SpineParseNet: Spine Parsing for Volumetric MR Image by a Two-Stage Segmentation Framework With Semantic Image Representation

Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intr...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on medical imaging Jg. 40; H. 1; S. 262 - 273
Hauptverfasser:	Pang, Shumao, Pang, Chunlan, Zhao, Lei, Chen, Yangfan, Su, Zhihai, Zhou, Yujia, Huang, Meiyan, Yang, Wei, Lu, Hai, Feng, Qianjin
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	United States IEEE 01.01.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	3D segmentation Computed tomography Deep learning graph convolution Graph representations Graphical representations Image processing Image representation Image segmentation Intervertebral discs Learning systems Magnetic resonance imaging Medical treatment Semantics Spine Three-dimensional displays Two dimensional displays Vertebrae
ISSN:	0278-0062, 1558-254X, 1558-254X
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments.
AbstractList	Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments. Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments.Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant role in various spinal disease diagnoses and treatments of spine disorders, yet is still a challenge due to the inter-class similarity and intra-class variation of spine images. Existing fully convolutional network based methods failed to explicitly exploit the dependencies between different spinal structures. In this article, we propose a novel two-stage framework named SpineParseNet to achieve automated spine parsing for volumetric MR images. The SpineParseNet consists of a 3D graph convolutional segmentation network (GCSN) for 3D coarse segmentation and a 2D residual U-Net (ResUNet) for 2D segmentation refinement. In 3D GCSN, region pooling is employed to project the image representation to graph representation, in which each node representation denotes a specific spinal structure. The adjacency matrix of the graph is designed according to the connection of spinal structures. The graph representation is evolved by graph convolutions. Subsequently, the proposed region unpooling module re-projects the evolved graph representation to a semantic image representation, which facilitates the 3D GCSN to generate reliable coarse segmentation. Finally, the 2D ResUNet refines the segmentation. Experiments on T2-weighted volumetric MR images of 215 subjects show that SpineParseNet achieves impressive performance with mean Dice similarity coefficients of 87.32 ± 4.75%, 87.78 ± 4.64%, and 87.49 ± 3.81% for the segmentations of 10 vertebrae, 9 IVDs, and all 19 spinal structures respectively. The proposed method has great potential in clinical spinal disease diagnoses and treatments.
Author	Zhou, Yujia Pang, Chunlan Chen, Yangfan Pang, Shumao Feng, Qianjin Zhao, Lei Su, Zhihai Huang, Meiyan Yang, Wei Lu, Hai
