Objective:To establish three machine learning prediction models based on CT imaging characteristics of papillary thyroid carcinoma (PTC) , and use SHAP (shapley additive explanations) analysis to investigate the contribution of each CT image features in the best model.Methods:CT imaging features in 426 cases of 440 PTCs confirmed pathologically from Jan. 2016 to Jan. 2021 at the affiliated Hangzhou First People’s Hospital of Westlake University Medical School were retrospectively analyzed. compared with 467 cases of 528 nodular goiter (NG) , evaluating the distribution of four CT characteristics: cookie bite sign, enhanced range of narrowing/blur (ERNB) , microcalcifications, and irregular shape. We split the data into 8∶2 ratio for training and testing sets, then constructed three machine learning models using XGBoost, RF, and SVM. Based on AUC, accuracy, F1 score, and other metrics, we selected the best model. Lastly, we used SHAP values to assess each CT feature’s contribution and positive/negative effects on the model.Results:Among 440 PTC and 528 NG nodules, CT features like cookie bite sign, ERNB, microcalcifications, and irregular shape occurred in 326 and 30 ( χ 2=483.05, P<0.001) , 363 and 106 ( χ 2=374.45, P<0.001) , 158 and 53 ( χ 2=94.24, P<0.001) , and 354 and 52 ( χ 2=491.34, P<0.001) nodules, respectively. The machine learning models built using XGBoost, RF, and SVM had AUC, accuracy, and F1 scores ranging from 0.884~0.925, 0.867~0.873, and 0.844~0.854 respectively on the training set. On the test set, the scores ranged from 0.869~0.923, 0.845~0.871, and 0.803~0.845. Among them, the XGBoost model demonstrated the highest diagnostic performance on the test set. Among the four CT features, irregular shape had the highest absolute SHAP value, positively contributing to PTC diagnosis. Conclusion:XGBoost model showed the highest PTC diagnostic performance. Irregular shape had the greatest positive impact on PTC diagnosis.

Objective:Papillary thyroid carcinoma with a maximum tumor diameter of ≤1 cm was defined as papillary thyroid carcinoma (PTC). To explore the clinical risk factors of central lymph node metastasis (CLNM) in PTC at different locations.Methods:The clinical and pathological data of 1383 cases with solitary PTC in Hangzhou First People’s Hospital were retrospectively analyzed, and they were divided into isthmus group (175 cases), near-isthmus group (95 cases) and lateral lobe group (1113 cases) according to their tumor location. Univariate and multivariate analyses were used to analyze the relationship between gender, age, tumor maximum diameter, Hashimoto’s thyroiditis (HT) and CLNM, and the threshold for the occurrence of CLNM in each group of age and tumor maximum diameter was determined by the area under the receiver operating characteristic (ROC) .Results:The proportion of CLNM in the isthmus group, near-isthmus group and the lateral lobe group were 39.4% (69/175), 35.8% (34/95) and 29.6% (329/1113), respectively ( χ2=7.84, P=0.020). The intra-group comparison showed that there were statistical differences between the isthmus group and the lateral lobe group ( χ2=6.90, P=0.011), and there were no statistical differences between the isthmus group and near-isthmus group ( χ2=0.35, P=0.601), and near-isthmus group and the lateral leaf group ( χ2=1.62, P=0.313). Univariate and multivariate analysis showed that male ( OR: 3.697) and age < 38.5 years ( OR: 4.727) were independent risk factors for CLNM in PTC in the Isthmus Group, while male ( OR: 2.193), without HT ( OR: 1.702), tumor maximum diameter > 6.5 mm ( OR: 2.535) and age < 45.5 years ( OR: 3.030) were independent risk factors for CLNM in PTC in the lateral lobe group. Conclusions:Male sex and age are independent risk factors for CLNM in isthmus and lateral lobe PTC, and uncomplicated HT and tumor maximum diameter are also independent risk factors for CLNM in lateral lobe PTC. The incidence of CLNM in PTC in the isthmus, near-isthmus and lateral lobes decreased sequentially, and PTC in the near isthmus can not be simply regarded as the isthmus or lateral lobe PTC, and the lymph nodes in the central area should be fully evaluated before surgery to provide individualized treatment.

