Uncertainty estimation in diffusion MRI using the nonlocal bootstrap

Pew Thian Yap, Hongyu An, Yasheng Chen, Dinggang Shen

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

In this paper, we propose a new bootstrap scheme, called the nonlocal bootstrap (NLB) for uncertainty estimation. In contrast to the residual bootstrap, which relies on a data model, or the repetition bootstrap, which requires repeated signal measurements, NLB is not restricted by the data structure imposed by a data model and obviates the need for time-consuming multiple acquisitions. NLB hinges on the observation that local imaging information recurs in an image. This self-similarity implies that imaging information coming from spatially distant (nonlocal) regions can be exploited for more effective estimation of statistics of interest. Evaluations using in silico data indicate that NLB produces distribution estimates that are in closer agreement with those generated using Monte Carlo simulations, compared with the conventional residual bootstrap. Evaluations using in vivo data demonstrate that NLB produces results that are in agreement with our knowledge on white matter architecture.

Original languageEnglish
Article number6807726
Pages (from-to)1627-1640
Number of pages14
JournalIEEE Transactions on Medical Imaging
Volume33
Issue number8
DOIs
Publication statusPublished - 2014 Jan 1

Fingerprint

Diffusion Magnetic Resonance Imaging
Magnetic resonance imaging
Uncertainty
Data structures
Computer Simulation
Imaging techniques
Hinges
Statistics
White Matter

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

Uncertainty estimation in diffusion MRI using the nonlocal bootstrap. / Yap, Pew Thian; An, Hongyu; Chen, Yasheng; Shen, Dinggang.

In: IEEE Transactions on Medical Imaging, Vol. 33, No. 8, 6807726, 01.01.2014, p. 1627-1640.

Research output: Contribution to journalArticle

Yap, Pew Thian ; An, Hongyu ; Chen, Yasheng ; Shen, Dinggang. / Uncertainty estimation in diffusion MRI using the nonlocal bootstrap. In: IEEE Transactions on Medical Imaging. 2014 ; Vol. 33, No. 8. pp. 1627-1640.
@article{2c1061db4de74a9b8c28aa51c897fe9e,
title = "Uncertainty estimation in diffusion MRI using the nonlocal bootstrap",
abstract = "In this paper, we propose a new bootstrap scheme, called the nonlocal bootstrap (NLB) for uncertainty estimation. In contrast to the residual bootstrap, which relies on a data model, or the repetition bootstrap, which requires repeated signal measurements, NLB is not restricted by the data structure imposed by a data model and obviates the need for time-consuming multiple acquisitions. NLB hinges on the observation that local imaging information recurs in an image. This self-similarity implies that imaging information coming from spatially distant (nonlocal) regions can be exploited for more effective estimation of statistics of interest. Evaluations using in silico data indicate that NLB produces distribution estimates that are in closer agreement with those generated using Monte Carlo simulations, compared with the conventional residual bootstrap. Evaluations using in vivo data demonstrate that NLB produces results that are in agreement with our knowledge on white matter architecture.",
keywords = "Bootstrap, diffusion magnetic resonance imaging (MRI), estimator, nonlocal means, nonparametric kernel regression, sampling distribution, self-similarity, uncertainty",
author = "Yap, {Pew Thian} and Hongyu An and Yasheng Chen and Dinggang Shen",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/TMI.2014.2320947",
language = "English",
volume = "33",
pages = "1627--1640",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "8",

}

TY - JOUR

T1 - Uncertainty estimation in diffusion MRI using the nonlocal bootstrap

AU - Yap, Pew Thian

AU - An, Hongyu

AU - Chen, Yasheng

AU - Shen, Dinggang

PY - 2014/1/1

Y1 - 2014/1/1

N2 - In this paper, we propose a new bootstrap scheme, called the nonlocal bootstrap (NLB) for uncertainty estimation. In contrast to the residual bootstrap, which relies on a data model, or the repetition bootstrap, which requires repeated signal measurements, NLB is not restricted by the data structure imposed by a data model and obviates the need for time-consuming multiple acquisitions. NLB hinges on the observation that local imaging information recurs in an image. This self-similarity implies that imaging information coming from spatially distant (nonlocal) regions can be exploited for more effective estimation of statistics of interest. Evaluations using in silico data indicate that NLB produces distribution estimates that are in closer agreement with those generated using Monte Carlo simulations, compared with the conventional residual bootstrap. Evaluations using in vivo data demonstrate that NLB produces results that are in agreement with our knowledge on white matter architecture.

AB - In this paper, we propose a new bootstrap scheme, called the nonlocal bootstrap (NLB) for uncertainty estimation. In contrast to the residual bootstrap, which relies on a data model, or the repetition bootstrap, which requires repeated signal measurements, NLB is not restricted by the data structure imposed by a data model and obviates the need for time-consuming multiple acquisitions. NLB hinges on the observation that local imaging information recurs in an image. This self-similarity implies that imaging information coming from spatially distant (nonlocal) regions can be exploited for more effective estimation of statistics of interest. Evaluations using in silico data indicate that NLB produces distribution estimates that are in closer agreement with those generated using Monte Carlo simulations, compared with the conventional residual bootstrap. Evaluations using in vivo data demonstrate that NLB produces results that are in agreement with our knowledge on white matter architecture.

KW - Bootstrap

KW - diffusion magnetic resonance imaging (MRI)

KW - estimator

KW - nonlocal means

KW - nonparametric kernel regression

KW - sampling distribution

KW - self-similarity

KW - uncertainty

UR - http://www.scopus.com/inward/record.url?scp=84905595000&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905595000&partnerID=8YFLogxK

U2 - 10.1109/TMI.2014.2320947

DO - 10.1109/TMI.2014.2320947

M3 - Article

C2 - 24801775

AN - SCOPUS:84905595000

VL - 33

SP - 1627

EP - 1640

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 8

M1 - 6807726

ER -