Multiple-Instance Learning Algorithms for Computer-Aided Detection

Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on biomedical engineering Ročník 55; číslo 3; s. 1015 - 1021
Hlavní autoři:	Dundar, M. Murat, Fung, Glenn, Krishnapuram, Balaji, Rao, R. Bharat
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	United States IEEE 01.03.2008 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Algorithms Alternate optimization Artificial Intelligence Biomedical imaging Colonic Neoplasms - diagnostic imaging Computed tomography convex hull Design automation Fisher discriminant Humans Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Labeling Magnetic resonance imaging Medical diagnostic imaging multiple-instance learning (MIL) Pattern Recognition, Automated - methods Pulmonary Embolism - diagnostic imaging Radiography Reproducibility of Results Sensitivity and Specificity Studies Training data X-ray detection X-ray detectors X-ray imaging fisher discriminant alternate optimization convex hull multiple instance learning
ISSN:	0018-9294, 1558-2531
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally expensive for these datasets. We describe CH, a framework for learning a convex hull representation of multiple instances that is significantly faster than existing MIL algorithms. Our CH framework applies to any standard hyperplane-based learning algorithm, and for some algorithms, is guaranteed to find the global optimal solution. Experimental studies on two different CAD applications further demonstrate that the proposed algorithm significantly improves diagnostic accuracy when compared to both MIL and traditional classifiers. Although not designed for standard MIL problems (which have both positive and negative bags and relatively balanced datasets), comparisons against other MIL methods on benchmark problems also indicate that the proposed method is competitive with the state-of-the-art.
AbstractList	Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.o., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally expensive for these datasets. We describe CH, a framework for learning a convex huil representation of multiple instances that is significantly taster than existing MIL algorithms. Our CH framework apples to any standard hyperplane-based barring algorithm, and for some algorithms, is guaranteed to find the global optimal solution. Experimental studies on two different CAD applications further demonstrate that the proposed algorithm significantly improves diagnostic accuracy when compared to both MIL and traditional classifiers. Although not designed for standard MIL problems (which have both positive and negative bags and relatively balanced datasets), comparisons against ofter MIL methods on benchmark problems also indicate that the proposed method is competitive with the state-of-the-art. Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally expensive for these datasets. We describe CH, a framework for learning a Convex Hull representation of multiple instances that is significantly faster than existing MIL algorithms. Our CH framework applies to any standard hyperplane-based learning algorithm, and for some algorithms, is guaranteed to find the global optimal solution. Experimental studies on two different CAD applications further demonstrate that the proposed algorithm significantly improves diagnostic accuracy when compared to both MIL and traditional classifiers. Although not designed for standard MIL problems (which have both positive and negative bags and relatively balanced datasets), comparisons against other MIL methods on benchmark problems also indicate that the proposed method is competitive with the state-of-the-art. Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally expensive for these datasets. We describe CH, a framework for learning a convex hull representaion of multiple instances that is significantly faster than existing MIL algorithms. Our CH framework applies to any standard hyperpiane-based learning algorithm, and for some algorithms, is guaranteed to find the global optimal solution. Experimental studies on two different CAD applications further demonstrate that the proposed algorithm significantly improves diagnostic accuracy when compared to both MIL and traditional classifiers. Although not designed for standard MIL problems (which have both positive and negative bags and relatively balanced datasets), comparisons against other MIL methods on benchmark problems also indicate that the proposed method is competitive with the state-of-the-art. Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally expensive for these datasets. We describe CH, a framework for learning a Convex Hull representation of multiple instances that is significantly faster than existing MIL algorithms. Our CH framework applies to any standard hyperplane-based learning algorithm, and for some algorithms, is guaranteed to find the global optimal solution. Experimental studies on two different CAD applications further demonstrate that the proposed algorithm significantly improves diagnostic accuracy when compared to both MIL and traditional classifiers. Although not designed for standard MIL problems (which have both positive and negative bags and relatively balanced datasets), comparisons against other MIL methods on benchmark problems also indicate that the proposed method is competitive with the state-of-the-art.Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances. Existing MIL algorithms are much too computationally expensive for these datasets. We describe CH, a framework for learning a Convex Hull representation of multiple instances that is significantly faster than existing MIL algorithms. Our CH framework applies to any standard hyperplane-based learning algorithm, and for some algorithms, is guaranteed to find the global optimal solution. Experimental studies on two different CAD applications further demonstrate that the proposed algorithm significantly improves diagnostic accuracy when compared to both MIL and traditional classifiers. Although not designed for standard MIL problems (which have both positive and negative bags and relatively balanced datasets), comparisons against other MIL methods on benchmark problems also indicate that the proposed method is competitive with the state-of-the-art. Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data typically consists of a few positive bags, and a very large number of negative instances.