Author_xml	– sequence: 1 givenname: Shumao orcidid: 0000-0003-0409-8562 surname: Pang fullname: Pang, Shumao email: pangshumao@126.com organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China – sequence: 2 givenname: Chunlan surname: Pang fullname: Pang, Chunlan email: pangchl@sysucc.org.cn organization: Department of Nuclear Medicine, Sun Yat-sen University Cancer Center, Guangzhou, China – sequence: 3 givenname: Lei surname: Zhao fullname: Zhao, Lei email: lei6730@smu.edu.cn organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China – sequence: 4 givenname: Yangfan surname: Chen fullname: Chen, Yangfan email: cyangfan4@gmail.com organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China – sequence: 5 givenname: Zhihai surname: Su fullname: Su, Zhihai email: 13265092954@163.com organization: Department of Spinal Surgery, The Fifth Affiliated Hospital, Sun Yat-sen University, Zhuhai, China – sequence: 6 givenname: Yujia surname: Zhou fullname: Zhou, Yujia email: zyj.shmily08@gmail.com organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China – sequence: 7 givenname: Meiyan surname: Huang fullname: Huang, Meiyan email: huangmeiyan11@gmail.com organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China – sequence: 8 givenname: Wei orcidid: 0000-0002-2161-3231 surname: Yang fullname: Yang, Wei email: weiyanggm@gmail.com organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China – sequence: 9 givenname: Hai surname: Lu fullname: Lu, Hai email: hailu_nanfang@163.com organization: Department of Spinal Surgery, The Fifth Affiliated Hospital, Sun Yat-sen University, Zhuhai, China – sequence: 10 givenname: Qianjin orcidid: 0000-0001-8647-0596 surname: Feng fullname: Feng, Qianjin email: fengqj99@fimmu.com organization: Guangdong Provincial Key Laboratory of Medical Image Processing, School of Biomedical Engineering, Southern Medical University, Guangzhou, China
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/32956047$$D View this record in MEDLINE/PubMed
BookMark	eNp9kUtv1DAURi1URKcteyQkZIkNm0xv_MiDXVXRMlJbUGcK7CwnczO4JPZgO6q66H8nITMsumBlffI5V77-jsiBdRYJeZPCPE2hPF1dL-YMGMw5MAlF_oLMUimLhEnx44DMgOVFApCxQ3IUwj1AKiSUr8ghZ6XMQOQz8rTcGotftQ94g_Ej_RvpmI3d0MZ5-s21fYfRm5pe39JFpzdIq0eq6erBJcs4xiVuOrRRR-MsvfC6wwfnf9HvJv4c7jpt4yBP5i1uPYY9fEJeNroN-Hp3HpO7i0-r88_J1ZfLxfnZVVJzkcdEFjzNBANe4bqoM8kzxhtZsnRdi5xnouJNKZhuygpQsrKuRFHnzRq51ByEkPyYfJjmbr373WOIqjOhxrbVFl0fFBNCFLlkfETfP0PvXe_t8LqBykUhhWDFQL3bUX3V4Vptvem0f1T7jx2AbAJq70Lw2KjaTDtHr02rUlBjg2poUI0Nql2DgwjPxP3s_yhvJ8Ug4j-8ZDDQnP8BQ1-kog
CODEN	ITMID4
CitedBy_id	crossref_primary_10_1016_j_media_2021_102258 crossref_primary_10_1007_s11547_025_01996_y crossref_primary_10_1088_1361_6560_ad111b crossref_primary_10_1002_jor_25303 crossref_primary_10_1038_s41598_024_84301_7 crossref_primary_10_1109_TMI_2024_3367868 crossref_primary_10_1007_s11760_025_04531_8 crossref_primary_10_1016_j_compbiomed_2022_106079 crossref_primary_10_1016_j_media_2023_103061 crossref_primary_10_1186_s41747_023_00385_2 crossref_primary_10_1109_TCSVT_2023_3338860 crossref_primary_10_3390_bioengineering11101031 crossref_primary_10_1007_s11548_024_03219_7 crossref_primary_10_1016_j_compbiomed_2022_106190 crossref_primary_10_1002_ima_23174 crossref_primary_10_1016_j_compmedimag_2023_102244 crossref_primary_10_1109_TMI_2022_3179128 crossref_primary_10_1016_j_compmedimag_2023_102245 crossref_primary_10_1002_mp_16302 crossref_primary_10_1016_j_mri_2025_110505 crossref_primary_10_1007_s11760_024_03548_9 crossref_primary_10_1016_j_bspc_2025_107809 crossref_primary_10_1155_2022_4792532 crossref_primary_10_3390_math11143091 crossref_primary_10_1007_s10462_024_10918_9 crossref_primary_10_1016_j_media_2023_102786 crossref_primary_10_1016_j_media_2021_102261 