Multi-Scale Retina Vessel Segmentation in OCTA with a Vascular Connectivity Module in the Convolutional Neural Network

Junjie Lin1; Xingyue Wang1; Jiansheng Fang1; Na Zeng1; Xiaoxi Lu1; Jingqi Huang1; Yan Hu1; Heng Meng2; Jiang Liu1

10.1109/ISBI53787.2023.10230688

2023

1945-7928

978-1-6654-7359-0

2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)

2023-April

1-5

18-21 April 2023

Cartagena, Colombia

The segmentation of retinal blood vessels in optical coherence tomography angiography (OCTA) is of great importance for the diagnosis and treatment of various diseases such as diabetic retinopathy and dementia. Currently, UNet is one of the classical and popular networks in the segmentation field. Although significant progress has been achieved with the rapid development of UNet-based neural networks, some critical issues in retinal vessel segmentation remain unsolved. First, blood vessels in OCTA show large variations in length and width, imposing challenges in identifying the small vessels at the ends. Second, the vessels should be continuous and smooth, and the capillaries should not detach from the main vessels. Nevertheless, the current UNet-based neural networks lack the capability to preserve the shape of prior information. This study introduces a modified UNet framework for retinal vessel segmentation using OCTA images. First, multi-scale learning modules are employed to improve the ability of the network to extract multi-scale vessel objects. Then, we introduce a novel vascular connectivity module in the network to incorporate prior shape information. The proposed method id extensively evaluated on a public dataset named OCTA500, with significantly improved performance compared with the state-of-the-art methods.

vessel segmentation UNet optical coherence tomography angiography multi-scale vascular connectivity

第一

CPCI-S ; EI

WOS:001062050500365

20233914806136

Blood ; Blood vessels ; Convolutional neural networks ; Eye protection ; Image segmentation ; Microcirculation ; Ophthalmology ; Optical tomography

Biomedical Engineering:461.1 ; Biological Materials and Tissue Engineering:461.2 ; Medicine and Pharmacology:461.6 ; Optical Devices and Systems:741.3 ; Imaging Techniques:746 ; Accidents and Accident Prevention:914.1

IEEE

1.Research Institute of Trustworthy Autonomous Systems and Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2.Department of Neurology, The First Affiliated Hospital, Clinical Neuroscience Institute of Jinan University, Guangzhou, China

Junjie Lin,Xingyue Wang,Jiansheng Fang,et al. Multi-Scale Retina Vessel Segmentation in OCTA with a Vascular Connectivity Module in the Convolutional Neural Network[C],2023:1-5.