Pancreatic magnetic resonance imaging texture analysis in chronic pancreatitis: a feasibility and validation study.

PURPOSE: This feasibility and validation study addresses the potential use of magnetic resonance imaging (MRI) texture analysis of the pancreas in patients with chronic pancreatitis (CP). METHODS: Extraction of 851 MRI texture features from diffusion weighted imaging (DWI) of the pancreas was performed in 77 CP patients and 22 healthy controls. Features were reduced to classify patients into subgroups, and a Bayes classifier was trained using a tenfold cross-validation forward selection procedure. The classifier was optimized to obtain the best average m-fold accuracy, sensitivity, specificity, and positive predictive value. Classifiers were: presence of disease (CP vs. healthy controls), etiological risk factors (alcoholic vs. nonalcoholic etiology of CP and tobacco use vs. no tobacco use), and complications to CP (presumed pancreatogenic diabetes vs. no diabetes and pancreatic exocrine insufficiency vs. normal pancreatic function). RESULTS: The best classification performance was obtained for the disease classifier selecting only five of the original features with 98% accuracy, 97% sensitivity, 100% specificity, and 100% positive predictive value. The risk factor classifiers obtained good performance using 9 (alcohol: 88% accuracy) and 10 features (tobacco: 86% accuracy). The two complication classifiers obtained similar accuracies with only 4 (diabetes: 83% accuracy) and 3 features (exocrine pancreatic function: 82% accuracy). CONCLUSION: Pancreatic texture analysis demonstrated to be feasible in patients with CP and discriminate clinically relevant subgroups based on etiological risk factors and complications. In future studies, the method may provide useful information on disease progression (monitoring) and detection of biomarkers characterizing early-stage CP.

Systematic approach for assessment of imaging features in chronic pancreatitis: a feasibility and validation study from the Scandinavian Baltic Pancreatic Club (SBPC) database.

PURPOSE: There is an unmet need for new systems with quantitative pancreatic imaging assessments to support better diagnosis and understand development of chronic pancreatitis (CP). The aims were to present such an approach for assessment of imaging features in CP, to apply this system in a multi-center cohort of CP patients (feasibility study), and to report inter-reader agreement between expert radiologists (validation study). METHODS: The feasibility study included pancreatic computed tomography (CT) or magnetic resonance imaging (MRI) from 496 patients with definitive CP in the Scandinavian Baltic Pancreatic Club (SBPC) database. Images were assessed according to the new SBPC imaging system (quantitative assessments of ductal and parenchymal features). Inter-reader agreement of reported imaging parameters was investigated for 80 CT and 80 MRI examinations by two expert radiologists. RESULTS: Reporting of the imaging features into the imaging system was deemed feasible for > 80% of CT and > 90% of MRI examinations. Quantitative assessments of main pancreatic duct diameters, presence/number/diameter of calcifications, and gland diameters had high levels of inter-reader agreement with κ-values of 0.75-0.87 and intraclass correlation coefficients of 0.74-0.97. The more subjective assessments, e.g., irregular main pancreatic duct and dilated side-ducts, had poor to moderate agreement with κ-values of 0.03-0.44. CONCLUSION: The presented system provides a feasible mean for systematic assessment of CP imaging features. Imaging parameters based on quantitative assessment, as opposed to subjective assessments, have better reproducibility and should be preferred in the development of new grading systems for understanding pathophysiology and disease progression in CP.

Pancreatic calcifications associate with diverse aetiological risk factors in patients with chronic pancreatitis: A multicentre study of 1500 cases.

BACKGROUND: Pancreatic calcifications is a common finding in patients with chronic pancreatitis (CP), but the underlying pathophysiology is incompletely understood. Past studies for risk factors of calcifications have generally been focused on single parameters or limited by small sample sizes. The aim of this study was to explore several patient and disease characteristics and their associations with pancreatic calcifications in a large cohort of CP patients with diverse aetiological risk factors. METHODS: This was a multicentre, cross-sectional study including 1509 patients with CP. Patient and disease characteristics were compared for patients with calcifications (n = 912) vs. without calcifications (n = 597). Multivariable logistic regression was performed to assess the parameters independently associated with calcifications. RESULTS: The mean age of patients was 53.9 ±â€¯14.5 years and 1006 (67%) were men. The prevalence of calcifications was 60.4% in the overall patient cohort, but highly variable between patients with different aetiological risk factors (range: 2-69%). On multivariate analysis, alcoholic aetiology (OR 1.76 [95% CI, 1.39-2.24]; p < 0.001) and smoking aetiology (OR 1.77 [95% CI, 1.39-2.26], p < 0.001) were positively associated with the presence of calcifications, while an autoimmune aetiology was negatively associated with calcifications (OR 0.15 [95% CI, 0.08-0.27], p < 0.001). Patients with pancreatic calcifications were more likely to have undergone pancreatic duct stenting (OR 1.59 [95%CI, 1.16-2.19], p = 0.004). CONCLUSION: The presence of pancreatic calcifications is associated with diverse aetiological risk factors in patients with CP. This observation attest to the understanding of CP as a complex disease and may have implications for disease classification.