RESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
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.
RESUMO
The precise estimation of blood vessel centerline and width is a prerequisite condition for the quantitative and visualized diagnosis of blood vessel disease in fundus images. In this paper, a retinal blood vessel segmentation algorithm based on centerline extraction is proposed. According to the characteristics of the fundus image and retinal blood vessels, the image is convoluted with the masks of discrete Gaussian partial derivative kernels. The centerline is determined by differential geometric properties of the blood vessels and the width is also calculated. The precision of our method can reach sub-pixel level with a fast computation speed. The experiments on several kinds of fundus images showed that the method worked quickly and accurately.
Assuntos
Humanos , Algoritmos , Fundo de Olho , Aumento da Imagem , Métodos , Vasos RetinianosRESUMO
Placido disk is widely used in corneal topography. In order to solve the problem that the convex of the corneal can not be precisely located in the Placido corneal topography system, an algorithm of corneal reconstruction based on the Placido disk was introduced. The key of this method is the calculation of radius of corneal convex by using the innermost ring data. Based on image analysis result, we precisely calculated the radius of corneal convex iteratively by connecting the convex and the first ring using a circle, and then calculated the location of all the reflect point and its power. At last we created the pseudo color map of the human corneal. The corneal was simulated by using standard steel sphere, and the calculating errors of the result were all below 0.25D. It showed that the algorithm used in this work could get relatively accurate powers and would have fair stability.
Assuntos
Humanos , Algoritmos , Córnea , Patologia , Topografia da Córnea , Métodos , Padrões de Referência , Aberrações de Frente de Onda da Córnea , Processamento de Imagem Assistida por ComputadorRESUMO
Objective To discuss the application effect of task-driven basic nursing probation based on the action research. Methods Using the frame of Lewin's action research, with random sampling, we selected a class for the study, for the first time in the traditional training model, and the second time in the task-driven model based on the action research. and information was collected according to the interviews and diary records, narrative description was used for records of the results. Results Action research promoted changes in basic nursing probation model, constructed knowledge, ability and improved various kinds of ability of nursing students. Conclusions The task-driven probation model improved the quality of clinic practice, which proved to be effective.
RESUMO
In the laser ablation refractive surgeries, the corneal ablation model and its realization by laser are difficult to design. They greatly affect the results of those surgeries. This paper firstly presents a mathematical model for corneal ablation to correct the refractive error of spherical myopia, and then gives a technique of planning laser focus positions on cornea to realize the ablation model. Based on the principle of the correction for spherical myopia using small beam laser, our excimer laser corneal surgery system has been able to perform such refractive surgery. Now the corneal surgery system has been applied to clinical practice. Thirty-nine eyes with spherical myopia underwent LASIK using this kind of system. Their refractive states have been greatly improved. Preoperatively, the mean sphere was -5.57+/-2.95 D and the mean uncorrected visual acuity 0.12+/-0.07. One day after surgery, the mean sphere was -0.03+/-0.57 D and the mean uncorrected visual acuity 0.90+/-0.29. One month after surgery, the mean sphere was -0.68+/-0.98 D, and the mean uncorrected visual acuity 1.0+/-0.26.
Assuntos
Humanos , Lasers de Excimer , Modelos Biológicos , Miopia , Cirurgia Geral , Ceratectomia Fotorrefrativa , Métodos , Resultado do Tratamento , Acuidade VisualRESUMO
The excimer laser diopter correction has proven to be efficient and safe. This paper presents the principle of excimer laser refractive surgery. Based on analyzing the mathematics model of the human eye cornea, the authors have proposed a new model which can be used to proceed the myopia, hyperopia, astigmatism diopter correction. Also studied were the excimer laser's ablation mechanism and the flying-spot scanning technology. The research results have been directly applied to Ophthalmic excimer laser system. The correction of diopter is well improved.