Scan of visceral fat ‘helps predict MI’
A radiological trainee has received a prize for automating the assessment of body composition
An automated method for analysing body composition from one slice of an abdominal CT scan is better than BMI for predicting risk of MI and stroke, US researchers say.
The multidisciplinary team used artificial intelligence techniques to develop a fully automated way of determining body-composition metrics from abdominal CT images.
They used more than 33,000 abdominal CT exams performed on 23,136 adults (mean age 52 years, 57% female) most of whom were free of major cardiovascular and cancer diagnoses at the time of imaging.
For each individual, the researchers calculated body-composition areas using the CT slice at the third lumbar-spine vertebra.
