imagedx: Nash

AI-Powered Digital Assays

Reveal Biosciences is creating a new generation of data powered pathology to enhance research and improve global healthcare. Reveal combines cutting edge artificial intelligence (AI) with traditional histopathology to transform tissue biology into actionable data. imageDx™, our data-powered pathology platform provides secure whole slide image management and AI-based image processing in the cloud. Our fully automated laboratory and experienced scientists also provide histopathology, immunohistochemistry (IHC) and in situ hybridization (ISH) expertise for a wide range of pharmaceutical, biotech, academic, and government institutions. With a world class team of data and research scientists focused on addressing some of the biggest problems in healthcare, Reveal is developing a pipeline of AI-based digital assays for preclinical research, clinical trials, and decision support.

A: Masson’s Trichrome-stained liver tissue with a masked portal region. B: H&E-stained liver tissue with a masked ballooning cell.

Summary: Non-alcoholic fatty liver disease (NAFLD) is one of the most common causes of chronic liver disease. It results in an accumulation of fat in the liver (steatosis), and can progress to a more pathologically significant form of NAFLD known as non-alcoholic steatohepatitis (NASH). Patients or rodent models of NAFLD and NASH present on a spectrum of the disease, characterized by hepatitis (inflammation) and hepatocellular ballooning (cellular injury), which can lead to excessive fibrosis and scarring.

Currently, diagnosis is confirmed by liver histology that is qualitatively analyzed by experienced pathologists who assign scores for each feature. However, documented inter-pathologist variability in scoring and the semi-quantitative nature of the scoring system itself highlight the need for new quantitative methods to ensure the unbiased, consistent assessment of disease.

imageDx™: NASH is a collection of artificial intelligence (AI)-based pathology models to provide quantitative histopathology data from liver tissue.  These machine learning algorithms were developed with input from experienced veterinary pathologists with the goal of providing a more quantitative and reproducible analysis of the tissue pathology.  The data outputs are listed below.

Tissue Feature

Output

Steatosis

 Macro-vesicular

 Micro-vesicular

Mean Vesicle Size

Mean Lipid per Hepatocyte

Steatosis Score

Percentage (%), Area (mm2)

 Percentage (%)

 Percentage (%)

um2

um2

Algorithm-derived score

Ballooning Hepatocyte Density

Ballooning Score

Ballooning cells per cm2

Algorithm-derived score

Immune Cells

Immune Cell Foci

Inflammation Score

Count, Area (mm2), Density (cells/mm2)

Foci count, Mean foci size

Algorithm-derived score

Fibrosis Area

Fibrosis Intensity

Fibrosis Score

mm2, Percentage (%)

Intensity Units

Semi-Automated Score

Mallory Bodies

Present or Absent

Tissue Area Analyzed

mm2

For research use only. © 2020 Reveal Biosciences, Inc.

Pathology Revealed

Subscribe to our  newsletter to receive updates, access digital pathology resources, and more.