There are no files associated with this item.
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.citation.endPage | 152 | - |
dc.citation.startPage | 143 | - |
dc.citation.title | MAGNETIC RESONANCE IMAGING | - |
dc.citation.volume | 59 | - |
dc.contributor.author | Bao, Shunxing | - |
dc.contributor.author | Bermudez, Camilo | - |
dc.contributor.author | Huo, Yuankai | - |
dc.contributor.author | Parvathaneni, Prasanna | - |
dc.contributor.author | Rodriguez, William | - |
dc.contributor.author | Resnick, Susan M. | - |
dc.contributor.author | D'Haese, Pierre-Francois | - |
dc.contributor.author | McHugo, Maureen | - |
dc.contributor.author | Heckers, Stephan | - |
dc.contributor.author | Dawant, Benoit M. | - |
dc.contributor.author | Lyu, Ilwoo | - |
dc.contributor.author | Landman, Bennett A. | - |
dc.date.accessioned | 2023-12-21T19:06:48Z | - |
dc.date.available | 2023-12-21T19:06:48Z | - |
dc.date.created | 2021-03-05 | - |
dc.date.issued | 2019-06 | - |
dc.description.abstract | Magnetic resonance imaging (MRI) is an important tool for analysis of deep brain grey matter structures. However, analysis of these structures is limited due to low intensity contrast typically found in whole brain imaging protocols. Herein, we propose a big data registration-enhancement (BDRE) technique to augment the contrast of deep brain structures using an efficient large-scale non-rigid registration strategy. Direct validation is problematic given a lack of ground truth data. Rather, we validate the usefulness and impact of BDRE for multi-atlas (MA) segmentation on two sets of structures of clinical interest: the thalamic nuclei and hippocampal subfields. The experimental design compares algorithms using T1-weighted 3T MRI for both structures (and additional 7 T MRI for the thalamic nuclei) with an algorithm using BDRE. As baseline comparisons, a recent denoising (DN) technique and a super-resolution (SR) method are used to preprocess the original 3 T MRI. The performance of each MA segmentation is evaluated by the Dice similarity coefficient (DSC). BDRE significantly improves mean segmentation accuracy over all methods tested for both thalamic nuclei (3 T imaging: 9.1%; 7 T imaging: 15.6%; ON: 6.9%; SR: 16.2%) and hippocampal subfields (3 T T1 only: 8.7%; DN: 8.4%; SR: 8.6%). We also present DSC performance for each thalamic nucleus and hippocampal subfield and show that BDRE can help MA segmentation for individual thalamic nuclei and hippocampal subfields. This work will enable large-scale analysis of clinically relevant deep brain structures from commonly acquired T1 images. | - |
dc.identifier.bibliographicCitation | MAGNETIC RESONANCE IMAGING, v.59, pp.143 - 152 | - |
dc.identifier.doi | 10.1016/j.mri.2019.03.014 | - |
dc.identifier.issn | 0730-725X | - |
dc.identifier.scopusid | 2-s2.0-85063605182 | - |
dc.identifier.uri | https://scholarworks.unist.ac.kr/handle/201301/50106 | - |
dc.identifier.wosid | 000465062800018 | - |
dc.language | 영어 | - |
dc.publisher | ELSEVIER SCIENCE INC | - |
dc.title | Registration-based image enhancement improves multi-atlas segmentation of the thalamic nuclei and hippocampal subfields | - |
dc.type | Article | - |
dc.description.isOpenAccess | FALSE | - |
dc.relation.journalWebOfScienceCategory | Radiology, Nuclear Medicine & Medical Imaging | - |
dc.relation.journalResearchArea | Radiology, Nuclear Medicine & Medical Imaging | - |
dc.type.docType | Article | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Non-rigid registration | - |
dc.subject.keywordAuthor | Deep brain structure | - |
dc.subject.keywordAuthor | Big data | - |
dc.subject.keywordPlus | MRI | - |
dc.subject.keywordPlus | SUPERRESOLUTION | - |
dc.subject.keywordPlus | RECONSTRUCTION | - |
Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Tel : 052-217-1404 / Email : scholarworks@unist.ac.kr
Copyright (c) 2023 by UNIST LIBRARY. All rights reserved.
ScholarWorks@UNIST was established as an OAK Project for the National Library of Korea.