Automated retinal vessel segmentation technology has become an important tool for disease screening and diagnosis in clinical medicine. However, most of the available methods of retinal vessel segmentation still have problems such as poor accuracy and low generalization ability. This is because the symmetrical and asymmetrical patterns between blood vessels are complicated, and the contrast between the vessel and the background is relatively low due to illumination and pathology. Robust vessel segmentation of the retinal image is essential for improving the diagnosis of diseases such as vein occlusions and diabetic retinopathy. Automated retinal vein segmentation remains a challenging task. In this paper, we proposed an automatic retinal vessel segmentation framework using deep fully convolutional neural networks (FCN), which integrate novel methods of data preprocessing, data augmentation, and full convolutional neural networks. It is an end-to-end framework that automatically and efficiently performs retinal vessel segmentation. The framework was evaluated on three publicly available standard datasets, achieving F1 score of 0.8321, 0.8531, and 0.8243, an average accuracy of 0.9706, 0.9777, and 0.9773, and average area under the Receiver Operating Characteristic (ROC) curve of 0.9880, 0.9923 and 0.9917 on the DRIVE, STARE, and CHASE_DB1 datasets, respectively. The experimental results show that our proposed framework achieves state-of-the-art vessel segmentation performance in all three benchmark tests.

Accurate segmentation of retinal vessels is a basic step in Diabetic retinopathy(DR) detection. Most methods based on deep convolutional neural network (DCNN) have small receptive fields, and hence they are unable to capture global context information of larger regions, with difficult to identify pathological. The final segmented retina vessels contain more noise with low classificaiton accuracy. Therefore, in this paper, we propose a DCNN structure named as D-Net. In the encoding phase, we reduced the loss of feature information by reducing the downsampling factor, which reduced the difficulty of tiny thin vessels segmentation. We use the combined dilated convolution to effectively enlarges the receptive field of the network and alleviate the ‘grid problem’ that exists in the standard dilated convolution. In the proposed Multi-Scale Information Fusion module (MSIF), parallel convolution layers with different dilation rates are used, so that the model can obtain more dense feature information and better capture retinal vessel information of different sizes. In the decoding module, the skip layer connection is used to propagate context information to higher resolution layers, so as to prevent low-level information from passing the entire network structure. Finally, our method was verified on DRIVE, STARE and CHASE dataset. The experimental results show that our network structure outperforms some state-of-art method, such as N4-fields, U-Net, and DRIU in terms of accuracy, sensitivity, specificity, and AUCROC. Particularly, D-Net outperforms U-Net by 1.04 %, 1.23 % and 2.79 % in DRIVE, STARE, and CHASE three dataset, respectively.

Glaucoma is a chronic eye disease that causes loss of vision and it is irreversible. Accurate segmentation of optic disc and optic cup is a basic step in screening glaucoma. The most existing deep convolutional neural network (DCNN) methods have insufficient feature information extraction, and hence they are susceptible to pathological regions and low-quality images, with have poor ability to restore context information. Finally, the accuracy of the model segmentation is low. In this paper, we propose GL-Net, a multi-label DCNN model that combines the generative adversarial networks. GL-Net consists of two network structures including a Generator and a Discriminator. In the Generator, we use skip connection to promote the fusion of low-level feature information and high-level feature information, which alleviates the difficulty of restoring detailed feature information during upsampling, and reduces the downsampling factor, effectively alleviating excessive feature information loss. In the loss function, we add the L ¹ distance function and the cross-entropy function to prevent the mode collapse when the model is trained, which makes the segmentation result more accurate. We use transfer learning and data augmentation to alleviate the problem of insufficient data and over-fitting of the model during training. Finally, GL-Net was verified on DRISHTI-GS1 dataset. The experimental results show that GL-Net outperforms some state-of-the-art method, such as M-Net, Stack-U-Net, RACE-net, and BCRF in terms of F1 and boundary distance localization error (BLE). Particularly, in the optic cup segmentation, GL-Net outperforms RACE-net by 3.5% and 4.16 pixels in terms of F1 and BLE, respectively.

Single Shot MultiBox Detector (SSD) has achieved good results in object detection but there are problems such as insufficient understanding of context information and loss of features in deep layers. In order to alleviate these problems, we propose a single-shot object detection network Context Perception-SSD (CP-SSD). CP-SSD promotes the network’s understanding of context information by using context information scene perception modules, so as to capture context information for objects of different scales. Deep layer feature map used semantic activation module, through self-supervised learning to adjust the context feature information and channel interdependence, and enhance useful semantic information. CP-SSD was validated on benchmark dataset PASCAL VOC 2007. The experimental results show that, compared with SSD, the mean Average Precision (mAP) of the CP-SSD detection method reaches 77.8%, which is 0.6% higher than that of SSD, and the detection effect was significantly improved in images with difficult to distinguish the object from the background.