Hybrid Genetic and Variational Expectation-Maximization Algorithm for Gaussian-Mixture-Model-Based Brain MR Image Segmentation

The expectation-maximization (EM) algorithm has been widely applied to the estimation of Gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper,...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on information technology in biomedicine Ročník 15; číslo 3; s. 373 - 380
Hlavní autoři:	Tian, GuangJian, Xia, Yong, Zhang, Yanning, Feng, Dagan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.05.2011
Témata:	Algorithms Bayes Theorem Brain - anatomy & histology Brain modeling Estimation Female Gallium Gaussian mixture model (GMM) genetic algorithm (GA) Genetic algorithms Humans Image Processing, Computer-Assisted - methods Image resolution Image segmentation Information technology Magnetic Resonance Imaging - methods Male MRI Normal Distribution variational Bayes inference
ISSN:	1089-7771, 1558-0032, 1558-0032
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	The expectation-maximization (EM) algorithm has been widely applied to the estimation of Gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.
AbstractList	The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation. The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However, the EM algorithm is deterministic and intrinsically prone to overfitting the training data and being trapped in local optima. In this paper, we propose a hybrid genetic and variational EM (GA-VEM) algorithm for brain MR image segmentation. In this approach, the VEM algorithm is performed to estimate the GMM, and the GA is employed to initialize the hyperparameters of the conjugate prior distributions of GMM parameters involved in the VEM algorithm. Since GA has the potential to achieve global optimization and VEM can steadily avoid overfitting, the hybrid GA-VEM algorithm is capable of overcoming the drawbacks of traditional EM-based methods. We compared our approach to the EM-based, VEM-based, and GA-EM based segmentation algorithms, and the segmentation routines used in the statistical parametric mapping package and FMRIB Software Library in 20 low-resolution and 17 high-resolution brain MR studies. Our results show that the proposed approach can improve substantially the performance of brain MR image segmentation.
Author	Yong Xia Yanning Zhang GuangJian Tian Dagan Feng
Author_xml	– sequence: 1 givenname: GuangJian surname: Tian fullname: Tian, GuangJian email: tianguangjian@gmail.com organization: China Realtime Database Co. Ltd, State Grid Electric Power Research Institute, Nanjing, China. tianguangjian@gmail.com – sequence: 2 givenname: Yong surname: Xia fullname: Xia, Yong – sequence: 3 givenname: Yanning surname: Zhang fullname: Zhang, Yanning – sequence: 4 givenname: Dagan surname: Feng fullname: Feng, Dagan
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/21233052$$D View this record in MEDLINE/PubMed
