Discriminant Convex Non-negative Matrix Factorization for the classification of human brain tumours

•Brain tumours can be diagnosed on the basis of magnetic resonance spectroscopy (MRS).•A new method to introduce class information into a convex variant of NMF is presented.•Novel techniques for diagnostic predictions of unseen MRS are described.•The new method and techniques are experimentally asse...

Full description

Saved in:
Bibliographic Details
Published in:Pattern recognition letters Vol. 34; no. 14; pp. 1734 - 1747
Main Authors: Vilamala, Albert, Lisboa, Paulo J.G., Ortega-Martorell, Sandra, Vellido, Alfredo
Format: Journal Article Publication
Language:English
Published: Elsevier B.V 15.10.2013
Subjects:
ISSN:0167-8655, 1872-7344
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract •Brain tumours can be diagnosed on the basis of magnetic resonance spectroscopy (MRS).•A new method to introduce class information into a convex variant of NMF is presented.•Novel techniques for diagnostic predictions of unseen MRS are described.•The new method and techniques are experimentally assessed with real MRS data.•The new methods are predictive and generate very tumour type-specific MRS sources. The medical analysis of human brain tumours commonly relies on indirect measurements. Among these, magnetic resonance imaging (MRI) and spectroscopy (MRS) predominate in clinical settings as tools for diagnostic assistance. Pattern recognition (PR) methods have successfully been used in this task, usually interpreting diagnosis as a supervised classification problem. In MRS, the acquired spectral signal can be analyzed in an unsupervised manner to extract its constituent sources. Recently, this has been successfully accomplished using Non-negative Matrix Factorization (NMF) methods. In this paper, we present a method to introduce the available class information into the unsupervised source extraction process of a convex variant of NMF. Novel techniques to generate diagnostic predictions for new, unseen spectra using the proposed Discriminant Convex-NMF are also described and experimentally assessed.
AbstractList •Brain tumours can be diagnosed on the basis of magnetic resonance spectroscopy (MRS).•A new method to introduce class information into a convex variant of NMF is presented.•Novel techniques for diagnostic predictions of unseen MRS are described.•The new method and techniques are experimentally assessed with real MRS data.•The new methods are predictive and generate very tumour type-specific MRS sources. The medical analysis of human brain tumours commonly relies on indirect measurements. Among these, magnetic resonance imaging (MRI) and spectroscopy (MRS) predominate in clinical settings as tools for diagnostic assistance. Pattern recognition (PR) methods have successfully been used in this task, usually interpreting diagnosis as a supervised classification problem. In MRS, the acquired spectral signal can be analyzed in an unsupervised manner to extract its constituent sources. Recently, this has been successfully accomplished using Non-negative Matrix Factorization (NMF) methods. In this paper, we present a method to introduce the available class information into the unsupervised source extraction process of a convex variant of NMF. Novel techniques to generate diagnostic predictions for new, unseen spectra using the proposed Discriminant Convex-NMF are also described and experimentally assessed.
The medical analysis of human brain tumours commonly relies on indirect measurements. Among these, magnetic resonance imaging (MRI) and spectroscopy (MRS) predominate in clinical settings as tools for diagnostic assistance. Pattern recognition (PR) methods have successfully been used in this task, usually interpreting diagnosis as a supervised classification problem. In MRS, the acquired spectral signal can be analyzed in an unsupervised manner to extract its constituent sources. Recently, this has been successfully accomplished using Non-negative Matrix Factorization (NMF) methods. In this paper, we present a method to introduce the available class information into the unsupervised source extraction process of a convex variant of NMF. Novel techniques to generate diagnostic predictions for new, unseen spectra using the proposed Discriminant Convex-NMF are also described and experimentally assessed. Peer Reviewed
Author Ortega-Martorell, Sandra
Lisboa, Paulo J.G.
