Abstract
Retinal vessel segmentation plays a vital role in computer-aided diagnosis and treatment of retinal diseases. Considering the low contrast between retinal vessels and the background image, complex structural information as well as blurred boundaries between tissue and blood vessels, the retinal vessel image segmentation algorithm based on the improved U-Net network is proposed in the paper. The algorithm introduces an attention mechanism and densely connected network into the original U-Net network and realizes the automatic segmentation of retinal vessels. According to the test results of the algorithm on commonly-used datasets of the DRIVE and STARE fundus images, respectively, the accuracy is 0.9663 and 0.9684; the sensitivity is 0.8075 and 0.8437; the specificity is 0.9814 and 0.9762; the AUC values are 0.9846 and 0.9765; and the F-measures are 0.8203 and 0.8419, respectively. In the paper, the Attention-Dense-UNet (AD-UNet) algorithm is applied to segment human bulbar conjunctival micro-vessels. The experimental results show that the algorithm can achieve ideal segmentation results.
Highlights
Retinal vasculopathy of the human body can reflect the severity of cardiovascular diseases such as hypertension, coronary heart disease and diabetes
Retinal vessel segmentation is usually performed by manual segmentation, which is influenced by human factors, requires additional time, and cannot meet the requirements of large-scale fundus image processing
Finding an efficient and accurate fundus image segmentation algorithm through computer assistance to realize automatic segmentation technology for vessel images is significant for improving the diagnosis efficiency of vessel diseases and reducing medical costs
Summary
Retinal vasculopathy of the human body can reflect the severity of cardiovascular diseases such as hypertension, coronary heart disease and diabetes. Holistically-nested edge detection (HED); Fig. 7 (f) is the segmentation result of deep retinal image understanding (DRIU); and Fig. 7 (g) is the segmentation result of U-Net. As observed for the first and second fundus images, for the images of fundus with lesions analyzed by the algorithm proposed in the paper, tiny and coarse blood vessels show better segmentation performance and stronger robustness in terms of segmentation results than the ground truth for complex areas of cross blood vessels and low contrast tiny blood vessels.By contrast,the V-GAN algorithm is affected by lesions: a fracture phenomenon appears in the vessel segmentation results, and more micro-vessel details are lost. The superiority of this algorithm in the segmentation of complex fundus vessel structures is fully reflected
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
