A Multi-branch Hybrid Transformer Network for Corneal Endothelial Cell Segmentation

Zhang，Yinglin1,6; Higashita，Risa1,5; Fu，Huazhu7; Xu，Yanwu8; Zhang，Yang1; Liu，Haofeng1; Zhang，Jian6; Liu，Jiang1,2,3,4

10.1007/978-3-030-87193-2_10

2021

0302-9743

1611-3349

LECT NOTES ARTIF INT

12901 LNCS

99-108

Corneal endothelial cell segmentation plays a vital role in quantifying clinical indicators such as cell density, coefficient of variation, and hexagonality. However, the corneal endothelium’s uneven reflection and the subject’s tremor and movement cause blurred cell edges in the image, which is difficult to segment, and need more details and context information to release this problem. Due to the limited receptive field of local convolution and continuous downsampling, the existing deep learning segmentation methods cannot make full use of global context and miss many details. This paper proposes a Multi-Branch hybrid Transformer Network (MBT-Net) based on the transformer and body-edge branch. Firstly, we use the convolutional block to focus on local texture feature extraction and establish long-range dependencies over space, channel, and layer by the transformer and residual connection. Besides, we use the body-edge branch to promote local consistency and to provide edge position information. On the self-collected dataset TM-EM3000 and public Alisarine dataset, compared with other State-Of-The-Art (SOTA) methods, the proposed method achieves an improvement.

Corneal endothelial cell segmentation Deep learning Multi-branch Transformer

第一 ; 通讯

英语

EI

20214110990350

Cytology ; Deep learning ; Endothelial cells ; Image segmentation ; Medical imaging ; Textures

Biomedical Engineering:461.1 ; Biological Materials and Tissue Engineering:461.2 ; Ergonomics and Human Factors Engineering:461.4 ; Biology:461.9 ; Information Theory and Signal Processing:716.1 ; Imaging Techniques:746

2-s2.0-85116454101

Scopus

1.Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
2.Cixi Institute of Biomedical Engineering,Chinese Academy of Sciences,Ningbo,China
3.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation,Department of Computer Science and Engineering,Southern University of Science and Technology,Shenzhen,518055,China
4.Research Institute of Trustworthy Autonomous Systems,Southern University of Science and Technology,Shenzhen,518055,China
5.Tomey Corporation,Nagoya,451-0051,Japan
6.Global Big Data Technologies Centre,University of Technology Sydney,Ultimo,Australia
7.Inception Institute of Artificial Intelligence,Abu Dhabi,United Arab Emirates
8.Intelligent Healthcare Unit,Baidu, Beijing,100085,China

Zhang，Yinglin,Higashita，Risa,Fu，Huazhu,et al. A Multi-branch Hybrid Transformer Network for Corneal Endothelial Cell Segmentation[C],2021:99-108.