Light-weight spatio-temporal graphs for segmentation and ejection fraction prediction in cardiac ultrasound
This work addresses the need for accurate cardiovascular diagnosis through automated echocardiography analysis, representing an incremental improvement with a novel method for a known bottleneck in medical imaging.
The authors tackled automated left ventricle segmentation and ejection fraction prediction in cardiac ultrasound by proposing EchoGraphs, a method using Graph Convolutional Networks to detect anatomical keypoints, achieving state-of-the-art ejection fraction estimation and improved robustness and inference runtime on the EchoNet dataset.
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.