Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

LINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images

Full metadata record
DC Field Value Language
dc.contributor.authorWang, Li-
dc.contributor.authorGao, Yaozong-
dc.contributor.authorShi, Feng-
dc.contributor.authorLi, Gang-
dc.contributor.authorGilmore, John H.-
dc.contributor.authorLin, Weili-
dc.contributor.authorShen, Dinggang-
dc.date.accessioned2021-09-04T18:56:31Z-
dc.date.available2021-09-04T18:56:31Z-
dc.date.created2021-06-15-
dc.date.issued2015-03-
dc.identifier.issn1053-8119-
dc.identifier.urihttps://scholar.korea.ac.kr/handle/2021.sw.korea/94340-
dc.description.abstractSegmentation of infant brain MR images is challenging due to insufficient image quality, severe partial volume effect, and ongoing maturation and myelination processes. In the first year of life, the image contrast between white and gray matters of the infant brain undergoes dramatic changes. In particular, the image contrast is inverted around 6-8 months of age, and the white and gray matter tissues are isointense in both T1- and T2-weighted MR images and thus exhibit the extremely low tissue contrast, which poses significant challenges for automated segmentation. Most previous studies used multi-atlas label fusion strategy, which has the limitation of equally treating the different available image modalities and is often computationally expensive. To cope with these limitations, in this paper, we propose a novel learning-based multi-source integration framework for segmentation of infant brain images. Specifically, we employ the random forest technique to effectively integrate features from multi-source images together for tissue segmentation. Here, the multi-source images include initially only the multi-modality (T1, T2 and FA) images and later also the iteratively estimated and refined tissue probability maps of gray matter, white matter, and cerebrospinal fluid. Experimental results on 119 infants show that the proposed method achieves better performance than other state-of-the-art automated segmentation methods. Further validation was performed on the MICCAI grand challenge and the proposed method was ranked top among all competing methods. Moreover, to alleviate the possible anatomical errors, our method can also be combined with an anatomically-constrained multi-atlas labeling approach for further improving the segmentation accuracy. (C) 2014 Elsevier Inc. All rights reserved.-
dc.languageEnglish-
dc.language.isoen-
dc.publisherACADEMIC PRESS INC ELSEVIER SCIENCE-
dc.subjectMR-IMAGES-
dc.subjectAUTOMATIC SEGMENTATION-
dc.subjectLONGITUDINAL DEVELOPMENT-
dc.subjectSPARSE REPRESENTATION-
dc.subjectTISSUE SEGMENTATION-
dc.subjectBIRTH-
dc.subjectPERFORMANCE-
dc.subjectSELECTION-
dc.subjectATLASES-
dc.subjectCORTEX-
dc.titleLINKS: Learning-based multi-source IntegratioN frameworK for Segmentation of infant brain images-
dc.typeArticle-
dc.contributor.affiliatedAuthorShen, Dinggang-
dc.identifier.doi10.1016/j.neuroimage.2014.12.042-
dc.identifier.scopusid2-s2.0-84920882082-
dc.identifier.wosid000349618600018-
dc.identifier.bibliographicCitationNEUROIMAGE, v.108, pp.160 - 172-
dc.relation.isPartOfNEUROIMAGE-
dc.citation.titleNEUROIMAGE-
dc.citation.volume108-
dc.citation.startPage160-
dc.citation.endPage172-
dc.type.rimsART-
dc.type.docTypeArticle-
dc.description.journalClass1-
dc.description.journalRegisteredClassscie-
dc.description.journalRegisteredClassscopus-
dc.relation.journalResearchAreaNeurosciences & Neurology-
dc.relation.journalResearchAreaRadiology, Nuclear Medicine & Medical Imaging-
dc.relation.journalWebOfScienceCategoryNeurosciences-
dc.relation.journalWebOfScienceCategoryNeuroimaging-
dc.relation.journalWebOfScienceCategoryRadiology, Nuclear Medicine & Medical Imaging-
dc.subject.keywordPlusMR-IMAGES-
dc.subject.keywordPlusAUTOMATIC SEGMENTATION-
dc.subject.keywordPlusLONGITUDINAL DEVELOPMENT-
dc.subject.keywordPlusSPARSE REPRESENTATION-
dc.subject.keywordPlusTISSUE SEGMENTATION-
dc.subject.keywordPlusBIRTH-
dc.subject.keywordPlusPERFORMANCE-
dc.subject.keywordPlusSELECTION-
dc.subject.keywordPlusATLASES-
dc.subject.keywordPlusCORTEX-
dc.subject.keywordAuthorInfant brain images-
dc.subject.keywordAuthorIsointense stage-
dc.subject.keywordAuthorRandom forest-
dc.subject.keywordAuthorMulti-modality-
dc.subject.keywordAuthorContext feature-
dc.subject.keywordAuthorTissue segmentation-
Files in This Item
There are no files associated with this item.
Appears in
Collections
Graduate School > Department of Artificial Intelligence > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE