Xijia Deng1, Meiling Liu1, Jianqing Sun2, Min Li1, Daihong Liu1, Lan Li1, Jiayang Fang1, Xiaoxia Wang1, Jiuquan Zhang3. 1. Department of Radiology, Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400030, People's Republic of China; Key Laboratory for Biorheological Science and Technology of Ministry of Education (Chongqing University), Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400044, People's Republic of China. 2. Clinical Science, Philips Healthcare, Shanghai, 200072, People's Republic of China. 3. Department of Radiology, Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400030, People's Republic of China; Key Laboratory for Biorheological Science and Technology of Ministry of Education (Chongqing University), Chongqing University Cancer Hospital & Chongqing Cancer Institute & Chongqing Cancer Hospital, Chongqing 400044, People's Republic of China. Electronic address: zhangjq_radiol@foxmail.com.
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.
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.