Echocardiography plays a critical role in the diagnosis and monitoring of various cardiac diseases; however, metrics of cardiac function derived from conventional b-mode imaging rely on idealized geometries of the left ventricle (LV), which can subsequently cause mischaracterization of disease states. Recent advancements in four-dimensional ultrasound (4DUS) mitigate the need for idealized geometries, and when employed with small animal models of cardiac disease, provide a firm foundation for exploring regional kinematics in these pathologies. To aid in the process of tracking LV motion throughout the cardiac cycle, manually defined spatio-temporal positions, at uniformly spaced locations across the LV (i.e. 6 rotations around x 4 parallel slices down), were fed into a machine learning algorithm that could then be used to predict LV wall positions in a new dataset. Since the dimensionality of the data was much higher than the number of observed samples, principal component analysis was used to project the data into a lower dimensional subspace. The compressed data was then used along with regression splines to predict the locations of the LV endo- and epi-cardial boundaries in relation to the central kinematic-axis. The models were able to explain approximately 90% of the variation in the boundary distances, resulting in a procedure that can adequately estimate boundary wall locations in a new 4DUS dataset. The continued development of more complex machine learning algorithms and addition of unique disease model data will help create an automated tool for 4DUS-based cardiac phenotyping that has standardized outputs, is drastically faster than manual segmentation, and robust against inter-user variability.

Machine Learning Driven Contouring of High-Frequency Four-Dimensional Cardiac Ultrasound Data

The Virtual Technical Meeting of the Society of Engineering Science 2020 is the first fully virtual meeting of the SES community to envision and connect during the hiatus created by Covid-19, providing a platform for the exchange of ideas, and to showcase the latest research in the field of engineering science.

[Visit the Programme](https://drive.google.com/file/d/1BoCPBzrr1IQFANuzQI8a-paXCJoOcCkB/view?usp=sharing) | [Visit the Prerecorded Video/Poster List](https://drive.google.com/file/d/1XHLeEXJxEFjCSsNScuLDfMwy1X7oy7oJ/view?usp=sharing) | [View the Session Grid](https://drive.google.com/file/d/1VeDOC-Ev5m_ymYjXnjaXSZHR3_DARiLt/view?usp=sharing)