LVSnake: Accurate and robust left ventricle contour localization for myocardial infarction detection

Localization of the left ventricle (LV) in echocardiography is important for the diagnosis of cardiovascular diseases. Previous deep learning approaches leverage semantic segmentation models to perform LV or myocardium segmentation and extract important LV parameters from the binary segmentation masks. Although these algorithms yield promising segmentation results, their per-pixel classification characteristic and complex postprocessing process of the binary masks compromise their robustness and speed. In this paper, inspired by the DeepSnake algorithm in the computer vision community, we develop a deep learning model called LVSnake for left ventricle localization. Our model generates the initial contour by connecting three key landmarks of the left ventricle output by our model including the start point, the apex point, and the end point of the endocardium. Then, a contour adjustment module is designed to refine the initial contour coordinates so as to obtain the final position of the endocardium. The extracted endocardium coordinates are used to perform Myocardial Infarction (MI) detection. Experiment results on the HMC-QU dataset indicate that our model performs more favorably against previous approaches in terms of localization accuracy and robustness. The overall Endpoint-Error (EPE) of our model reaches 3.4 pixels. Using ventricular endocardium location extracted by our method to perform MI detection, the classification accuracy reaches 83.1% which exceeds that of existing studies (79.2%). Our proposed LVSnake can robustly and accurately extract LV positions from echocardiography, which can be used for MI detection. •We proposed the LVSnake model which directly outputs the LV contour.•Our model achieves accurate and robust performance on the LV localization task.•We labeled the LV contour of an MI detection dataset which will be released.•The MI detection’s accuracy has improved using the LV contour extracted by our model.