Intravoxel incoherent motion diffusion-weighted imaging for evaluating the pancreatic perfusion in cirrhotic patients.

PURPOSE: To assess the characteristics of pancreatic perfusion in normal pancreas versus cirrhotic patients using intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI). METHODS: A total of 67 cirrhotic patients and 33 healthy subjects underwent IVIM on a 3.0 T MRI scanner. Diffusion coefficient (ADCslow), pseudo-diffusion coefficient (ADCfast), and perfusion fraction (f) were calculated based on the bi-exponential model. The pancreatic IVIM-derived parameters were then compared. In the cirrhotic group, the relationship was analyzed between IVIM-derived pancreatic parameters and different classes of hepatic function as determined by the Child-Pugh classification. Also, the pancreatic IVIM-derived parameters were compared among different classes of cirrhosis as determined by the Child-Pugh classification. RESULTS: The f value of the pancreas in cirrhotic patients was significantly lower than that in normal subjects (p = 0.01). In the cirrhotic group, the f value of the pancreas decreased with the increase of the Child-Pugh classification (R = - 0.49, p = 0.00). The f value of the pancreas was significantly higher in Child-Pugh class A patients than in class B and C patients (p = 0.02, 0.00, respectively), whereas there was no significant difference between class B and C patients (p = 0.16). CONCLUSION: The IVIM-derived perfusion-related parameter (f value) could be helpful for the evaluation of pancreatic perfusion in liver cirrhosis. Our data also suggest that the blood perfusion decrease in the pancreas is present in liver cirrhosis, and the pancreatic perfusion tends to decrease with the increasing severity of hepatic function. TRIAL REGISTRATION: Trial registration number is 2021-ky-68 and date of registration for prospectively registered trials is February 23, 2022.

A radiomics model of contrast-enhanced computed tomography for predicting post-acute pancreatitis diabetes mellitus.

Background: Diabetes mellitus can occur after acute pancreatitis (AP), but the accurate quantitative methods to predict post-acute pancreatitis diabetes mellitus (PPDM-A) are lacking. This retrospective study aimed to establish a radiomics model based on contrast-enhanced computed tomography (CECT) for predicting PPDM-A. Methods: A total of 374 patients with first-episode AP were retrospectively enrolled from two tertiary referral centers. There were 224 patients in the training cohort, 56 in the internal validation cohort, and 94 in the external validation cohort, and there were 86, 22, and 27 patients with PPDM-A in these cohorts, respectively. The clinical characteristics were collected from the hospital information system. A total of 2,398 radiomics features, including shape-based features, first-order histogram features, high order textural features, and transformed features, were extracted from the arterial- and venous-phase CECT images. Intraclass correlation coefficients were used to assess the intraobserver reliability and interobserver agreement. Random forest-based recursive feature elimination, collinearity analysis, and least absolute shrinkage and selection operator (LASSO) were used for selecting the final features. Three classification methods [eXtreme Gradient Boosting (XGBoost), Adaptive Boosting, and Decision Tree] were used to build three models and performances of the three models were compared. Each of the three classification methods were used to establish the clinical model, radiomics model, and combined model for predicting PPDM-A, resulting in a total of nine classifiers. The predictive performances of the models were evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F1-score. Results: Eleven radiomics features were selected after a reproducibility test and dimensionality reduction. Among the three classification methods, the XGBoost classifier showed better and more consistent performances. The AUC of the XGBoost's radiomics model to predict PPDM-A in the training, internal, and external cohorts was good (0.964, 0.901, and 0.857, respectively). The AUC of the XGBoost's combined model to predict PPDM-A in the training, internal, and external cohorts was good (0.980, 0.901, and 0.882, respectively). The AUC of the XGBoost's clinical model to predict PPDM-A in the training, internal, and external cohorts did not perform well (0.685, 0.733, and 0.619, respectively). In the external validation cohort, the AUC of the XGBoost's radiomics model was significantly higher than that of the clinical model (0.857 vs. 0.619, P<0.001), but there was no significant difference between the combined and radiomics models (0.882 vs. 0.857, P=0.317). Conclusions: The radiomics model based on CECT performs well and can be used as an early quantitative method to predict the occurrence of PPDM-A.