crossref_primary_10_1007_s11831_022_09805_9 crossref_primary_10_1016_j_compbiomed_2024_108282 crossref_primary_10_1038_s41597_024_03090_w crossref_primary_10_1016_j_compmedimag_2025_102531 crossref_primary_10_1109_ACCESS_2022_3160179 crossref_primary_10_1155_2021_9654059 crossref_primary_10_1186_s13018_024_05002_5 crossref_primary_10_1016_j_bspc_2025_108137 crossref_primary_10_1016_j_media_2024_103283 crossref_primary_10_1007_s10278_025_01424_7 crossref_primary_10_1088_1361_6501_ad876d crossref_primary_10_1109_TIP_2021_3136619 crossref_primary_10_3390_bioengineering10080963 crossref_primary_10_1016_j_compbiomed_2024_108570 crossref_primary_10_3390_healthcare11040484 crossref_primary_10_1016_j_iot_2025_101709 crossref_primary_10_1109_TIP_2024_3431451 crossref_primary_10_1109_TMI_2024_3501365 crossref_primary_10_1016_j_bspc_2025_107956 crossref_primary_10_1002_jmri_28735 crossref_primary_10_1109_TIM_2024_3500060 crossref_primary_10_1111_os_13431 crossref_primary_10_3389_fphys_2023_1027076 crossref_primary_10_3390_math10050796 crossref_primary_10_7759_cureus_25686 crossref_primary_10_3390_ijerph191912857 crossref_primary_10_1016_j_bspc_2023_104918 crossref_primary_10_1088_1742_6596_2089_1_012013 crossref_primary_10_1016_j_artmed_2025_103247 crossref_primary_10_1038_s41551_025_01497_3 crossref_primary_10_1007_s11517_023_02963_3 crossref_primary_10_1007_s11263_024_02015_9 crossref_primary_10_1016_j_compbiomed_2023_106839 crossref_primary_10_1016_j_bspc_2023_105682 crossref_primary_10_1016_j_image_2023_117013 crossref_primary_10_3390_math10122099 crossref_primary_10_1109_ACCESS_2021_3131216 crossref_primary_10_3389_fnagi_2022_841297 crossref_primary_10_1016_j_media_2024_103380 crossref_primary_10_1007_s00521_025_11481_2 crossref_primary_10_1007_s42452_025_07138_3 crossref_primary_10_1016_j_jbo_2024_100649 crossref_primary_10_1002_mp_16467 crossref_primary_10_1002_jmri_28877 crossref_primary_10_1016_j_patcog_2025_111417 crossref_primary_10_1109_TIP_2024_3482189 crossref_primary_10_1177_02841851231204214 crossref_primary_10_1016_j_media_2023_102906 crossref_primary_10_1088_1361_6560_acaae9 crossref_primary_10_1016_j_bspc_2023_105278 crossref_primary_10_1088_1361_6560_acef9f crossref_primary_10_3389_fpubh_2022_926229 crossref_primary_10_3390_math10101665 crossref_primary_10_1016_j_eswa_2023_122330 crossref_primary_10_1016_j_artmed_2024_102771 crossref_primary_10_1109_JIOT_2024_3520994 crossref_primary_10_32604_cmes_2024_056424 crossref_primary_10_1177_08953996241299998 crossref_primary_10_1109_TIM_2022_3171613 crossref_primary_10_1109_ACCESS_2025_3555879 crossref_primary_10_1016_j_bspc_2025_108169 crossref_primary_10_1016_j_jvcir_2023_103991 crossref_primary_10_1109_JBHI_2022_3214999 crossref_primary_10_3389_fpubh_2022_863307 crossref_primary_10_1016_j_bspc_2022_104021 crossref_primary_10_1088_1361_6560_acb199 crossref_primary_10_1016_j_compmedimag_2022_102125 crossref_primary_10_1038_s41746_025_01964_w crossref_primary_10_1038_s41598_024_79244_y crossref_primary_10_1007_s10462_025_11185_y
Cites_doi	10.1109/TMI.2017.2667578 10.1109/COMPSAC.2019.00109 10.1109/CVPR.2017.195 10.1162/neco.1997.9.8.1735 10.1007/978-3-319-14148-0_18 10.1109/TMI.2013.2244903 10.1109/JBHI.2020.2969084 10.1109/JBHI.2018.2872810 10.1007/978-3-319-41827-8_10 10.1109/CVPR.2016.90 10.1016/j.neuroimage.2006.01.015 10.1016/j.media.2019.02.005 10.1016/j.media.2018.08.005 10.1016/j.media.2018.01.004 10.1088/0031-9155/57/24/8357 10.1109/CVPR.2019.00763 10.1016/j.spinee.2019.01.001 10.1109/ACCESS.2019.2962608 10.1109/ISBI.2018.8363715 10.1016/j.media.2012.06.006 10.1109/ISBI.2019.8759413 10.1007/978-3-319-43775-0_34 10.1006/cviu.1997.0608 10.1109/TBME.2012.2225833 10.1109/TMI.2019.2906727 10.1109/TMI.2015.2403285
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D NAPCQ P64 7X8
DOI	10.1109/TMI.2020.3025087
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Ceramic Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Nursing & Allied Health Premium Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef PubMed Materials Research Database Civil Engineering Abstracts Aluminium Industry Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Ceramic Abstracts Materials Business File METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Aerospace Database Nursing & Allied Health Premium Engineered Materials Abstracts Biotechnology Research Abstracts Solid State and Superconductivity Abstracts Engineering Research Database Corrosion Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic
DatabaseTitleList	Materials Research Database PubMed MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Medicine Engineering
EISSN	1558-254X
EndPage	273
ExternalDocumentID	32956047 10_1109_TMI_2020_3025087 9201093
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Science and Technology Project of Guangzhou grantid: 201704020033 – fundername: National Natural Science Foundation of China grantid: 81974275; U1501256; 81801780; 62001207 funderid: 10.13039/501100001809 – fundername: China Postdoctoral Science Foundation grantid: 2020M672712 funderid: 10.13039/501100002858
GroupedDBID	--- -DZ -~X .GJ 0R~ 29I 4.4 53G 5GY 5RE 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ACPRK AENEX AETIX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IBMZZ ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 VH1 AAYXX CITATION AAYOK NPM PKN RIG Z5M 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D NAPCQ P64 7X8
ID	FETCH-LOGICAL-c347t-583164203bed8c653623f5921dc47364b3f942af9b0e529cb48c7fde35a304453
IEDL.DBID	RIE
ISICitedReferencesCount	122
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000604883800023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0278-0062 1558-254X
IngestDate	Sun Sep 28 00:06:49 EDT 2025 Sun Jun 29 15:27:56 EDT 2025 Wed Feb 19 02:30:01 EST 2025 Sat Nov 29 05:14:08 EST 2025 Tue Nov 18 22:53:28 EST 2025 Wed Aug 27 02:32:37 EDT 2025
IsPeerReviewed	false
IsScholarly	true
Issue	1
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c347t-583164203bed8c653623f5921dc47364b3f942af9b0e529cb48c7fde35a304453
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-2161-3231 0000-0003-0409-8562 0000-0001-8647-0596
PMID	32956047
PQID	2474854428
PQPubID	85460
PageCount	12
ParticipantIDs	crossref_citationtrail_10_1109_TMI_2020_3025087 crossref_primary_10_1109_TMI_2020_3025087 ieee_primary_9201093 pubmed_primary_32956047 proquest_journals_2474854428 proquest_miscellaneous_2444875235
PublicationCentury	2000
PublicationDate	2021-Jan. 2021-1-00 2021-Jan 20210101
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– month: 01 year: 2021 text: 2021-Jan.
