The purpose of this study is to develop a deep learning algorithm for myocardial segmentation and apply it to a Python graphical user interface for cardiac MR image processing and analysis. We used a U-net architecture to simultaneously segment endocardial and epicardial borders. For training data, we used publicly available data and our internal data, both of which are from cardiac cine imaging. When the trained model was used in our Python GUI, myocardial segmentation exhibited moderate accuracy in cine data as well as in perfusion data.
This abstract and the presentation materials are available to members only; a login is required.