Objective:To investigate the role of complement C3a receptor in the diabetic nephropathy pathogenesis of db/db mice, and to provide a new target for prevention and treatment of diabetic nephropathy.Methods:Twelve 8-week-old male mice with type 2 diabetes mellitus (db/db mice) and 6 wild-type (db/m) mice were reared in the special pathogen free environment. The mice were grouped into db/m group, db/db group and C3a receptor antagonist group, with 6 mice in each group. db/db model mice were intraperitoneally injected with C3a receptor antagonist (SB290157, 10 mg/kg) once every two days for 8 weeks in C3a receptor antagonist group. Blood and urine samples were collected, and body weight of mice, fasting blood glucose, serum creatinine, blood urea nitrogen, urinary microalbumin/urinary creatinine and urinary N-acetyl-β- D-glucosaminidase (NAG) were detected. Renal tissues were collected, and HE, PAS and Masson stainings were used to observe the pathological changes. Immunohistochemistry, immunofluorescence and Western blotting were used to detect the protein expression levels of C3 and C3a receptor. Western blotting was used to analyze the protein expression levels of kidney injury molecule-1 (Kim-1), α-smooth muscle actin (α-SMA), zonula occluden-1 (ZO-1), vimentin and E-cadherin in renal tissues. Immunofluorescence was used to analyze the protein expression levels and distribution of α-SMA, ZO-1 and Kim-1, and immunohistochemistry was used to analyze the protein expression levels of interleukin-1 (IL-1) and tumor necrosis factor-α (TNF-α). TUNEL assay was used to detect apoptotic cells in renal tissues. Results:Compared with db/m group, body weight, fasting blood glucose, urinary microalbumin/urinary creatinine and urinary NAG in db/db group were significantly higher, while these indicators in C3a receptor antagonist group were slightly lower than those in db/db group (all P<0.01). There were no significant differences in serum creatinine and blood urea nitrogen among the three groups (all P>0.01). Compared with db/m group, db/db group had glomerular hypertrophy, necrosis and exfoliation of renal tubular epithelial cells, and dilation of renal tubules, and C3 and C3a receptor protein expression levels were higher (both P<0.01). Compared with db/db group, C3a receptor antagonist group had less glomerular lesions, mild necrosis of renal tubular epithelial cells and less tubular dilation. Compared with db/m group, the protein expression levels of Kim-1, IL-1 and TNF-α in kidney tissues of db/db group were significantly higher, while Kim-1, IL-1 and TNF-α in C3a receptor antagonist group were significantly lower than those in db/db group (all P<0.01). Compared with db/m group, the protein expression levels of α-SMA and vimentin of renal tubular epithelial cells in db/db group were significantly higher, while the protein expression levels of ZO-1 and E-cadherin were significantly lower (all P<0.01). Compared with db/db group, the protein expression levels of α-SMA and vimentin of renal tubular epithelial cells in C3a receptor antagonist group were significantly lower, and the protein expression levels of ZO-1 and E-cadherin were significantly higher (all P<0.01). Compared with db/m group, the number of apoptotic cells of kidney tissues in db/db group was increased, while the number of apoptotic cells in C3a receptor antagonist group was reduced compared with db/db group. Conclusions:The expression levels of C3 and C3a receptor of kidney tissues in db/db mice are significantly increased. Antagonistic C3a receptor can reduce the body weight, blood glucose, urinary microalbumin/urinary creatinine and urinary NAG, alleviate renal pathological injury, inhibit renal tissue inflammation, apoptosis and renal tubule epithelial-mesenchymal transition in db/db mice.

Pulmonary blast injury has become the main type of trauma in modern warfare, characterized by externally mild injuries but internally severe injuries, rapid disease progression, and a high rate of early death. The injury is complicated in clinical practice, often with multiple and compound injuries. Currently, there is a lack of effective protective materials, accurate injury detection instrument and portable monitoring and transportation equipment, standardized clinical treatment guidelines in various medical centers, and evidence-based guidelines at home and abroad, resulting in a high mortality in clinlcal practice. Therefore, the Trauma Branch of Chinese Medical Association and the Editorial Committee of Chinese Journal of Trauma organized military and civilian experts in related fields such as thoracic surgery and traumatic surgery to jointly develop the Clinical treatment guideline for pulmonary blast injury ( version 2023) by combining evidence for effectiveness and clinical first-line treatment experience. This guideline provided 16 recommended opinions surrounding definition, characteristics, pre-hospital diagnosis and treatment, and in-hospital treatment of pulmonary blast injury, hoping to provide a basis for the clinical treatment in hospitals at different levels.

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.

