Kirti Magudia, M.D., Ph.D., an abdominal imaging and ultrasound fellow at the University of California San Francisco, explains how an automated deep learning analysis of abdominal computed tomography (CT) images can produce a more precise measurement of body composition and better predicts major cardiovascular events, such as heart attack and stroke, better than overall weight or body mass index (BMI). This was according to a study she presented at the 2020 Radiological Society of North America (RSNA) virtual meeting.
Unlike BMI, which is based on height and weight, a single axial CT slice of the abdomen visualizes the volume of subcutaneous fat area, visceral fat area and skeletal muscle area. However, manually measuring these individual areas is time intensive and costly. A multidisciplinary team of researchers, including radiologists, a data scientist and biostatistician, developed a fully automated artificial intelligence (AI) method to determine body composition metrics from abdominal CT images.
Statistical analysis demonstrated that visceral fat area was independently associated with future heart attack and stroke. BMI was not associated with heart attack or stroke.
The software also offers a second set of eyes for more difficult to detect cases. Quickly determining is a stroke is ischemic or hemorrhagic is critical to the path of treatment. If caught early enough, TPA can be injected into patients to clear clots causing an ischemic stroke, but can cause massive brain damage or death if injected into a patient with a brain bleed. At advanced neuro-interventional centers, quickly determining the type of stroke is needed to know if they need to revascularize a patient or manage a hemorrhage. 
