Predicting preoperative lymph node metastasis in patients with high-grade serous ovarian cancer by using intratumoral and peritumoral radiomics: A retrospective cohort study
Listed in
This article is not in any list yet, why not save it to one of your lists.Abstract
Background Ovarian cancer (OC) carries the worst prognosis among gynecologic cancers, with high-grade serous ovarian cancer (HGSOC) as its most common subtype. Cytoreductive surgery (tumor resection), such as lymphadenectomy, is the cornerstone of OC treatment. However, controversy remains regarding whether lymphadenectomy should be performed during surgery; more than 30% of patients with OC undergo unnecessary lymphadenectomy, increasing surgical risks and prolonging postoperative recovery. By analyzing multidimensional imaging features, such as tumor morphology, texture, and density, radiomics can accurately quantify the biological characteristics of tumors. However, its application in OC needs to be explored further. This study aimed to explore radiomics' role in predicting lymph node metastasis risk in HGSOC. Methods This retrospective cohort analysis involved 273 participants from Qingdao University Affiliated Hospital and Rizhao People’s Hospital, and they were categorized into the training, testing, and external validation groups. Imaging characteristics were derived from the tumor region of interest and its surrounding areas (1–5 mm), and radiomics scores were calculated for each region. This approach was employed for assessing the diagnostic performance of different regions and identify the optimal one. We constructed a risk prediction model that integrated imaging features of the optimal region with independent clinical risk factors. Results The radiomic features of the tumor and its surrounding 3-mm extension region yielded area under the curve (AUC) values of 0.957 and 0.793 in the training and testing sets, respectively. After integrating the radiomic features of the tumor and its surrounding 3-mm extension region with clinical features, the AUC values in the training set, testing set, and external validation set were 0.971, 0.811, and 0.869, respectively, demonstrating strong predictive ability. Conclusions This study developed a model to assess lymph node metastasis likelihood in HGSOC patients. In the test and external validation cohorts, the model demonstrated excellent predictive performance. We believe the model can assist clinicians in identifying patients who are suitable for lymph node resection, thereby optimizing treatment decisions.