Objective:To evaluate the safety and effectiveness of physician modified stent grafts technique and in situ fenestration technique for reconstructing the left subclavian artery in endovascular repair of thoracic aortic lesions with insufficient proximal landing area.Methods:A retrospective analysis was conducted on the clinical data of 75 patients with aortic arch lesions treated with physician modified stent grafts and in situ fenestration techniques at the Interventional Diagnosis and Treatment Department of Beijing Anzhen Hospital affiliated with Capital Medical University from November 2021 to March 2024. Among them, 52 patients received within physician modified stent grafts (PMSGs group) and 23 patients received in situ fenestration (ISF group). Based on two fenestration techniques, to analyze the technical success rate of endovascular repair in reconstructing the left subclavian artery in the perioperative and early following up adverse events both groups.Results:The success rate of PMSGs group technique was 92.31% (48/52), while the success rate of ISF technique was 91.30%(21/23). In the PMSGs group, there was 1 case of TypeⅠa endoleak and 3 cases of TypeⅠc endoleak immediately during endovascular repair; There was 1 case of TypeⅠa endoleak and 1 case of vascular injury in the ISF group immediately during endovascular repair. One case of perioperative cerebral infarction and one case of transient blindness occurred in the PMSGs group; One case of transient blindness and 1 case of brachial artery thrombosis occurred in the perioperative period in the ISF group. During the follow-up period, there was 1 case of distal dissection aneurysm formation in the PMSGs group, and 3 cases of minor typeⅠc endoleak were found after 3 months; One case of subclavian artery stent occlusion and 2 cases of minor typeⅠc endoleak occurred in the ISF group 6 months later. There were no cases of aortic-related deaths during the follow-up period in both groups. There was no statistically significant difference in the technical success rate, incidence of adverse events during the perioperative period and follow-up period, and re-intervention rate between the two groups. The average fluoroscopy time consumed in the ISF group was significantly higher than that in the PMSGs group (34.57 min vs. 21.42 min, P<0.001), but the average hospitalization time in the PMSGs group was significantly higher than that in the ISF group (9.33 days vs. 4.71 days, P<0.001). Conclusion:PMSGs and ISF techniques for reconstructing the left subclavian artery in the treatment of thoracic aortic arch lesions showed good safety and effectiveness. The appropriate fenestration technique selected based on aorta arch anatomical and lesion conditions could achieve satisfactory efficacy in short-term, but long-term effects need to be further observed.

Objective:To establish three machine learning prediction models based on CT imaging characteristics of papillary thyroid carcinoma (PTC) , and use SHAP (shapley additive explanations) analysis to investigate the contribution of each CT image features in the best model.Methods:CT imaging features in 426 cases of 440 PTCs confirmed pathologically from Jan. 2016 to Jan. 2021 at the affiliated Hangzhou First People’s Hospital of Westlake University Medical School were retrospectively analyzed. compared with 467 cases of 528 nodular goiter (NG) , evaluating the distribution of four CT characteristics: cookie bite sign, enhanced range of narrowing/blur (ERNB) , microcalcifications, and irregular shape. We split the data into 8∶2 ratio for training and testing sets, then constructed three machine learning models using XGBoost, RF, and SVM. Based on AUC, accuracy, F1 score, and other metrics, we selected the best model. Lastly, we used SHAP values to assess each CT feature’s contribution and positive/negative effects on the model.Results:Among 440 PTC and 528 NG nodules, CT features like cookie bite sign, ERNB, microcalcifications, and irregular shape occurred in 326 and 30 ( χ 2=483.05, P<0.001) , 363 and 106 ( χ 2=374.45, P<0.001) , 158 and 53 ( χ 2=94.24, P<0.001) , and 354 and 52 ( χ 2=491.34, P<0.001) nodules, respectively. The machine learning models built using XGBoost, RF, and SVM had AUC, accuracy, and F1 scores ranging from 0.884~0.925, 0.867~0.873, and 0.844~0.854 respectively on the training set. On the test set, the scores ranged from 0.869~0.923, 0.845~0.871, and 0.803~0.845. Among them, the XGBoost model demonstrated the highest diagnostic performance on the test set. Among the four CT features, irregular shape had the highest absolute SHAP value, positively contributing to PTC diagnosis. Conclusion:XGBoost model showed the highest PTC diagnostic performance. Irregular shape had the greatest positive impact on PTC diagnosis.

