RESUMEN
Background: In recent years, the study of radiomics in thyroid diseases has developed rapidly. This study aimed to establish a preoperative radiomics prediction model for central compartment lymph node metastases (CLNMs) in papillary thyroid microcarcinoma (PTMC) patients using gradient-boosting decision tree (GBDT) model and evaluate the performance of the model. Methods: A total of 274 patients with PTMC admitted for thyroid surgery at China-Japan Union Hospital of Jilin University from January 2020 to July 2022 were retrospectively analyzed. Patients were randomized into training and validation cohorts according to a ratio of 8:2. Radiomics features were extracted from the ultrasound (US) images of PTMC lesions. The open-source software Pyradiomics was used to extract radiomics features, and WEKA software was used to select CLNM-related radiomics features. Clinical risk factors for CLNM were screened by statistical methods. The GBDT model was constructed by combining radiomics features and clinical risk factors, and compared with the diagnostic efficacy of US-reported cervical lymph node status. Shapley Additive exPlanations (SHAP) was applied to visualize and analyze the GBDT model globally and locally. Results: A total of seven radiomics features were significantly correlated with central lymph node status in the training and validation cohorts. The predictors in the GBDT model included the radiomics features, sex, age, and body mass index (BMI). The area under the curve (AUC) values of the GBDT model in the training and validation cohorts were 0.946 [95% confidence interval (CI): 0.920-0.972] and 0.845 (95% CI: 0.714-0.976), respectively, compared with 0.583 (95% CI: 0.508-0.659) and 0.582 (95% CI: 0.430-0.736) for US-reported lymph node status alone. The Delong test showed a significant difference between AUS in the training and validation cohorts (P<0.001, respectively). SHAP visual analysis showed the effect of each parameter on the GBDT model globally and locally. Decision curve analysis demonstrated the clinical utility of the GBDT model. Conclusions: The prediction of CLNM by the GBDT model, based on US radiomics features and clinical factors, can be better than that by using US alone in patients with PTMC. Furthermore, the GBDT model may serve a guidance of clinical decision for patient's treatment strategy.
RESUMEN
Background: Thyroid surgery is increasingly demanding in terms of cosmetic neck outcomes and protection of anterior neck function, so we have adopted an alternative sternocleidomastoid intermuscular approach (SMIA) for open/conventional thyroidectomy. The protection of recurrent laryngeal nerve (RLN) and external branch of superior laryngeal nerve (EBSLN) is the key and difficult point in thyroid surgery. The aim of this study was to testify the feasibility of RLN and EBSLN functional protection during SMIA thyroidectomy with the intraoperative neuromonitoring. Methods: A total of 39 patients and 39 RLN and EBSLNs who underwent monitored SMIA thyroidectomy were included. Thyroid gland is revealed and excised anterior to the cervical sheath between the sternal and clavicular heads of the sternocleidomastoid muscle. Standardized intraoperative neuromonitoring (IONM) procedures and postoperative laryngeal examination were performed to audit the SMIA. Following the four-step method, V1, R1, R2, and V2 were monitored and the signal values were recorded. Statistical analysis was used to evaluate the change of IONM amplitude of RLN, combined with the results of laryngoscopy before and after operation to determine the status of RLN. EBSLN injuries were identified from changes in cricothyroid muscle (CTM) twitch and EMG. SMIA video vignette is detailed. Results: All RLN and EBSLNs [17 on the left and 22 on the right] were monitored in 39 patients [5 men, 34 women; mean age 34.1±8.7 years; mean body mass index 22.5 (±3.0, 17.0-30.8) kg/m2] undergoing SMIA. For RLN of the affected side, we compared the V2 and V1 (1,236±672 vs. 1,240±428, P=0.973), R2 and R1 (1,676±778 vs. 1,656±765, P=0.849) signals separately, and the results were not statistically different (P>0.05). Comparing the V1 (1,240±428 vs. 1,309±395, P=0.601) signals of the bilateral recurrent laryngeal nerve, there was no statistical difference (P>0.05). CTM twitch and EMG were preserved. Conclusions: The SMIA technique appears feasible. RLN and EBSLN are easier to be exposed during thyroid surgery of SMIA, which is beneficial to the neuroprotection during the operation. At the same time, it can protect the anterior cervical function and improve the cosmetic effect after operation.