RESUMEN
Objective:To investigate the correlation of central compartment lymph node metastasis(CLNM) in stage T 1a solitary papillary thyroid carcinoma (PTC) with the clinicopathological characteristics, sonographic features and the number of lymph node dissection, and to analyze the risk factors of CLNM. Methods:The data of 218 patients with stage T 1a solitary PTC who underwent thyroid cancer surgery from January 2017 to May 2021 in Tangshan Union Medical College Hospital were retrospectively analyzed. All patients were divided into CLNM positive group and CLNM negative group according to CLNM. The age, gender, preoperative sonographic features, pathological type, the number of lymph node dissection and the number of metastasis were recorded. Logistic regression was used to analyze the risk factors of CLNM. Results:Among 218 patients, there were 71 cases (32.6%) in CLNM positive group and 147 cases (67.4%) in CLNM negative group. There were statistically significant differences in age, tumor diameter, capsular invasion in thyroid or not, tumor blood supply or not, and the number of lymph node dissection between two groups (all P < 0.05). There were no statistically significant differences in gender, clear tumor boundary or not, tumor shape, tumor aspect ratio, calcification, nodular goiter and Hashimoto's thyroiditis or not (all P > 0.05). Multivariate binary logistic regression analysis showed that age < 55 years ( OR = 2.995, 95% CI 1.228-7.307), capsular invasion in thyroid ( OR = 5.297, 95% CI 2.494-11.248) and the number of lymph node dissection ≥6 ( OR = 4.085, 95% CI 2.059-8.104) were independent risk factors of CLNM (all P < 0.05). Conclusions:Patients with stage T 1a solitary PTC, age < 55 years and capsular invasion in thyroid are prone to CLNM; sufficient number of lymph node dissection can get more accurate CLNM rate.
RESUMEN
Objective To establish an artificial intelligence model based on B-mode thyroid ultrasound images to predict central compartment lymph node metastasis(CLNM)in patients with papillary thyroid carcinoma(PTC). Methods We retrieved the clinical manifestations and ultrasound images of the tumors in 309 patients with surgical histologically confirmed PTC and treated in the First Medical Center of PLA General Hospital from January to December in 2018.The datasets were split into the training set and the test set.We established a deep learning-based computer-aided model for the diagnosis of CLNM in patients with PTC and then evaluated the diagnosis performance of this model with the test set. Result The accuracy,sensitivity,specificity,and area under receiver operating characteristic curve of our model for predicting CLNM were 80%,76%,83%,and 0.794,respectively. Conclusion Deep learning-based radiomics can be applied in predicting CLNM in patients with PTC and provide a basis for therapeutic regimen selection in clinical practice.