OVS‐Net: An effective feature extraction network for optical coherence tomography angiography vessel segmentation

• Published in: Computer animation and virtual worlds Vol. 33; no. 3-4
• Main Authors: Zhu, Chengzhang, Wang, Han, Xiao, Yalong, Dai, Yulan, Liu, Zixi, Zou, Beiji
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.06.2022; Wiley Subscription Services, Inc
• Subjects: Angiography; Blood vessels; Feature extraction; Image segmentation; Medical imaging; New technology; Ophthalmology; Optical Coherence Tomography; optical coherence tomography angiography; retinal vessel segmentation; Semantics; Tomography
• ISSN: 1546-4261; 1546-427X
• DOI: 10.1002/cav.2096

Optical coherence tomography angiography (OCTA), as a noninvasive imaging modality, has been widely used in clinical ophthalmology. However, the segmentation of retinal vessels in OCTA is under‐studied due to OCTA is a relatively new technology. In this article, an effective feature extraction network, OVS‐Net, is proposed for OCTA vessel segmentation. The OVS‐Net is divided into coarse stage and refine stage which structures are basically the same. In each stage, we utilize OctaveResBlock as the basic block to better extract the hierarchical multifrequency features of OCTA and capture the multiscale semantic features of the vessels. In order to improve the feature characterization, feature enhanced attention block is introduced into the network, which is proved to be more conducive for microvessel segmentation in our experiments. Multiscale feature blocks are introduced into the network to promote the deep integration of semantic features at different scales. Experiments on OCTA‐SS and OCTA‐500 datasets show that our proposed OVS‐Net achieves more competitive segmentation results than the existing methods, especially for microvessel segmentation. Randomized OVS‐Net for retinal vessel segmentation in OCTA images. Instead of ordinary convolution block, OVS‐Net is constructed by the OctaveBlock and OctaveResBlock. The FEAB is added to the network to capture the rich contextual information, and MFBs are added between the coarse stage and the refine stage to promote the deep integration of semantic features at different scales and restore vascular details. The evaluation metrics show that OVS‐Net is superior to most of the existing methods.