Related Experiment Video
Updated: Oct 6, 2025
Dynamic Contrast Enhanced Magnetic Resonance Imaging of an Orthotopic Pancreatic Cancer Mouse Model
Published on: April 18, 2015
Magnetic Resonance Imaging-Based Radiomics Models to Predict Early Extrapancreatic Necrosis in Acute Pancreatitis
Ting Zhou, Chao-Lian Xie1, Yong Chen2
1From the Department of Radiology, Sichuan Cancer Hospital and Institute, Sichuan Cancer Center, School of Medicine, University of Electronic Science and Technology of China, Chengdu.
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.
Insights
Radiomics models using magnetic resonance imaging (MRI) accurately predict early extrapancreatic necrosis (EXPN) in acute pancreatitis. These advanced imaging analysis techniques show high predictive performance for EXPN, outperforming traditional clinical models.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Acute pancreatitis is a serious condition with potential complications.
- Early detection of extrapancreatic necrosis (EXPN) is crucial for timely intervention and improved patient outcomes.
- Current prediction methods for EXPN have limitations.
Purpose of the Study:
- To investigate the efficacy of radiomics models derived from magnetic resonance imaging (MRI) for the early prediction of EXPN in acute pancreatitis.
- To compare the performance of radiomics models with existing clinical and imaging-based scores.
Main Methods:
- Radiomics features were extracted from T2-weighted and late arterial-phase MRI images of 135 patients with acute pancreatitis.
- Support vector machine models were developed using selected optimal features after dimension reduction.
- Model performance was evaluated against clinical models, MR severity index, and extrapancreatic inflammation scores.
Main Results:
- Both pancreatic parenchyma-based and extrapancreatic collection-based radiomics models demonstrated strong predictive accuracy in training and validation cohorts.
- The area under the curve values for radiomics models were consistently high, indicating excellent predictive performance.
- Radiomics models outperformed traditional clinical and imaging-based scores in predicting early EXPN.
Conclusions:
- MRI-based radiomics models offer a powerful tool for the early prediction of EXPN in acute pancreatitis.
- These models, utilizing both pancreatic parenchyma and extrapancreatic collection imaging, show excellent predictive capabilities.
- Radiomics analysis represents a significant advancement in assessing the severity and predicting complications of acute pancreatitis.