Vilamala, Albert
Vellido, Alfredo
Author_xml – sequence: 1
  givenname: Albert
  surname: Vilamala
  fullname: Vilamala, Albert
  email: avilamala@lsi.upc.edu
  organization: Universitat Politècnica de Catalunya, Departament de Llenguatges i Sistemes Informàtics, Barcelona, Spain
– sequence: 2
  givenname: Paulo J.G.
  surname: Lisboa
  fullname: Lisboa, Paulo J.G.
  organization: Liverpool John Moores University, Department of Mathematics and Statistics, Liverpool, United Kingdom
– sequence: 3
  givenname: Sandra
  surname: Ortega-Martorell
  fullname: Ortega-Martorell, Sandra
  organization: Departament de Bioquímica i Biología Molecular, Universitat Autònoma de Barcelona (UAB), Cerdanyola del Vallès, Barcelona, Spain
– sequence: 4
  givenname: Alfredo
  surname: Vellido
  fullname: Vellido, Alfredo
  organization: Universitat Politècnica de Catalunya, Departament de Llenguatges i Sistemes Informàtics, Barcelona, Spain
BookMark eNqFkMtKQzEQhoMoWC9v4CIvcI65nEuOC0GqVaHqRtchJ2eiKW1SkrSoT29qC4ILXQxhhvl-Jt8R2nfeAUJnlJSU0OZ8Vi5VCqBLRigvSV0SxvfQiIqWFS2vqn00ymttIZq6PkRHMc4IIQ3vxAjpaxt1sAvrlEt47N0a3vGjd4WDV5XsGvBDjrbveKJ08sF-5qF32PiA0xtgPVcxWmP1duwNflstlMN9UNbhtFr4VYgn6MCoeYTT3XuMXiY3z-O7Yvp0ez--mhaaVyIVAzBmuFZkaKmCBkRHTN-bXlQNH0AIonquhxY6KqBVjPeED3VFGam7wbCq5ceIbnN1XGmZfUDId0mv7E-zKUZaJhntGK8zU-2Y4GMMYOQy21DhQ1IiN3LlTG7lyo1cSWqZ5Wbs4hembfp2kPLP5__Bl1sYsoy1hSCjtuA0DDavJjl4-3fAFwjznKg
CitedBy_id crossref_primary_10_1155_2014_608158
crossref_primary_10_1002_nbm_5020
crossref_primary_10_1002_nbm_3439
crossref_primary_10_1002_nbm_4193
crossref_primary_10_1038_s41598_020_76686_y
crossref_primary_10_1109_TCSVT_2016_2539779
crossref_primary_10_3390_cancers15154002
crossref_primary_10_1016_j_eswa_2014_02_031
crossref_primary_10_1109_ACCESS_2018_2854232
crossref_primary_10_1371_journal_pone_0083773
Cites_doi 10.1002/mrm.10595
10.1371/journal.pone.0047824
10.1016/j.patrec.2004.02.002
10.1007/s10334-008-0146-y
10.1002/sim.1321
10.1016/j.crad.2003.08.006
10.1109/TMI.2004.834626
10.1038/44565
10.1111/j.2517-6161.1977.tb01600.x
10.1109/MCI.2009.935311
10.1016/j.patcog.2004.02.013
10.1109/TNN.2006.873291
10.1002/(SICI)1099-1492(199806/08)11:4/5<225::AID-NBM509>3.0.CO;2-Q
10.1002/nbm.1797
10.1109/LSP.2009.2027163
10.1016/j.crad.2006.09.012
10.1002/nbm.1016
10.1109/TPAMI.2008.277
10.1007/s10334-005-0023-x
10.1002/1099-1492(200005)13:3<129::AID-NBM619>3.0.CO;2-V
10.1162/neco.2007.19.10.2756
10.1016/j.neucom.2009.07.018
10.1007/s00401-007-0243-4
10.1002/(SICI)1099-1492(199705)10:3<99::AID-NBM461>3.0.CO;2-#
10.1109/TIFS.2007.902017
10.1142/S0218001405004198
10.1109/ICMLC.2011.6016680
10.1109/ICPR.2010.764
10.1016/j.patrec.2009.09.011
ContentType Journal Article
Publication
Contributor Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics
Universitat Politècnica de Catalunya. SOCO - Soft Computing
Contributor_xml – sequence: 1
  fullname: Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics
– sequence: 2
  fullname: Universitat Politècnica de Catalunya. SOCO - Soft Computing
Copyright 2013 Elsevier B.V.
info:eu-repo/semantics/openAccess
Copyright_xml – notice: 2013 Elsevier B.V.
