Office of Technology Transfer – University of Michigan

Method of Detecting Liver Disease, Including Cirrhosis

Technology #4836

Questions about this technology? Ask a Technology Manager

Download Printable PDF

Stewart C. Wang
Managed By
Drew Bennett
Associate Director - Software Licensing 734-615-4004
Patent Protection
US Patent Pending
US Patent Pending

Cirrhosis is the end consequence of all chronic liver disease and can lead to a host of severe complications, such as vascular disease, liver failure, and liver cancer, accounting for an estimated 1.2 million deaths each year in the United States. Cirrhosis is an important clinical landmark and traditionally diagnosed with a liver biopsy. The procedure is painful, carries a small risk of severe complications, and samples a questionably representative portion of the liver (1/50,000 of total volume). Diagnoses by biopsy are also complicated by subjective interpretations from clinicians, with up to 20% intra-observer discrepancy between different pathologists.

Non-invasive, computer-implemented method for detecting liver disease

Using a combination of imaging and computational analysis, a new method has been developed to non-invasively identify the presence of liver disease. The technology can detect liver diseases such as cirrhosis without the pain or risks of biopsy. In addition, the method relies on statistical models rather than human interpretation to produce consistent, unbiased diagnoses. A study comparing this method to AST-to-platelet ratio index (APRI), an established minimally invasive test of liver function, indicated superior performance by the new technology.


  • Detect liver diseases including cirrhosis.


  • Noninvasive
  • Objective diagnoses
  • Higher performance than alternative non-invasive methodsAvoid using “novel” and “new” to describe technology.Bottom of Form