JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Predicting preoperative lymph node metastasis in patients with high-grade serous ovarian cancer by using intratumoral and peritumoral radiomics: a retrospective cohort study

  • 0Department of Obstetrics and Gynecology, The Affiliated Hospital of Qingdao University, Qingdao, Shandong, China.
Bmc Medical Imaging +

|

August 13, 2025

|

August 13, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study developed a radiomics model to predict lymph node metastasis in high-grade serous ovarian cancer (HGSOC). The model accurately identifies patients needing lymph node resection, optimizing surgical decisions and improving patient outcomes.

Area Of Science

  • Oncology
  • Radiology
  • Medical Imaging

Background

  • Ovarian cancer (OC) has a poor prognosis, with high-grade serous ovarian cancer (HGSOC) being the most common subtype.
  • Cytoreductive surgery is standard OC treatment, but lymphadenectomy decisions remain controversial, leading to unnecessary procedures in over 30% of patients.
  • Radiomics offers a non-invasive method to analyze tumor characteristics from medical images, but its role in HGSOC requires further investigation.

Purpose Of The Study

  • To explore the utility of radiomics in predicting lymph node metastasis risk in patients with HGSOC.
  • To develop and validate a predictive model integrating radiomic and clinical features for HGSOC lymph node metastasis.

Main Methods

  • A retrospective cohort of 273 HGSOC patients was analyzed, divided into training, testing, and external validation groups.
  • Radiomic features were extracted from the tumor region of interest and surrounding areas (1-5 mm).
  • A risk prediction model was constructed using optimal radiomic features and independent clinical risk factors.

Main Results

  • Radiomic features from the tumor and a 3-mm surrounding region showed strong predictive performance (AUC 0.957 in training, 0.793 in testing).
  • The integrated model achieved high AUC values: 0.971 (training), 0.811 (testing), and 0.869 (external validation).
  • The model demonstrated excellent predictive ability across different cohorts.

Conclusions

  • A novel radiomics-based model effectively assesses lymph node metastasis risk in HGSOC patients.
  • The model shows excellent predictive performance in test and external validation cohorts.
  • This tool can aid clinicians in selecting appropriate candidates for lymph node resection, thereby refining treatment strategies.

Keywords: