Application of computerized 3D-CT texture analysis of pancreas for the assessment of patients with diabetes

Abstract

Objective: To evaluate the role of computerized 3D CT texture analysis of the pancreas as quantitative parameters for assessing diabetes.

Methods: Among 2,493 patients with diabetes, 39 with type 2 diabetes (T2D) and 12 with type 1 diabetes (T1D) who underwent CT using two selected CT scanners, were enrolled. We compared these patients with age-, body mass index- (BMI), and CT scanner-matched normal subjects. Computerized texture analysis for entire pancreas was performed by extracting 17 variable features. A multivariate logistic regression analysis was performed to identify the predictive factors for diabetes. A receiver operator characteristic (ROC) curve was constructed to determine the optimal cut off values for statistically significant variables.

Results: In diabetes, mean attenuation, standard deviation, variance, entropy, homogeneity, surface area, sphericity, discrete compactness, gray-level co-occurrence matrix (GLCM) contrast, and GLCM entropy showed significant differences (P < .05). Multivariate analysis revealed that a higher variance (adjusted OR, 1.002; P = .005), sphericity (adjusted OR, 1.649×104; P = .048), GLCM entropy (adjusted OR, 1.057×105; P = .032), and lower GLCM contrast (adjusted OR, 0.997; P < .001) were significant variables. The mean AUCs for each feature were 0.654, 0.689, 0.620, and 0.613, respectively (P < .05). In subgroup analysis, only larger surface area (adjusted OR, 1.000; P = .025) was a significant predictor for T2D.

Conclusions: Computerized 3D CT texture analysis of the pancreas could be helpful for predicting diabetes. A higher variance, sphericity, GLCM entropy, and a lower GLCM contrast were the significant predictors for diabetes.

Fig 1. Flow chart of study population.

The flowchart shows how the study population and the control group were selected.

Fig 2. The screenshot shows the texture analysis software program.

The segmentation of pancreatic parenchyma was manually conducted using an in-house software program, and texture features of the pancreatic parenchyma were automatically extracted and calculated by the software program.

Fig 3

3D reconstruction images of an (a) T2D pancreas and (b) its control, with their histograms representing texture features. Each image is from 58-year-old female, with BMI of 24.6 and 24.2, respectively. The T2D patient was not on non-insulin therapy. (c, d) Texture parameters of T2D patients show consistent results with multivariate analysis, including a higher variance (1255.754 HU vs. 753.929 HU), higher sphericity (0.368 vs. 0.347), higher GLCM entropy (4.105 vs. 3.963), and lower GLCM contrast (1132.840 vs. 1277.061).

Fig 4

Receiver operating characteristic (ROC) curve for (a) variance, (b) sphericity, (c) GLCM contrast, and (d) GLCM entropy for differentiation between diabetes and normal control.