Objective:To observe the protective effect of Qishen Yiqi Dripping Pills on myocardial ischemia-reperfusion injury in type 2 diabetic rats and its effects on mitochondrial autophagy phosphoglycerate mutase family member 5 (PGAM5)/Fun14 domain-containing protein 1 (FUNDC1) signaling pathway.Methods:48 male SD rats were divided into a blank control group, sham operation group, No.1 myocardial ischemia reperfusion injury (MIRI) group, No.2 MIRI group, inhibitor group, and Qishen Yiqi group. In addition to the blank control group and the No.1 MIRI group, the other 32 rats were fed with a high-fat diet combined with intraperitoneal injection of streptozotocin to establish animal models of diabetes. Then, the rats in the Qishen Yiqi group were ig Qishen Yiqi Gropping Pills 450 mg/kg, once daily. The rats in the inhibitor group were given Qishen Yiqi Gropping Pills and trimethylamine (3-MA) by intraperitoneal injection 100 mmol/L, once daily. And the rats in the other four groups were ig normal saline. One week after intragastric administration, except for the blank control group and the sham operation group, the rats in the other four groups were used to establish the animal model of myocardial ischemia-reperfusion injury by ligating the anterior descending branch of the left coronary artery for 30 min and reperfusion for 2 h. Then, the materials were taken after reperfusion for 2 h. Finally, the mortality of rats was calculated, the changes in creatine kinase (CK), lactate dehydrogenase (LDH), aspartate aminotransferase (AST), and the levels of superoxide dismutase (SOD) and malondialdehyde (MDA) in myocardial tissue were detected, and the expression level of PGAM5/FUNDC1 pathway node protein in myocardial tissue was measured by real-time fluorescence quantitative PCR.Results:Compared with the No.1 MIRI group, serum indicators of the AST, LDH, CK, and MDA levels in the No.2 MIRI model group increased (all P < 0.05), while the level of SOD decreased ( P < 0.05). Compared with the No.1 MIRI group, myocardial tissue indicators of FUNDC1, PGAM5, B cell lymphoma-xL (Bcl-xL), light chain 3 (LC3), autophagy associated protein 5 (ATG5), and Beclin-1 level decreased (all P < 0.05), the level of P62 increased ( P < 0.05), while the level of cysteinyl aspartate specific proteinase-9 (Caspase-9) increased, but he difference is not statistically significant ( P > 0.05). Compared with the No.2 MIRI group and the inhibitor group, serum indicators of the AST, LDH, CK, and MDA levels in the Qishen Yiqi group decreased (all P < 0.05), and the level of SOD increased ( P < 0.05). Compared with the No.2 MIRI group and the inhibitor group, myocardial tissue indicators of FUNDC1, PGAM5, Bcl-xL, LC3, ATG5, and Beclin-1 levels increased (all P < 0.05), while the levels of P62 and Caspase-9 decreased (all P < 0.05). Conclusions:High blood sugar levels can aggravate MIRI. Qishen Yiqi Dripping Pills can regulate mitochondrial autophagy through the PGAM5/FUNDC1 pathway and alleviate myocardial ischemia-reperfusion injury. MIRI plays a protective role in the myocardium of diabetic rats.

Objective:To evaluate the efficiency of ResNet50-OC model based on deep learning for multiple classification of color fundus photographs.Methods:The proprietary dataset (PD) collected in July 2018 in BenQ Hospital of Nanjing Medical University and EyePACS dataset were included.The included images were classified into five types of high quality, underexposure, overexposure, blurred edges and lens flare according to clinical ophthalmologists.There were 1 000 images (800 from EyePACS and 200 from PD) for each type in the training dataset and 500 images (400 from EyePACS and 100 from PD) for each type in the testing dataset.There were 5 000 images in the training dataset and 2 500 images in the testing dataset.All images were normalized and augmented.The transfer learning method was used to initialize the parameters of the network model, on the basis of which the current mainstream deep learning classification networks (VGG, Inception-resnet-v2, ResNet, DenseNet) were compared.The optimal network ResNet50 with best accuracy and Micro F1 value was selected as the main network of the classification model in this study.In the training process, the One-Cycle strategy was introduced to accelerate the model convergence speed to obtain the optimal model ResNet50-OC.ResNet50-OC was applied to multi-class classification of fundus image quality.The accuracy and Micro F1 value of multi-classification of color fundus photographs by ResNet50 and ResNet50-OC were evaluated.Results:The multi-classification accuracy and Micro F1 values of color fundus photographs of ResNet50 were significantly higher than those of VGG, Inception-resnet-v2, ResNet34 and DenseNet.The accuracy of multi-classification of fundus photographs in the ResNet50-OC model was 98.77% after 15 rounds of training, which was higher than 98.76% of the ResNet50 model after 50 rounds of training.The Micro F1 value of multi-classification of retinal images in ResNet50-OC model was 98.78% after 15 rounds of training, which was the same as that of ResNet50 model after 50 rounds of training.Conclusions:The proposed ResNet50-OC model can be accurate and effective in the multi-classification of color fundus photograph quality.One-Cycle strategy can reduce the frequency of training and improve the classification efficiency.