Objective:Papillary thyroid carcinoma with a maximum tumor diameter of ≤1 cm was defined as papillary thyroid carcinoma (PTC). To explore the clinical risk factors of central lymph node metastasis (CLNM) in PTC at different locations.Methods:The clinical and pathological data of 1383 cases with solitary PTC in Hangzhou First People’s Hospital were retrospectively analyzed, and they were divided into isthmus group (175 cases), near-isthmus group (95 cases) and lateral lobe group (1113 cases) according to their tumor location. Univariate and multivariate analyses were used to analyze the relationship between gender, age, tumor maximum diameter, Hashimoto’s thyroiditis (HT) and CLNM, and the threshold for the occurrence of CLNM in each group of age and tumor maximum diameter was determined by the area under the receiver operating characteristic (ROC) .Results:The proportion of CLNM in the isthmus group, near-isthmus group and the lateral lobe group were 39.4% (69/175), 35.8% (34/95) and 29.6% (329/1113), respectively ( χ2=7.84, P=0.020). The intra-group comparison showed that there were statistical differences between the isthmus group and the lateral lobe group ( χ2=6.90, P=0.011), and there were no statistical differences between the isthmus group and near-isthmus group ( χ2=0.35, P=0.601), and near-isthmus group and the lateral leaf group ( χ2=1.62, P=0.313). Univariate and multivariate analysis showed that male ( OR: 3.697) and age < 38.5 years ( OR: 4.727) were independent risk factors for CLNM in PTC in the Isthmus Group, while male ( OR: 2.193), without HT ( OR: 1.702), tumor maximum diameter > 6.5 mm ( OR: 2.535) and age < 45.5 years ( OR: 3.030) were independent risk factors for CLNM in PTC in the lateral lobe group. Conclusions:Male sex and age are independent risk factors for CLNM in isthmus and lateral lobe PTC, and uncomplicated HT and tumor maximum diameter are also independent risk factors for CLNM in lateral lobe PTC. The incidence of CLNM in PTC in the isthmus, near-isthmus and lateral lobes decreased sequentially, and PTC in the near isthmus can not be simply regarded as the isthmus or lateral lobe PTC, and the lymph nodes in the central area should be fully evaluated before surgery to provide individualized treatment.

Objective:To evaluate the safety and effectiveness of physician modified stent grafts technique and in situ fenestration technique for reconstructing the left subclavian artery in endovascular repair of thoracic aortic lesions with insufficient proximal landing area.Methods:A retrospective analysis was conducted on the clinical data of 75 patients with aortic arch lesions treated with physician modified stent grafts and in situ fenestration techniques at the Interventional Diagnosis and Treatment Department of Beijing Anzhen Hospital affiliated with Capital Medical University from November 2021 to March 2024. Among them, 52 patients received within physician modified stent grafts (PMSGs group) and 23 patients received in situ fenestration (ISF group). Based on two fenestration techniques, to analyze the technical success rate of endovascular repair in reconstructing the left subclavian artery in the perioperative and early following up adverse events both groups.Results:The success rate of PMSGs group technique was 92.31% (48/52), while the success rate of ISF technique was 91.30%(21/23). In the PMSGs group, there was 1 case of TypeⅠa endoleak and 3 cases of TypeⅠc endoleak immediately during endovascular repair; There was 1 case of TypeⅠa endoleak and 1 case of vascular injury in the ISF group immediately during endovascular repair. One case of perioperative cerebral infarction and one case of transient blindness occurred in the PMSGs group; One case of transient blindness and 1 case of brachial artery thrombosis occurred in the perioperative period in the ISF group. During the follow-up period, there was 1 case of distal dissection aneurysm formation in the PMSGs group, and 3 cases of minor typeⅠc endoleak were found after 3 months; One case of subclavian artery stent occlusion and 2 cases of minor typeⅠc endoleak occurred in the ISF group 6 months later. There were no cases of aortic-related deaths during the follow-up period in both groups. There was no statistically significant difference in the technical success rate, incidence of adverse events during the perioperative period and follow-up period, and re-intervention rate between the two groups. The average fluoroscopy time consumed in the ISF group was significantly higher than that in the PMSGs group (34.57 min vs. 21.42 min, P<0.001), but the average hospitalization time in the PMSGs group was significantly higher than that in the ISF group (9.33 days vs. 4.71 days, P<0.001). Conclusion:PMSGs and ISF techniques for reconstructing the left subclavian artery in the treatment of thoracic aortic arch lesions showed good safety and effectiveness. The appropriate fenestration technique selected based on aorta arch anatomical and lesion conditions could achieve satisfactory efficacy in short-term, but long-term effects need to be further observed.

