Evaluation of multi-classification method of color fundus photograph quality based on ResNet50-OC / 中华实验眼科杂志

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.

Evaluation of low-quality fundus image enhancement based on cycle-constraint adversarial network / 中华实验眼科杂志

Objective:To propose and evaluate the cycle-constraint adversarial network (CycleGAN) for enhancing the low-quality fundus images such as the blurred, underexposed and overexposed etc.Methods:A dataset including 700 high-quality and 700 low-quality fundus images selected from the EyePACS dataset was used to train the image enhancement network in this study.The selected images were cropped and uniformly scaled to 512×512 pixels.Two generative models and two discriminative models were used to establish CycleGAN.The generative model generated matching high/low-quality images according to the input low/high-quality fundus images, and the discriminative model determined whether the image was original or generated.The algorithm proposed in this study was compared with three image enhancement algorithms of contrast limited adaptive histogram equalization (CLAHE), dynamic histogram equalization (DHE), and multi-scale retinex with color restoration (MSRCR) to perform qualitative visual assessment with clarity, BRISQUE, hue and saturation as quantitative indicators.The original and enhanced images were applied to the diabetic retinopathy (DR) diagnostic network to diagnose, and the accuracy and specificity were compared.Results:CycleGAN achieved the optimal results on enhancing the three types of low-quality fundus images including the blurred, underexposed and overexposed.The enhanced fundus images were of high contrast, rich colors, and with clear optic disc and blood vessel structures.The clarity of the images enhanced by CycleGAN was second only to the CLAHE algorithm.The BRISQUE quality score of the images enhanced by CycleGAN was 0.571, which was 10.2%, 7.3%, and 10.0% higher than that of CLAHE, DHE and MSRCR algorithms, respectively.CycleGAN achieved 103.03 in hue and 123.24 in saturation, both higher than those of the other three algorithms.CycleGAN took only 35 seconds to enhance 100 images, only slower than CLAHE.The images enhanced by CycleGAN achieved accuracy of 96.75% and specificity of 99.60% in DR diagnosis, which were higher than those of oringinal images.Conclusions:CycleGAN can effectively enhance low-quality blurry, underexposed and overexposed fundus images and improve the accuracy of computer-aided DR diagnostic network.The enhanced fundus image is helpful for doctors to carry out pathological analysis and may have great application value in clinical diagnosis of ophthalmology.

Location and segmentation method of optic disc in fundus images based on deep learning / 中华眼底病杂志

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.

Clinical efficacy of laparoscopic common bile duct exploration combined with endoscopic nasobiliary drainage versus T-tube drainage in the treatment of choledocholithiasis: a Meta analysis / 中华消化外科杂志

