Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery
This provides a faster method for quantitative MRI compressed sensing, particularly in Magnetic Resonance Fingerprinting, though it is incremental as it builds on existing iterative algorithms.
The paper tackles the problem of slow compressed sensing reconstruction for signals on smooth manifolds by using cover trees and approximate nearest neighbor searches, achieving a 2-3 orders of magnitude reduction in computations while maintaining or improving accuracy in MRI applications.
We adopt data structure in the form of cover trees and iteratively apply approximate nearest neighbour (ANN) searches for fast compressed sensing reconstruction of signals living on discrete smooth manifolds. Levering on the recent stability results for the inexact Iterative Projected Gradient (IPG) algorithm and by using the cover tree's ANN searches, we decrease the projection cost of the IPG algorithm to be logarithmically growing with data population for low dimensional smooth manifolds. We apply our results to quantitative MRI compressed sensing and in particular within the Magnetic Resonance Fingerprinting (MRF) framework. For a similar (or sometimes better) reconstruction accuracy, we report 2-3 orders of magnitude reduction in computations compared to the standard iterative method which uses brute-force searches.