Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound

TL;DR

EchoGraphs introduces a novel GCN-based approach for cardiac ultrasound analysis, enabling accurate segmentation and ejection fraction prediction with improved robustness and efficiency, advancing automated cardiovascular diagnostics.

Contribution

The paper presents a new GCN-based method for simultaneous segmentation and EF prediction, leveraging local and global cardiac shape features, outperforming existing techniques.

Findings

Achieves state-of-the-art EF estimation accuracy.

Provides robust segmentation with faster inference.

Outperforms semantic segmentation in accuracy and speed.

Abstract

Accurate and consistent predictions of echocardiography parameters are important for cardiovascular diagnosis and treatment. In particular, segmentations of the left ventricle can be used to derive ventricular volume, ejection fraction (EF) and other relevant measurements. In this paper we propose a new automated method called EchoGraphs for predicting ejection fraction and segmenting the left ventricle by detecting anatomical keypoints. Models for direct coordinate regression based on Graph Convolutional Networks (GCNs) are used to detect the keypoints. GCNs can learn to represent the cardiac shape based on local appearance of each keypoint, as well as global spatial and temporal structures of all keypoints combined. We evaluate our EchoGraphs model on the EchoNet benchmark dataset. Compared to semantic segmentation, GCNs show accurate segmentation and improvements in robustness and inference runtime. EF is computed simultaneously to segmentations and our method also obtains state-of-the-art ejection fraction estimation. Source code is available online: https://github.com/guybenyosef/EchoGraphs.