Algorithm grades NASH from MRI scans in clinical study

LiverMultiScan image of patient with fatty liver disease postbariatric surgery (Perspectum Diagnostics)

Researchers have presented data suggesting software can grade NASH severity from MRI scans of the liver. The results open the door to the noninvasive stratification of the fast-growing number of people with the liver disease.

NASH has emerged as a concern for healthcare systems and a major opportunity for drug developers in recent years. The condition, a severe form of fatty liver disease, can arise as a comorbidity in people suffering from obesity and type 2 diabetes and can lead to cirrhosis. Drug developers including Intercept and Gilead are working on drugs to treat NASH. But assessing the condition remains challenging.  

Doctors still analyze liver biopsy specimens to stage patients with fatty liver disease, but they also have access to a growing pool of validated noninvasive tools that help with risk stratification and the grading of fibrosis.

Your Daily Newsletter — Free

Enjoying this story? Subscribe to FierceBiotech!

Biopharma is a fast-growing world where big ideas come along every day. Our subscribers rely on FierceBiotech as their must-read source for the latest news, analysis and data in the world of biotech and pharma R&D. To read on the go, sign up today to get biotech news and updates delivered right to your inbox!

Perspectum Diagnostics’ LiverMultiScan is designed to expand the noninvasive toolkit. The algorithm analyzes MRI scans to generate insights into a patient’s liver fat and other biomarkers relevant to the progression of liver disease. Perspectum picked up an expanded FDA approval for the algorithm late last year. And researchers have now published details of a 50-patient study of its effectiveness.

“Multiparametric MRI was superior for the grading of steatosis, grading of NASH severity and for excluding disease, but in this cohort was inferior for the staging of fibrosis,” researchers from universities in Birmingham and Edinburgh wrote in their paper about the study.

The data suggest the algorithm may be better at identifying patients for whom a liver biopsy is unnecessary than existing noninvasive approaches such as liver stiffness. If replicated at scale, the finding could generate savings for healthcare systems. The authors put the savings at around $190 per patient.