Objective To investigate the easier and more effective moduses of artificial respiration to the neonatal continuous chest compression eardiopulmonary resuscitation. Methods The experience of the treatment on 66 inpatient neonates(with 84 vices cardiac arrest) by continuous chest compression cardiopulmonary resuscitation was summarized. Based on different moduses of artificial respiration matched with mask-gasbag pressure breathing or tracheal intubation pressure breathing to cardiopulmonary resuscitation(CPR), and according to the principles of therandomized block design,sixty-six neonates in cardiac arrest were randomly divided into two groups of A and B. Fun-damental therapeutics in these two groups were alike. A group(38 cases with 53 vices cardiac arrest) was with mask-gasbag pressure breathing. B group(28 cases with 31 vices cardiac arrest) was with tracheal intubation gasbag pres-sure breathing. Time of cardiac arrest (Tca), time of cardiac restore independent rhythm(Tr), Time of cardiopul-monary resuscitation completed(Tc), achievement ratio of cardiopulmonary resuscitation, and 24 hours survival rateof these two groups were compared. Results Compared with B group, there was no significant deviation of Pca, Tr,Tc, the successful rate of CPR and 24 hours survival rate in A group. Comparing A group to B group, the Tea[ (0.99±0.75)rain vs (0.92±0.69)min, P = 0.69];Tr[(3.58±2.15)rain vs (3.66±2.01)min, P = 0.87];Tc [(23.28±9.26)min vs (23.73±9.51)min,P=0.84];suecessful rate of CPR [88.68% vs 83.87% ,P>0.05];24h survival rate [84.21% vs 82.14 %, P > 0.05 ]. Conclusion The mask-gasbag pressure breathing was an easy,safe and effective artificial respiration method for the neonatal continuous chest compression cardiopulmonary resusci-tation. Only in a few eases with airway resistance heightening was the modus of tracheal intubation gasbag pressure breathing applied.

Objective To construct an intelligent analysis system based on visual attention for diabetic retinopathy ( DR) assistant diagnosis and to realize the automatic screening and grading of fundus images of DR. Methods Total of 35126 DR fundus images were downloaded from the Diabetic Retinopathy Detection competition in the Data Modeling and Data Analysis Competition Platform (Kaggle),and 1200 fundus images were downloaded from the Messidor website. Firstly,according to the characteristics of DR fundus images,a series of preprocessing was carried out for retina images. Then,on the basis of VGG16 network,visual attention SENet module was introduced to improve the saliency of lesion features,and a deep convolution neural network SEVGG with complex network structure was generated. The network basically inherited some structural parameters of VGG16,and the parameters of SENet module were adjusted according to the basic network and training data set. Finally, the SEVGG network model was used to screen the DR fundus image,and the fundus image was divided into different levels according to the degree of lesions of DR in different periods. Configure the training platform and environment and perform algorithm performance verification experiments. Results The method proposed in this study was tested on different open standard datasets,and finally achieved high accuracy in image-based classification. The accuracy of 5 classification in Kaggle dataset was 83％,the sensitivity of lesion detection was 99. 86％ and the specificity was 99. 63％. The accuracy rate of the 4 classification in the Messidor data set was up to 88％,the sensitivity of the lesion detection was 98. 17％,and the specificity was 96. 39％. The introduction of visual attention was more significant for the focus of the lesion,which helped the accurate detection of DR. Conclusions This method effectively avoids some shortcomings of traditional artificial feature extraction and fundus image classification,and is more accurate for lesion recognition. It is not only superior to the previous method,but also shows better robustness and generalization.