Author	Krishnapuram, Balaji Rao, R. Bharat Dundar, M. Murat Fung, Glenn
Author_xml	– sequence: 1 givenname: M. Murat surname: Dundar fullname: Dundar, M. Murat email: murat.dundar@siemens.com organization: Siemens Med. Solutions, Malvern – sequence: 2 givenname: Glenn surname: Fung fullname: Fung, Glenn organization: Siemens Med. Solutions, Malvern – sequence: 3 givenname: Balaji surname: Krishnapuram fullname: Krishnapuram, Balaji organization: Siemens Med. Solutions, Malvern – sequence: 4 givenname: R. Bharat surname: Rao fullname: Rao, R. Bharat organization: Siemens Med. Solutions, Malvern
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/18334393$$D View this record in MEDLINE/PubMed
BookMark	eNqN0Utv1DAUBWALtaLTwh4JCUUsYJXBr_ixnA4FKk3VTVlbjnNdXCXxYDsL_j0J03ZRCejKsvSda-ueU3Q0xhEQekPwmhCsP92cX12sKcZyrbFuOH-BVqRpVE0bRo7QCmOiak01P0GnOd_NV664eIlOiGKMM81W6Pxq6kvY91BfjrnY0UG1A5vGMN5Wm_42plB-DLnyMVXbOOynAqnehA666jMUcCXE8RU69rbP8Pr-PEPfv1zcbL_Vu-uvl9vNrnacqVI3suloC85LIa2XyrfaS7CkdQAMW9c6zinzjrZSW2-hawUX2ndAnZK-adgZ-niYu0_x5wS5mCFkB31vR4hTNkoKyjERZJYf_iklZpowqf8LKVZKC6qeA-VMl6ffP4F3cUrjvBejBBWUiD__e3ePpnaAzuxTGGz6ZR5qmYE4AJdizgm8caHYZdkl2dAbgs3Sv1n6N0v_5tD_HMRPgo-z_x55e4gEAHjknAlMGsx-A6yaue4
CODEN	IEBEAX
CitedBy_id	crossref_primary_10_1016_j_clineuro_2020_105718 crossref_primary_10_1016_j_media_2019_03_009 crossref_primary_10_1109_RBME_2009_2034022 crossref_primary_10_1007_s11467_024_1391_x crossref_primary_10_1109_TKDE_2022_3232141 crossref_primary_10_1097_RCT_0000000000001386 crossref_primary_10_1109_TBME_2016_2530141 crossref_primary_10_1155_2020_8594090 crossref_primary_10_1016_j_neunet_2018_05_001 crossref_primary_10_1109_RBME_2017_2651164 crossref_primary_10_1007_s40134_017_0241_9 crossref_primary_10_1109_TMI_2014_2350539 crossref_primary_10_1109_TPAMI_2011_194 crossref_primary_10_3724_SP_J_1089_2010_10502 crossref_primary_10_1016_j_compbiomed_2011_06_010 crossref_primary_10_1109_TNNLS_2019_2892409 crossref_primary_10_1109_TMI_2016_2521442 crossref_primary_10_1016_j_micron_2013_01_003 crossref_primary_10_1016_j_wneu_2019_03_165 crossref_primary_10_1148_rg_2017160130 crossref_primary_10_3390_app10082945 crossref_primary_10_1016_j_media_2014_01_010 crossref_primary_10_1049_iet_ipr_2017_0536 crossref_primary_10_3390_electronics12173634
Cites_doi	10.1117/12.481369 10.1007/978-1-4757-2440-0 10.1137/0111043 10.1259/bjr/25777270 10.1016/S0004-3702(96)00034-3 10.3322/canjclin.54.1.8 10.7551/mitpress/1113.003.0012
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2008
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2008
DBID	97E RIA RIE AAYXX CITATION CGR CUY CVF ECM EIF NPM 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
DOI	10.1109/TBME.2007.909544
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE/IET Electronic Library (IEL) (UW System Shared) CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE 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 Biotechnology and BioEngineering Abstracts MEDLINE - Academic
