Objective:To develop a deep learning-based segmentation model MT-UNet to automatically segment bone metastases and benign bone lesions in bone scintigraphy with SPECT/CT.Methods:A total of 93 patients (48 males and 45 females, age 28-84 years) who underwent bone SPECT/CT in the Department of Nuclear Medicine, General Hospital of Northern Theater Command from June 2023 to December 2023 were enrolled retrospectively in this study, with a total of 184 bone lesions (94 benign lesions and 90 metastatic tumors). The MT-UNet was employed to segment bone lesions in SPECT, CT and SPECT/CT images respectively. Comparative analysis with 8 segmentation models was performed. The training set and validation set were divided by using 5-fold cross-validation and transfer learning was introduced to further enhance the robustness of the model. An additional cohort of 22 patients (15 males and 7 females, age 37-87 years) who received bone SPECT/CT in the Department of Nuclear Medicine, General Hospital of Northern Theater Command from April 2023 to May 2023 were included, comprising 40 bone lesions (22 benign lesions and 18 metastatic tumors) as the test set of MT-UNet. Segmentation performance of different models was assessed using accuracy, sensitivity, specificity, AUC, intersection over union and Dice similarity coefficient (DSC). Delong test was used to compare the segmentation efficacy among different models in the test set.Results:In the validation set, MT-UNet demonstrated DSC of 0.940, 0.962, and 0.963 for SPECT, CT, and SPECT/CT bone lesion segmentation, respectively, which were outperformed other models. Following transfer learning implementation, the SPECT/CT model′s DSC was improved to 0.984. In the test set, MT-UNet maintained comparable segmentation performance to the validation set, with significant AUC differences among the three models ( Z values: from -15.42 to -9.27, all P<0.01). Compared with conventional image interpretation, MT-UNet-based segmentation reduced physician interpretation time from 164min to 102min. Conclusion:MT-UNet has shown good performance in automatic segmentation of bone metastases and benign bone lesions, and is expected to become an important part of SPECT/CT image intelligent diagnosis system for bone metastases.

Objective To analyze the lung function condition and the prevalence of pulmonary ventilation disorders in the occupational population of Wuhan, and to explore their influencing factors. Methods Physical examination data from the Wuhan Prevention and Treatment Center for Occupational Diseases were used in this study, and finally 9499 people were selected as the study subjects. The linear regression model and logistic regression model were used to analyze the influencing factors of pulmonary ventilation function and pulmonary dysfunction. The restricted cubic spline was used to explore the nonlinear relationship. Results The prevalence of pulmonary ventilation disorders was 1.7%, and the lung function indexes FVC, FEV1, and FEV1/FVC were significantly lower in the population aged >27 years than in the population aged <27 years (P<0.001). The lung function indexes FVC and FEV1 were significantly lower in females than in males (P<0.001). The lung function indexes FVC and FEV1 were significantly lower in underweight occupational groups than in normal-weight groups (P<0.001), and FVC and FEV1 were significantly lower in dust-exposed occupational groups than in groups without dust exposure(P<0.05). Restricted cubic spline plots showed a nonlinear relationship between age and lung function indexes FVC and FEV1 (P_nonlinear< 0.05). Age and BMI were the risk factors for pulmonary ventilation disorders. Conclusion Age, gender, BMI, and dust exposure are risk factors for decreased FVC and FEV1. Age is the risk factor for decreased FEV1/FVC. Age and BMI are the risk factors for pulmonary ventilation disorders.

Objective:To develop a deep learning-based segmentation model MT-UNet to automatically segment bone metastases and benign bone lesions in bone scintigraphy with SPECT/CT.Methods:A total of 93 patients (48 males and 45 females, age 28-84 years) who underwent bone SPECT/CT in the Department of Nuclear Medicine, General Hospital of Northern Theater Command from June 2023 to December 2023 were enrolled retrospectively in this study, with a total of 184 bone lesions (94 benign lesions and 90 metastatic tumors). The MT-UNet was employed to segment bone lesions in SPECT, CT and SPECT/CT images respectively. Comparative analysis with 8 segmentation models was performed. The training set and validation set were divided by using 5-fold cross-validation and transfer learning was introduced to further enhance the robustness of the model. An additional cohort of 22 patients (15 males and 7 females, age 37-87 years) who received bone SPECT/CT in the Department of Nuclear Medicine, General Hospital of Northern Theater Command from April 2023 to May 2023 were included, comprising 40 bone lesions (22 benign lesions and 18 metastatic tumors) as the test set of MT-UNet. Segmentation performance of different models was assessed using accuracy, sensitivity, specificity, AUC, intersection over union and Dice similarity coefficient (DSC). Delong test was used to compare the segmentation efficacy among different models in the test set.Results:In the validation set, MT-UNet demonstrated DSC of 0.940, 0.962, and 0.963 for SPECT, CT, and SPECT/CT bone lesion segmentation, respectively, which were outperformed other models. Following transfer learning implementation, the SPECT/CT model′s DSC was improved to 0.984. In the test set, MT-UNet maintained comparable segmentation performance to the validation set, with significant AUC differences among the three models ( Z values: from -15.42 to -9.27, all P<0.01). Compared with conventional image interpretation, MT-UNet-based segmentation reduced physician interpretation time from 164min to 102min. Conclusion:MT-UNet has shown good performance in automatic segmentation of bone metastases and benign bone lesions, and is expected to become an important part of SPECT/CT image intelligent diagnosis system for bone metastases.

