Abstract
Analyzing and understanding the movement of the mitral valve is of vital importance in cardiology, as the treatment and prevention of several serious heart diseases depend on it. Unfortunately, large amounts of noise as well as a highly varying image quality make the automatic tracking and segmentation of the mitral valve in two-dimensional echocardiographic videos challenging. In this paper, we present a fully automatic and unsupervised method for segmentation of the mitral valve in two-dimensional echocardiographic videos, independently of the echocardiographic view. We propose a bias-free variant of the robust non-negative matrix factorization (RNMF) along with a window-based localization approach, that is able to identify the mitral valve in several challenging situations. We improve the average f1-score on our dataset of 10 echocardiographic videos by 0.18 to a f1-score of 0.56.
Highlights
The precise movement of the mitral valve is of crucial importance for a proper blood flow [1]
For evaluation of the EchoNet-Dynamic dataset [52], we used the same hyperparameters as listed in Tables 2 and 3 for 46 selected videos, which almost all have the characteristic of showing a second heart valve besides the mitral valve
As our method is not designed to distinguish between two valves, we performed additional experiments after masking the second heart valve from the videos and were able to increase the segmentation accuracy to an f1-score of 0.51 for segmentation with windowing and 0.43 for automatic segmentation
Summary
The precise movement of the mitral valve is of crucial importance for a proper blood flow [1]. Accurate detection of mitral valve disease is of great importance for the treatment and prevention of several diseases. In old age, a defect of a heart valve is a common disease. According to Mohty et al [2], more than 12.5% of the elderly people of 75 years or over suffer from heart valve diseases. In a study in 2006, mitral regurgitation, which is a disease of the mitral valve that does not close tightly and partially allows the blood to flow back, was the most measured common kind of heart disease [3].
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