BookMark	eNqFkUuP0zAUhS00iHnAD0BIyDtWKb5-xM5yOho6laZCgsI2cuybYpRHsROpw4LfTjops2ABq_vQd-6VzrkkZ13fISGvgS0AWPF-u94uF5wBLDiwHIR6Ri5AKZMxJvjZ1DNTZFprOCeXKX1nDKQC8YKcc-BCMMUvyK-7hyoGT1fY4RActZ2nX20Mdgh9Zxt6e9ijGx6nbGMPoQ0_Hwd63ez6GIZvLa37SFd2TCnYiQmHYYyYbXqPTba0CT1dRhs6uvlE163dIf2Muxa7-eZL8ry2TcJXp3pFvny43d7cZfcfV-ub6_vMSamGTHBfWeNy40AVWHuLToNXzueF8iC8dtNGMq1EIXXNjK9qV2tZ8bquZMGduCLv5rv72P8YMQ1lG5LDprEd9mMqjZZgTMH5_8lcaqO0ZBP59kSOVYu-3MfQ2vhQ_jF3AmAGXOxTilg_IcDKY4DlMcDyGGB5CnDS6L80LsxWDZOLzT-Vb2ZlQMSnTyo3hotC_AZimanm
CODEN	ITIBFX
CitedBy_id	crossref_primary_10_1109_TASC_2014_2347316 crossref_primary_10_1016_j_engappai_2022_105079 crossref_primary_10_1016_j_neucom_2016_08_147 crossref_primary_10_1016_j_neucom_2012_12_081 crossref_primary_10_1007_s10489_014_0633_y crossref_primary_10_1016_j_eswa_2021_114591 crossref_primary_10_1109_TII_2018_2799928 crossref_primary_10_1007_s11042_021_10738_x crossref_primary_10_1109_TITB_2012_2227273 crossref_primary_10_1016_j_sigpro_2021_108141 crossref_primary_10_1186_s42492_020_00064_8 crossref_primary_10_1016_j_mri_2015_03_008 crossref_primary_10_1002_env_2871 crossref_primary_10_1007_s10772_019_09618_5 crossref_primary_10_1007_s11042_018_5792_0 crossref_primary_10_1109_JSEN_2023_3283863 crossref_primary_10_1002_tee_22272 crossref_primary_10_1007_s13735_018_0162_2 crossref_primary_10_1016_j_cviu_2016_04_004 crossref_primary_10_1016_j_cmpb_2013_06_006 crossref_primary_10_3390_diagnostics12102535 crossref_primary_10_1007_s13369_016_2278_0 crossref_primary_10_1007_s11831_018_9257_4 crossref_primary_10_1109_TSMC_2022_3212975 crossref_primary_10_1007_s10762_015_0146_8 crossref_primary_10_1016_j_bspc_2013_07_010 crossref_primary_10_1097_WNP_0b013e3182570f94 crossref_primary_10_1016_j_compbiomed_2012_11_001 crossref_primary_10_1002_cmr_a_21390 crossref_primary_10_1016_j_bbr_2016_09_022 crossref_primary_10_1002_ima_22267 crossref_primary_10_1155_2014_813197 crossref_primary_10_3390_e15083295 crossref_primary_10_1016_j_oceaneng_2024_117870 crossref_primary_10_1038_s41699_018_0084_0 crossref_primary_10_1002_jmri_24517 crossref_primary_10_1016_j_mri_2014_05_003 crossref_primary_10_1007_s11042_022_12335_y crossref_primary_10_1016_j_bbe_2019_04_004 crossref_primary_10_1016_j_inffus_2023_101987 crossref_primary_10_1134_S1054661819010115 crossref_primary_10_1007_s11042_018_6005_6 crossref_primary_10_1109_JIOT_2024_3412134 crossref_primary_10_1016_j_asoc_2015_05_039 crossref_primary_10_1109_TMI_2011_2165342 crossref_primary_10_1186_1687_6180_2014_59
Cites_doi	10.1016/0887-8994(91)90064-R 10.1109/TNN.2006.891114 10.1109/TSMCB.2006.872273 10.1118/1.1944912 10.1148/radiology.218.2.r01fe44586 10.1109/ISBI.2004.1398500 10.1109/TCBB.2007.70244 10.1109/TMI.2009.2014372 10.1109/42.906424 10.1109/TPAMI.2007.70775 10.1109/TBME.2007.895104 10.1109/42.20356 10.1002/int.10091 10.1109/TIP.2005.860624 10.1109/34.824822 10.1007/978-3-540-28650-9_3 10.1109/MSP.2008.929620 10.1109/42.932740 10.1016/S0167-9473(02)00177-9 10.1016/j.neuroimage.2004.07.051 10.1080/00949658908811178 10.1016/j.csda.2007.07.011 10.1006/nimg.2001.0800 10.1109/NSSMIC.2004.1466365 10.1016/S0031-3203(97)00045-9 10.1109/TMI.2007.895453 10.1109/TMI.2006.880668 10.1093/sysbio/45.3.380 10.1016/S0893-6080(97)00133-0 10.1109/42.650883 10.1007/978-3-540-85988-8_6 10.1109/TNN.2007.891635 10.1109/TPAMI.2005.162 10.1016/S1361-8415(01)00039-1 10.1109/TMI.2002.806587 10.1109/42.811270 10.1109/TMI.2006.880682
