Abstract #4780

Neural style transfer: Applications in cardiac MR image registration

Alper Ozan Turgut¹, Matthew Van Houten², Junyu Wang², Xue Feng², and Michael Salerno³

¹School of Medicine, University of Virginia, Charlottesville, VA, United States, ²Biomedical Engineering, University of Virginia, Charlottesville, VA, United States, ³Department of Medicine and Radiology, Stanford University, Stanford, CA, United States

Synopsis

Contrast-enhanced cardiac magnetic resonance (CMR) stress perfusion imaging shows excellent utility in evaluating coronary artery disease¹. Registering perfusion CMR image series is difficult due to the varying image contrast. Neural style transfer is a deep learning method used to transfer the “style” of one domain to another while preserving the content. Two neural style transfer networks were implemented in Python using TensorFlow and PyTorch. Training of each network was done using three, slice matched patient profiles and cine-like perfusion images were generated and registered. This method is compared to a KL-transform based registration approach.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.