Objective:To observe and analyze the accuracy of the optic disc positioning and segmentation method of fundus images based on deep learning.Methods:The model training strategies were training and evaluating deep learning-based optic disc positioning and segmentation methods on the ORIGA dataset. A deep convolutional neural network (CNN) was built on the Caffe framework of deep learning. A sliding window was used to cut the original image of the ORIGA data set into many small pieces of pictures, and the deep CNN was used to determine whether each small piece of picture contained the complete disc structure, so as to find the area of the disc. In order to avoid the influence of blood vessels on the segmentation of the optic disc, the blood vessels in the optic disc area were removed before segmentation of the optic disc boundary. A deep network of optic disc segmentation based on image pixel classification was used to realize the segmentation of the optic disc of fundus images. The accuracy of the optic disc positioning and segmentation method was calculated based on deep learning of fundus images. Positioning accuracy=T/N, T represented the number of fundus images with correct optic disc positioning, and N represented the total number of fundus images used for positioning. The overlap error was used to compare the difference between the segmentation result of the optic disc and the actual boundary of the optic disc.Results:On the dataset from ORIGA, the accuracy of the optic disc localization can reach 99.6%, the average overlap error of optic disc segmentation was 7.1%. The calculation errors of the average cup-to-disk ratio for glaucoma images and normal images were 0.066 and 0.049, respectively. Disc segmentation of each image took an average of 10 ms.Conclusion:The algorithm can locate the disc area quickly and accurately, and can also segment the disc boundary more accurately.

Objective To propose a deep learning-based retinal image quality classification network, FA-Net,to make convolutional neural network ( CNN) more suitable for image quality assessment in eye disease screening system. Methods The main network of FA-Net was composed of VGG-19. On this basis,attention mechanism was added to the CNN. By using transfer learning method in training, the weight of ImageNet was used to initialize the network. The attention net is based on foreground extraction by extracting the blood vessel and suspected regions of lesion and assigning higher weights to region of interest to enhance the learning of these important areas. Results Total of 2894 fundus images were used for training FA-Net. FA-Net achieved 97. 65％ classification accuracy on a test set containing 2170 fundus images,with the sensitivity and specificity of 0. 978 and 0. 960,respectively,and the area under curve(AUC) was 0. 995. Conclusions Compared with other CNNs,the proposed FA-Net has better classification performance and can evaluate retinal fundus image quality more accurately and efficiently. The network takes into account the human visual system ( HVS) and human attention mechanism. By adding attention module into the VGG-19 network structure, the classification results can be better interpreted as well as better classification performance.

Objective To construct the new diet intervention scheme of dyslipidemia of university teachers, discuss the effect of this plan on eating behavior change. Methods Choose two groups of college teachers in Harbin, who were hyperlipemia and had physical examinations from June to September, 2014. 44 teachers from one college were conducted the new dietary intervention as experimental group, 37 teachers from another college were the control group, used the usual method. Compared two groups before and after the intervention of dietary behavior and blood lipid. Results The experimental group′s dietary behaviors changed strongly after implement the new dietary intervention, the scores of DTS before the experiment (58.82 ± 18.47) points,3 months after the experiment (48.36 ± 14.25) points and 6 months after the experiment (44.18±14.92) points were statistically significant (F=21.308, P < 0.01). There was no statistically significant difference in control group (F = 1.129, P > 0.05), respectively (60.51 ± 16.91) points, (57.19 ± 16.35) points, (56.92 ± 21.35) points. After 6 months, the experimental group′s subjects of TC was (4.28±3.73) mmol/L, the control group was (6.23±1.04) mmol/L, the difference was statistically significant (t = 3.082, P < 0.05), there were no significant differences in TG, LDL-C and HDL-C of the two groups (P>0.05). Conclusions The new dietary guidance plan can effectively improve and maintain the dietary behavior in hyperlipidemia college teachers, and decrease the blood lipid level.