ContentType	Journal Article
DBID	97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 7QO 7TK 8FD FR3 P64
DOI	10.1109/TITB.2011.2106135
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic Biotechnology Research Abstracts Neurosciences Abstracts Technology Research Database Engineering Research Database Biotechnology and BioEngineering Abstracts
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic Engineering Research Database Biotechnology Research Abstracts Technology Research Database Neurosciences Abstracts Biotechnology and BioEngineering Abstracts
DatabaseTitleList	MEDLINE - Academic MEDLINE Engineering Research Database
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	1558-0032
EndPage	380
ExternalDocumentID	21233052 10_1109_TITB_2011_2106135 5688239
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS AETIX AGQYO AGSQL AHBIQ AI. AIBXA ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD F5P HZ~ H~9 IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P RIA RIE RNS TN5 VH1 AAYXX CITATION CGR CUY CVF ECM EIF NPM PKN RIG 7X8 7QO 7TK 8FD FR3 P64
ID	FETCH-LOGICAL-c445t-32dba8c68c159efdaec71d5cd695d13d7caec40753947f08dbfcf74b2ffb492c3
IEDL.DBID	RIE
ISICitedReferencesCount	73
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000290170300004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1089-7771 1558-0032
IngestDate	Tue Oct 07 09:24:52 EDT 2025 Fri Sep 05 05:01:44 EDT 2025 Wed Feb 19 01:48:35 EST 2025 Tue Nov 18 21:35:28 EST 2025 Sat Nov 29 05:35:19 EST 2025 Tue Aug 26 17:17:22 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c445t-32dba8c68c159efdaec71d5cd695d13d7caec40753947f08dbfcf74b2ffb492c3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23
PMID	21233052
PQID	864785740
PQPubID	23479
PageCount	8
ParticipantIDs	pubmed_primary_21233052 ieee_primary_5688239 crossref_primary_10_1109_TITB_2011_2106135 proquest_miscellaneous_864785740 crossref_citationtrail_10_1109_TITB_2011_2106135 proquest_miscellaneous_874188922
PublicationCentury	2000
PublicationDate	2011-May 2011-05-00 20110501
PublicationDateYYYYMMDD	2011-05-01
PublicationDate_xml	– month: 05 year: 2011 text: 2011-May
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States
PublicationTitle	IEEE transactions on information technology in biomedicine
PublicationTitleAbbrev	TITB
PublicationTitleAlternate	IEEE Trans Inf Technol Biomed
PublicationYear	2011
Publisher	IEEE
Publisher_xml	– name: IEEE
References	ref13 ref34 ref37 ref15 ref36 ref14 ref31 ref30 ref33 ref11 ref10 ref2 ref1 ref39 ref17 ref38 ref16 (ref35) 0 ref18 dimitris (ref19) 2003; 41 tipping (ref25) 2004 ref24 ref23 talairach (ref41) 1988 ref26 ref20 ref42 tohka (ref43) 0 ref22 ref44 goldberg (ref32) 1989 bishop (ref21) 2007 ref28 ref27 kaus (ref12) 2001; 218 ref29 ref8 ref7 ref9 ref4 ref3 ref6 ref5 (ref40) 0
