Home    About Journal    Editorial Board    Instruction    Subscribe    Download    Messages Board    Contact Us    中文
  May. 7, 2025  
Quick Search
Chinese Journal of Biomedical Engineering  2019, Vol. 38 Issue (1): 1-8    DOI: 10.3969/j.issn.0258-8021.2019.01.001
Regular Papers Current Issue | Archive | Adv Search |
Blood Vessel Segmentation of Fundus Images Based on Improved U Network
Gao Hongjie1, Qiu Tianshuang1#*, Chou Yuanting1, Zhou Ming2, Zhang Xiaobo2
1Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian 116024, Liaoning, China;
2Department of Ophthalmology, Zhongshan Hospital Affiliated to Dalian University, Dalian 116001, Liaoning, China
Download: PDF (5662 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The blood vessel segmentation of fundus images is the basis of computer-aided diagnosis of ophthalmology and other related diseases. Early diagnosis and monitoring of diseases such as diabetic retinopathy, hypertension and arteriosclerosis can be performed by segmenting the vascular structure in the fundus image. However, existing segmentation algorithms are challenged with low accuracy and low sensitivity. This paper proposed an improved U-Net fundus image segmentation algorithm based on the basic theory of deep learning. Firstly, the problem of less fundus data set was solved by reducing the number of pooling layers and upsampling layers of the traditional U-Net. Secondly, the use efficiency of the feature was improved by changing the traditional convolutional layer serial connection method to the residual mapping. Finally, the batch normalization and PReLU activation functions are added between the convolutional layers to optimize the network, which further improved the network performance. This paper conducted experiments on two public fundus databases, DRIVE and CHASE_DB1. The 160 000 image blocks were randomly extracted from each database and are sent into the improved network for training and testing. The sensitivity, accuracy and AUC (area under the ROC curve) of the algorithm were 2.47%, 0.21% and 0.35%, higher than those of the existing contrasted algorithms. The proposed algorithm improves the low accuracy and low sensitivity of small blood vessels segmentation in fundus images, and segmented small blood vessels better with low contrast.
Key wordsfundus image      vessel segmentation      U-Net      network optimization     
Received: 01 August 2018     
PACS:  R318  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Gao Hongjie
Qiu Tianshuang
Chou Yuanting
Zhou Ming
Zhang Xiaobo
Cite this article:   
Gao Hongjie,Qiu Tianshuang,Chou Yuanting, et al. Blood Vessel Segmentation of Fundus Images Based on Improved U Network[J]. Chinese Journal of Biomedical Engineering, 2019, 38(1): 1-8.
URL:  
http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2019.01.001     OR     http://cjbme.csbme.org/EN/Y2019/V38/I1/1
Copyright © Editorial Board of Chinese Journal of Biomedical Engineering
Supported by:Beijing Magtech