JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Multimodal MRI-based radiomics models for the preoperative prediction of lymphovascular space invasion of endometrial carcinoma

  • 0Department of Radiology, The First Affiliated Hospital of Soochow University, Suzhou, China.
Bmc Medical Imaging +

|

September 20, 2024

|

September 20, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

A combined MRI radiomics and conventional model effectively predicts lymphovascular space invasion (LVSI) in endometrial carcinoma (EC) patients, aiding preoperative decision-making.

Area Of Science

  • Radiology
  • Oncology
  • Medical Imaging

Background

  • Lymphovascular space invasion (LVSI) is a critical prognostic factor in endometrial carcinoma (EC).
  • Accurate preoperative detection of LVSI is essential for optimal treatment planning and patient management.
  • Current imaging methods have limitations in reliably identifying LVSI.

Purpose Of The Study

  • To assess the predictive performance of MRI-based radiomics for detecting LVSI in EC.
  • To compare radiomics, conventional MRI features, and a combined model for LVSI prediction.

Main Methods

  • Retrospective analysis of 160 EC patients.
  • Development of a radiomics model using T2-weighted and DCE-MRI.
  • Establishment of a conventional MRI model incorporating FIGO stage and invasion parameters.
  • Creation of a combined model integrating radiomics and conventional features.
  • Validation using ROC curve analysis and Delong tests.

Main Results

  • The combined model showed superior performance in predicting LVSI in both training (AUC: 0.934) and testing (AUC: 0.905) cohorts.
  • The radiomics model outperformed the clinical model in the training cohort (AUC: 0.899 vs. 0.8862).
  • In the test cohort, the radiomics model (AUC: 0.812) did not outperform the clinical model (AUC: 0.8758), highlighting the benefit of combination.

Conclusions

  • The combined MRI radiomics and conventional model is valuable for preoperative LVSI prediction in EC.
  • This integrated approach can potentially improve clinical decision-making for EC patients.
  • Further validation in larger cohorts may solidify its role in routine practice.

Keywords: