Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries
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 tissue...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2019-09-01
|
Series: | Frontiers in Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/article/10.3389/fnins.2019.00909/full |
id |
doaj-a625efac63ed42a9b52d4c4d9843c8d9 |
---|---|
record_format |
Article |
spelling |
doaj-a625efac63ed42a9b52d4c4d9843c8d92020-11-24T22:16:03ZengFrontiers Media S.A.Frontiers in Neuroscience1662-453X2019-09-011310.3389/fnins.2019.00909461918Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator LibrariesXinyuan Zhang0Xinyuan Zhang1Xinyuan Zhang2Yanqiu Feng3Yanqiu Feng4Wufan Chen5Wufan Chen6Xin Li7Andreia V. Faria8Qianjin Feng9Qianjin Feng10Susumu Mori11School of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaDepartment of Radiology, School of Medicine, Johns Hopkins University, Washington, ME, United StatesSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaDepartment of Radiology, School of Medicine, Johns Hopkins University, Washington, ME, United StatesDepartment of Radiology, School of Medicine, Johns Hopkins University, Washington, ME, United StatesSchool of Biomedical Engineering, Southern Medical University, Guangzhou, ChinaGuangdong Provincial Key Laboratory of Medical Image Processing, Southern Medical University, Guangzhou, ChinaDepartment of Radiology, School of Medicine, Johns Hopkins University, Washington, ME, United StatesLinear 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.https://www.frontiersin.org/article/10.3389/fnins.2019.00909/fulllinear registrationmediator selectionT1-weighted brain imageMNI spacedice value |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xinyuan Zhang Xinyuan Zhang Xinyuan Zhang Yanqiu Feng Yanqiu Feng Wufan Chen Wufan Chen Xin Li Andreia V. Faria Qianjin Feng Qianjin Feng Susumu Mori |
spellingShingle |
Xinyuan Zhang Xinyuan Zhang Xinyuan Zhang Yanqiu Feng Yanqiu Feng Wufan Chen Wufan Chen Xin Li Andreia V. Faria Qianjin Feng Qianjin Feng Susumu Mori Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries Frontiers in Neuroscience linear registration mediator selection T1-weighted brain image MNI space dice value |
author_facet |
Xinyuan Zhang Xinyuan Zhang Xinyuan Zhang Yanqiu Feng Yanqiu Feng Wufan Chen Wufan Chen Xin Li Andreia V. Faria Qianjin Feng Qianjin Feng Susumu Mori |
author_sort |
Xinyuan Zhang |
title |
Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries |
title_short |
Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries |
title_full |
Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries |
title_fullStr |
Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries |
title_full_unstemmed |
Linear Registration of Brain MRI Using Knowledge-Based Multiple Intermediator Libraries |
title_sort |
linear registration of brain mri using knowledge-based multiple intermediator libraries |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Neuroscience |
issn |
1662-453X |
publishDate |
2019-09-01 |
description |
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. |
topic |
linear registration mediator selection T1-weighted brain image MNI space dice value |
url |
https://www.frontiersin.org/article/10.3389/fnins.2019.00909/full |
work_keys_str_mv |
AT xinyuanzhang linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT xinyuanzhang linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT xinyuanzhang linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT yanqiufeng linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT yanqiufeng linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT wufanchen linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT wufanchen linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT xinli linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT andreiavfaria linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT qianjinfeng linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT qianjinfeng linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries AT susumumori linearregistrationofbrainmriusingknowledgebasedmultipleintermediatorlibraries |
_version_ |
1725791621811798016 |