OCT2Former: A retinal OCT-angiography vessel segmentation transformer. (May 2023)

• Record Type: Journal Article
• Authors: Tan, Xiao; Chen, Xinjian; Meng, Qingquan; Shi, Fei; Xiang, Dehui; Chen, Zhongyue; Pan, Lingjiao; Zhu, Weifang
• Is Part Of: Computer methods and programs in biomedicine. Volume 233(2023)
• Publication Date: 2023-05
• Subjects: Optical coherence tomography angiography -- Retinal vessel segmentation -- Transformer -- Dynamic token aggregation -- Deep learning; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2023.107454
• Languages: English
• ISSNs: 0169-2607

Abstract

Abstract: Background and objective: Retinal vessel segmentation plays an important role in the automatic retinal disease screening and diagnosis. How to segment thin vessels and maintain the connectivity of vessels are the key challenges of the retinal vessel segmentation task. Optical coherence tomography angiography (OCTA) is a noninvasive imaging technique that can reveal high-resolution retinal vessels. Aiming at make full use of its characteristic of high resolution, a new end-to-end transformer based network named as OCT 2 Former (OCT-a Transformer) is proposed to segment retinal vessel accurately in OCTA images. Methods: The proposed OCT 2 Former is based on encoder-decoder structure, which mainly includes dynamic transformer encoder and lightweight decoder. Dynamic transformer encoder consists of dynamic token aggregation transformer and auxiliary convolution branch, in which the multi-head dynamic token aggregation attention based dynamic token aggregation transformer is designed to capture the global retinal vessel context information from the first layer throughout the network and the auxiliary convolution branch is proposed to compensate for the lack of inductive bias of the transformer and assist in the efficient feature extraction. A convolution based lightweight decoder is proposed to decode features efficiently and reduce the complexity of the proposed OCT 2 Former. Results: The proposed OCT 2 Former is validated on three publicly available datasets i.e. OCTA-SS, ROSE-1, OCTA-500 (subset OCTA-6M and OCTA-3M). The Jaccard indexes of the proposed OCT 2 Former on these datasets are 0.8344, 0.7855, 0.8099 and 0.8513, respectively, outperforming the best convolution based network 1.43, 1.32, 0.75 and 1.46%, respectively. Conclusion: The experimental results have demonstrated that the proposed OCT 2 Former can achieve competitive performance on retinal OCTA vessel segmentation tasks.