GL-Fusion: Global-Local Fusion Network for Multi-view Echocardiogram Video Segmentation

TL;DR

This paper introduces GL-Fusion, a novel network that effectively combines global and local multi-view information to improve the accuracy of echocardiogram video segmentation, addressing cross-view disparity challenges.

Contribution

The paper proposes a new global-local fusion network with specialized modules for multi-view context extraction, and introduces a multi-view echocardiogram dataset for evaluation.

Findings

Achieves 82.29% dice score, 7.83% higher than baseline.

Outperforms existing state-of-the-art methods.

First multi-view approach for echocardiogram video segmentation.

Abstract

Cardiac structure segmentation from echocardiogram videos plays a crucial role in diagnosing heart disease. The combination of multi-view echocardiogram data is essential to enhance the accuracy and robustness of automated methods. However, due to the visual disparity of the data, deriving cross-view context information remains a challenging task, and unsophisticated fusion strategies can even lower performance. In this study, we propose a novel Gobal-Local fusion (GL-Fusion) network to jointly utilize multi-view information globally and locally that improve the accuracy of echocardiogram analysis. Specifically, a Multi-view Global-based Fusion Module (MGFM) is proposed to extract global context information and to explore the cyclic relationship of different heartbeat cycles in an echocardiogram video. Additionally, a Multi-view Local-based Fusion Module (MLFM) is designed to extract correlations of cardiac structures from different views. Furthermore, we collect a multi-view echocardiogram video dataset (MvEVD) to evaluate our method. Our method achieves an 82.29% average dice score, which demonstrates a 7.83% improvement over the baseline method, and outperforms other existing state-of-the-art methods. To our knowledge, this is the first exploration of a multi-view method for echocardiogram video segmentation. Code available at: https://github.com/xmed-lab/GL-Fusion