A Patch-Wise Deep Learning Approach for Myocardial Blood Flow Quantification with Robustness to Noise and Nonrigid Motion.
Khalid YoussefBobby HeydariLuis Zamudio RiveroTaylor BeaulieuKarandeep CheemaRohan DharmakumarBehzad SharifPublished in: EMBC (2021)
Keyphrases
- deep learning
- blood flow
- phase contrast
- nonrigid motion
- motion analysis
- patient specific
- unsupervised learning
- point correspondences
- motion tracking
- boundary conditions
- left ventricular
- machine learning
- pairwise
- image sequences
- low contrast
- mental models
- image patches
- velocity field
- magnetic resonance
- motion model
- automated analysis
- multiple views
- finite element model
- motion estimation
- multiscale