PAENet: A Progressive Attention-Enhanced Network for 3D to 2D Retinal Vessel Segmentation

TL;DR

PAENet is a novel neural network that leverages attention mechanisms and feature fusion to improve 3D to 2D retinal vessel segmentation in OCTA images, achieving state-of-the-art results.

Contribution

The paper introduces PAENet with new modules like APM, QAM, and FFM, enhancing feature extraction and fusion for better segmentation performance.

Findings

Achieves state-of-the-art segmentation accuracy on OCTA-500 dataset.

Effectively captures dependencies in 4D feature tensors.

Improves detail preservation in 2D segmentation through feature fusion.

Abstract

3D to 2D retinal vessel segmentation is a challenging problem in Optical Coherence Tomography Angiography (OCTA) images. Accurate retinal vessel segmentation is important for the diagnosis and prevention of ophthalmic diseases. However, making full use of the 3D data of OCTA volumes is a vital factor for obtaining satisfactory segmentation results. In this paper, we propose a Progressive Attention-Enhanced Network (PAENet) based on attention mechanisms to extract rich feature representation. Specifically, the framework consists of two main parts, the three-dimensional feature learning path and the two-dimensional segmentation path. In the three-dimensional feature learning path, we design a novel Adaptive Pooling Module (APM) and propose a new Quadruple Attention Module (QAM). The APM captures dependencies along the projection direction of volumes and learns a series of pooling coefficients for feature fusion, which efficiently reduces feature dimension. In addition, the QAM reweights the features by capturing four-group cross-dimension dependencies, which makes maximum use of 4D feature tensors. In the two-dimensional segmentation path, to acquire more detailed information, we propose a Feature Fusion Module (FFM) to inject 3D information into the 2D path. Meanwhile, we adopt the Polarized Self-Attention (PSA) block to model the semantic interdependencies in spatial and channel dimensions respectively. Experimentally, our extensive experiments on the OCTA-500 dataset show that our proposed algorithm achieves state-of-the-art performance compared with previous methods.