• Jinyu Liang, Xiaowen Huang, Hangtong Hu, Yihao Liu, Qian Zhou, Qinghua Cao, Wei Wang, Baoxian Liu, Yanling Zheng, Xin Li, Xiaoyan Xie, Mingde Lu, Sui Peng, Longzhong Liu, and Haipeng Xiao.
• 1 Department of Medical Ultrasonics, Institute of Diagnostic and Interventional Ultrasound, The First Affiliated Hospital of Sun Yat-sen University , Guangzhou, People's Republic of China .
• Thyroid. 2018 Aug 1; 28 (8): 1024-1033.

BackgroundVisual interpretation of ultrasound (US) images alone may not be sensitive enough to detect important features of potentially malignant thyroid nodules. The aim of this study was to develop a radiomics score using US imaging to predict the probability for malignancy of thyroid nodules as compared with the Thyroid Imaging, Reporting, and Data System (TI-RADS) scoring criteria proposed by the American College of Radiology (ACR).MethodsOne hundred thirty-seven pathologically proven thyroid nodules from hospital 1 were enrolled as a training cohort, while 95 nodules from hospital 2 served as the validation cohort. A radiomics score using US images was developed from the training cohort. Two junior and two senior radiologists reviewed all images and scored each nodule according to the 2017 updated ACR TI-RADS scoring criteria. Univariate logistic regression analysis was used to develop the prediction models based on the radiomics score and ACR scores. The performance of the models was evaluated and compared with respect to discrimination, calibration, and clinical application in the validation cohort.ResultsUnivariate regression indicated that the radiomics score and ACR scores were predictors for thyroid nodule malignancy (all p < 0.001). Five prediction models were built based on the above scores. The radiomics score showed good discrimination with an AUC of 0.921 in the training cohort and 0.931 in the validation cohort, which was significantly better than the ACR scores of junior radiologists in both cohorts. Although five models showed good calibration (all p > 0.05), the model based on the radiomics score presented the lowest errors (E max = 0.073 or E aver = 0.028) in predicting and calibrating probabilities. Decision curve analysis demonstrated that the model using the radiomics score added more benefit than using the ACR scores of junior radiologists.ConclusionCompared with ACR TI-RADS evaluation by junior radiologists, the radiomics score showed good performance in predicting malignancy of thyroid nodules in our set of histologically verified thyroid nodules from two tertiary hospitals.

26 keywords...

hide…