Meeting Banner
Abstract #0248

Unsupervised Ischemia Detection at Rest with CP-BOLD Cardiac MRI: A Simulation Study Employing Independent Component Analysis

Rita Morisi 1 , Rohan Dharmakumar 2,3 , and Sotirios A. Tsaftaris 1,4

1 IMT Institute for Advanced Studies, Lucca, LU, Italy, 2 Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, United States, 3 Medicine, University of California, Los Angeles, California, United States, 4 Electrical Engineering and Computer Science, Northwestern University, Evanston, Evanston, IL, United States

Cardiac-phase resolved Blood Oxygen-Level-Dependent (CP-BOLD) MRI is a new approach capable of detecting an ongoing ischemia without the need for provocative stress. Current disease assessment relies on segmental analysis and uses only a few cardiac phases of the cine acquisition. It is expected that using all phases can permit pixel-level characterization. This work explores Independent Component Analysis (ICA) for pixel-level ischemia characterization. Using simulated data we demonstrate the potential utility of ICA for overcoming existing limitations in discriminating ischemic territories on the basis of CP-BOLD

This abstract and the presentation materials are available to members only; a login is required.

Join Here