Feasibility of MRI-based radiomics features for predicting lymph node metastases and VEGF expression in cervical cancer. Issue 134 (January 2021)

• Record Type: Journal Article
• Authors: Deng, Xijia; Liu, Meiling; Sun, Jianqing; Li, Min; Liu, Daihong; Li, Lan; Fang, Jiayang; Wang, Xiaoxia; Zhang, Jiuquan
• Is Part Of: European journal of radiology. Issue 134(2021)
• Publication Date: 2021-01
• Subjects: LN Lymph node -- VEGF Vascular endothelial growth factor -- LNM Lymph node metastasis -- PET Positron emission tomography -- FIGO International Federation of Gynecology and Obstetrics -- ROI Region of interest -- LASSO Least absolute shrinkage and selection operator -- AUC Area under the receiver operating curve -- DCA Decision curve analysis; Radiomics -- Cervical cancer -- Lymph nodes -- Vascular endothelial growth factor -- Magnetic resonance imaging; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2020.109429
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: Radiomics analysis is feasible in preoperative evaluation of cervical cancer. The radiomics model for LNM showed better predictive efficacy than FIGO stages. Radiomics features of MRI is valuable for the discrimination of VEGF expression. Abstract: Purpose: To investigate the predictive value of MRI-based radiomics features for lymph node metastasis (LNM) and vascular endothelial growth factor (VEGF) expression in patients with cervical cancer. Method: A total of 163 patients with cervical cancer were enrolled in this study. A total of 134 patients were included for LNM differentiation, and 118 were included for VEGF expression discrimination. The patients were randomly assigned to the training group or test group at a ratio of 2:1. Radiomics features were extracted from T1WI enhanced and T2WI MRI scans of each patient, and tumor stage was also documented according to the International Federation of Gynecology and Obstetrics (FIGO) guidelines. The least absolute shrinkage and selection operator algorithm was used for feature selection. The results of 5-fold cross validation were applied to select the best classification models. The performances of the constructed models were further evaluated with the test group. Results: Sixteen radiomics features and the FIGO stage were selected to construct the LNM discrimination model. The LNM prediction model achieved the best diagnostic performance, with areas under the receiver operating curve (AUCs) of 0.95 and 0.88 in the training group and test group, respectively. Nine radiomics characteristics were screened to build the VEGF prediction model, with AUCs of 0.82 and 0.70 in the training group and test group, respectively. Decision curve analysis confirmed their clinical usefulness. Conclusions: The presented radiomics prediction models demonstrated potential to noninvasively differentiate LNM and VEGF expression in cervical cancer.