Segmentation of retinal image vessels based on fully convolutional network with depthwise separable convolution and channel weighting.
10.7507/1001-5515.201801054
- Author:
Lei GENG
1
;
Ling QIU
1
;
Jun WU
2
,
3
;
Zhitao XIAO
1
;
Fang ZHANG
1
Author Information
1. Tianjin Polytechnic University, School of Electronics and Information Engineering, Tianjin 300387, P.R.China;Tianjin Key Laboratory of Optoelectronic Detection and Systems, Tianjin 300387, P.R.China.
2. Tianjin Polytechnic University, School of Electronics and Information Engineering, Tianjin 300387, P.R.China;Tianjin Key Laboratory of Optoelectronic Detection and Systems, Tianjin 300387, P.R.China.zhenkongwujun@
3. com.
- Publication Type:Journal Article
- Keywords:
channel weighting;
depthwise separable convolution;
fully convolutional network;
segmentation of retinal blood vessels
- From:
Journal of Biomedical Engineering
2019;36(1):107-115
- CountryChina
- Language:Chinese
-
Abstract:
Diseases such as diabetes and hypertension can lead to change the shape of the retinal blood vessels. Segmentation of fundus images is a key step in the process of quantitative analysis of the disease, which is instructive in the analysis and diagnosis of clinical diseases. In this paper, a method for the segmentation of retinal image vessels based on fully convolutional network (FCN) with depthwise separable convolution and channel weighting is presented. Firstly, CLAHE and Gamma correction of the green channel of the fundus image are used to enhance the contrast. Then, in order to adapt to network training, the enhanced image is divided into patches to expand the data. Finally, the depthwise separable convolution instead of the standard convolution method is used to increase the network width. Meanwhile, the channel weighting module is introduced to explicitly model the relationship between the characteristic channels in order to improve the distinguishability of the features. The combination of them is applied to the FCN and the results of expert manual identification are used to supervise the experiment on the DRIVE database. The results show that the segmentation accuracy of the proposed method in DRIVE database reached 0.963 0 and AUC reached 0.983 1. The segmentation accuracy in STARE database reached 0.962 0 and AUC achieved 0.983 0. To some extent, the proposed method has better feature resolution and better segmentation performance.
