Machine learning based assessment of liver fat identifies patients at risk for severe COVID-19

In a latest article revealed in The Lancet’s eBioMedicine open entry journal, a crew from Emory University and University Hospitals (UH) Cleveland shared outcomes from a multi-site research that indicated that patients with nonalcoholic fatty liver illness—also called hepatic steatosis – one was one-and-a-half occasions extra prone to develop severe COVID-19.

The crew obtained the outcomes utilizing a deep learning-based hepatic fat assessment (DeHFt) pipeline that it developed to offer automated measurements of liver fat from customary CT scans. Study collaborators included Case Western Reserve University, Wuhan University, the Atlanta Veterans Administration Medical Center, and Guangdong Academy of Medical Sciences.

“We know that hepatic steatosis is a risk factor for COVID-19. Now we can use this pipeline to identify high-risk patients and based on that, clinicians can make better informed decisions about levels of care and the early use of therapeutic agents, such as antivirals ,” said Gourav Modanwal, first author of the study and a researcher in the Wallace H. Coulter Department of Biomedical Engineering at Emory University School of Medicine and Georgia Institute of Technology College of Engineering.

The DeHFt process uses coronary artery calcium CT scans, which are commonly used to detect and measure calcium-containing plaque in a patient’s arteries. In addition to showing the heart, the images also include portions of the liver and spleen, so they provide an opportunity to evaluate liver fat. However, they have not historically been used to assess hepatic fat due to the difficulty of manually measuring areas of interest to clinicians with higher magnification and resolution. The DeHFt pipeline can perform the job quickly and accurately, and it eliminates the inherent variability between CT scan readings among radiologists.

Deep learning, which is a type of artificial intelligence that mimics the way humans acquire knowledge, is the basis of the two-step DeHFt process. First, a segmentation model is trained to segment the liver and spleen using coronary calcium CT scans. Then CT attenuation – examination of the intensity of liver and spleen – is estimated using stacks of liver and spleen slices visible in 3D. Lower liver intensities reflect more fat infiltration, while the spleen serves as a control to compare the liver-to-spleen ratio.

“This is a very exciting and translationally relevant finding. Our study suggests that machine learning based on routine CT scans can aid in accurate quantification of liver fat, which has implications beyond COVID-19 severity assessment,” stated Anant Madabhushi, the research’s senior creator and a professor within the Wallace H. Coulter Department of Biomedical Engineering at Emory School of Medicine and Georgia Institute of Technology College of Engineering.

Hepatic attenuation on CT scans is a surrogate marker for cardiometabolic risk, together with sort 2 diabetes and its development. “This new pipeline provides an important avenue for CT-based analysis of fat and metabolic risk that is scalable for population-level imaging and can be used for risk stratification for cardiometabolic disease,” stated research co-author Sadeer Al-Kindi, MD, director of the cardiovascular phenomenon core and co-director of the Vascular Metabolic Center at the UH Harrington Heart & Vascular Institute. “We are currently working to translate this and validate it in several large cohorts for risk prediction.”

Modanwal says the DeHFt pipeline holds promise for dependable, reproducible liver fat measurements, offering an built-in cardiometabolic and COVID-19 risk software.

“It’s a unique way to see if a patient has fatty liver disease or not using CT scans,” he says. “We can apply the pipeline to millions of cases rather than relying on time-consuming manual examination of scans.”