Systems and methods for assessing liver pathology

US12383191B1 · kind B1 · utility

Assignee

• PathAI, Inc. · US

Inventors

• Amaro N. Taylor-Weiner · Brooklyn, US
• Harsha Vardhan Pokkalla · Brookline, US
• Hunter L. Elliott · Boston, US
• Benjamin P. Glass · Boston, US
• Ilan N. Wapinski · Cambridge, US
• Aditya Khosla · Sunnyvale, US
• Murray Resnick · Sharon, US
• Michael Christopher Montalto · Albany, US
• Andrew H. Beck · Brookline, US
• Zahil Shanis · Claymont, US
• Aryan Pedawi · Austin, US
• Quang Huy Le · Malden, US
• Jason K. Wang · Los Angeles, US
• Maryam Pouryahya · Bethesda, US
• Kenneth Knute Leidal · Cambridge, US
• Oscar M. Carrasco-Zevallos · Somerville, US
• Dinkar Juyal · Boston, US
• Charles Biddle-Snead · New York, US
• Katy Wack · Pittsburgh, US

Key dates

• Filing date: May 3, 2021
• Grant date: Aug 12, 2025
• Expiry date: Nov 23, 2043

Classification

• Technology area (CPC G): Physics
• CPC primary: G06T2207/30056
• WIPO field: Medical technology
• WIPO sector: Instruments

Abstract

In some aspects, the described systems and methods provide for a method for training a deep learning model to assess liver pathology, including accessing annotated liver pathology images associated with a group of patients in one or more randomized controlled clinical trials of nonalcoholic steatohepatitis therapy, each of the annotated liver pathology images including at least one annotation describing one or more tissue characteristic categories for a portion of the image, and training the deep learning model based on the annotated liver pathology images to predict the tissue characteristic categories, selected from a group comprising steatosis, lobular inflammation, hepatocyte ballooning, and fibrosis stage.