Objective:To determine the clinical factors affecting Central lymph node metastases (CLNM) of single Papillary thyroid carcinoma (PTC). To predict the value of age for CLNM under different genders and the status of Hashimoto’s thyroiditis (HT) .Methods:The clinical data of 4 115 patients with PTMC (≤10.0 mm) and 664 patients with PTC (> 10.0 mm) in Hangzhou First People’s Hospital affiliated to Westlake University Medical School from Jan. 2010 to Aug. 2023 were retrospectively analyzed, and the independent risk factors of PTMC and PTC CLNM were identified by univariate and multivariate logistic regression analysis. According to different gender and HT status, the patients were divided into male group, female group, HT group and non-HT group. The optimal age threshold and diagnostic efficacy of CLNM in each subgroup were determined by Receiver operating characteristic area under the curve (AUC) .Results:The proportion of CLNM in 3451 PTMCs and 664 PTCs was 27.2% (937/3451) and 58.9% (391/664) ( χ2=256.565, P<0.050), respectively. Univariate and multivariate regression analysis showed that larger tumor ( OR 1.230), male ( OR 2.085), older age ( OR 0.960) and HT ( OR 0.697) were independent predictors of the occurrence of CLNM in PTMC. Only male ( OR 1.460) and older ( OR 0.963) PTC were independently associated with CLNM. Subgroup analysis showed that the age-predicted AUC of CLNM in male, HT and non-HT patients in PTC were higher than that of PTMC, which were 0.642-0.689 and 0.635-0.659, respectively. The age thresholds of female, HT and non-HT subgroups in PTC were lower than those in PTMC, which were 38.5 to 39.5 years old and 41.5 to 42.5 years old, respectively. Conclusions:Larger tumor, male, older patients and HT can independently predict the risk of CLNM in PTMC, while only male and older people can independently predict the risk of CLNM in PTC. There are certain differences in the age of CLNM occurrence between PTMC and PTC patients with different genders and HT combination status. It is of great significance to correctly understand these differences for providing personalized clinical treatment.

Objective:To explore the diagnostic efficacy of enhanced CT value in central lymph node metastasis (CLNM) of papillary thyroid carcinoma (PTC) with Hashimoto’s thyroiditis (HT) .Methods:The 209 central lymph nodes of 209 patients with PTC confirmed by surgery and pathology were retrospectively analyzed, and they were divided into HT group and non-HT group, including 77 lymph nodes (52 negative and 25 positive) in the HT-PTC group and 132 lymph nodes (74 negative and 58 positive) in the non-HT group. The CT values of lymph nodes were measured on enhanced CT images, and the optimal thresholds and corresponding sensitivity and specificity of enhanced CT values in the two groups were analyzed by the receiver operating characteristic curve.Results:The enhanced CT values of metastatic lymph nodes in the two groups were (103.2±21.1) Hu and (101.9±25.4) Hu, respectively ( t=0.23, P>0.05), and the enhanced CT values of benign lymph nodes were (72.0±15.8) Hu and (68.5±10.9) Hu, respectively ( t=-1.38, P>0.05). The area under the curve of enhanced CT values in the HT group and non-HT group were 0.882 and 0.918, respectively, and the optimal thresholds were 78.8 Hu and 74.7 Hu, respectively, with corresponding sensitivity of 92.0% and 91.4%, and specificity of 67.3% and 77.0%, respectively, for the diagnosis of CLNM in the two groups. Conclusion:The enhanced CT value has high and similar diagnostic efficiency for CLNM in HT group and non-HT group, providing a theoretical basis for the early clinical development of individualized treatment plans.

