Evaluation of Radiomics Models Based on Computed Tomography for Distinguishing Between Benign and Malignant Thyroid Nodules

The aim of the study was to investigate the diagnostic value of radiomics models based on computed tomography (CT) in distinguishing between benign and malignant thyroid nodules. MATERIALS AND METHODS: We conducted a retrospective analysis of the clinical and imaging data of 172 patients with pathology-confirmed thyroid nodules (83 benign nodules and 89 malignant nodules). All patients underwent a plain CT scan + arterial and venous contrast enhancement before the operation. Using the stratified random sampling method, patients were divided into a training group (121 cases) and a test group (51 cases) at a ratio of 7:3. A.K. software was used to extract radiomics features from the preoperative CT images, and minimum redundancy maximum relevance and least absolute shrinkage and selection operator regression analyses were then used for feature screening and model construction. Receiver operating characteristic (ROC) curves were constructed for the training and test groups to verify model performance and evaluate the efficacy of the radiomics features in identifying benign and malignant thyroid nodules. We then used the most efficient models to construct a nomogram. For the training group, 1-way analysis of variance and multivariate logistic regression analysis were used to screen statistically significant clinical features, and the radiomics scores were combined to construct a radiomics nomogram. We used ROC curve analysis to evaluate the predictive performance of the model. RESULTS: Screening yielded 21 radiomics features that were used to construct a model for differentiating between benign and malignant thyroid nodules. For the training group, the area under the ROC curve of the prediction models for the noncontrast, arterial phase, and venous phase scans were 0.86 (95% confidence interval [CI], 0.79–0.92), 0.89 (95% CI, 0.83–0.95), and 0.88 (95% CI, 0.82–0.94), respectively, and the corresponding diagnostic accuracy was 0.78, 0.84, and 0.83. For the test group, the corresponding 3-phase under the ROC curves for the test group were 0.76 (95% CI, 0.63–0.90), 0.78 (95% CI, 0.65–0.91), and 0.76 (95% CI, 0.62–0.90), and the corresponding accuracy was 0.63, 0.77, and 0.75. Thus, the arterial phase model exhibited the best diagnostic performance. The multivariate logistic regression results showed that morphology regularity and the cystic degeneration ratio were independent clinical risk factors for predicting benign and malignant thyroid nodules. The arterial phase radiomics score and clinically independent factors were then used to construct a nomogram. The nomogram had good discriminability for the training group (0.93; 95% CI, 0.88–0.98) and the test group (0.84; 95% CI, 0.73–0.95), achieving significantly higher accuracies than the radiomics score and clinical characteristics alone. CONCLUSIONS: The radiomics nomogram constructed by combining radiomics characteristics and clinical risk factors was efficacious for distinguishing benign and malignant thyroid nodules.