文献类型：期刊文献

英文题名：Fundus Retinal Vessels Image Segmentation Method Based on Improved U-Net

作者：Han, J.[1];Wang, Y.[1];Gong, H.[1]

通讯作者：Wang, Y[1]

机构：[1]Beijing Union Univ, Smart City Coll, Beijing 100101, Peoples R China

第一机构：北京联合大学继续教育学院

通讯机构：[1]corresponding author), Beijing Union Univ, Smart City Coll, Beijing 100101, Peoples R China.|[1141733]北京联合大学继续教育学院;[11417]北京联合大学;

年份：2022

卷号：43

期号：6

起止页码：628-639

外文期刊名：IRBM

收录：;Scopus(收录号：2-s2.0-85126542428);WOS:【SCI-EXPANDED(收录号:WOS:000917956100011)】；

基金：Funding This work has been supported by: National Natural Science Foundation of China under Grant 61872042 and 61572077; Key project of Science and Technology Plan of Beijing Municipal Educa-tion Commission under Grant KZ201911417048.

语种：英文

外文关键词：U-Net; Fundus retinal blood vessels; Non-local; Attention mechanism; Medical image segmentation

摘要：Objectives: Although the segmentation of retinal vessels in the fundus is of great significance for screening and diagnosing retinal vascular diseases, it remains difficult to detect the low contrast and the information around the lesions provided by retinal vessels in the fundus and to locate and segment micro-vessels in the fine-grained area. To overcome this problem, we propose herein an improved U-Net segmentation method NoL-UNet.Material and methods: This work introduces NoL-UNet. First of all, the ordinary convolution block of the U-Net network is changed to random dropout convolution blocks, which can better extract the relevant features of the image and effectively alleviate the network overfitting. Next, a NoL-Block attention mechanism added to the bottom of the encoding-decoding structure expands the receptive field and enhances the correlation of pixel information without increasing the number of parameters.Results: The proposed method is verified by applying it to the fundus image datasets DRIVE, CHASE_DB1, and HRF. The AUC for DRIVE, CHASE_DB1 and HRF is 0.9861, 0.9891 and 0.9893, Se for DRIVE, CHASE_DB1 and HRF is 0.8489, 0.8809 and 0.8476, and the Acc for DRIVE, CHASE_DB1 and HRF is 0.9697, 0.9826 and 0.9732, respectively. The total number of parameters is 1.70M, and for DRIVE, it takes 0.050s to segment an image.