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

Lei Mou, Yitian Zhao, Li Chen, Jun Cheng, Zaiwang Gu, Huaying Hao, Hong Qi, Yalin Zheng, Alejandro F. Frangi, Jiang Liu

Abstract

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.
BibTeX
@inproceedings{mou2019cs,
  author = {Lei Mou and Yitian Zhao and Li Chen and Jun Cheng and Zaiwang Gu and Huaying Hao and Hong Qi and Yalin Zheng and Alejandro F. Frangi and Jiang Liu},
  title = {{CS-Net: Channel and Spatial Attention Network for Curvilinear Structure Segmentation}},
  booktitle = {International Conference on Medical Image Computing and Computer-Assisted Intervention},
  year = {2019},
  doi = {10.1007/978-3-030-32239-7\_80},
}

Loading related content...

Figure