Visual steatosis assessment: method-dependent variation and systematically higher estimates compared with AI measurement.

Saadiya Nazli¹, Abdelrahman Shaaban², Ameya Patil¹, Lindsey Smith³, Lucas Stetzik⁴, Bashar Hasan⁵, Rofyda Elhalaby¹, Adilson DaCosta¹, Priya Sivasubramaniam⁶, Byoung Uk Park⁷, Murli Krishna⁸, Marcela Salomao⁹, Rish Pai¹⁰, Maxwell Smith⁹, Daniela Allende¹¹, Christopher P Hartley¹, Hee Eun Lee¹, Zongming Eric Chen¹, Kristina A Matkowskyj¹, Rondell P Graham¹, Roger K Moreira¹

¹Department of Laboratory Medicine and Pathology, Mayo Clinic, Rochester, Minnesota, USA.

²Department of Pathology, University of Virginia, Charlottesville, Virginia, USA.

³MySME, Birmingham, Alabama, USA.

⁴Aiforia Technologies, Rochester, Minnesota, USA.

⁵Department of Preventive, Occupational, and Aerospace Medicine, Mayo Clinic, Rochester, Minnesota, USA.

⁶Department of Pathology, Medical College of Wisconsin, Milwaukee, Wisconsin, USA.

⁷Department of Pathology, University of Minnesota, Minneapolis, Minnesota, USA.

⁸Department of Laboratory Medicine and Pathology, Mayo Clinic, Jacksonville, Florida, USA.

⁹Department of Laboratory Medicine and Pathology, Mayo Clinic, Scottsdale, Arizona, USA.

¹⁰Department of Laboratory Medicine and Pathology, University of Toronto, Toronto, Ontario, Canada.

¹¹Department of Pathology, Cleveland Clinic, Cleveland, Ohio, USA.

PubMed DOI

Abstract

AIMS: Despite its clinical importance, histological steatosis assessment remains poorly standardized and highly variable among pathologists. We examined determinants of this variability by comparing pathologist estimates with quantitative artificial intelligence (AI) based measurements. METHODS AND RESULTS: Ten experienced liver pathologists from four institutions evaluated a limited set of 20 pe…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.