Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery

Mohammad Golbabaee, Zhouye Chen, Yves Wiaux, Mike E. Davies

Research output: Contribution to conferencePaperpeer-review

Abstract / Description of output

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.
Original languageUndefined/Unknown
Publication statusPublished - 23 Jun 2017
EventIEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP): MLSP 2017 - Tokyo, Tokyo, Japan
Duration: 25 Sept 201728 Jan 2018
https://signalprocessingsociety.org/blog/mlsp-2017-2017-ieee-international-workshop-machine-learning-signal-processing

Conference

ConferenceIEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)
Country/TerritoryJapan
CityTokyo
Period25/09/1728/01/18
Internet address

Keywords / Materials (for Non-textual outputs)

  • stat.ML

Cite this