SERR-U-Net: Squeeze-and-Excitation Residual and Recurrent Block-Based U-Net for Automatic Vessel Segmentation in Retinal Image. (10th August 2021)

• Record Type: Journal Article
• Authors: Wang, Jinke; Li, Xiang; Lv, Peiqing; Shi, Changfa
• Other Names: Tsui Po-Hsiang Academic Editor.
• Is Part Of: Computational and mathematical methods in medicine. Volume 2021(2021)
• Publication Date: 2021-08-10
• Subjects: Medicine -- Computer simulation -- Periodicals; Medicine -- Mathematical models -- Periodicals; 610.11
• DOI: 10.1155/2021/5976097
• Languages: English
• ISSNs: 1748-670X

Abstract

Abstract : Background and Objective . Accurate segmentation of retinal vessels is considered as an important prerequisite for computer-aided diagnosis of ophthalmic diseases, diabetes, glaucoma, and other diseases. Although current learning-based methods have greatly improved the performance of retinal vessel segmentation, the accuracy could not meet the requirements of clinical assistance yet. Methods . A new SERR-U-Net framework for retinal vessel segmentation is proposed, which leverages technologies including Squeeze-and-Excitation (SE), residual module, and recurrent block. First, the convolution layers of encoder and decoder are modified on the basis of U-Net, and the recurrent block is used to increase the network depth. Second, the residual module is utilized to alleviate the vanishing gradient problem. Finally, to derive more specific vascular features, we employed the SE structure to introduce attention mechanism into the U-shaped network. In addition, enhanced super-resolution generative adversarial networks (ESRGANs) are also deployed to remove the noise of retinal image. Results . The effectiveness of this method was tested on two public datasets, DRIVE and STARE. In the experiment of DRIVE dataset, the accuracy and AUC (area under the curve) of our method were 0.9552 and 0.9784, respectively, and for SATRE dataset, 0.9796 and 0.9859 were achieved, respectively, which proved a high accuracy and promising prospect on clinical assistance. Conclusion . An improved U-Net network combining SE, ResNet, and recurrent technologies is developed for automatic vessel segmentation from retinal image. This new model enables an improvement on the accuracy compared to learning-based methods, and its robustness in circumvent challenging cases such as small blood vessels and intersection of vessels is also well demonstrated and validated.