3-D Fully Convolutional Networks for Multimodal Isointense Infant Brain Image Segmentation
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Nie, Dong | - |
dc.contributor.author | Wang, Li | - |
dc.contributor.author | Adeli, Ehsan | - |
dc.contributor.author | Lao, Cuijin | - |
dc.contributor.author | Lin, Weili | - |
dc.contributor.author | Shen, Dinggang | - |
dc.date.accessioned | 2021-09-01T18:15:36Z | - |
dc.date.available | 2021-09-01T18:15:36Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2019-03 | - |
dc.identifier.issn | 2168-2267 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/67203 | - |
dc.description.abstract | Accurate segmentation of infant brain images into different regions of interest is one of the most important fundamental steps in studying early brain development. In the isointense phase (approximately 6-8 months of age), white matter and gray matter exhibit similar levels of intensities in magnetic resonance (MR) images, due to the ongoing myelination and maturation. This results in extremely low tissue contrast and thus makes tissue segmentation very challenging. Existing methods for tissue segmentation in this isointense phase usually employ patch-based sparse labeling on single modality. To address the challenge, we propose a novel 3-D multimodal fully convolutional network (FCN) architecture for segmentation of isointense phase brain MR images. Specifically, we extend the conventional FCN architectures from 2-D to 3-D, and, rather than directly using FCN, we intuitively integrate coarse (naturally high-resolution) and dense (highly semantic) feature maps to better model tiny tissue regions, in addition, we further propose a transformation module to better connect the aggregating layers; we also propose a fusion module to better serve the fusion of feature maps. We compare the performance of our approach with several baseline and state-of-the-art methods on two sets of isointense phase brain images. The comparison results show that our proposed 3-D multimodal FCN model outperforms all previous methods by a large margin in terms of segmentation accuracy. In addition, the proposed framework also achieves faster segmentation results compared to all other methods. Our experiments further demonstrate that: 1) carefully integrating coarse and dense feature maps can considerably improve the segmentation performance; 2) batch normalization can speed up the convergence of the networks, especially when hierarchical feature aggregations occur; and 3) integrating multimodal information can further boost the segmentation performance. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC | - |
dc.subject | AUTOMATIC SEGMENTATION | - |
dc.subject | MR-IMAGES | - |
dc.subject | LONGITUDINAL DEVELOPMENT | - |
dc.subject | SURFACE-AREA | - |
dc.subject | BIRTH | - |
dc.subject | INTEGRATION | - |
dc.title | 3-D Fully Convolutional Networks for Multimodal Isointense Infant Brain Image Segmentation | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Shen, Dinggang | - |
dc.identifier.doi | 10.1109/TCYB.2018.2797905 | - |
dc.identifier.scopusid | 2-s2.0-85041812887 | - |
dc.identifier.wosid | 000458655900033 | - |
dc.identifier.bibliographicCitation | IEEE TRANSACTIONS ON CYBERNETICS, v.49, no.3, pp.1123 - 1136 | - |
dc.relation.isPartOf | IEEE TRANSACTIONS ON CYBERNETICS | - |
dc.citation.title | IEEE TRANSACTIONS ON CYBERNETICS | - |
dc.citation.volume | 49 | - |
dc.citation.number | 3 | - |
dc.citation.startPage | 1123 | - |
dc.citation.endPage | 1136 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Automation & Control Systems | - |
dc.relation.journalResearchArea | Computer Science | - |
dc.relation.journalWebOfScienceCategory | Automation & Control Systems | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Artificial Intelligence | - |
dc.relation.journalWebOfScienceCategory | Computer Science, Cybernetics | - |
dc.subject.keywordPlus | AUTOMATIC SEGMENTATION | - |
dc.subject.keywordPlus | MR-IMAGES | - |
dc.subject.keywordPlus | LONGITUDINAL DEVELOPMENT | - |
dc.subject.keywordPlus | SURFACE-AREA | - |
dc.subject.keywordPlus | BIRTH | - |
dc.subject.keywordPlus | INTEGRATION | - |
dc.subject.keywordAuthor | 3-D fully convolutional network (3D-FCN) | - |
dc.subject.keywordAuthor | brain MR image | - |
dc.subject.keywordAuthor | isointense phase | - |
dc.subject.keywordAuthor | multimodality MR images | - |
dc.subject.keywordAuthor | tissue segmentation | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.