Premium
TH‐D‐204B‐01: Theory and Applications in MR Imaging of Compressive Sensing
Author(s) -
Goldstein T,
Osher S
Publication year - 2010
Publication title -
medical physics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.473
H-Index - 180
eISSN - 2473-4209
pISSN - 0094-2405
DOI - 10.1118/1.3469546
Subject(s) - compressed sensing , perspective (graphical) , computer science , artificial intelligence , iterative reconstruction , computer vision , imaging science
This talk will introduce the concept of compressed sensing (CS). We will begin with some intuitive justification for CS. Compressed sensing will then be discussed from a more rigourous perspective and theoretical results will be presented. The application of the CS theory to magnetic resonance imaging will then be discussed. Finally we shall discuss the split Bregman method ‐ a fast numerical scheme for reconstructing images from compressed sensing data. Learning Objective: 1. Understand the basic theory of compressed sensing and the advantages it offers. 2. Understand how compressed sensing can be applied to MRI 3. Understand the computational challenges of compressed sensing and the split Bregman method for reconstructing images from compressed data.