DatabaseTitle	CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) 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 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	Engineering Research Database MEDLINE Engineering Research Database MEDLINE - Academic Engineering Research Database Materials 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/IET Electronic Library (IEL) (UW System Shared) 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	1558-2531
EndPage	1021
ExternalDocumentID	2324548341 18334393 10_1109_TBME_2007_909544 4360150
Genre	orig-research Evaluation Studies Journal Article
GroupedDBID	--- -~X .55 .DC .GJ 0R~ 29I 4.4 53G 5GY 5RE 5VS 6IF 6IK 6IL 6IN 85S 97E AAJGR AARMG AASAJ AAWTH AAYJJ ABAZT ABJNI ABQJQ ABVLG ACGFO ACGFS ACIWK ACKIV ACNCT ACPRK ADZIZ AENEX AETIX AFFNX AFRAH AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CHZPO CS3 DU5 EBS EJD F5P HZ~ H~9 IAAWW IBMZZ ICLAB IDIHD IEGSK IFIPE IFJZH IPLJI JAVBF LAI MS~ O9- OCL P2P RIA RIE RIL RNS TAE TN5 VH1 VJK X7M ZGI ZXP AAYXX CITATION CGR CUY CVF ECM EIF NPM RIG 7QF 7QO 7QQ 7SC 7SE 7SP 7SR 7TA 7TB 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8
ID	FETCH-LOGICAL-c438t-575d2becf767af78fb9f7ea1bcee30acbc4423fc2b79afaedb6469fde2c87f553
IEDL.DBID	RIE
ISICitedReferencesCount	29
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000253733800018&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0018-9294
IngestDate	Tue Oct 07 09:25:38 EDT 2025 Sun Nov 09 11:35:34 EST 2025 Mon Oct 06 18:05:31 EDT 2025 Tue Oct 07 09:55:27 EDT 2025 Mon Jun 30 08:32:02 EDT 2025 Thu Apr 03 06:58:21 EDT 2025 Sat Nov 29 03:34:45 EST 2025 Tue Nov 18 21:46:36 EST 2025 Wed Aug 27 02:53:46 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Keywords	fisher discriminant alternate optimization convex hull multiple instance learning
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c438t-575d2becf767af78fb9f7ea1bcee30acbc4423fc2b79afaedb6469fde2c87f553
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23 ObjectType-Undefined-1 ObjectType-Feature-3
PMID	18334393
PQID	862621661
PQPubID	23462
PageCount	7
ParticipantIDs	proquest_miscellaneous_876240161 proquest_miscellaneous_20889628 proquest_journals_862621661 pubmed_primary_18334393 crossref_citationtrail_10_1109_TBME_2007_909544 proquest_miscellaneous_20878891 ieee_primary_4360150 proquest_miscellaneous_70391379 crossref_primary_10_1109_TBME_2007_909544
PublicationCentury	2000
PublicationDate	2008-03-01
PublicationDateYYYYMMDD	2008-03-01
PublicationDate_xml	– month: 03 year: 2008 text: 2008-03-01 day: 01
PublicationDecade	2000
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on biomedical engineering
PublicationTitleAbbrev	TBME
PublicationTitleAlternate	IEEE Trans Biomed Eng
PublicationYear	2008