References_xml	– ident: ref42 doi: 10.1016/0887-8994(91)90064-R – year: 0 ident: ref40 – ident: ref31 doi: 10.1109/TNN.2006.891114 – ident: ref30 doi: 10.1109/TSMCB.2006.872273 – ident: ref6 doi: 10.1118/1.1944912 – volume: 218 start-page: 586 year: 2001 ident: ref12 article-title: Automated segmentation of MR images of brain tumors publication-title: Radiology doi: 10.1148/radiology.218.2.r01fe44586 – ident: ref8 doi: 10.1109/ISBI.2004.1398500 – ident: ref27 doi: 10.1109/TCBB.2007.70244 – ident: ref3 doi: 10.1109/TMI.2009.2014372 – ident: ref13 doi: 10.1109/42.906424 – ident: ref28 doi: 10.1109/TPAMI.2007.70775 – ident: ref2 doi: 10.1109/TBME.2007.895104 – ident: ref15 doi: 10.1109/42.20356 – ident: ref37 doi: 10.1002/int.10091 – start-page: 461 year: 2007 ident: ref21 publication-title: Pattern Recognition and Machine Learning – ident: ref23 doi: 10.1109/TIP.2005.860624 – ident: ref1 doi: 10.1109/34.824822 – start-page: 41 year: 2004 ident: ref25 publication-title: Advanced Lectures on Machine Learning doi: 10.1007/978-3-540-28650-9_3 – year: 1988 ident: ref41 publication-title: Co-Planar Stereotaxic Atlas of the Human Brain – ident: ref20 doi: 10.1109/MSP.2008.929620 – ident: ref10 doi: 10.1109/42.932740 – year: 0 ident: ref43 – ident: ref26 doi: 10.1016/S0167-9473(02)00177-9 – year: 1989 ident: ref32 publication-title: Genetic Algorithms in Search Optimization and Machine Learning – ident: ref36 doi: 10.1016/j.neuroimage.2004.07.051 – ident: ref39 doi: 10.1080/00949658908811178 – ident: ref38 doi: 10.1016/j.csda.2007.07.011 – ident: ref11 doi: 10.1006/nimg.2001.0800 – ident: ref7 doi: 10.1109/NSSMIC.2004.1466365 – ident: ref16 doi: 10.1016/S0031-3203(97)00045-9 – ident: ref34 doi: 10.1109/TMI.2007.895453 – ident: ref5 doi: 10.1109/TMI.2006.880668 – ident: ref44 doi: 10.1093/sysbio/45.3.380 – ident: ref29 doi: 10.1016/S0893-6080(97)00133-0 – ident: ref14 doi: 10.1109/42.650883 – ident: ref22 doi: 10.1007/978-3-540-85988-8_6 – ident: ref4 doi: 10.1109/TNN.2007.891635 – year: 0 ident: ref35 – volume: 41 start-page: 577 year: 2003 ident: ref19 article-title: Choosing initial values for the EM algorithm for finite mixtures publication-title: Comput Stat Data Anal doi: 10.1016/S0167-9473(02)00177-9 – ident: ref33 doi: 10.1109/TPAMI.2005.162 – ident: ref9 doi: 10.1016/S1361-8415(01)00039-1 – ident: ref17 doi: 10.1109/TMI.2002.806587 – ident: ref18 doi: 10.1109/42.811270 – ident: ref24 doi: 10.1109/TMI.2006.880682
SSID	ssj0014513
Score	2.283194
Snippet	The expectation-maximization (EM) algorithm has been widely applied to the estimation of Gaussian mixture model (GMM) in brain MR image segmentation. However,... The expectation-maximization (EM) algorithm has been widely applied to the estimation of gaussian mixture model (GMM) in brain MR image segmentation. However,...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	373
