JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Preoperative prediction of lymph node metastasis in endometrial cancer patients via an intratumoral and peritumoral multiparameter MRI radiomics nomogram

  • 0Department of Radiology, Shaanxi Provincial Tumor Hospital, Xi'an, China.
Frontiers in Oncology +

|

October 4, 2024

|

October 4, 2024

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a new nomogram using MRI radiomics and clinical data to predict lymph node metastasis in endometrial cancer patients, improving preoperative assessment accuracy.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Lymph node metastasis (LNM) is crucial for endometrial cancer (EC) treatment decisions.
  • Current preoperative methods for assessing LNM in EC are often insufficient.

Purpose Of The Study

  • To develop and validate a nomogram for preoperative prediction of LNM in EC patients.
  • To integrate intra- and peritumoral radiomics features with multiparameter MRI data.

Main Methods

  • A cohort of 374 EC patients was divided into training, test, and validation sets.
  • Radiomic features were extracted from T2-weighted imaging (T2WI) and apparent diffusion coefficient (ADC) mapping.
  • A nomogram was constructed using selected radiomics features and clinical parameters (CA125, tumor area ratio).

Main Results

  • The developed nomogram demonstrated high AUCs (0.864-0.878) across all cohorts.
  • The nomogram outperformed the radiomics-only model (Radscore) and clinical model in predicting LNM.
  • Decision curve analysis (DCA) and net reclassification index (NRI) confirmed superior diagnostic performance and clinical utility.

Conclusions

  • A multiparameter MRI radiomics nomogram integrating intra- and peritumoral features shows promise for preoperative LNM prediction in EC.
  • This nomogram offers improved diagnostic accuracy and clinical benefit over existing methods.

Keywords: