Fully automatic segmentation of paraspinal muscles from 3D torso CT images via multi-scale iterative random forest classifications
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kamiya, Naoki | - |
dc.contributor.author | Li, Jing | - |
dc.contributor.author | Kume, Masanori | - |
dc.contributor.author | Fujita, Hiroshi | - |
dc.contributor.author | Shen, Dinggang | - |
dc.contributor.author | Zheng, Guoyan | - |
dc.date.accessioned | 2021-09-02T04:08:30Z | - |
dc.date.available | 2021-09-02T04:08:30Z | - |
dc.date.created | 2021-06-19 | - |
dc.date.issued | 2018-11 | - |
dc.identifier.issn | 1861-6410 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/71927 | - |
dc.description.abstract | PurposeTo develop and validate a fully automatic method for segmentation of paraspinal muscles from 3D torso CT images.MethodsWe propose a novel learning-based method to address this challenging problem. Multi-scale iterative random forest classifications with multi-source information are employed in this study to speed up the segmentation and to improve the accuracy. Here, multi-source images include the original torso CT images and later also the iteratively estimated and refined probability maps of the paraspinal muscles. We validated our method on 20 torso CT data with associated manual segmentation. We randomly partitioned the 20 CT data into two evenly distributed groups and took one group as the training data and the other group as the test data.ResultsThe proposed method achieved a mean Dice coefficient of 93.0%. It took on average 46.5s to segment a 3D torso CT image with the size ranging from 512x512x802 voxels 512 x 512 x 1031 voxels..ConclusionsOur fully automatic, learning-based method can accurately segment paraspinal muscles from 3D torso CT images. It generates segmentation results that are better than those achieved by the state-of-the-art methods. | - |
dc.language | English | - |
dc.language.iso | en | - |
dc.publisher | SPRINGER HEIDELBERG | - |
dc.subject | INDIVIDUAL MUSCLES | - |
dc.subject | AUTO-CONTEXT | - |
dc.subject | VOLUME | - |
dc.subject | WATER | - |
dc.subject | THIGH | - |
dc.subject | MRI | - |
dc.subject | FAT | - |
dc.title | Fully automatic segmentation of paraspinal muscles from 3D torso CT images via multi-scale iterative random forest classifications | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Shen, Dinggang | - |
dc.identifier.doi | 10.1007/s11548-018-1852-1 | - |
dc.identifier.scopusid | 2-s2.0-85053263313 | - |
dc.identifier.wosid | 000451461700002 | - |
dc.identifier.bibliographicCitation | INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, v.13, no.11, pp.1697 - 1706 | - |
dc.relation.isPartOf | INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY | - |
dc.citation.title | INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY | - |
dc.citation.volume | 13 | - |
dc.citation.number | 11 | - |
dc.citation.startPage | 1697 | - |
dc.citation.endPage | 1706 | - |
dc.type.rims | ART | - |
dc.type.docType | Article | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scie | - |
dc.description.journalRegisteredClass | scopus | - |
dc.relation.journalResearchArea | Engineering | - |
dc.relation.journalResearchArea | Radiology, Nuclear Medicine & Medical Imaging | - |
dc.relation.journalResearchArea | Surgery | - |
dc.relation.journalWebOfScienceCategory | Engineering, Biomedical | - |
dc.relation.journalWebOfScienceCategory | Radiology, Nuclear Medicine & Medical Imaging | - |
dc.relation.journalWebOfScienceCategory | Surgery | - |
dc.subject.keywordPlus | INDIVIDUAL MUSCLES | - |
dc.subject.keywordPlus | AUTO-CONTEXT | - |
dc.subject.keywordPlus | VOLUME | - |
dc.subject.keywordPlus | WATER | - |
dc.subject.keywordPlus | THIGH | - |
dc.subject.keywordPlus | MRI | - |
dc.subject.keywordPlus | FAT | - |
dc.subject.keywordAuthor | Paraspinal muscles | - |
dc.subject.keywordAuthor | CT | - |
dc.subject.keywordAuthor | Segmentation | - |
dc.subject.keywordAuthor | Random forest | - |
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.