– notice: info:eu-repo/semantics/openAccess
DBID AAYXX
CITATION
XX2
DOI 10.1016/j.patrec.2013.05.023
DatabaseName CrossRef
Recercat
DatabaseTitle CrossRef
DatabaseTitleList

DeliveryMethod fulltext_linktorsrc
Discipline Engineering
Computer Science
EISSN 1872-7344
EndPage 1747
ExternalDocumentID oai_recercat_cat_2072_219235
10_1016_j_patrec_2013_05_023
S0167865513002213
GroupedDBID --M
.DC
.~1
0R~
123
1RT
1~.
1~5
4.4
457
4G.
53G
5VS
7-5
71M
8P~
9JN
AABNK
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
J1W
JJJVA
KOM
LG9
LY1
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
RNS
ROL
SDF
SDG
SDP
SES
SPC
SPCBC
SST
SSV
SSZ
T5K
TN5
UNMZH
WH7
XPP
ZMT
~G-
--K
1B1
29O
9DU
AAQXK
AATTM
AAXKI
AAYWO
AAYXX
ABDPE
ABWVN
ACLOT
ACNNM
ACRPL
ACVFH
ADCNI
ADJOM
ADMUD
ADMXK
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
ASPBG
AVWKF
AZFZN
CITATION
EFKBS
EJD
FEDTE
FGOYB
HLZ
HVGLF
HZ~
IHE
R2-
RPZ
SBC
SDS
SEW
VOH
WUQ
Y6R
~HD
XX2
ID FETCH-LOGICAL-c348t-de22f3ca0d71ae6e890fbbfb8463de880ab3cd7e918e7a23b03d5412059df2473
ISICitedReferencesCount 14
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000323794200020&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0167-8655
IngestDate Fri Nov 07 13:54:27 EST 2025
Sat Nov 29 03:58:38 EST 2025
Tue Nov 18 20:40:14 EST 2025
Fri Feb 23 02:26:35 EST 2024
IsDoiOpenAccess true
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Issue 14
Keywords Magnetic resonance spectroscopy
Discriminant Convex Non-negative Matrix Factorization
Source separation
Brain tumours
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c348t-de22f3ca0d71ae6e890fbbfb8463de880ab3cd7e918e7a23b03d5412059df2473
OpenAccessLink https://recercat.cat/handle/2072/219235
PageCount 14
ParticipantIDs csuc_recercat_oai_recercat_cat_2072_219235
crossref_primary_10_1016_j_patrec_2013_05_023
crossref_citationtrail_10_1016_j_patrec_2013_05_023
elsevier_sciencedirect_doi_10_1016_j_patrec_2013_05_023
PublicationCentury 2000
PublicationDate 2013-10-15
PublicationDateYYYYMMDD 2013-10-15
PublicationDate_xml – month: 10
  year: 2013
  text: 2013-10-15
  day: 15
PublicationDecade 2010
PublicationTitle Pattern recognition letters
PublicationYear 2013
Publisher Elsevier B.V
Publisher_xml – name: Elsevier B.V
References Ladroue, Howe, Griffiths, Tate (b0085) 2003; 50
Wild, Curry, Dougherty (b0175) 2004; 37
Fan, Sun, Wu, Guo, Guo (b0030) 2004; 59
Kotsia, Zafeiriou, Pitas (b0080) 2007; 2
Louis, Ohgaki, Wiestler, Cavenee, Burger, Jouvet, Scheithauer, Kleihues (b0125) 2007; 114
Sajda, Du, Brown, Stoyanova, Shungu, Mao, Parra (b0140) 2004; 23
Vellido, Romero, Julià-Sapé, Majós, Moreno-Torres, Arús (b0155) 2012; 25
Lee, Seung (b0090) 1999; 401
Han, Li (b0050) 2011; 12
Lee, D.D., Seung, H.S., 2001. Algorithms for non-negative matrix factorization. In: Advances in Neural Information Processing Systems (NIPS), pp. 556–562.
Liu, Zheng (b0120) 2004; 25
Tate, Underwood, Acosta, Julià-Sapé, Majós, Moreno-Torres, Howe, van der Graaf, Lefournier, Murphy, Loosemore, Ladroue, Wesseling, Bosson, Cabañas, Simonetti, Gajewicz, Calvar, Capdevila, Wilkins, Bell, Rémy, Heerschap, Watson, Griffiths, Arús (b0150) 2006; 19
Ortega-Martorell, Lisboa, Vellido, Simões, Pumarola, Julià-Sapé, Arús (b0135) 2012; 7
Govindaraju, Young, Maudsley (b0045) 2000; 13
González-Navarro, Belanche-Muñoz, Romero, Vellido, Julià-Sapé, Arús (b0040) 2010; 73
Hollingworth, Medina, Lenkinski, Shibata, Bernal, Zurakowski, Comstock, Jarvik (b0055) 2006; 27
Julià-Sapé, Acosta, Mier, Arús, Watson (b0075) 2006; 19
Zafeiriou, Tefas, Buciu, Pitas (b0180) 2006; 17
García-Gómez, Luts, Julià-Sapé, Krooshof, Tortajada, Robledo, Melssen, Fuster-García, Olier, Postma, Monleón, Moreno-Torres, Pujol, Candiota, Martínez-Bisbal, Suykens, Buydens, Celda, Van Huffel, Arús, Robles (b0035) 2009; 22
IMM, 2006. NMF: DTU Toolbox. Collection of NMF algorithms implemented for Matlab. Technical University of Denmark. URL
Lisboa, Vellido, Tagliaferri, Napolitano, Ceccarelli, Martín-Guerrero, Biganzoli (b0115) 2010; 5
Wang, Li, Zhang (b0165) 2008
El-Deredy (b0025) 1997; 10
Ortega-Martorell, Lisboa, Vellido, Julià-Sapé, Arús (b0130) 2012; 13
Dempster, Laird, Rubin (b0010) 1977; 39
Lee, Yoo, Choi (b0100) 2010; 17
Sibtain, Howe, Saunders (b0145) 2007; 62
Ding, X., Lee, J.H., Lee, S.W., 2011. A constrained alternating least squares nonnegative matrix factorization algorithm enhances task-related neuronal activity detection from single subjects fMRI data. In: Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC), vol. 1, pp. 338–343.
Lisboa, Kirby, Vellido, Lee, El-Deredy (b0110) 1998; 11
Brodersen, K.H., Ong, C.S., Stephan, K.E., Buhmann, J.M., 2010. The balanced accuracy and its posterior distribution. In: Proceedings of the IEEE 2010 International Conference on, Pattern Recognition (ICPR), pp. 3121–3124.
Jain (b0070) 2010; 31
Ding, Li, Jordan (b0015) 2010; 32
Lin (b0105) 2007; 19
.
Huang, Lisboa, El-Deredy (b0060) 2003; 22
Vilamala, Belanche, Vellido (b0160) 2012
Wang, Jia, Hu, Turk (b0170) 2005; 19
Govindaraju (10.1016/j.patrec.2013.05.023_b0045) 2000; 13
10.1016/j.patrec.2013.05.023_b0095
Jain (10.1016/j.patrec.2013.05.023_b0070) 2010; 31
Lee (10.1016/j.patrec.2013.05.023_b0100) 2010; 17
Sajda (10.1016/j.patrec.2013.05.023_b0140) 2004; 23
Huang (10.1016/j.patrec.2013.05.023_b0060) 2003; 22
Wang (10.1016/j.patrec.2013.05.023_b0165) 2008
Lisboa (10.1016/j.patrec.2013.05.023_b0110) 1998; 11
Tate (10.1016/j.patrec.2013.05.023_b0150) 2006; 19
Fan (10.1016/j.patrec.2013.05.023_b0030) 2004; 59
Hollingworth (10.1016/j.patrec.2013.05.023_b0055) 2006; 27
Ortega-Martorell (10.1016/j.patrec.2013.05.023_b0135) 2012; 7
Julià-Sapé (10.1016/j.patrec.2013.05.023_b0075) 2006; 19
Lee (10.1016/j.patrec.2013.05.023_b0090) 1999; 401
El-Deredy (10.1016/j.patrec.2013.05.023_b0025) 1997; 10
Kotsia (10.1016/j.patrec.2013.05.023_b0080) 2007; 2
Wild (10.1016/j.patrec.2013.05.023_b0175) 2004; 37
Lin (10.1016/j.patrec.2013.05.023_b0105) 2007; 19
10.1016/j.patrec.2013.05.023_b0020
Liu (10.1016/j.patrec.2013.05.023_b0120) 2004; 25
10.1016/j.patrec.2013.05.023_b0065
Lisboa (10.1016/j.patrec.2013.05.023_b0115) 2010; 5
Zafeiriou (10.1016/j.patrec.2013.05.023_b0180) 2006; 17
Vilamala (10.1016/j.patrec.2013.05.023_b0160) 2012
García-Gómez (10.1016/j.patrec.2013.05.023_b0035) 2009; 22
10.1016/j.patrec.2013.05.023_b0005
González-Navarro (10.1016/j.patrec.2013.05.023_b0040) 2010; 73
Louis (10.1016/j.patrec.2013.05.023_b0125) 2007; 114
Ladroue (10.1016/j.patrec.2013.05.023_b0085) 2003; 50
Sibtain (10.1016/j.patrec.2013.05.023_b0145) 2007; 62
Han (10.1016/j.patrec.2013.05.023_b0050) 2011; 12
Ortega-Martorell (10.1016/j.patrec.2013.05.023_b0130) 2012; 13
Vellido (10.1016/j.patrec.2013.05.023_b0155) 2012; 25
Dempster (10.1016/j.patrec.2013.05.023_b0010) 1977; 39
Wang (10.1016/j.patrec.2013.05.023_b0170) 2005; 19
Ding (10.1016/j.patrec.2013.05.023_b0015) 2010; 32
References_xml – volume: 10
  start-page: 99
  year: 1997
  end-page: 124
  ident: b0025
  article-title: Pattern recognition approaches in biomedical and clinical magnetic resonance spectroscopy: a review
  publication-title: NMR in Biomedicine
– volume: 114
  start-page: 97
  year: 2007
  end-page: 109
  ident: b0125
  article-title: The 2007 WHO classification of tumours of the central nervous system
  publication-title: Acta Neuropathologica
– volume: 13
  start-page: 129
  year: 2000
  end-page: 153
  ident: b0045
  article-title: Proton NMR chemical shifts and coupling constants for brain metabolites
  publication-title: NMR in Biomedicine
– volume: 59
  start-page: 77
  year: 2004
  end-page: 85
  ident: b0030
  article-title: In vivo single-voxel proton MR spectroscopy in the differentiation of high-grade gliomas and solitary metastases
  publication-title: Clinical Radiology
– volume: 25
  start-page: 893
  year: 2004
  end-page: 897
  ident: b0120
  article-title: Non-negative matrix factorization based methods for object recognition
  publication-title: Pattern Recognition Letters
– volume: 50
  start-page: 697
  year: 2003
  end-page: 703
  ident: b0085
  article-title: Independent component analysis for automated decomposition of in vivo magnetic resonance spectra
  publication-title: Magnetic Resonance in Medicine
– volume: 22
  start-page: 5
  year: 2009
  end-page: 18
  ident: b0035
  article-title: Multiproject–multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy
  publication-title: Magnetic Resonance Materials in Physics, Biology and Medicine (MAGMA)
– volume: 17
  start-page: 683
  year: 2006
  end-page: 695
  ident: b0180
  article-title: Exploiting discriminant information in nonnegative matrix factorization with application to frontal face verification
  publication-title: IEEE Transactions on Neural Networks
– volume: 32
  start-page: 45
  year: 2010
  end-page: 55
  ident: b0015
  article-title: Convex and semi-nonnegative matrix factorizations
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
– volume: 12
  start-page: 57
  year: 2011
  ident: b0050
  article-title: Multi-resolution independent component analysis for high-performance tumor classification and biomarker discovery
  publication-title: BMC Bioinformatics
– volume: 19
  start-page: 22
  year: 2006
  end-page: 33
  ident: b0075
  article-title: A multi-centre, web-accessible and quality control-checked database of in vivo MR spectra of brain tumour patients
  publication-title: Magnetic Resonance Materials in Physics, Biology and Medicine (MAGMA)
– volume: 23
  start-page: 1453
  year: 2004
  end-page: 1465
  ident: b0140
  article-title: Nonnegative matrix factorization for rapid recovery of constituent spectra in magnetic resonance chemical shift imaging of the brain
  publication-title: IEEE Transactions on Medical Imaging
– reference: Lee, D.D., Seung, H.S., 2001. Algorithms for non-negative matrix factorization. In: Advances in Neural Information Processing Systems (NIPS), pp. 556–562.
