Wednesday, December 1 | 9:30 a.m.-10:30 a.m. | SSGI11-3 | Room TBA
Deep learning can identify CT biomarkers that help detect and predict type 2 diabetes in patients undergoing CT for other indications, according to a presentation to be delivered Wednesday morning."The diagnosis of diabetes is associated with CT biomarkers, especially measures of pancreas CT attenuation and visceral fat," wrote a team led by Hima Tallam, a medical and doctoral student at Rutgers New Jersey Medical School in Wayne, NJ, in a study abstract.
Tallam and colleagues conducted a study that included 8,992 patients who underwent colorectal cancer screening with CT colonography; of these, 572 had type 2 diabetes and 1,880 were dysglycemic. The researchers segmented images of the pancreas using a deep-learning algorithm that flagged biomarkers such as CT attenuation, volume, fat content, and the fractal dimension of the organ, as well as visceral fat and atherosclerotic plaque.
The deep-learning model showed that diabetics had lower pancreas CT attenuation and higher visceral fat than those patients who did not have the disease. Other key predictors of type 2 diabetes on CT included the following:
- Fractal dimension of the pancreas
- Severity of abdominal aortic plaque
- Body mass index (BMI) higher than 30 kg/m2
"Fully-automated CT biomarkers can be used for the opportunistic detection and prediction of type 2 diabetes on scans performed for other indications," Tallam and colleagues concluded.
![Axial images from unenhanced calcium score cardiac CT (left) and curved planar reformation images from CT angiography (right) show that higher long-term exposure to air pollution is associated with greater coronary artery calcium and more obstructive coronary artery disease (CAD). Top row: Images in a 68-year-old male patient with higher 10-year mean ambient air pollution exposure (7.9 μg/m3 for particulate matter measuring ≤2.5 μm in diameter [PM2.5] and 17.4 parts per billion [ppb] for NO2) with extensive CAD (coronary artery calcium score [CACS] >1,000 and obstructive CAD [≥70% diameter stenosis]). Bottom row: Images in a 57-year-old female patient with lower 10-year mean ambient air pollution exposure (6.3 μg/m3 for PM2.5 and 4.6 ppb for NO2) with no CAD (CACS = 0 and no obstructive stenosis).](https://img.auntminnie.com/mindful/smg/workspaces/default/uploads/2026/06/hanneman.r6SMLzkezo.png?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