Objective To investigate the diagnostic value of intraductal ultrasonography (IDUS) and bile tumor marker in differential diagnosis of suspected biliary stricture.Methods A total of 57 patients with biliary stricture (8 benign strictures,49 cases of malignant strictures),who underwent IDUS and tests of serum and bile tumor markers (CA19-9 and CEA),were analyzed.The sensitivity,specificity,positive predictive value,negative predictive value and accuracy were compared among the outcomes of B-ultrasonography,CT,MRCP,IDUS,as well as IDUS combined with bile tumor markers.Results The specificity of the IDUS and the combined group were 63.6％ (7/11) and 77.8％ (7/9) respectively (P ＞ 0.05).The positive predictive value of the IDUS and the combined group were 91.8％ (45/49) and 95.9％ (47/49) respectively (P ＞0.05).The diagnostic accuracy of the IDUS and the combined group were 91.2％ (52/57) and 94.7％ (54/57) respectively (P ＞0.05).Data of the two groups were significantly higher than conventional imaging like B-ultrasound,CT and MRCP.The accuracy of IDUS combined with bile CEA for the diagnosis of distal bile duct cancer was 97.9％ (46/47),significantly higher than that of IDUS.Conclusion IDUS combined with biliary tumor markers is of high value for distinguishing the bile benign from malignant stricture.IDUS combined with biliary CEA test can improve the diagnostic accuracy of distal malignant biliary stricture diseases.

Objective To investigate the diagnostic value of intraductal ultrasonography for the quality of biliary stricture.Methods Data of the patients who had received operation because of biliary stricture after IDUS examination from 2006 to 2010 were collected.IDUS results were compared with those of operation.Results There were 43 cases of malignant strictures and 6 benign strictures in total.The sensitivity,specificity,positive predictive value,negative predictive value and diagnostic accuracy of intraductal uhrasonography for the quality of biliary stricture were 97.7％ ( 42/43 ),83.3％ ( 5/6 ),97.7％ ( 42/43 ),83.3％ (5/6) and 95.9％ (47/49),respectively,which were significantly higher than conventional imaging like ultrasound B,CT and MRCP.Twenty one cases in 32 were diagnosed as malignant biliary stricture with cytological brushing,with the diagnostic accuracy of 65.6％.All cases had been diagnosed by IDUS.Conclusion Intraductal ultrasonography is of high diagnostic value for biliary stricture.However,cytological brushing based on IDUS is of limited diagnostic value for malignant biliary stricture.

ObjectiveTo investigate the clinicopathologic features,therapy,and prognosis of primary small cell carcinoma of the pancreas.MethodsDatabases including Chinese Journal Full-text Database,VIP Database for Chinese Technical Periodicals,Medline/Pubmed,and OVID were searched electronically up to April 2012.A systematic review was performed together with one case in our hospital.ResultsTwenty-eight articles fulfilling the criteria consisting of 46 patients with pathologically confirmed diagnosis of primary small cell carcinoma of the pancreas were studied,together with 1 patient in our Drum Tower Hospital,finally 47patients were included.The results of this systematic review showed:( 1 ) Primary small cell carcinoma of the pancreas was more common in men with a median age of 62.The most common clinical presentations were abdominal pain,jaundice and weight loss.Para-neoplastic syndrome was rarely observed.(2)Most cases were found to have abnormally elevated serum levels of neuron-specific enolase.CT displayed heterogeneous,and marked enhancing masses in most cases.The conclusive diagnosis depended on histological confirmation.(3)63.8％ of the cases were found to be associated with metastasis at the time of diagnosis.The overall median survival time was 28 weeks.(4) There was no consensus on the treatment of primary small cell carcinoma of the pancreas. Chemotherapy was currently considered as the treatment of choice among the systematic management for these patients.ConclusionsPrimary small cell carcinoma of the pancreas was a rare and aggressive neuroendocrine tumor with a poor prognosis.