Back to all papers

Multiparametric MRI Radiomics-Based Interpretable Machine Learning Model for the Prediction of Lymphovascular Space Invasion in Endometrial Cancer.

July 20, 2026pubmed logopapers

Authors

Meng W,Dou H,Yin J,Ma W,Wang X,Liu J,Shi F

Affiliations (5)

  • School of Public Health, Shandong Second Medical University, Weifang, China (W.M., F.S.).
  • School of Medical Imaging, Shandong Second Medical University, Weifang, China (H.D., J.Y., X.W.,J.L.).
  • Affiliated Hospital of Shandong Second Medical University, Weifang, China (X.W., J.L.).
  • Affiliated Hospital of Shandong Second Medical University, Weifang, China (X.W., J.L.); School of Medical Imaging, Shandong Second Medical University, Weifang, China (H.D., J.Y., X.W.,J.L.).
  • School of Public Health, Shandong Second Medical University, Weifang, China (W.M., F.S.). Electronic address: [email protected].

Abstract

To develop and validate a machine learning model combining multiparametric Magnetic Resonance Imaging (MRI) radiomics and clinical indicators for predicting lymphovascular space invasion (LVSI) in endometrial cancer (EC). This retrospective study enrolled EC patients who underwent preoperative MRI at two centers. Of 567 initially screened patients, 408 were included per inclusion/exclusion criteria, divided into training and validation sets by hospital. Clinical risk factors and intratumoral/peritumoral radiomic features were identified. Six machine learning algorithms were used to build models; the one with the highest validation Area Under the Curve (AUC) was optimal. Five additional models were developed, and performance was evaluated via AUC, calibration curves, and decision curve analysis (DCA). Logistic regression identified CA125 and tumor diameter as independent LVSI risk factors. Six machine learning models were built with CA125, tumor diameter, Rad_Score1 and Rad_Score2; the NeuralNetwork performed best (validation AUC=0.803). The combined clinical-intratumoral-peritumoral radiomics model achieved the highest AUC(training AUC = 0.863, validation AUC = 0.803), with good calibration (Hosmer-Lemeshow test, P > 0.05) and favorable net clinical benefit (threshold 0.1-0.7). SHapley Additive exPlanations (SHAP) analysis enhanced model interpretability. This study systematically compared the predictive performance of six machine learning models for LVSI in EC, identifying the NeuralNetwork model as the most optimal. The combined clinical-intratumoral-peritumoral radiomics model, alongside its SHAP visualization tool, enhanced the accuracy (ACC) of non-invasive preoperative LVSI prediction, demonstrating certain potential for clinical application.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 11k+ peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.