)

Calretinin, a calcium-binding protein, is a widely utilized marker for mesothelial differentiation. There is accumulating evidence of calretinin expression in epithelial and mesenchymal malignancies as well. The objectives of this study were 1) further delineate the expression of calretinin in grade 3 breast carcinomas in the context of molecular subtypes and 2) identify the impact of calretinin expression on overall- and disease-free survival. On the basis of immunohistochemical expression of estrogen receptor (ER), progesterone receptor (PR), human epidermal growth factor receptor-2 (HER2), CK5/6 and epidermal growth factor receptor (EGFR), 214 grade 3 invasive ductal carcinomas were stratified into 36 luminal A, 63 luminal B, 24 HER2-positive, 81 basal-like (including 13 metaplastic carcinomas), and 10 unclassified. Tissue microarrays were analyzed for immunohistochemical expression of calretinin. High-level calretinin expression was identified in a significant proportion of basal-like (54.3%), HER2 (33.3%) and unclassified (30%) tumors. In contrast, luminal A and B subtypes demonstrated high-level calretinin expression in only 11.1% and 12.7%, respectively (P<0.0001). Within the basal-like group, 38.5% of the metaplastic carcinomas demonstrated high-level expression, associated predominantly with the epithelial component and squamous metaplasia. High-level calretinin expression was strongly associated with decreased overall survival in the entire cohort of grade 3 cancer (P=0.0096) and in the basal-like group (P=0.039). Multivariate analysis revealed that both tumor stage and high-level calretinin expression were independent predictors of overall survival (P=0.0002 and P=0.0023, respectively). In conclusion, high-level calretinin expression is most common in grade 3 tumors with a basal-like phenotype and is associated with poor overall survival.

No abstract