AUTHOR=Li Mei hua , Liu Long , Feng Lian , Zheng Li jun , Xu Qin mei , Zhang Yin juan , Zhang Fu rong , Feng Lin na TITLE=Prediction of cervical lymph node metastasis in solitary papillary thyroid carcinoma based on ultrasound radiomics analysis JOURNAL=Frontiers in Oncology VOLUME=14 YEAR=2024 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2024.1291767 DOI=10.3389/fonc.2024.1291767 ISSN=2234-943X ABSTRACT=Objective

To assess the utility of predictive models using ultrasound radiomic features to predict cervical lymph node metastasis (CLNM) in solitary papillary thyroid carcinoma (PTC) patients.

Methods

A total of 570 PTC patients were included (456 patients in the training set and 114 in the testing set). Pyradiomics was employed to extract radiomic features from preoperative ultrasound images. After dimensionality reduction and meticulous selection, we developed radiomics models using various machine learning algorithms. Univariate and multivariate logistic regressions were conducted to identify independent risk factors for CLNM. We established clinical models using these risk factors. Finally, we integrated radiomic and clinical models to create a combined nomogram. We plotted ROC curves to assess diagnostic performance and used calibration curves to evaluate alignment between predicted and observed probabilities.

Results

A total of 1561 radiomics features were extracted from preoperative ultrasound images. After dimensionality reduction and feature selection, 16 radiomics features were identified. Among radiomics models, the logistic regression (LR) model exhibited higher predictive efficiency. Univariate and multivariate logistic regression results revealed that patient age, tumor size, gender, suspicious cervical lymph node metastasis, and capsule contact were independent predictors of CLNM (all P < 0.05). By constructing a clinical model, the LR model demonstrated favorable diagnostic performance. The combined model showed superior diagnostic efficacy, with an AUC of 0.758 (95% CI: 0.712-0.803) in the training set and 0.759 (95% CI: 0.669-0.849) in the testing set. In the training dataset, the AUC value of the nomogram was higher than that of the clinical and radiomics models (P = 0.027 and 0.002, respectively). In the testing dataset, the AUC value of the nomogram model was also greater than that of the radiomics models (P = 0.012). However, there was no significant statistical difference between the nomogram and the clinical model (P = 0.928). The calibration curve indicated a good fit of the combined model.

Conclusion

Ultrasound radiomics technology offers a quantitative and objective method for predicting CLNM in PTC patients. Nonetheless, the clinical indicators persists as irreplaceable.