Evaluation of Automatic Processing of Quantitative Perfusion Images in Patients with Suspected Coronary Artery Disease
Matthew Van Houten1, Xue Feng1, Yang Yang2, Patricia Rodriguez Lozano1, Christopher Kramer1, and Michael Salerno3
1University of Virginia, Charlottesville, VA, United States, 2Icahn School of Medicine at Mount Sinai, New York, NY, United States, 3Stanford University, Stanford, CA, United States
We developed high resolution quantitative perfusion sequence, along with DCNN network to automatically segment the image sets for motion correction. We deployed the acquisition and post-processing on patients with suspected coronary artery disease and compared the results to their coronary angiography findings. Our sequence and processing successfully match the angiography results.
This abstract and the presentation materials are available to members only;
a login is required.