by
Gus Iversen, Editor in Chief | August 07, 2024
A new study reports that routine health screening with CT scans can identify individuals at risk for type 2 diabetes, highlighting the potential of opportunistic imaging, where routine imaging is used to gather broader health information.
The study, published in
Radiology and conducted by researchers in Korea, assessed the effectiveness of automated CT-derived markers in predicting diabetes and related cardiometabolic conditions. The research included 32,166 adults aged 25 and older who underwent health screening with 18F-fluorodeoxyglucose (18F-FDG) PET/CT.
"Given the significant burden of diabetes and its complications, we aimed to explore whether automated and precise imaging analyses could enhance early detection and risk stratification beyond conventional methods," said senior study author Dr. Seungho Ryu, from Kangbuk Samsung Hospital at Sungkyunkwan University School of Medicine in Seoul.
Ad Statistics
Times Displayed: 5216
Times Visited: 8 Final days to save an extra 10% on Imaging, Ultrasound, and Biomed parts web prices.* Unlimited use now through September 30 with code AANIV10 (*certain restrictions apply)
Using clinically validated deep learning algorithms, Dr. Ryu and his team analyzed the CT images. These algorithms facilitated 3D segmentation and quantification of body components such as visceral fat, subcutaneous fat, muscle mass, liver density, and aortic calcium. The analysis revealed that visceral fat had the highest predictive performance for both prevalent and incident diabetes. Combining multiple markers — visceral fat, muscle area, liver fat fraction, and aortic calcification — improved the predictive accuracy.
The study found that automated multiorgan CT analysis identified individuals at high risk for diabetes and other cardiometabolic comorbidities more effectively than traditional risk factors. These CT-derived markers also identified other conditions such as fatty liver, coronary artery calcium scores above 100, osteoporosis, and sarcopenia.
In clinical practice, these CT-derived markers could enhance diabetes screening and risk assessment, allowing for more personalized and timely interventions. The researchers plan to validate their findings in more diverse populations and explore integrating CT-derived markers with other diagnostic tools.
