Retinal Vessel Segmentation via Adversarial Learning and Iterative Refinement

作     者：顾闻 徐奕 GU Wen;XU Yi

作者机构：School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China 

出 版 物：《Journal of Shanghai Jiaotong university(Science)》 (上海交通大学学报（英文版）)

年 卷 期：2024年第29卷第1期

页      面：73-80页

核心收录：

学科分类：08[工学] 081101[工学-控制理论与控制工程] 0811[工学-控制科学与工程] 081102[工学-检测技术与自动化装置] 

主　　题：medical image processing retinal image segmentation adversarial learning iterative refinement 

摘      要：Retinal vessel segmentation is a challenging medical task owing to small size of dataset,micro blood vessels and low image *** address these issues,we introduce a novel convolutional neural network in this paper,which takes the advantage of both adversarial learning and recurrent neural *** iterative design of network with recurrent unit is performed to refine the segmentation results from input retinal image *** unit preserves high-level semantic information for feature reuse,so as to output a sufficiently refined segmentation map instead of a coarse ***,an adversarial loss is imposing the integrity and connectivity constraints on the segmented vessel regions,thus greatly reducing topology errors of *** experimental results on the DRIVE dataset show that our method achieves area under curve and sensitivity of 98.17%and 80.64%,*** method achieves superior performance in retinal vessel segmentation compared with other existing state-of-the-art methods.