CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation

Mou, Lei, Zhao, Yitian, Chen, Li, Cheng, Jun, Gu, Zaiwang, Hao, Huaying, Qi, Hong, Zheng, Yalin ORCID: 0000-0002-7873-0922, Frangi, Alejandro and Liu, Jiang
(2019) CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation. In: 22nd International Conference, 2019-10-13 - 2019-10-17, Shenzhen, China.

[img] Text
Mou2019_Chapter_CS-NetChannelAndSpatialAttenti.pdf - Author Accepted Manuscript

Download (2MB) | Preview


The detection of curvilinear structures in medical images, e.g., blood vessels or nerve fibers, is important in aiding management of many diseases. In this work, we propose a general unifying curvilinear structure segmentation network that works on different medical imaging modalities: optical coherence tomography angiography (OCT-A), color fundus image, and corneal confocal microscopy (CCM). Instead of the U-Net based convolutional neural network, we propose a novel network (CS-Net) which includes a self-attention mechanism in the encoder and decoder. Two types of attention modules are utilized - spatial attention and channel attention, to further integrate local features with their global dependencies adaptively. The proposed network has been validated on five datasets: two color fundus datasets, two corneal nerve datasets and one OCT-A dataset. Experimental results show that our method outperforms state-of-the-art methods, for example, sensitivities of corneal nerve fiber segmentation were at least 2% higher than the competitors. As a complementary output, we made manual annotations of two corneal nerve datasets which have been released for public access.

Item Type: Conference or Workshop Item (Unspecified)
Uncontrolled Keywords: Curvilinear structure, Segmentation, Encoder and decoder
Depositing User: Symplectic Admin
Date Deposited: 08 Jun 2020 08:50
Last Modified: 18 Jan 2023 23:50
DOI: 10.1007/978-3-030-32239-7_80
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3089651