Objective To construct and validate of a nomogram predictive model for high-volume lymph node metastasis(HVM)in multifocal papillary thyroid carcinoma(MPTC).Methods Between January 2010 to January 2024,a total of 1146 and 234 patients with multifocal papillary thyroid carcinoma(MPTC)were diagnosed at Hangzhou First People's Hospital(Center A)and Hangzhou Cancer Hospital(Center B),respectively.Patients from Center A were randomly allocated to training set(n=803)and testing set(n=343)in a 7:3 ratio,while those from Center B(n=234)comprised an external validation set.Independent risk factors for HVM in MPTC patients were identified through univariate and multivariate Logistic regression analysis in training set,leading to the development of a nomogram predictive model.The generalizability of this model was subsequently assessed using both testing set and external validation set.The area under the curve(AUC)of receiver operating characteristic curve,sensitivity,and specificity evaluate the discriminative ability of the model.Results The incidence of HVM was 13.3％at center A and 12.8％at center B.Logistic regression identified male gender(OR=2.91,95％CI:1.835-4.599),maximum lesion diameter(OR=1.05,95％CI:1.021-1.070),and age(OR=0.95,95％CI:0.936-0.972)as independent risk factors for HVM.Anomogram based on these factors showed an AUC of 0.767 with 72.6％sensitivity and 70.2％specificity in training set,and 0.838 with 94.9％sensitivity and 68.4％specificity in testing set,and 0.769 with 63.3％sensitivity and 84.3％specificity in external validation set.The calibration curve demonstrated good agreement with the ideal curve.Conclusion The prediction model constructed based on clinical risk factors can effectively predict the probability of HVM in MPTC patients.

Objective:To investigate the predictive value of dual-phase enhanced CT for central lymph node metastasis (CLNM) in papillary thyroid microcarcinoma (PTMC) .Methods:The CT data of 220 central lymph nodes in 182 cases of PTMC confirmed by surgery and pathology were retrospectively analyzed. The lymph nodes were divided into 0.3 cm-0.4 cm group, 0.4 cm-0.5 cm and ≥ 0.5 cm groups according to the size of them. The CT values of arterial phase and venous phase of lymph nodes were measured, respectively. The distribution of dual-phase CT values of lymph nodes in the three groups was analyzed by t test. The optimal threshold values of dual-phase enhanced CT values of lymph nodes in each group were obtained by receiver operating characteristic (ROC) . Results:The area under ROC curve of arterial phase CT in predicting CLNM was 0.717, 0.707 and 0.761, the optimal threshold was 71.4Hu, 63.3Hu and 72.9Hu, and the sensitivity and specificity were 50.0% and 92.3%, 63.6% and 81.0%, 52.4% and 82.9%, respectively. The area under the ROC curve of venous phase CT value in predicting CLNM was 0.744, 0.729, and 0.662, the optimal thresholds were 71.1 HU, 80.3 HU, and 61.3 HU, and the sensitivity and specificity were 52.8% and 87.2%, 54.2% and 86.7%, 82.6% and 46.7%, respectively. The sensitivity and specificity of dual-phase combined CT values in predicting CLNM in 3 groups were 44.1% and 94.7%, 50.0% and 88.1%, 52.4% and 85.4%, respectively.Conclusion:Dual-phase enhanced CT can effectively predict central lymph node metastasis of PTMC, and the combination of the two can further improve the specificity of predicting CLNM and provide an important basis for reducing unnecessary surgical trauma.