To determine the performance of a deep learning-based super-resolution (SR) dynamic contrast-enhanced (DCE) radiomic model in predicting nonspecific molecular profile (NSMP) endometrial cancer (EC).
Approach:
Study Population: 140 surgically confirmed EC patients were included, divided into training and testing cohorts.
Image Reconstruction: Deep learning-based SR reconstruction techniques were applied to convert original-resolution DCE images into SR images.
Model Development: Radiomic features were extracted from both SR and OR images, and models were developed using logistic regression, support vector machine, and multilayer perceptron algorithms.
Performance Evaluation: Model performance was evaluated via area under the curve (AUC) analysis and decision curve analysis (DCA).
Key Findings:
In the testing set, AUC values for the SR-DCE model were 0.841 (95% CI: 0.724–0.959), 0.800 (95% CI: 0.664–0.937), and 0.764 (95% CI: 0.618–0.911), while for the OR-DCE model they were 0.637 (95% CI: 0.464–0.810), 0.603 (95% CI: 0.422–0.785), and 0.656 (95% CI: 0.495–0.818).
Interpretation:
Limitations:
The study was retrospective and conducted at a single institution.
The sample size may limit the generalizability of the findings.
