Snake with Shifted Window: Learning to Adapt Vessel Pattern for OCTA Segmentation

TL;DR

This paper introduces SSW-OCTA, a novel model combining deformable convolutions and swin-transformer to improve segmentation of retinal vessels in OCTA images, achieving state-of-the-art results on OCTA-500 dataset.

Contribution

The paper presents a new model that adapts to OCTA image characteristics by integrating deformable convolutions and swin-transformer for enhanced vessel segmentation.

Findings

Achieved state-of-the-art performance on OCTA-500 dataset.

Effectively captures complex retinal vessel structures.

Demonstrates the advantage of combining deformable convolutions with transformers.

Abstract

Segmenting specific targets or structures in optical coherence tomography angiography (OCTA) images is fundamental for conducting further pathological studies. The retinal vascular layers are rich and intricate, and such vascular with complex shapes can be captured by the widely-studied OCTA images. In this paper, we thus study how to use OCTA images with projection vascular layers to segment retinal structures. To this end, we propose the SSW-OCTA model, which integrates the advantages of deformable convolutions suited for tubular structures and the swin-transformer for global feature extraction, adapting to the characteristics of OCTA modality images. Our model underwent testing and comparison on the OCTA-500 dataset, achieving state-of-the-art performance. The code is available at: https://github.com/ShellRedia/Snake-SWin-OCTA.