Automated quantification and architectural pattern detection of hepatic fibrosis in NAFLD.

Accurate detection and quantification of hepatic fibrosis remain essential for assessing the severity of non-alcoholic fatty liver disease (NAFLD) and its response to therapy in clinical practice and research studies. Our aim was to develop an integrated artificial intelligence-based automated tool to detect and quantify hepatic fibrosis and assess its architectural pattern in NAFLD liver biopsies. Digital images of the trichrome-stained slides of liver biopsies from patients with NAFLD and different severity of fibrosis were used. Two expert liver pathologists semi-quantitatively assessed the severity of fibrosis in these biopsies and using a web applet provided a total of 987 annotations of different fibrosis types for developing, training and testing supervised machine learning models to detect fibrosis. The collagen proportionate area (CPA) was measured and correlated with each of the pathologists semi-quantitative fibrosis scores. Models were created and tested to detect each of six potential fibrosis patterns. There was good to excellent correlation between CPA and the pathologist score of fibrosis stage. The coefficient of determination (R2) of automated CPA with the pathologist stages ranged from 0.60 to 0.86. There was considerable overlap in the calculated CPA across different fibrosis stages. For identification of fibrosis patterns, the models areas under the receiver operator curve were 78.6% for detection of periportal fibrosis, 83.3% for pericellular fibrosis, 86.4% for portal fibrosis and >90% for detection of normal fibrosis, bridging fibrosis, and presence of nodule/cirrhosis. In conclusion, an integrated automated tool could accurately quantify hepatic fibrosis and determine its architectural patterns in NAFLD liver biopsies.

Automated assessment of steatosis in murine fatty liver.

Although mice are commonly used to study different aspects of fatty liver disease, currently there are no validated fully automated methods to assess steatosis in mice. Accurate detection of macro- and microsteatosis in murine models of fatty liver disease is important in studying disease pathogenesis and detecting potential hepatotoxic signature during drug development. Further, precise quantification of macrosteatosis is essential for quantifying effects of therapies. Here, we develop and validate the performance of automated classifiers built using image processing and machine learning methods for detection of macro- and microsteatosis in murine fatty liver disease and study the correlation of automated quantification of macrosteatosis with expert pathologist's semi-quantitative grades. The analysis is performed on digital images of 27 Hematoxylin & Eosin stained murine liver biopsy samples. An expert liver pathologist scored the amount of macrosteatosis and also annotated macro- and microsteatosis lesions on the biopsy images using a web-application. Using these annotations, supervised machine learning and image processing techniques, we created classifiers to detect macro- and microsteatosis. For macrosteatosis prediction, the model's precision, sensitivity and area under the receiver operator characteristic (AUROC) were 94.2%, 95%, 99.1% respectively. When correlated with pathologist's semi-quantitative grade of steatosis, the model fits with a coefficient of determination value of 0.905. For microsteatosis prediction, the model has precision, sensitivity and AUROC of 79.2%, 77%, 78.1% respectively. Validation by the expert pathologist of classifier's predictions made on unseen images of biopsy samples showed 100% and 63% accuracy for macro- and microsteatosis, respectively. This novel work demonstrates that fully automated assessment of steatosis is feasible in murine liver biopsies images. Our classifier has excellent sensitivity and accuracy for detection of macrosteatosis in murine fatty liver disease.