CSU-Net: A Context Spatial U-Net for Accurate Blood Vessel Segmentation in Fundus Images

Blood vessel segmentation in fundus images is a critical procedure in the diagnosis of ophthalmic diseases. Recent deep learning methods achieve high accuracy in vessel segmentation but still face the challenge to segment the microvascular and detect the vessel boundary. This is due to the fact that...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2021-04, Vol.25 (4), p.1128-1138
Main Authors: Wang, Bo, Wang, Shengpei, Qiu, Shuang, Wei, Wei, Wang, Haibao, He, Huiguang
Format: Article
Language:English
Subjects:
Artificial neural networks
Biomedical imaging
blood vessel segmentation
Blood vessels
Coders
Context
Convolution
CSU-Net
Deep learning
Entropy
Feature extraction
feature fusion
Fundus images
Image processing
Image segmentation
Machine learning
Medical imaging
Microvasculature
Modules
Neural networks
Receptive field
Spatial data
structure loss
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Blood vessel segmentation in fundus images is a critical procedure in the diagnosis of ophthalmic diseases. Recent deep learning methods achieve high accuracy in vessel segmentation but still face the challenge to segment the microvascular and detect the vessel boundary. This is due to the fact that common Convolutional Neural Networks (CNN) are unable to preserve rich spatial information and a large receptive field simultaneously. Besides, CNN models for vessel segmentation usually are trained by equal pixel level cross-entropy loss, which tend to miss fine vessel structures. In this paper, we propose a novel Context Spatial U-Net (CSU-Net) for blood vessel segmentation. Compared with the other U-Net based models, we design a two-channel encoder: a context channel with multi-scale convolution to capture more receptive field and a spatial channel with large kernel to retain spatial information. Also, to combine and strengthen the features extracted from two paths, we introduce a feature fusion module (FFM) and an attention skip module (ASM). Furthermore, we propose a structure loss, which adds a spatial weight to cross-entropy loss and guide the network to focus more on the thin vessels and boundaries. We evaluated this model on three public datasets: DRIVE, CHASE-DB1 and STARE. The results show that the CSU-Net achieves higher segmentation accuracy than the current state-of-the-art methods.
ISSN:2168-2194
2168-2208
DOI:10.1109/JBHI.2020.3011178