Objective:To systematically evaluate the clinical efficacy of laparoscopic common bile duct exploration (LCBDE) combined with endoscopic nasobiliary drainage (ENBD) versus T-tube drainage in the treatment of choledocholithiasis.Methods:Databases including PubMed(Medline), Embase, the Cochrane Library, Web of Science, Wanfang, CNKI and CBM were searched for literatures from January 1960 to May 2019 with the key words including "胆总管结石病,胆总管结石; T管引流, T管;鼻胆管引流,经内镜鼻胆管引流术, ENBD管, ENBD引流; cholelithiasis, common bile duct stone, jaundice, obstructive, Jaundice, gallstone; T-tube drainage, T-tube, t-tube, biliary tract drainge, drainge tube; endoscopic nasobiliary drainage, nasobiliary drainage, nasobiliary tube, endoscopic drainage tubes, endoscopic drainage tube, endoscopic retrograde biliary drainage" . The randomized controlled trials (RCTs) and high quality non-randomized controlled trials (NRCTs) on comparing ENBD and T-tube drainage during laparoscopic choledocholithotomy were included.Patients who received LCBDE combined with preoperative or intraoperative ENBD were allocated into ENBD group, and patients who received LCBDE combined with postoperative T-tube drainage were allocated into T-tube drainage group. Reported outcomes: operation time, volume of intraoperative blood loss, duration of postoperative hospital stay, time to drainage tube removal, time to postoperative gastrointestinal function recovery, treatment expenses, rate of surgical failure, incidence of postoperative biliary fistula, incidence of postoperative incisional infection, incidence of postoperative residual stones, incidence of postoperative pancreatitis, incidence of postoperative hyperamylasemia, incidence of postoperative bile peritonitis. Count data were represented as odds ratio ( OR) and 95% confidence interval (95% CI). Measurement data were represented as mean difference ( MD) and 95% CI. The I2 and Q tests were used to analyze literature heterogeneity. I2≤50% or P>0.10 indicated no significant heterogeneity, so fixed effects model was used for Meta analysis. I2>50% and P≤0.10 indicated a significant heterogeneity, so random effects model was used for Meta analysis. When analyzing the measurement data, subgroup analysis of individual indicators was performed if there were more than 4 RCTs included, and NRCTs were analyzed for supplement if there were no more than 4 RCTs included. When analyzing the count data, RCTs and NRCTs were combined for analysis. Funnel plots were used to test potential publication bias if there were more than or equal to 10 studies included, while no test was needed if there were less than 10 studies included. Results:(1) Document retrival: 26 literatures meeting the standards were included, including 9 RCTs and 17 NRCTs (4 semi-randomized studies and 13 case-control studies). There were 2 098 patients, including 1 114 patients in the ENBD group and 984 patients in the T-tube drainage group. (2) Results of Meta analysis. ① Duration of postoperative hospital stay: there was a significant difference in the duration of postoperative hospital stay between the ENBD group and T-tube drainage group ( MD=-6.53, 95% CI: -8.64 to -4.43, P<0.05). Further analysis of 9 RCTs showed significant differences in the duration of postoperative hospital stay between patients without acute complications of choledocholithiasis in the ENBD group and those in the T-tube drainage group, between patients with acute complications of choledocholithiasis in the ENBD group and T-tube drainage group, respectively ( MD=-5.88, -8.77, 95% CI: -8.32 to -3.45, -12.39 to -5.15, P<0.05). ② Time to drainage tube removal: for the RCTs, there was a significant difference in the time to drainage tube removal between the ENBD group and T-tube drainage group ( MD=-46.01, 95% CI: -83.64 to -8.37, P<0.05). For the NRCTs, there was a significant difference in the time to drainage tube removal between the ENBD group and T-tube drainage group ( MD=-24.05, 95% CI: -32.93 to -15.18, P<0.05). ③ Time to postoperative gastrointestinal function recovery: for the RCTs, there was a significant difference in the time to postoperative gastrointestinal function recovery between the ENBD group and T-tube drainage group ( MD=17.80, 95% CI: -31.11 to -4.48, P<0.05). For the NRCTs, there was a significant difference in the time to drainage tube removal between the ENBD group and T-tube drainage group ( MD=-5.64, 95% CI: -10.16 to -1.12, P<0.05). ④ Incidence of postoperative biliary fistula: there was a significant difference in the incidence of postoperative biliary fistula between the ENBD group and T-tube drainage group ( OR=0.50, 95% CI: 0.28-0.89, P<0.05). ⑤ Incidence of postoperative incisional infection: there was a significant difference in the incidence of postoperative incisional infection between the ENBD group and T-tube drainage group ( OR=0.35, 95% CI: 0.17-0.73, P<0.05). (3) Analysis of publication bias. The incidence of postoperative biliary fistula in the two groups was analyzed by funnel plot based on the 15 studies. The bilateral symmetry was presented in the funnel plot for incidence of postoperative biliary fistula, suggesting that publication bias had little influence on results of Meta analysis. Conclusion:For patients with choledocholithiasis that endoscopic lithotomy is not feasible, LCBDE combined with ENBD can significantly shorten duration of postoperative hospital stay, time to drainage tube removal, postoperative gastrointestinal function recovery time, reduce the incidence of postoperative biliary fistula and incisional infection compared with LCBDE combined with T-tube drainage.

The impact of childhood abuse and exposure to family violence on college students' self-esteem / 中华行为医学与脑科学杂志

Objective To investigate the impact of childhood abuse and exposure to family violence on college students'self-esteem.Methods Using Childhood Trauma Questionnaire-28 Item Short Form(CTQ-SF),Witness to interparental Violence Questionnaire,Self-esteem Scale(SES),and to investigate 412 college students tional abuse,emotional ignorance,physical ignorance or exposure to interparental physical violence had lower selfesteem(28.04±4.31,28.43±3.81,28.55±3.70,28.66±3.67,28.15±3.87),compared to the students withStudy showed the self-esteem was negatively correlated with childhood physical abuse,emotional abuse,sexual abuse,emotional ignorance,physical ignorance and exposure to interparental physical violence(r=-0.134,-0.216,-0.359,-0.250,-0.170,P＜0.01).Study showed most significant correlation between childhood emotional ignorance,childhood emotional abuse and self-esteem.Conclusion The experience of childhood abuse and ignorance,exposure to family violence have side effects on college students'self-esteem.The most important factors are childhood emotional ignorance and emotional abuse.