ABSTRACT
Objective:To investigate the value of artificial intelligence in screening normal or abnormal four-chamber view of the fetal heart.Methods:Selecting 3 996 pictures of normal and abnormal end systolic four chamber views and 450 video clips from the database of Beijing Key Laboratory of Fetal Heart Disease Maternal and Fetal Medicine Research in Beijing Anzhen Hospital as training set, test set and verification set to train, test and verify DGACNN model. ①Comparing DGACNN, DGACNN-ALOCC and other classification models(Densenet, Resnet50, InceptionV3, InceptionResnetV2) to detect the model with the most advanced level by recognizing 200 normal pictures and 200 abnormal pictures. ②Fetal echocardiographers were divided into three groups according to their experiences: primary, intermediate and advanced, 3 doctors in each group, and comparing the average score between each group or three groups and DGACNN by recognizing 100 normal pictures and 100 abnormal pictures.Results:①When the the false positive rate(FPR) was in the range of 20%, the recognition accuracy of DGACNN was the highest with 0.850, the recognition accuracy of other models were DGACNN-ALOCC 0.835, Densenet 0.780, Resnet50 0.700, InceptionV3 0.670, InceptionResnetV2 0.650, respectively. ②When FPR was in the range of 20%, the area under ROC curve of DGACNN was the largest with 0.881, the area under ROC curve of other models were DGACNN-ALOCC 0.864, Densenet 0.850, Resnet50 0.822, Inceptionv3 0.779, InceptionResnetV2 0.703, respectively. ③When the FPR was in the range of 20%, the average recognition accuracy of the senior fetal echocardiographer group was the highest with 0.863, followed by DGACNN 0.840, which was higher than the average recognition accuracy of the primary and intermediate groups with 0.760, 0.807; the average recognition accuracy of DGACNN was higher than the total average recognition accuracy of the primary, intermediate and advanced groups with 0.810.Conclusions:Artificial intelligence is accessible in screening four chamber view of fetal echocardiography, with high recognition accuracy.
ABSTRACT
Objective To discuss the predisposing causes and echocardiographic findings of abnormal cardiac calcifications in fetuses.Methods The echocardiographic and pathological data of 12 fetuses with abnormal cardiac calcifications were retrospectively reviewed,and the pregnancy outcome,predisposing cause and echocardiographic features were analyzed.Results Associated maternal positive anti-SSA/SSB antibody was found in 8 fetuses.The echocardiographic findings of these 8 fetuses were extensive hyper-echogenic thickened atrial wall,interatrial septal and atrioventricular roof.Cardiac myocardium dystrophic calcification was found in 3 fetuses with focal or extensive hyper-echogenic of myocardium.Idiopathic infantile calcification with thickening and hyper-echogenic wall of main pulmonary artery and aorta with obvious stenosis of artery were observed in 1 fetus.One fetus with dystrophic myocardium calcification was continued in pregnancy,1 maternal anti-SSA/SSB antibody (+) baby was born,and 10 fetuses were terminated.Conclusion Maternal anti SSA/ SSB antibody (-) is predominantly associated with fetal cardiac calcification.Fetal abnormal cardiac calcification with different predisposing causes have different echocardiographic features.
ABSTRACT
Objective To investigate the distribution and drug resistance of pathogens in cancer patients with nosocomial infections. Methods Pathogens isolated from cancer patients with nosocomial infections in Zhejiang Cancer Hospital from 2004 to 2008 were analyzed. Results Totally 3454 strains of pathogens were isolated, including 1900 strains of Gram-negative bacilli (55.0%), 838 strains of fungi (24.3%), and 716 strains of Gram-positive bacteria (20.7%). Pathogenic bacteria Escherichia coli and Candida albicans were isolated mainly from surgical wound, urinary tract, respiratory tract and oral cavity. The drug resistant rates for Gram-negative Escherichia coli and Gram-positive staphylococci were high, and Candida albicans was sensitive to all antifungal drugs. Conclusion Opportunistic pathogens account for most nosocomial infections in cancer patients, and some of them are of high-level resistance to antimicrobial agents.
ABSTRACT
OBJECTIVE To evaluate the risk factors for postoperative nosocomial infection(NI) among inpatients with cervical carcinoma.METHODS A prospective and retrospective study was carried out to investigate the clinical data of patients with cervical carcinoma in department of gynecology during the period from Jan 1 to Dec 31,2003.RESULTS The incidence and case incidence of NI were 22.88% and 23.99%,urinary tract infection((52.3%)) was the most common infection,followed by vaginal margin infection and pelvic infection.NI was closely related with diabetes mellitus,the duration of catheter reservation,and different operators.CONCLUSIONS NI is high in postoperative patients with cervical carcinoma,which should be paid attention during the course of clinical treatment.
ABSTRACT
OBJECTIVE To explore the risk factors of infection in patients with chemotherapy-induced neutropenia in order to offer scientific references for clinical treatment.METHODS With case-control study,two hundred and fifty-six cancer patients with chemotherapy-induced neutropenia were compared between the infection group and non-infection group.The data were analyzed on risk factors by univariate analysis(Chi-square test) and multivariate analysis(non-conditional Logistic regression models).RESULTS Multivariate analysis showed that early lymphopenia after chemotherapy(OR=3.347),the depth of the Absolute neutrophil count nadir(