CS-Net: Channel and spatial attention network for curvilinear structure segmentation

Mou，Lei1,2; Zhao，Yitian2; Chen，Li1; Cheng，Jun2; Gu，Zaiwang2; Hao，Huaying2; Qi，Hong3; Zheng，Yalin4; Frangi，Alejandro2,5; Liu，Jiang2,6

10.1007/978-3-030-32239-7_80

2019

0302-9743

1611-3349

LECT NOTES ARTIF INT

11764 LNCS

721-730

GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND

SPRINGER INTERNATIONAL PUBLISHING AG

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.

Curvilinear structure Encoder and decoder Segmentation

其他

英语

CPCI-S ; EI

National Science Foundation Program of China[61601029][61773297]

Computer Science ; Engineering ; Microscopy ; Neurosciences & Neurology ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging

Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Engineering, Biomedical ; Microscopy ; Neuroimaging ; Imaging Science & Photographic Technology ; Radiology, Nuclear Medicine & Medical Imaging

WOS:000548734200080

20194807768305

Medical computing ; Medical imaging ; Decoding ; Optical tomography ; Network coding ; Image segmentation ; Neural networks ; Channel coding

Biomedical Engineering:461.1 ; Biological Materials and Tissue Engineering:461.2 ; Information Theory and Signal Processing:716.1 ; Data Communication, Equipment and Techniques:722.3 ; Data Processing and Image Processing:723.2 ; Computer Applications:723.5 ; Optical Devices and Systems:741.3 ; Imaging Techniques:746

2-s2.0-85075630946

Scopus

1.School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan,China
2.Cixi Institute of Biomedical Engineering,Chinese Academy of Sciences,Ningbo,China
3.Department of Ophthalmology,Peking University Third Hospital,Beijing,China
4.Department of Eye and Vision Science,University of Liverpool,Liverpool,United Kingdom
5.School of Computing,University of Leeds,Leeds,United Kingdom
6.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,China

Mou，Lei,Zhao，Yitian,Chen，Li,et al. CS-Net: Channel and spatial attention network for curvilinear structure segmentation[C]. GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND:SPRINGER INTERNATIONAL PUBLISHING AG,2019:721-730.