Deep learning identifies CT biomarkers that help diagnose type 2 diabetes

By Kate Madden Yee, staff writer

November 15, 2021 --

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.


To read this and get access to all of the exclusive content on create a free account or sign-in now.

Member Sign In:
MemberID or Email Address:  
Do you have a password?
No, I want a free membership.
Yes, I have a password:  
Forgot your password?
Sign in using your social networking account:
Sign in using your social networking