Browsing by Subject "liver biopsy"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Automated assessment of steatosis in murine fatty liver
    (PLOS, 2018-05-10) Sethunath, Deepak; Morusu, Siripriya; Tuceryan, Mihran; Cummings, Oscar W.; Zhang, Hao; Yin, Xiao-Ming; Vanderbeck, Scott; Chalasani, Naga; Gawrieh, Samer; Computer and Information Science, School of Science
    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.
  • Thumbnail Image
    Item
    Serum high mobility group box 1 protein levels are not associated with either histological severity or treatment response in children and adults with nonalcoholic fatty liver disease
    (PLOS, 2017-11-02) Yates, Katherine P.; Deppe, Ross; Comerford, Megan; Masuoka, Howard; Cummings, Oscar W.; Tonascia, James; Chalasani, Naga; Vuppalanchi, Raj; Medicine, School of Medicine
    Aim Serum high mobility group box 1 protein (HMGB1) is a proinflammatory molecule that could potentially serve as a biomarker for non-alcoholic fatty liver disease (NAFLD) and non-alcoholic steatohepatitis (NASH) due to its correlation with degree of liver fibrosis. The aim of the current study was to examine the cross-sectional and longitudinal relationships between serum HMGB1 levels and liver histology in adults and children with NAFLD participating in two large randomized controlled trials. Methods Serum HMGB1 levels were measured at various time points in adults and children with NAFLD, who participated in PIVENS and TONIC clinical trials respectively. PIVENS trial compared vitamin E or pioglitazone to placebo in adults whereas TONIC trial compared vitamin E or metformin to placebo in children. Participants had liver biopsies at baseline and the end of treatment (96 weeks), and liver histology was reviewed by a central committee of study pathologists. Results In the cross-sectional analyses (n = 205 for PIVENS and 109 for TONIC), there was no significant relationship between serum HMGB1 levels and histological features such as steatosis, ballooning, inflammation, fibrosis, or presence of steatohepatitis in either adults or children. Serum HMGB1 levels did not change significantly during treatment either with placebo, vitamin E therapy (P = 0.81) or pioglitazone (P = 0.09) in the PIVENS trial. Similarly, serum HMGB1 levels did not change significantly during treatment either with placebo, metformin (P = 0.15) or vitamin E (P = 0.23) in the TONIC trial. In the longitudinal analyses (n = 105 for PIVENS and 109 for TONIC), changes in serum HMGB1 levels did not correlate with histologic improvement or resolution of NASH in either adults or children. There was no relationship between serum HMGB1 and ALT levels in either adults or children with NAFLD. Conclusion Serum HMGB1 levels were not associated with histological severity or treatment response in either children or adults with NAFLD.