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	mika (ref11) 2000; 12 ref15 zhou (ref18) 2003; 2837 ref14 mangasarian (ref8) 2005 mangasarian (ref9) 2000 lee (ref7) 2000 bezdek (ref2) 2003; 11 ref17 jerebko (ref6) 2006; 2837 maron (ref10) 1998; 10 ref4 ref3 andrews (ref1) 2003 zhang (ref16) 2001; 14 ref5 quist (ref12) 2004 ramon (ref13) 2000
References_xml	– volume: 14 start-page: 1073 year: 2001 ident: ref16 publication-title: Advances in neural information processing systems – year: 2000 ident: ref7 publication-title: RSVM Reduced support vector machines – ident: ref17 doi: 10.1117/12.481369 – volume: 2837 start-page: 492 year: 2003 ident: ref18 article-title: ensembles of multi-instance learners publication-title: Proc 14th Eur Conf Mach Learning – ident: ref14 doi: 10.1007/978-1-4757-2440-0 – volume: 10 year: 1998 ident: ref10 publication-title: Advances in Neural Information Processing Systems 10 – ident: ref15 doi: 10.1137/0111043 – start-page: 561 year: 2003 ident: ref1 publication-title: Advances in Neural Information Processing Systems 15 – volume: 12 start-page: 591 year: 2000 ident: ref11 publication-title: Advances in neural information processing systems – year: 2000 ident: ref13 article-title: multi instance neural networks publication-title: Proc ICML-2000 Workshop Attribute-Value and Relational Learning – volume: 11 start-page: 351 year: 2003 ident: ref2 article-title: convergence of alternating optimization publication-title: Neural Parallel Sci Comput – ident: ref3 doi: 10.1259/bjr/25777270 – ident: ref4 doi: 10.1016/S0004-3702(96)00034-3 – ident: ref5 doi: 10.3322/canjclin.54.1.8 – year: 2004 ident: ref12 article-title: computer-aided detection of pulmonary embolism on multi-detector ct publication-title: Proce 90th Meeting Radiol Soc North America (RSNA) – volume: 2837 start-page: 169 year: 2006 ident: ref6 article-title: symmetric curvature patterns for colonic polyp detection publication-title: Proc 14th Eur Conf Mach Learning – year: 2005 ident: ref8 publication-title: Multiple instance classification via successive linear programming – start-page: 135 year: 2000 ident: ref9 publication-title: Advances in Large Margin Classifiers doi: 10.7551/mitpress/1113.003.0012
SSID	ssj0014846
Score	2.0753293
Snippet	Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.e., the training data... Many computer-aided diagnosis (CAD) problems can be best modelled as a multiple-instance learning (MIL) problem with unbalanced data, i.o., the training data...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1015
SubjectTerms	Algorithms Alternate optimization Artificial Intelligence Biomedical imaging Colonic Neoplasms - diagnostic imaging Computed tomography convex hull Design automation Fisher discriminant Humans Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Labeling Magnetic resonance imaging Medical diagnostic imaging multiple-instance learning (MIL) Pattern Recognition, Automated - methods Pulmonary Embolism - diagnostic imaging Radiography Reproducibility of Results Sensitivity and Specificity Studies Training data X-ray detection X-ray detectors X-ray imaging
