Purdue Research Foundation

Frederick William Damen

Craig Jonathan Goergen

Guang Lin

David Taylor Newton

A system and methods for machine learning driven contouring of cardiac ultrasound data is provided. A system may receive cardiac imaging data generated by an ultrasound device directed at a left ventricle of a heart. The imaging data may include a time dimension and a plurality of spatial dimensions. The system may align the image data with an axis that passes through an apex and base of the left ventricle. The system may predict, based on a machine learning model and the imaging data, locations of a plurality of anchor points over a cardiac cycle. The system may output the predicted locations of the anchor points.

System and methods for machine learning driven contouring cardiac ultrasound data

A system may receive imaging data generated by an imaging device directed at a heart. The system may receive a first input operation indicative of a selected time-frame. The system may display images of the heart based on the intensity values mapped to the selected time-frame. The system may receive, based on interaction with the images, an apex coordinate and a base coordinate. The system may calculate, based on the apex coordinate and the base coordinate, a truncated ellipsoid representative an endocardial or epicardial boundary of the heart. The system may generate a four-dimensional mesh comprising three-dimensional vertices spaced along the mesh. The system may overlay, on the displayed images, markers representative of the vertices. The system may receive a second input operation corresponding to a selected marker. The system may enhance the mesh by adjusting or interpolating vertices across multiple time-frames.

Growing community of inventors

Chicago, IL, United States of America

Frederick William Damen