AI-enabled Abdominal CT Can Detect Early Indications of Diabetes
Type 2 diabetes mellitus is a common disease affecting approximately 13% of all U.S. adults; an additional 34.5% meet the criteria for prediabetes. It often develops over several years, with a slow onset of symptoms. Without intervention, patients with impaired blood glucose tests have been shown to develop type 2 diabetes up to 8 years after their initial blood test, indicating a long prodrome phase. However, a recent study suggests that fully automated deep learning-based CT biomarkers can detect and predict type 2 diabetes mellitus. The study findings were published in the journal Radiology on April 05, 2022.
CT biomarkers outside the pancreas may also play an important role. Patients with type 2 diabetes may have more severe atherosclerosis in pancreas-bound arteries, including the splenic artery in the peripancreatic region, and may show signs of liver disease. Visceral fat and muscle mass may also be good predictors of type 2 diabetes. Previous studies on this topic have shown significant results but were limited by manual methods and small study samples. Therefore, Dr Ronald M Summers and his team conducted a study to investigate abdominal CT biomarkers for type 2 diabetes mellitus in a large clinical data set using fully automated deep learning.
In this retrospective study, the researchers evaluated noncontrast abdominal CT images assessed from consecutive patients who underwent routine colorectal cancer screening with CT colonography from 2004 to 2016. They segmented the pancreas using a deep learning method that outputs measurements of interest, including CT attenuation, volume, fat content, and the pancreas fractal dimension. They further assessed additional biomarkers such as visceral fat, atherosclerotic plaque, liver and muscle CT attenuation, and muscle volume. They performed univariable and multivariable analyses separating patients into groups based on the time between type 2 diabetes diagnosis and CT data and including clinical factors such as sex, age, body mass index (BMI), BMI greater than 30 kg/m2, and height. The best set of predictors for type 2 diabetes was determined using multinomial logistic regression.
Key findings of the study:
- Among 8992 patients in the test set, the researcher noted that 572 had type 2 diabetes mellitus.
- They found that the deep learning model had a mean Dice similarity coefficient for the pancreas of 0.69 ± 0.17, similar to the interobserver Dice similarity coefficient of 0.69 ± 0.09.
- Upon univariable analysis, they found that patients with diabetes had, on average, lower pancreatic CT attenuation (mean, 18.74 HU ± 16.54 vs 29.99 HU ± 13.41) and greater visceral fat volume (mean, 235.0 mL ± 108.6 vs 130.9 mL ± 96.3) than those without diabetes.
- They noted that the patients with diabetes also showed a progressive decrease in pancreatic attenuation with a greater duration of disease.
- In a final multivariable model, they found pairwise areas under the receiver operating characteristic curve (AUCs) of 0.81 and 0.85 between patients without and patients with diabetes who were diagnosed 0–2499 days before and after undergoing CT, respectively.
- However, in multivariable analysis, they noted that adding clinical data did not improve upon CT-based AUC performance (AUC = 0.67 for the CT-only model vs 0.68 for the CT and clinical model).
- They highlighted that the best predictors of type 2 diabetes mellitus included intrapancreatic fat percentage, pancreatic fractal dimension, plaque severity between the L1 and L4 vertebra levels, average liver CT attenuation, and BMI.
The authors concluded, "Our study shows that through a multivariable approach, we can use fully automated abdominal CT biomarkers for the opportunistic detection and prediction of type 2 diabetes mellitus at CT performed for other indications. In the field of medical image analysis, improvement in automated pancreas segmentations and its application to clinical problems is needed. This study is a step toward the wider use of automated methods to address clinical challenges. Future work may be focused on predicting type 2 diabetes in a prospective study".
For further information:
DOI: https://doi.org/10.1148/radiol.211914
Keywords:
CT biomarkers, type 2 diabetes mellitus, percentage, pancreatic fractal dimension, plaque severity, BMI, liver CT, Deep learning methods, visceral fat, pancreatic CT, Radiology.
