Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery

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

doi:10.1109/MLSP.2017.8168167

Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery

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

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

5 Citations (SciVal)

Abstract

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 language	English
Title of host publication	2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)
Publisher	IEEE
ISBN (Electronic)	978-1-5090-6341-3
ISBN (Print)	978-1-5090-6342-0
DOIs	https://doi.org/10.1109/MLSP.2017.8168167
Publication status	Published - 7 Dec 2017

Publication series

Name	Machine Learning for Signal Processing
Publisher	IEEE
Volume	2017
ISSN (Print)	1551-2541
ISSN (Electronic)	2378-928X

Keywords

stat.ML

Access to Document

10.1109/MLSP.2017.8168167

https://arxiv.org/abs/1706.07834

Cite this

Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery. / Golbabaee, Mohammad; Chen, Zhouye; Wiaux, Yves et al.
2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2017. (Machine Learning for Signal Processing; Vol. 2017).

Research output: Chapter or section in a book/report/conference proceeding › Chapter in a published conference proceeding

@inproceedings{9974c13499ea4421817d5c76d0821391,

title = "Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery",

abstract = " 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. ",

keywords = "stat.ML",

author = "Mohammad Golbabaee and Zhouye Chen and Yves Wiaux and Davies, {Mike E.}",

year = "2017",

month = dec,

day = "7",

doi = "10.1109/MLSP.2017.8168167",

language = "English",

isbn = "978-1-5090-6342-0",

series = "Machine Learning for Signal Processing",

publisher = "IEEE",

booktitle = "2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)",

address = "USA United States",

}

TY - GEN

T1 - Cover Tree Compressed Sensing for Fast MR Fingerprint Recovery

AU - Golbabaee, Mohammad

AU - Chen, Zhouye

AU - Wiaux, Yves

AU - Davies, Mike E.

PY - 2017/12/7

Y1 - 2017/12/7

N2 - 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.

AB - 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.

KW - stat.ML

U2 - 10.1109/MLSP.2017.8168167

DO - 10.1109/MLSP.2017.8168167

M3 - Chapter in a published conference proceeding

SN - 978-1-5090-6342-0

T3 - Machine Learning for Signal Processing

BT - 2017 IEEE 27th International Workshop on Machine Learning for Signal Processing (MLSP)

PB - IEEE

ER -