Development and validation of a CT-based radiomics nomogram for predicting cervical lymph node metastasis in papillary thyroid carcinoma

Objective: This study aimed to develop and validate a radiomics nomogram based on 40 KeV images and iodine density maps derived from dual-layer spectral detector CT (DLSDCT) for predicting cervical lymph node (LN) metastasis in patients with papillary thyroid carcinoma (PTC). Methods: A total of 214 LNs from 143 patients with histopathologically confirmed PTC in our hospital were included in the study. The LNs were randomly divided into a training group (n = 150) and a validation group (n = 64) in a 7:3 ratio. Radiomics features were extracted from non-enhanced, arterial phase, and venous phase 40 KeV images, as well as arterial phase and venous phase iodine density maps. Recursive feature elimination (RFE) and logistic regression (LR) were used for feature selection and radiomics score construction. A multivariate logistic regression model was established, incorporating the radiomics score and CT image features. The receiver operating characteristic (ROC) curve was used to evaluate the model's performance. The Hosmer-Lemeshow test and calibration curve were used to assess the model's goodness of fit, while decision curve analysis (DCA) evaluated its clinical applicability. Results: The radiomics features consisted of 11 LN-related features that exhibited a good predictive effect. The radiomics nomogram, which included radiomics features, lymphatic hilum status, and significant enhancement in the arterial phase, demonstrated excellent calibration and discrimination in both the training set (AUC = 0.955; 95% confidence interval [CI]: 0.924-0.985) and the validation set (AUC = 0.928; 95% CI: 0.861-0.994). The decision curve analysis confirmed the clinical validity of our nomogram. The DeLong test comparing the radiomics-clinical nomogram with the clinical model yielded a p-value of <0.001. Conclusions: The radiomics nomogram, incorporating radiomics features and CT image features, serves as a non-invasive preoperative prediction tool with high accuracy in predicting cervical lymph node metastasis in patients with PTC.