Objective To analyze the influencing factors of tumor-specific mortality in patients with advanced endometrial carcinoma and construct a risk prediction model.Methods A total of 150 patients with advanced endometrial carcinoma admitted to the Fourth Clinical College of Zhejiang Chinese Medical University,Hangzhou First People's Hospital from January 2020 to January 2023 were selected as subjects.Cox regression was employed to analyze factors influencing mortality in advanced endometrial carcinoma.A Logistic regression model was constructed,with receiver operating characteristic(ROC)curve used to evaluate model discrimination,calibration curve for precision assessment,and decision curve for net benefit evaluation.Results Overall 2-year survival rate of 150 patients was 58.67％.The univariate analysis demonstrated that histological grade,lymph node metastasis,tumor maximum diameter,and preoperative carcinoembryonic antigen 125(CA125)levels were all significant risk factors for mortality in advanced endometrial carcinoma(P＜0.05).Multivariate analysis confirmed these parameters as independent prognostic indicators(P＜0.05).A Logistic regression model established using multivariate Cox regression yielded a C index of 0.873(95％CI:0.792-0.951).ROC curve analysis revealed the model's area under the curve for predicting mortality risk factors in advanced endometrial carcinoma was 0.916(95％CI:0.872-0.960).Conclusion The linear chart prediction model constructed based on histological grading,lymph node metastasis,maximum tumor diameter and preoperative CA125 level in this study can effectively predict the death of advanced endometrial carcinoma.

Objective To analyze the influencing factors of tumor-specific mortality in patients with advanced endometrial carcinoma and construct a risk prediction model.Methods A total of 150 patients with advanced endometrial carcinoma admitted to the Fourth Clinical College of Zhejiang Chinese Medical University,Hangzhou First People's Hospital from January 2020 to January 2023 were selected as subjects.Cox regression was employed to analyze factors influencing mortality in advanced endometrial carcinoma.A Logistic regression model was constructed,with receiver operating characteristic(ROC)curve used to evaluate model discrimination,calibration curve for precision assessment,and decision curve for net benefit evaluation.Results Overall 2-year survival rate of 150 patients was 58.67％.The univariate analysis demonstrated that histological grade,lymph node metastasis,tumor maximum diameter,and preoperative carcinoembryonic antigen 125(CA125)levels were all significant risk factors for mortality in advanced endometrial carcinoma(P＜0.05).Multivariate analysis confirmed these parameters as independent prognostic indicators(P＜0.05).A Logistic regression model established using multivariate Cox regression yielded a C index of 0.873(95％CI:0.792-0.951).ROC curve analysis revealed the model's area under the curve for predicting mortality risk factors in advanced endometrial carcinoma was 0.916(95％CI:0.872-0.960).Conclusion The linear chart prediction model constructed based on histological grading,lymph node metastasis,maximum tumor diameter and preoperative CA125 level in this study can effectively predict the death of advanced endometrial carcinoma.

Objective To observe the value of 3D Res2Net deep learning model for predicting volume doubling time(VDT)of solid pulmonary nodule.Methods Chest CT data of 734 patients with solid pulmonary nodules were retrospectively analyzed.The patients were divided into progressive group(n=218)and non-progressive group(n=516)according to whether lung nodule volume increased by ≥25％during follow-up or not,also assigned into training set(n=515)and validation set(n=219)at a ratio of 7∶3.Then a clinical model was constructed based on clinical factors being significantly different between groups,CT features model was constructed based on features of nodules on 2D CT images using convolutional neural network,and 3D Res2Net model was constructed based on Res2Net network using 3D CT images as input.Receiver operating characteristic curve was drawn,and the area under the curve(AUC)was calculated.Taken actual VDT as gold standard,the efficacy of the above models for predicting solid pulmonary nodule'VDT≤400 days were evaluated.Results No significant difference of predicting efficacy for solid pulmonary nodule'VDT≤400 days was found among clinical model,CT feature model and 3D Res2Net model,the AUC of which was 0.689,0.698 and 0.734 in training set,0.692,0.714 and 0.721 in validation set,respectively.3D Res2Net model needed 5-7 s to predict VDT of solid pulmonary nodules,with an average time of(5.92±1.08)s.Conclusion 3D Res2Net model could be used to predict VDT of solid pulmonary nodules,which might obviously reduce manual interpreting time.

Objective To investigate the value of CT value in differential diagnosis of benign and malignant thyroid calcification.Methods The CT plain scan data of 48 cases of thyroid benign calcification and 26 cases of thyroid malignant calcification confirmed by pathology were analyzed retrospectively,and the CT values of 74 cases of thyroid calcification were measured.The best threshold and the maximum area under the receiver operator characteristic(ROC)curve for differentiating benign and malignant thyroid calcification were determined by plotting ROC curve,and the corresponding specificity,sensitivity,positive predictive value,negative predictive value,false positive rate,false negative rate,accuracy and Jordan index were calculated.Then the optimal threshold value was used as a parameter for differential diagnosis of benign and malignant thyroid calcification,and we adoptted χ2 analyze the statistical difference between benign and malignant thyroid calcification in CT gray value.Results The area under the ROC curve was 0.814,and the 95%confidence interval(CI)was 0.712-0.915.When the CT value was 869.5HU(for the convenience of 870HU),the specificity was 69.2%,the sensitivity was 81.3%,the positive predictive value was 64.3%,the negative predictive value was 82.6%,the false positive rate was 20.8%,and the false negative rate was 30.8%,the accuracy was 75.7%and the maximum of the Youden index was 0.505.When 870HU was taken as the differential diagnosis parameter of thyroid benign and malignant calcification(χ2=16.795,P<0.001).Conclusion When the CT value is 870HU,it has important value in differential diagnosis of benign and malignant thyroid calcification.