Title	Multiple-Instance Learning Algorithms for Computer-Aided Detection
URI	https://ieeexplore.ieee.org/document/4360150 https://www.ncbi.nlm.nih.gov/pubmed/18334393 https://www.proquest.com/docview/862621661 https://www.proquest.com/docview/20878891 https://www.proquest.com/docview/20889628 https://www.proquest.com/docview/70391379 https://www.proquest.com/docview/876240161
Volume	55
WOSCitedRecordID	wos000253733800018&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/IET Electronic Library (IEL) (UW System Shared) customDbUrl: eissn: 1558-2531 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014846 issn: 0018-9294 databaseCode: RIE dateStart: 19640101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Lb9NAEB6VCiE4UGh5mJbiAxckljje9T6OKbQCiVQcCsrNWq9n20jFQYnD72dfcUEilXqz5LHlndnRfOOZ_QbgLWpL_VRCwrnShLWFIdqlBUSbylpeNVwFxpsfX8X5uZzN1LcdeD-chUHE0HyGH_xlqOW3C7P2v8pGjPKYoN8TgsezWkPFgMl4KKcYOwcuFduUJAs1ujiZnkayQuUABQujeCSlLhTTf6JRGK-yHWmGiHO2d7dvfQKPE7LMJ3ErPIUd7Pbh0V98g_vwYJoq6QdwMk2dhORLAIgG80S1eplPri8Xy3l_9XOVO0ibbwY_kMm8xTb_hH1o3-qewfez04uPn0map0AMo7InDpm1pbOZFVxoK6RtlBWox40LlLTQpjHMgStrykYobTW2DXfJs22xNFLYqqLPYbdbdPgS8qpombE4lsblUyiZtKIpjHN-Ybh2Vs9gtNFrbRLZuJ95cV2HpKNQtTeKn4Ep6miUDN4NT_yKRBu3yB54hQ9ySdcZHG5MVydPXNU-YyvHDoVk8Ga461zI10V0h4v1yr1ZCinV7RJS8VJulxCeaZ8KlUG-RcKHHeYBdgYv4ra6WWfaja_-v65DeBi7VHzn2xHs9ss1vob75nc_Xy2PnTPM5HFwhj-6XgSv
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3db9MwED9NAwF74GMDlg1YHnhBwjSNHX88drBpE23FQ0F7ixznPCqNFLUpf_9sxw0g0Um8Rcoliu98ut_lzvcDeIvaUs9KSDhXmrA6M0S7tIBoU1jLi4qrMPHm21hMp_LqSn3Zgff9WRhEDM1n-MFfhlp-vTBr_6tswCjvEvR7njkrntbqawZMdsdysqFz4VyxTVEyU4PZ6eSsG1eoHKRggYxHUuqCMf0rHgWCle1YM8Sc8yf_97VP4XHElumo2wzPYAebfdj7Y-LgPjyYxFr6AZxOYi8huQwQ0WAah61ep6Ob68Vy3n7_sUodqE031A9kNK-xTj9hGxq4mufw9fxs9vGCREYFYhiVLXHYrM6d1azgQlshbaWsQD2sXKikmTaVYQ5eWZNXQmmrsa64S59tjbmRwhYFfQG7zaLBQ0iLrGbG4lAal1GhZNKKKjPO_YXh2tk9gcFGr6WJ48Y968VNGdKOTJXeKJ4FU5SdURJ41z_xsxu1cYfsgVd4Lxd1ncDxxnRl9MVV6XO2fOhwSAIn_V3nRL4yohtcrFfuzVJIqe6WkIrncruE8LP2qVAJpFskfOBhHmIn8LLbVr_XGXfj0b_XdQIPL2aTcTm-nH4-hkddz4rvg3sFu-1yja_hvvnVzlfLN8ElbgFJbwcQ
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=Multiple-instance+learning+algorithms+for+computer-aided+detection&rft.jtitle=IEEE+transactions+on+biomedical+engineering&rft.au=Dundar%2C+M+Murat&rft.au=Fung%2C+Glenn&rft.au=Krishnapuram%2C+Balaji&rft.au=Rao%2C+R+Bharat&rft.date=2008-03-01&rft.issn=0018-9294&rft.volume=55&rft.issue=3&rft.spage=1015&rft_id=info:doi/10.1109%2FTBME.2007.909544&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0018-9294&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0018-9294&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0018-9294&client=summon