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 analyze the clinicopathological features of IgA nephropathy (IgAN) patients with anemia and the influencing factors of prognosis. Methods: The clinical and pathological data of patients diagnosed with primary IgAN at the First Affiliated Hospital of Fujian Medical University from January 1, 2006 to December 31, 2016 were retrospectively analyzed. The patients were divided into anemia group and non-anemia group according to whether the patient was anemia or not. The clinical and pathological data of the two groups were collected. All of them were followed up from the date of renal biopsy to January 1, 2018. Survival curves of the two groups were drawn by Kaplan-Meier method, and compared by Log-rank test. Multivariate Cox proportional hazards regression model was adopted to explore the influencing factors of prognosis in IgAN patients. Results: A total of 231 subjects were enrolled, including 122 males (52.8%), and the male-female ratio was 1.12∶1. Their age was (34.8±10.1) years (15-68 years). There were 70 patients (30.3%) in anemia group, 161 cases (69.7%) in non-anemic group. Compared with non-anemia group, anemia group had higher proportion of females, lower serum albumin, higher proportion of tubular atrophy/interstitial fibrosis (T1/2), endothelial cell proliferation (E1) and crescent formation (C1/2), which were statistically significant (all P<0.05). The patients had a median follow-up time as 6.3 years (0.3-12.9 years). Survival analysis showed that patients in anemia group had lower cumulative renal survival rate than that in non-anemia group (χ²=15.234, P<0.001). Multivariate Cox hazards regression analysis revealed that anemia (HR=3.820, 95%CI 1.674-8.719, P=0.001), tubular atrophy/interstitial fibrosis (T1/2) (HR=3.770, 95%CI 1.026-13.852, P=0.046), glomerular segmental sclerosis/adhesion (S1) (HR=4.211, 95%CI 1.139-15.576, P=0.031), hypertension (HR=2.988, 95%CI 1.276-6.999, P=0.012), increased 24 h urinary protein (HR=1.103, 95%CI 1.046-1.163, P<0.001) and estimated glomerular filtration (eGFR)<60 ml·min^-1·(1.73 m²)^-1 (HR=3.725, 95%CI 1.639-8.462, P=0.002) were the independent risk factors for poor renal prognosis in patients with IgAN. Conclusions The clinicopathological features of IgAN patients with anemia are relatively serious, and the renal cumulative survival rate is lower. Anemia, tubular atrophy/interstitial fibrosis (T1/2), glomerular segmental sclerosis/adhesion (S1), hypertension, increased urinary protein and eGFR<60 ml·min^-1·(1.73 m²)^-1 are the independent risk factors for poor renal prognosis in patients with IgAN.

Objective: To investigate the effect and mechanism of renal fibrosis after macrophage depletion in C3-deficient unilateral ureteral obstruction mice. Methods: Renal interstitial fibrosis model was established by unilateral ureteral obstruction (UUO) in male C3-deficient mice and age-matched C57BL/6 WT mice (8-12 weeks of age). Mice were randomly divided into 4 groups, including sham operation in wild type group (WT/sham) (n=18), UUO operation in wild type group (WT/UUO) (n=18), sham operation in C3-deficient group (C3KO/sham) (n=18), and UUO operation in C3-deficient group (C3KO/UUO) (n=18). The expression of complement C3 was detected by immunohistochemical staining and renal interstitial macrophages were assessed by immunofluorescence staining. Tubulointerstitial fibrosis was observed by both HE staining and Masson staining after 14 days of UUO. Collagen accumulation and score of tubulointerstitial injury were obtained. Wild type and C3-deficient UUO mice were treated by liposome clodronate in early or late stage respectively and then interstitially infiltrated macrophages and renal fibrosis were analysed. Mice were sacrificed randomly at 3,7,14 days after UUO and obstructed kidneys were collected. Macrophage phenotype was detected by double-labeling immunofluorescence with F4/80 and iNOS for the M1, F4/80 and CD206 for the M2 macrophage subpopulation. iNOS, Arg-1 and CD206 were also detected by western blot. Results: C3 deficient mice exhibited attenuated renal fibrosis, reduced collagen accumulation and tubulointerstitial injury score compared with WT mice (P<0.01). Meanwhile, macrophage depletion in early or late stage of UUO reduced renal fibrosis in WT mice, but had no effect on C3-deficient UUO mice. Decreased accumulation of M1 macrophages and expression of iNOS, increased accumulation of M2 macrophages and expression of Arg-1, CD206 were found in C3 deficient mice compared with WT mice in early stage of UUO (P<0.01). Conclusion Renal fibrosis is not reduced after depletion of macrophages in C3 deficient UUO mice due to the altered macrophage polarization.

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 generate various types of diabetic retinopathy ( DR) fundus images automatically by computer vision algorithm. Methods A method based on deep learning to generate fundus images was proposed,which used the vascular vein of the fundus image and the text description of lesions as the constraint conditions to generate fundus image. The text description was encoded by using a long short-term memory ( LSTM) , and the vascular vein image was encoded by a convolutional neural network (CNN). Then the encoded information was combined and used to generate a fundus image by generative adversarial networks ( GAN ) . Results The results showed that the algorithm can generate realistic fundus images. However, the image detail features were not obvious because the text-encoded recurrent neural network ( RNN ) loss function did not converge well. Conclusions Using the GAN can generate realistic DR fundus images, which has certain application value in expanding medical data. However,the generation of detail features in small areas still needs improvement.

Objective To propose a model for accurately segmenting blood vessels in medical fundus images. Methods The algorithm of deep learning was used for the task of automatic segmentation of blood vessels in retinal fundus images in this paper. An improved vascular segmentation algorithm was proposed. For the different types of blood vessels in the fundus image, a multi-scale network structure was designed to extract features of both main blood vessels and vessel branches at the same time. Results The segmentation model proposed could achieve good results on all kinds of blood vessels even if they have low contrast and few obvious characteristics. The automatic vessel segmentation of retinal fundus images was implemented, and the performance of the model was evaluated through multiple evaluation indexes which are widely used in the field of medical image segmentation in the test stage. A specificity of 0. 9829,an F1 score of 0. 7944,a G-mean of 0. 8748,an Matthews correlation coefficient(MCC) of 0. 7764 and a specificity of 0. 9782 were obtained on the DRIVE dataset. An F1 score of 0. 7735 and an MCC of 0. 7573 were obtained on the STARE data set. Conclusions The proposed method has a great improvement over the segmentation algorithm of the same task. Furthermore,the results generated by our model can achieve comparable effect with the segmentation of human doctor.