Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries

Alzheimer’s Disease Neuroimaging Initiative (ADNI)

Research output: Contribution to journalArticle

Abstract

Linear registration is often the crucial first step for various types of image analysis. Although this is mathematically simple, failure is not uncommon. When investigating the brain by magnetic resonance imaging (MRI), the brain is the target organ for registration but the existence of other tissues, in addition to a variety of fields of view, different brain locations, orientations and anatomical features, poses some serious fundamental challenges. Consequently, a number of different algorithms have been put forward to minimize potential errors. In the present study, we tested a knowledge-based approach that can be combined with any form of registration algorithm. This approach consisted of a library of intermediate images (mediators) with known transformation to the target image. Test images were first registered to all mediators and the best mediator was selected to ensure optimum registration to the target. In order to select the best mediator, we evaluated two similarity criteria: the sum of squared differences and mutual information. This approach was applied to 48 mediators and 96 test images. In order to reduce one of the main drawbacks of the approach, increased computation time, we reduced the size of the library by clustering. Our results indicated clear improvement in registration accuracy.

Original languageEnglish (US)
Article number909
JournalFrontiers in Neuroscience
Volume13
DOIs
StatePublished - Sep 11 2019

Fingerprint

Libraries
Magnetic Resonance Imaging
Brain
Cluster Analysis

Keywords

  • dice value
  • linear registration
  • mediator selection
  • MNI space
  • T1-weighted brain image

ASJC Scopus subject areas

  • Neuroscience(all)

Cite this

Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries. / Alzheimer’s Disease Neuroimaging Initiative (ADNI).

In: Frontiers in Neuroscience, Vol. 13, 909, 11.09.2019.

Research output: Contribution to journalArticle

Alzheimer’s Disease Neuroimaging Initiative (ADNI). / Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries. In: Frontiers in Neuroscience. 2019 ; Vol. 13.
@article{2d97cfa5296e4388ada8e1f78d81d582,
title = "Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries",
abstract = "Linear registration is often the crucial first step for various types of image analysis. Although this is mathematically simple, failure is not uncommon. When investigating the brain by magnetic resonance imaging (MRI), the brain is the target organ for registration but the existence of other tissues, in addition to a variety of fields of view, different brain locations, orientations and anatomical features, poses some serious fundamental challenges. Consequently, a number of different algorithms have been put forward to minimize potential errors. In the present study, we tested a knowledge-based approach that can be combined with any form of registration algorithm. This approach consisted of a library of intermediate images (mediators) with known transformation to the target image. Test images were first registered to all mediators and the best mediator was selected to ensure optimum registration to the target. In order to select the best mediator, we evaluated two similarity criteria: the sum of squared differences and mutual information. This approach was applied to 48 mediators and 96 test images. In order to reduce one of the main drawbacks of the approach, increased computation time, we reduced the size of the library by clustering. Our results indicated clear improvement in registration accuracy.",
keywords = "dice value, linear registration, mediator selection, MNI space, T1-weighted brain image",
author = "{Alzheimer’s Disease Neuroimaging Initiative (ADNI)} and Xinyuan Zhang and Yanqiu Feng and Wufan Chen and Xin Li and Faria, {Andreia V.} and Qianjin Feng and Susumu Mori",
year = "2019",
month = "9",
day = "11",
doi = "10.3389/fnins.2019.00909",
language = "English (US)",
volume = "13",
journal = "Frontiers in Neuroscience",
issn = "1662-4548",
publisher = "Frontiers Research Foundation",

}

TY - JOUR

T1 - Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries

AU - Alzheimer’s Disease Neuroimaging Initiative (ADNI)

AU - Zhang, Xinyuan

AU - Feng, Yanqiu

AU - Chen, Wufan

AU - Li, Xin

AU - Faria, Andreia V.

AU - Feng, Qianjin

AU - Mori, Susumu

PY - 2019/9/11

Y1 - 2019/9/11

N2 - Linear registration is often the crucial first step for various types of image analysis. Although this is mathematically simple, failure is not uncommon. When investigating the brain by magnetic resonance imaging (MRI), the brain is the target organ for registration but the existence of other tissues, in addition to a variety of fields of view, different brain locations, orientations and anatomical features, poses some serious fundamental challenges. Consequently, a number of different algorithms have been put forward to minimize potential errors. In the present study, we tested a knowledge-based approach that can be combined with any form of registration algorithm. This approach consisted of a library of intermediate images (mediators) with known transformation to the target image. Test images were first registered to all mediators and the best mediator was selected to ensure optimum registration to the target. In order to select the best mediator, we evaluated two similarity criteria: the sum of squared differences and mutual information. This approach was applied to 48 mediators and 96 test images. In order to reduce one of the main drawbacks of the approach, increased computation time, we reduced the size of the library by clustering. Our results indicated clear improvement in registration accuracy.

AB - Linear registration is often the crucial first step for various types of image analysis. Although this is mathematically simple, failure is not uncommon. When investigating the brain by magnetic resonance imaging (MRI), the brain is the target organ for registration but the existence of other tissues, in addition to a variety of fields of view, different brain locations, orientations and anatomical features, poses some serious fundamental challenges. Consequently, a number of different algorithms have been put forward to minimize potential errors. In the present study, we tested a knowledge-based approach that can be combined with any form of registration algorithm. This approach consisted of a library of intermediate images (mediators) with known transformation to the target image. Test images were first registered to all mediators and the best mediator was selected to ensure optimum registration to the target. In order to select the best mediator, we evaluated two similarity criteria: the sum of squared differences and mutual information. This approach was applied to 48 mediators and 96 test images. In order to reduce one of the main drawbacks of the approach, increased computation time, we reduced the size of the library by clustering. Our results indicated clear improvement in registration accuracy.

KW - dice value

KW - linear registration

KW - mediator selection

KW - MNI space

KW - T1-weighted brain image

UR - http://www.scopus.com/inward/record.url?scp=85073020740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073020740&partnerID=8YFLogxK

U2 - 10.3389/fnins.2019.00909

DO - 10.3389/fnins.2019.00909

M3 - Article

C2 - 31572107

AN - SCOPUS:85073020740

VL - 13

JO - Frontiers in Neuroscience

JF - Frontiers in Neuroscience

SN - 1662-4548

M1 - 909

ER -