Magnetic Resonance Imaging-Based Radiomics Models to Predict Early Extrapancreatic Necrosis in Acute Pancreatitis.

OBJECTIVE: The aim of the study was to investigate radiomics models based on magnetic resonance imaging (MRI) for predicting early extrapancreatic necrosis (EXPN) in acute pancreatitis. METHODS: Radiomics features were extracted from T2-weighted images of extrapancreatic collections and late arterial-phase images of the pancreatic parenchyma for 135 enrolled patients (94 in the primary cohort, including 47 EXPN patients and 41 in the validation cohort, including 20 EXPN patients). The optimal features after dimension reduction were used for radiomics modeling through a support vector machine. A clinical model, the MR severity index score, and extrapancreatic inflammation on MRI were evaluated. RESULTS: Twelve optimal features from the extrapancreatic collection images and 10 from the pancreatic parenchyma images were selected for modeling. The pancreatic parenchyma-based and extrapancreatic collection-based radiomics models showed good predictive accuracy in both the training and validation cohorts. The areas under the curve of the extrapancreatic collection-based radiomics model (0.969 and 0.976) were consistent with those of the pancreatic parenchyma-based model (0.931 and 0.921) for both cohorts and better than those of the clinical model and imaging scores for both cohorts. CONCLUSIONS: The MRI-based radiomics models of both the extrapancreatic collections and the pancreatic parenchyma had excellent predictive performance for early EXPN.

Sinistral Portal Hypertension in Acute Pancreatitis: A Magnetic Resonance Imaging Study.

OBJECTIVE: The aim of the study was to study the prevalence and characteristics of sinistral portal hypertension (SPH) in acute pancreatitis (AP) and its correlation with the severity of AP. METHODS: Retrospectively studied 633 patients with AP admitted to our institution and underwent magnetic resonance imaging (MRI). Diagnosis of SPH was based on clinical manifestations, laboratory tests, and MRI. The venous system and pancreatitis were evaluated on T1 weighted imaging, T2 weighted imaging, and dynamic-enhancement MRI. Data on patients' demographics, etiology, organ failure, MR severity index, and clinical outcomes were all collected. RESULTS: The SPH was detected in 21 patients (3.3%, 21/633). There was no statistical difference in organ failure between patients with SPH and without SPH (P > 0.05). The prevalence of SPH in males and females was 5.1% (17/336) versus 1.3% (4/297) (χ(2) = 6.775, P = 0.009), in edematous and necrotizing AP was 0.4% (2/510) versus 15.5% (19/123) (χ(2) = 65.413, P = 0.000), and in mild, moderate, and severe AP, based on MR severity index, were 0.6% (2/334) versus 2.9% (8/276) versus 47.8% (11/23) (χ(2) = 55.977, P = 0.000), respectively. CONCLUSIONS: The SPH rarely occurs in AP, and its risk is higher in males. Its presence is strongly associated with the local conditions of pancreatitis.

Radiomics model of contrast-enhanced computed tomography for predicting the recurrence of acute pancreatitis.

OBJECTIVES: To predict the recurrence of acute pancreatitis (AP) by constructing a radiomics model of contrast-enhanced computed tomography (CECT) at AP first attack. METHODS: We retrospectively enrolled 389 first-attack AP patients (271 in the primary cohort and 118 in the validation cohort) from three tertiary referral centers; 126 and 55 patients endured recurrent attacks in each cohort. Four hundred twelve radiomics features were extracted from arterial and venous phase CECT images, and clinical characteristics were gathered to develop a clinical model. An optimal radiomics signature was chosen using a multivariable logistic regression or support vector machine. The radiomics model was developed and validated by incorporating the optimal radiomics signature and clinical characteristics. The performance of the radiomics model was assessed based on its calibration and classification metrics. RESULTS: The optimal radiomics signature was developed based on a multivariable logistic regression with 10 radiomics features. The classification accuracy of the radiomics model well predicted the recurrence of AP for both the primary and validation cohorts (87.1% and 89.0%, respectively). The area under the receiver operating characteristic curve (AUC) of the radiomics model was significantly better than that of the clinical model for both the primary (0.941 vs. 0.712, p = 0.000) and validation (0.929 vs. 0.671, p = 0.000) cohorts. Good calibration was observed for all the models (p > 0.05). CONCLUSIONS: The radiomics model based on CECT performed well in predicting AP recurrence. As a quantitative method, radiomics exhibits promising performance in terms of alerting recurrent patients to potential precautions. KEY POINTS: • The incidence of recurrence after an initial episode of acute pancreatitis is high, and quantitative methods for predicting recurrence are lacking. • The radiomics model based on contrast-enhanced computed tomography performed well in predicting the recurrence of acute pancreatitis. • As a quantitative method, radiomics exhibits promising performance in terms of alerting recurrent patients to the potential need to take precautions.

Spleen and splenic vascular involvement in acute pancreatitis: an MRI study.

BACKGROUND: To investigate the spleen and splenic vascular involvement in acute pancreatitis (AP) and their correlations with the severity of AP using magnetic resonance imaging (MRI). METHODS: MRI of 239 patients with AP was retrospectively reviewed to assess splenic and splenic vascular complications, and the severity of AP. The severity of AP was graded by the MRI severity index (MRSI) and the New Revised Classification of AP 2012. The intravoxel incoherent motion (IVIM) parameters (D, D*, and f) of spleen were measured. Thirty-five subjects without pancreatic and splenic disorders were enrolled as controls for IVIM parameters. RESULTS: Among the 239 patients with AP, splenomegaly (16.7%), splenic infarction (0.4%), splenic vein thrombosis (4.2%), phlebitis (7.5%) and arteritis (4.2%) were observed. Splenic vascular involvement was positively correlated with the severity of AP based on both the MRSI and the New Revised Classification of AP 2012 (P<0.05). In the control and AP groups, the splenic f values were (0.164±0.074) vs. (0.210±0.095) (P=0.023) respectively. In AP patients with and without splenomegaly, f = (0.240±0.091) vs. (0.203±0.095) (P<0.001). CONCLUSIONS: Splenic vascular involvement and splenomegaly were common in AP. The vascular involvement was associated with the severity of AP. This complication should be considered when severity and prognosis of AP are assessed. Quantitative analysis of the spleen with IVIM might be a useful imaging biomarker for splenic perfusion changes in AP, especially in those with splenomegaly.

Genetic Polymorphisms: A Novel Perspective on Acute Pancreatitis.

Acute pancreatitis (AP) is a complex disease that results in significant morbidity and mortality. For many decades, it has compelled researchers to explore the exact pathogenesis and the understanding of the pathogenesis of AP has progressed dramatically. Currently, premature trypsinogen activation and NF-κB activation for inflammation are two remarkable hypotheses for the mechanism of AP. Meanwhile, understanding of the influence of genetic polymorphisms has resulted in tremendous development in the understanding of the advancement of complex diseases. Now, genetic polymorphisms of AP have been noted gradually and many researchers devote themselves to this emerging area. In this review, we comprehensively describe genetic polymorphisms combined with the latest hypothesis of pathogenesis associated with AP.