Search

To develop and validate a clinical-radiomics model that incorporates radiomics signatures and pretreatment clinicopathological parameters to identify multimodality therapy candidates among patients with early-stage cervical cancer.Between January 2017 and February 2021, 235 patients with IB1-IIA1 cervical cancer who underwent radical hysterectomy were enrolled and divided into training (n = 194, training:validation = 8:2) and testing (n = 41) sets according to surgical time. The radiomics features of each patient were extracted from preoperative sagittal T2-weighted images. Significance testing, Pearson correlation analysis, and Least Absolute Shrinkage and Selection Operator were used to select radiomic features associated with multimodality therapy administration. A clinical-radiomics model incorporating radiomics signature, age, 2018 Federation International of Gynecology and Obstetrics (FIGO) stage, menopausal status, and preoperative biopsy histological type was developed to identify multimodality therapy candidates. A clinical model and a clinical-conventional radiological model were also constructed. A nomogram and decision curve analysis were developed to facilitate clinical application.The clinical-radiomics model showed good predictive performance, with an area under the curve, sensitivity, and specificity in the testing set of 0.885 (95% confidence interval: 0.781-0.989), 78.9%, and 81.8%, respectively. The AUC, sensitivity, and specificity of the clinical model and clinical-conventional radiological model were 0.751 (0.603-0.900), 63.2%, and 63.6%, 0.801 (0.661-0.942), 73.7%, and 68.2%, respectively. A decision curve analysis demonstrated that when the threshold probability was 20%, the clinical-radiomics model or nomogram may be more advantageous than the treat all or treat-none strategy.The clinical-radiomics model and nomogram can potentially identify multimodality therapy candidates in patients with early-stage cervical cancer.• Pretreatment identification of multimodality therapy candidates among patients with early-stage cervical cancer helped to select the optimal primary treatment and reduce severe complication risk and costs. • The clinical-radiomics model achieved a better prediction performance compared with the clinical model and the clinical-conventional radiological model. • An easy-to-use nomogram exhibited good performance for individual preoperative prediction.

ImportanceEpithelial ovarian carcinoma is heterogeneous and classified according to the World Health Organization Tumour Classification, which is based on histologic features and molecular alterations. Preoperative prediction of the histologic subtypes could aid in clinical management and disease prognostication.ObjectiveTo assess the value of radiomics based on contrast-enhanced computed tomography (CT) in differentiating histologic subtypes of epithelial ovarian carcinoma in multicenter data sets.Design, Setting, and ParticipantsIn this diagnostic study, 665 patients with histologically confirmed epithelial ovarian carcinoma were retrospectively recruited from 4 centers (Hong Kong, Guangdong Province of China, and Seoul, South Korea) between January 1, 2012, and February 28, 2022. The patients were randomly divided into a training cohort (n = 532) and a testing cohort (n = 133) with a ratio of 8:2. This process was repeated 100 times. Tumor segmentation was manually delineated on each section of contrast-enhanced CT images to encompass the entire tumor. The Mann-Whitney U test and voted least absolute shrinkage and selection operator were performed for feature reduction and selection. Selected features were used to build the logistic regression model for differentiating high-grade serous carcinoma and non–high-grade serous carcinoma.ExposuresContrast-enhanced CT-based radiomics.Main Outcomes and MeasuresIntraobserver and interobserver reproducibility of tumor segmentation were measured by Dice similarity coefficients. The diagnostic efficiency of the model was assessed by receiver operating characteristic curve and area under the curve.ResultsIn this study, 665 female patients (mean [SD] age, 53.6 [10.9] years) with epithelial ovarian carcinoma were enrolled and analyzed. The Dice similarity coefficients of intraobserver and interobserver were all greater than 0.80. Twenty radiomic features were selected for modeling. The areas under the curve of the logistic regression model in differentiating high-grade serous carcinoma and non–high-grade serous carcinoma were 0.837 (95% CI, 0.835-0.838) for the training cohort and 0.836 (95% CI, 0.833-0.840) for the testing cohort.Conclusions and RelevanceIn this diagnostic study, radiomic features extracted from contrast-enhanced CT were useful in the classification of histologic subtypes in epithelial ovarian carcinoma. Intraobserver and interobserver reproducibility of tumor segmentation was excellent. The proposed logistic regression model offered excellent discriminative ability among histologic subtypes.