Abstract
Retinal blood vessels are the basis for clinical diagnosis of some diseases. Achieving automatic retinal vessel segmentation from fundus images is an important and challenging work. In this paper, a neural network architecture based on the Dense U-net using Inception module is proposed for retinal vessel segmentation. First, the skip connections in traditional U-net are replaced with Dense Block to achieve full fusion of features from shallow layers to deep layers. Then, the Inception module is applied to supersede the traditional convolution operation. Thus, vessel features corresponding to the convolution kernels of different sizes can be extracted. Finally, Generative Adversarial Networks (GAN) are adopted in the training phase. The Dense U-net using Inception module is treated as the generator of GAN, and a multilayer neural network is created as the discriminator of GAN. The generator and discriminator are trained alternately. The loss function is a combination of segmentation loss and GAN loss. So that segmentation results can be fitted to the ground truth from both pixel value and pixel distribution. The algorithm proposed in this paper is verified on the public Digital Retinal Images for Vessel Extraction (DRIVE) dataset, where the Dice rate reaches 82.15%, and the AU-ROC and AU-PR reach 0.9772 and 0.9058, respectively. Experiments show that the proposed algorithm is effective in realizing automatic retinal vessel segmentation.
Highlights
Retinal blood vessels contain considerable information which related to human health
The fundus images have the following characteristics: low contrast between vessel and background, serious interference in the lesion area and complex vascular structure which bring a lot of challenge to achieve retinal vessel segmentation [5]
Many automatic segmentation algorithms for retinal vessels have been proposed for Computer-Aided Diagnosis (CAD)
Summary
Retinal blood vessels contain considerable information which related to human health. Observing the morphological structure of the retinal blood vessels in fundus images is used in the screening of retinal vascular diseases and in the auxiliary diagnosis of other diseases, such as stroke [1], hypertension [2], diabetes-induced retinopathy [3], and glaucoma [4]. The fundus images have the following characteristics: low contrast between vessel and background, serious interference in the lesion area and complex vascular structure which bring a lot of challenge to achieve retinal vessel segmentation [5]. The primary method of retinal vessel segmentation is manual annotation by professional doctors. Many automatic segmentation algorithms for retinal vessels have been proposed for Computer-Aided Diagnosis (CAD). Achieving automatic retinal vessel segmentation can reduce the doctors’ workload and avoid the subjective influence from different doctors on the segmentation results
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have