Objective To investigate the diagnostic significance of CT in thyroid benign solitary coarse calcification nodules (BCCN).Methods A total of 56 BCCN confirmed by surgical pathology in 55 patients were evaluated,and they were compared with 33 papillary thyroid carcinoma (PTC) in 32 patients.The distribution differences of the average CT values and the maximum CT values in BCCN and PTC were observed.The optimal thresholds of the average CT values and the maximum CT values in BCCN and PTC were established by re ceiver operating characteristic(ROC) curve analysis.Results The average CT values in BCCN and PTC were significantly different (t=4.992,P=0.000).The ROC area under curve (AUC) was 0.757 (95％ confidence interval 0.0657-0.0857).When the critical value was 743.4 Hu,Youden index was the largest and the sensitivity and specificity was 48.2％ and 93.9％,respectively.When the critical value was 891.1 Hu,the sensitivity and specificity was 21.4％ and 100％,respectively.The maximum CT values in BCCN and PTC were significantly different (t=5.029,P=0.000).The ROC AUC was 0.775 (95％ confidence interval 0.0681-0.0869).When the critical value was 1201.5 Hu,Youden index was the largest and the sensitivity and specificity was 51.7％ and 91.0％,respectively.When the critical value was 1373.5 Hu,the sensitivity and specificity was 42.9％ and 100％,respectively.Conclusions CT value is of great significance to the diagnosis of BCCN and has high specificity.Compared with the average CT value,the maximum CT value has a relatively higher sensitivity,providing an important base for reducing unnecessary surgical trauma.

Objective To investigate the diagnostic value of computed tomography (CT) histogram analysis for thyroid malignant solitary coarse calcification nodules (MSCN).Methods A total of 89 thyroid solitary coarse calcification nodules (coarse calcification ≥5 mm,no definite soft tissue around calcification) confirmed either by surgery or histopathological examination in 86 patients enrolled in this study from Jan.2009 to Dec.2015 were evaluated,including 33 MSCN from 32 patients and 56 benign solitary coarse calcification nodules (BSCN) from 56 patients.Overall,27 cut-off values were calculated by N (4 ≤ N ≤ 30) times of 50 Hounsfield units (HU) in the range of 200 HU to 1500 HU,and each cut-off value and the differences in the corresponding area percentages in the CT histogram were recorded for MSCN and BSCN.The optimal cut-off value and the corresponding area percentage were established by receiver operating characteristic (ROC) curve analysis.Results In the 24 groups with an ROC area under the curve (AUC) of more than 0.7,at a cut-off value of 1150 HU and at an area percentage of no less than 98.4％,the ROC AUC reached a maximum of 0.86,and the accuracy,sensitivity,and specificity were 70.8％,93.9％,and 57.1％,respectively.At a cut-off value of 450 HU and at an area percentage of no less than 46.3％,the accuracy,sensitivity,and specificity were 76.4％,48.5％,and 92.9％,respectively.At a cut-off value of 550 HU and at an area percentage of no less than 81.5％,the accuracy,sensitivity,and specificity were 75.3％,33.3％,and 100％,respectively.Conclusions In comparison with the cut-off value of 1150 HU with an area percentage of no less than 98.4％,the sensitivities for the cut-off value of 450 HU with an area percentage of no less than 46.3％ and for the cut-off value of 550 HU with an area percentage of no less than 81.5％ were lower;however,the specificities increased significantly,providing an important basis for reducing the misdiagnosis of MSCN.

Objective To investigate the clinical pathologic features of ovarian malignant mesoderm mixed tumor (malignant mixed mesodermal tumor of uterus ,MMMT ) ,and its differential diagnosis ,clinical treatment and prognosis .Methods A retrospec‐tive analysis of the clinicopathological data of 9 patients with MMMT in our hospital from January 1985 to December 1985 was per‐formed ,and the clinicopathological data included routine paraffin section of HE staining and special staining and immunohistochemi‐cal study .Results Results showed that 8 cases were examined by ultrasound with side ovarian tumor ,1 case of patients with bilat‐eral ovarian tumors .Histological examination showed that there was 5 cases of endometrial carcinoma in epithelial components ,3 ca‐ses in clear cell carcinoma ,1 case in mucous adenocarcinoma .Composition of mesenchymal cells were fusiform or irregular shape , weaving or beam pattern ,or chaotic ,which 4 cases showed chondrosarcoma ,2 cases showed bone sarcoma component and glandular epithelial cell keratin and stromal elements vimentin (Cytokeratin ,CK) of 9 cases were + ,and estrogen receptor (estrogen recep‐tor ,ER) detection of 3 cases were + ,Progesterone receptor(PR) detection of 2 cases were + ,protein (desmin) of 2 cases were + ;highly glycosylation type I transmembrane glycoprotein (CD34) of 1 case was + .Conclusion Histological appearance is the main detection methods of ovarian malignant germ layer in the diagnosis of mixed tumor ,and B ultrasonic and CA125 inspection at the same time can effciently improve the accuracy of clinical diagnosis .