Objective To explore the value of 64-row helical CT multi-phase enhancement scan combined with angiography (CTA)in the diagnosis of pulmonary mass.Methods Two hundred and sixty-five patients with pulmonary mass confirmed by pa-thology were checked,analyzed the CT sign of multi-phase enhancement scan and the blood supply of pulmonary mass displayed by CTA.Results Lung cancer was mainly supplied by bronchial arteries,some by body arteries,the feeding arteries display rate of lung cancer group was significantly higher than that of benign disease group(P <0.05).CT enhancement peak value of lung cancer group was significantly higher than that of tuberculoma group,inflammatory pseudotumor group and hamartoma group(P <0.05), but no significant difference between hemanginoma group(P >0.05).Enhancement dynamic curves of lung cancer group was differ-ent from benign lesion groups:Lung cancer without obvious enhancement in pulmonary artery phase,CT value increased rapidly in aorta phase,120 s reached peak,and declined slowly in delay phase;CT value of tuberculoma was increased slowly without obvious peak;CT value of inflammatory increased gradually in pulmonary artery phase,90 s reached the peak;hamartoma was no obvious enhancement;Hemangioma enhanced rapidly after strengthening in the pulmonary artery phase,reached the peak at about 15 s,and then decreased slowly.Conclusion 64-row helical CT multi-phase enhancement scan combined with angiography have important clinical value,which can differentiate malignant mass from benign ones.

Modern medical quality management is characterized by professionalism, continuity and comprehensiveness. It is necessary to strengthen the communication and cooperation among health administrative authorities, medical institutions and professionals. Since 2011, based on the guidance of the interactive governance theory and the governance interface as a platform, Zhejiang Province had explored and established a relatively independent third-party quality evaluation service organization, which aimed to correct such setbacks as the imbalance and inadequacy of medical quality management. Through the interaction of organization interface, management interface, service interface, information interface and method interface, the province had initially achieved the multi-level diagonal governance in medical quality management, and transformed the traditional management relationship into an interactive relationship. This practice had achieved desirable results in improving the quality control work network, updating management methods, and improving medical quality and safety, serving as reference in upgrading the medical quality and safety management of medical institutions in China.

Objective:To explore the application effect of blended learning in clinical practice of undergraduate students majoring in medical imaging diagnosis.Methods:A total of 60 undergraduate students majoring in medical imaging diagnosis who practiced in the Department of Radiology of Chongqing General Hospital from 2017 to 2019 were selected as subjects. The students were divided into experimental group and control group, each with 30 students. During the internship, the experimental group adopted the blended learning, including lecture-based learning, case-based learning, problem-based learning and team-based learning according to different teaching scenarios. While the control group adopted the traditional teaching mode. At the end of the internship, the test scores of the two groups of intern students were compared, and the satisfaction degree of the teaching was investigated by questionnaire. SPSS 19.0 was used to conduct t-test and Chi-square test. Results:The score of theoretical knowledge examination in the experimental group was (90.27±5.38) points, and that in the control group was (83.13±7.57) points. The difference between the two groups was statistically significant ( t=4.21, P<0.001). The score of imaging analysis examination in the experimental group was (90.07 ± 4.80) points, and that in the control group was (82.13±8.71) points. The difference between the two groups was statistically significant ( t=4.37, P<0.001). The results of the satisfaction survey showed that the overall satisfaction with teaching was 76.7% (23/30) in the experimental group and 50.0% (15/30) in the control group, with statistically significant difference ( χ2= 6.57, P=0.037). Conclusion:The blended learning has a good effect in the teaching of undergraduate students majoring in medical imaging diagnosis.

Objective: To determine whether noncontrast computed tomography (NCCT) models based on multivariable, radiomics features, and machine learning (ML) algorithms could further improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH). Materials and Methods: We retrospectively reviewed 261 patients with sICH who underwent initial NCCT within 6 hours of ictus and follow-up CT within 24 hours after initial NCCT, between April 2011 and March 2019. The clinical characteristics, imaging signs and radiomics features extracted from the initial NCCT images were used to construct models to discriminate early HE. A clinical-radiologic model was constructed using a multivariate logistic regression (LR) analysis. Radiomics models, a radiomics-radiologic model, and a combined model were constructed in the training cohort (n = 182) and independently verified in the validation cohort (n = 79). Receiver operating characteristic analysis and the area under the curve (AUC) were used to evaluate the discriminative power. Results: The AUC of the clinical-radiologic model for discriminating early HE was 0.766. The AUCs of the radiomics model for discriminating early HE built using the LR algorithm in the training and validation cohorts were 0.926 and 0.850, respectively.The AUCs of the radiomics-radiologic model in the training and validation cohorts were 0.946 and 0.867, respectively. The AUCs of the combined model in the training and validation cohorts were 0.960 and 0.867, respectively. Conclusion NCCT models based on multivariable, radiomics features and ML algorithm could improve the discrimination of early HE. The combined model was the best recommended model to identify sICH patients at risk of early HE.