Sequential vessel segmentation via deep channel attention network

TL;DR

This paper introduces a novel deep encoder-decoder network with temporal-spatial feature extraction and channel attention for sequential vessel segmentation in X-ray coronary angiography images, outperforming existing methods.

Contribution

The proposed network uniquely combines 3D convolutions, skip connections, and channel attention mechanisms for improved vessel segmentation in sequential images.

Findings

Outperforms state-of-the-art methods in quantitative metrics

Effective handling of complex backgrounds and noise

Demonstrates superior visual segmentation results

Abstract

This paper develops a novel encoder-decoder deep network architecture which exploits the several contextual frames of 2D+t sequential images in a sliding window centered at current frame to segment 2D vessel masks from the current frame. The architecture is equipped with temporal-spatial feature extraction in encoder stage, feature fusion in skip connection layers and channel attention mechanism in decoder stage. In the encoder stage, a series of 3D convolutional layers are employed to hierarchically extract temporal-spatial features. Skip connection layers subsequently fuse the temporal-spatial feature maps and deliver them to the corresponding decoder stages. To efficiently discriminate vessel features from the complex and noisy backgrounds in the XCA images, the decoder stage effectively utilizes channel attention blocks to refine the intermediate feature maps from skip connection layers for subsequently decoding the refined features in 2D ways to produce the segmented vessel masks. Furthermore, Dice loss function is implemented to train the proposed deep network in order to tackle the class imbalance problem in the XCA data due to the wide distribution of complex background artifacts. Extensive experiments by comparing our method with other state-of-the-art algorithms demonstrate the proposed method's superior performance over other methods in terms of the quantitative metrics and visual validation. The source codes are at https://github.com/Binjie-Qin/SVS-net