PublicationDecade	2020
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on medical imaging
PublicationTitleAbbrev	TMI
PublicationTitleAlternate	IEEE Trans Med Imaging
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref35 kingma (ref34) 2014 ref12 kipf (ref28) 2016; abs 1609 2907 ref15 chen (ref25) 2018 ref14 lee (ref33) 2017 ref31 ref30 ref11 sekuboyina (ref13) 2017 ref10 ref2 ref1 ref17 ronneberger (ref24) 2015 ref19 ref18 sekuboyina (ref16) 2017 çiçek (ref32) 2016 korez (ref9) 2015 ref23 ref26 ref20 ref22 ref21 ref27 ref29 ref8 ref7 ref4 ref3 ref6 ref5
References_xml	– ident: ref10 doi: 10.1109/TMI.2017.2667578 – start-page: 424 year: 2016 ident: ref32 article-title: 3D U-Net: Learning dense volumetric segmentation from sparse annotation publication-title: Proc Int Conf Med Image Comput Comput -Assist Intervent – ident: ref17 doi: 10.1109/COMPSAC.2019.00109 – ident: ref30 doi: 10.1109/CVPR.2017.195 – volume: abs 1609 2907 year: 2016 ident: ref28 article-title: Semi-supervised classification with graph convolutional networks publication-title: CoRR – ident: ref26 doi: 10.1162/neco.1997.9.8.1735 – ident: ref3 doi: 10.1007/978-3-319-14148-0_18 – ident: ref7 doi: 10.1109/TMI.2013.2244903 – ident: ref20 doi: 10.1109/JBHI.2020.2969084 – ident: ref21 doi: 10.1109/JBHI.2018.2872810 – ident: ref4 doi: 10.1007/978-3-319-41827-8_10 – ident: ref23 doi: 10.1109/CVPR.2016.90 – ident: ref31 doi: 10.1016/j.neuroimage.2006.01.015 – ident: ref19 doi: 10.1016/j.media.2019.02.005 – year: 2014 ident: ref34 article-title: Adam: A method for stochastic optimization publication-title: Proc 3rd Int Conf Learn Representations – ident: ref27 doi: 10.1016/j.media.2018.08.005 – start-page: 801 year: 2018 ident: ref25 article-title: Encoder-decoder with atrous separable convolution for semantic image segmentation publication-title: Proc Eur Conf Comput Vis (ECCV) – year: 2017 ident: ref16 article-title: A localisation-segmentation approach for multi-label annotation of lumbar vertebrae using deep nets publication-title: arXiv 1703 04347 – ident: ref15 doi: 10.1016/j.media.2018.01.004 – ident: ref6 doi: 10.1088/0031-9155/57/24/8357 – ident: ref29 doi: 10.1109/CVPR.2019.00763 – ident: ref1 doi: 10.1016/j.spinee.2019.01.001 – ident: ref22 doi: 10.1109/ACCESS.2019.2962608 – ident: ref14 doi: 10.1109/ISBI.2018.8363715 – ident: ref8 doi: 10.1016/j.media.2012.06.006 – ident: ref18 doi: 10.1109/ISBI.2019.8759413 – start-page: 117 year: 2015 ident: ref9 article-title: Deformable model-based segmentation of intervertebral discs from MR spine images by using the SSC descriptor publication-title: Proc Int Workshop Challenge Comput Methods Clin Appl Spine Imag – ident: ref12 doi: 10.1007/978-3-319-43775-0_34 – start-page: 108 year: 2017 ident: ref13 article-title: Attention-driven deep learning for pathological spine segmentation publication-title: Proc Int Workshop Challenge Comput Methods Clin Appl Musculoskeletal Imag – start-page: 234 year: 2015 ident: ref24 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput Comput -Assist Intervent – ident: ref2 doi: 10.1006/cviu.1997.0608 – ident: ref5 doi: 10.1109/TBME.2012.2225833 – ident: ref35 doi: 10.1109/TMI.2019.2906727 – ident: ref11 doi: 10.1109/TMI.2015.2403285 – year: 2017 ident: ref33 article-title: Superhuman accuracy on the SNEMI3D connectomics challenge publication-title: arXiv 1706 00120 [cs]
