TY  - UNPB
T2  - ISMRM 23st Annual Meeting
ID  - eprints2766
UR  - http://ismrm.org/15/program_files/ThuEPS01.htm#Vessel_Wall_&_Cardiovascular_Image_Processing
Y1  - 2015/06/04/
TI  - Data Driven Feature Learning for Representation of Myocardial BOLD MR Images
AV  - none
N2  - Cardiac phase-dependent variations of myocardial signal intensities in Cardiac Phase-resolved Blood-Oxygen-Level-Dependent (CP-BOLD) MRI can be exploited for the identification of ischemic territories. This technique requires segmentation to isolate the myocardium. However, spatio-temporal variations of BOLD contrast, prove challenging for existing automated myocardial segmentation techniques, because they were developed for acquisitions where contrast variations in the myocardium are minimal. Appropriate feature learning mechanisms are necessary to best represent appearance and texture in CP-BOLD data. Here we propose and validate a feature learning technique based on multiscale dictionary model that learns to sparsely represent effective patterns under healthy and ischemic conditions.
A1  - Mukhopadhyay, Anirban
A1  - Bevilacqua, Marco
A1  - Oksuz, Ilkay
A1  - Dharmakumar, Rohan
A1  - Tsaftaris, Sotirios A.
M2  - Toronto, Ontario, Canada
ER  -