SubjectTerms	Algorithms Bayes Theorem Brain - anatomy & histology Brain modeling Estimation Female Gallium Gaussian mixture model (GMM) genetic algorithm (GA) Genetic algorithms Humans Image Processing, Computer-Assisted - methods Image resolution Image segmentation Information technology Magnetic Resonance Imaging - methods Male MRI Normal Distribution variational Bayes inference
Title	Hybrid Genetic and Variational Expectation-Maximization Algorithm for Gaussian-Mixture-Model-Based Brain MR Image Segmentation
URI	https://ieeexplore.ieee.org/document/5688239 https://www.ncbi.nlm.nih.gov/pubmed/21233052 https://www.proquest.com/docview/864785740 https://www.proquest.com/docview/874188922
Volume	15
WOSCitedRecordID	wos000290170300004&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: 1558-0032 dateEnd: 20121231 omitProxy: false ssIdentifier: ssj0014513 issn: 1089-7771 databaseCode: RIE dateStart: 19970101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB61FUJw4NECXR6VD5wQponj57GLKO1hKwQL2luU-NGutJtF-6jKhd-OJ_FGIEElblFkJ5G-iT3jme8bgNfS-eCdF1TKmlFucB0UTlPFghaqEsq7rtmEurjQk4n5tANvey6M974tPvPv8LLN5buF3eBR2bGQ0R8szC7sKiU7rlafMeAiT8X0JnqMKk8ZzDwzx-Pz8bAT62QYABWiVQBmMZIX7I_tqO2v8m9Xs91yTh_-38c-ggfJtSQnnS08hh3f7MP93wQH9-HuKKXSD-Dn2Q8kaxHUnY4TSNU48i0GzulwkKAGsu3y9HRU3UznibBJTmaXi-V0fTUn0d8lH6vNCnmYdDS9wWQExeZqMzqMm6MjQ-w_QUafyfk8Llvki7-cJ6pT8wS-nn4Yvz-jqRkDtZyLNS2YqyttpbbRAfLBVd6q3AnrpBEuL5yy8U6MDkVhuAqZdnWwQfGahVBzw2zxFPaaReMPgUiMeaSJnkvteDBay8oyz4LzJljn-QCyLSalTUrl2DBjVrYRS2ZKRLRERMuE6ADe9FO-dzIdtw0-QLj6gQmpAZAt8GX8xzBxUjV-sVmVGgm5QvHsliGoAqQNYwN41tlM__itqT3_-2tfwL3unBqLKF_C3nq58a_gjr1eT1fLo2jqE33Umvov-5n6bw
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9QwEB6VgngceLQUlqcPnBBus44d28cuouyKZoVgQb1FiR_tSrtZtA9ULvx2PIk3AgkqcYsiO4n0TewZz3zfALzKrPPOOkGzrGKUa1wHhVVUMq-ELIV0tm02IcdjdXamP-7Am44L45xris_cIV42uXy7MBs8KjsSWfAHU30NrgvOWdKytbqcARf9WE6vg88o-zGH2U_00WQ0GbRynQxDoFQ0GsAsxPKC_bEhNR1W_u1sNpvOyb3_-9z7cDc6l-S4tYYHsOPqPbjzm-TgHtzMYzJ9H34OfyBdi6DydJhAytqSryF0jseDBFWQTZupp3l5OZ1HyiY5np0vltP1xZwEj5e8LzcrZGLSfHqJ6QiK7dVmdBC2R0sG2IGC5J_IaB4WLvLZnc8j2al-CF9O3k3eDmlsx0AN52JNU2arUplMmeACOW9LZ2TfCmMzLWw_tdKEOyE-FKnm0ifKVt54ySvmfcU1M-kB7NaL2j0GkmHUk-ngu1SWe61UVhrmmLdOe2Md70GyxaQwUascW2bMiiZmSXSBiBaIaBER7cHrbsq3VqjjqsH7CFc3MCLVA7IFvgh_GaZOytotNqtCISVXSJ5cMQR1gJRmrAePWpvpHr81tSd_f-1LuDWc5KfF6Wj84Sncbk-tsaTyGeyulxv3HG6Y7-vpavmiMfhfO2n8zg
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=Hybrid+Genetic+and+Variational+Expectation-Maximization+Algorithm+for+Gaussian-Mixture-Model-Based+Brain+MR+Image+Segmentation&rft.jtitle=IEEE+transactions+on+information+technology+in+biomedicine&rft.au=GuangJian+Tian&rft.au=Yong+Xia&rft.au=Yanning+Zhang&rft.au=Dagan+Feng&rft.date=2011-05-01&rft.issn=1089-7771&rft.eissn=1558-0032&rft.volume=15&rft.issue=3&rft.spage=373&rft.epage=380&rft_id=info:doi/10.1109%2FTITB.2011.2106135&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TITB_2011_2106135
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1089-7771&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1089-7771&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1089-7771&client=summon