SSID	ssj0014509
Score	2.6297758
Snippet	Spine parsing (i.e., multi-class segmentation of vertebrae and intervertebral discs (IVDs)) for volumetric magnetic resonance (MR) image plays a significant...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	262
SubjectTerms	3D segmentation Computed tomography Deep learning graph convolution Graph representations Graphical representations Image processing Image representation Image segmentation Intervertebral discs Learning systems Magnetic resonance imaging Medical treatment Semantics Spine Three-dimensional displays Two dimensional displays Vertebrae
Title	SpineParseNet: Spine Parsing for Volumetric MR Image by a Two-Stage Segmentation Framework With Semantic Image Representation
URI	https://ieeexplore.ieee.org/document/9201093 https://www.ncbi.nlm.nih.gov/pubmed/32956047 https://www.proquest.com/docview/2474854428 https://www.proquest.com/docview/2444875235
Volume	40
WOSCitedRecordID	wos000604883800023&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1558-254X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014509 issn: 0278-0062 databaseCode: RIE dateStart: 19820101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61FUJwKNBSCJTKSFyQCOv4sY57Q4gVldhV1S6wt8h2HKjEZqs226oH_nvHzkM9ABKnxPI4ifSNY3-eF8AbX5WZ1VymVFiXCst9qnOjUqorQ6WzGS1j1ZIvajbLFwt9vAHvhlgY7310PvPvw2205Zcrtw5HZSMdTLeab8KmUqqN1RosBkK27hwsZIylY9abJKkezadHSAQZ8tOw4Oeh7h5ngReEmip3VqNYXuXvO8244kwe_d-3PobtbmdJPrSq8AQ2fL0DD-_kG9yB-9POkr4Lv0_P8XqMtNbPfHNIYpOENkoS3MmSb_G_FRL4k-kJOVrij4fYG2LI_HqV4h4Vm6f-x7KLXarJpHfzIt_Pmp_Yt0TQcHA78iR63PbCT-Hr5NP84-e0K8WQOi5UE2KzkFcxyq0vczeWuOzxSmqWlU4oPkaMKy2YqbSlXjLtrMidqkrPpeFUCMn3YKte1f45EFPmNtPaCkFNYFe6otpIqUyZlcbkLIFRD0nhujzloVzGryLyFaoLxLMIeBYdngm8HUactzk6_iG7G7Aa5DqYEtjvUS-6SXxZMKFELgUStAReD904_YJNxdR-tQ4yIlA-xmUCz1ptGZ7dK9mLP7_zJTxgwUEmnufsw1Zzsfav4J67as4uLw5Qxxf5QdTxW7T_9Ko
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Zb9QwEB6VgjgeOFqOQAEj8YLUsI6PTcwbQqy6YndVtQv0LfIVqMRmqzYL4oH_jsc51AdA4imxPE4ifePMjOcCeOkrlxnFZUqFsakw3Keq0HlKVaWptCajLnYtmeWLRXFyog63YH_IhfHex-Az_xpvoy_fre0Gj8pGCl23il-Bq1IIlrXZWoPPQMg2oINhzVg6Zr1TkqrRcj4NpiALFiqK_AI773GGlgF2Vbkkj2KDlb_rmlHmTO7839fehdudbknetsxwD7Z8vQO3LlUc3IHr886Xvgu_js_C9TAYtn7hmzckDgmOAyUJuiz5FP9cWMKfzI_IdBV-PcT8JJosf6zToKWG4bH_suqyl2oy6QO9yOfT5muYWwXYwuJ25VGMue2J78PHyfvlu4O0a8aQWi7yBrOzgmXFKDfeFXYsg-DjlVQsc1bkfBxQrpRgulKGesmUNaKweeU8l5pTISR_ANv1uvaPgGhXmEwpIwTVaF-piiotZa5d5rQuWAKjHpLSdpXKsWHGtzJaLFSVAc8S8Sw7PBN4Naw4a6t0_IN2F7Ea6DqYEtjrUS-7bXxRMpGLAnmtSODFMB02IHpVdO3XG6QRaPQxLhN42HLL8OyeyR7_-Z3P4cbBcj4rZ9PFhydwk2G4TDzd2YPt5nzjn8I1-705vTh_Fjn9N9AH9wk
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=SpineParseNet%3A+Spine+Parsing+for+Volumetric+MR+Image+by+a+Two-Stage+Segmentation+Framework+With+Semantic+Image+Representation&rft.jtitle=IEEE+transactions+on+medical+imaging&rft.au=Pang%2C+Shumao&rft.au=Pang%2C+Chunlan&rft.au=Zhao%2C+Lei&rft.au=Chen%2C+Yangfan&rft.date=2021-01-01&rft.pub=IEEE&rft.issn=0278-0062&rft.volume=40&rft.issue=1&rft.spage=262&rft.epage=273&rft_id=info:doi/10.1109%2FTMI.2020.3025087&rft_id=info%3Apmid%2F32956047&rft.externalDocID=9201093
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0278-0062&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0278-0062&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0278-0062&client=summon