– volume: 25
  start-page: 819
  year: 2012
  end-page: 828
  ident: b0155
  article-title: Robust discrimination of glioblastomas from metastatic brain tumors on the basis of single-voxel
  publication-title: NMR in Biomedicine
– volume: 27
  start-page: 1404
  year: 2006
  end-page: 1411
  ident: b0055
  article-title: A systematic literature review of magnetic resonance spectroscopy for the characterization of brain tumors
  publication-title: American Journal of Neuroradiology
– volume: 39
  start-page: 1
  year: 1977
  end-page: 38
  ident: b0010
  article-title: Maximum likelihood from incomplete data via the EM algorithm
  publication-title: Journal of the Royal Statistical Society, Series B (Methodological)
– reference: Brodersen, K.H., Ong, C.S., Stephan, K.E., Buhmann, J.M., 2010. The balanced accuracy and its posterior distribution. In: Proceedings of the IEEE 2010 International Conference on, Pattern Recognition (ICPR), pp. 3121–3124.
– start-page: 1
  year: 2008
  end-page: 12
  ident: b0165
  article-title: Semi-supervised clustering via matrix factorization
  publication-title: Proceedings of the Eighth SIAM Int. Conf. Data Mining (SDM)
– volume: 401
  start-page: 788
  year: 1999
  end-page: 791
  ident: b0090
  article-title: Learning the parts of objects by non-negative matrix factorization
  publication-title: Nature
– volume: 62
  start-page: 109
  year: 2007
  end-page: 119
  ident: b0145
  article-title: The clinical value of proton magnetic resonance spectroscopy in adult brain tumours
  publication-title: Clinical Radiology
– volume: 73
  start-page: 622
  year: 2010
  end-page: 632
  ident: b0040
  article-title: Feature and model selection with discriminatory visualization for diagnostic classification of brain tumors
  publication-title: Neurocomputing
– volume: 19
  start-page: 2756
  year: 2007
  end-page: 2779
  ident: b0105
  article-title: Projected gradient methods for nonnegative matrix factorization
  publication-title: Neural Computation
– volume: 2
  start-page: 588
  year: 2007
  end-page: 595
  ident: b0080
  article-title: A novel discriminant non-negative matrix factorization algorithm with applications to facial image characterization problems
  publication-title: IEEE Transactions on Information Forensics and Security
– volume: 19
  start-page: 1
  year: 2005
  end-page: 17
  ident: b0170
  article-title: Non-negative matrix factorization framework for face recognition
  publication-title: International Journal of Pattern Recognition and Artificial Intelligence
– volume: 31
  start-page: 651
  year: 2010
  end-page: 666
  ident: b0070
  article-title: Data clustering: 50 years beyond
  publication-title: Pattern Recognition Letters
– volume: 22
  start-page: 147
  year: 2003
  end-page: 164
  ident: b0060
  article-title: Tumour grading from magnetic resonance spectroscopy: a comparison of feature extraction with variable selection
  publication-title: Statistics in Medicine
– reference: Ding, X., Lee, J.H., Lee, S.W., 2011. A constrained alternating least squares nonnegative matrix factorization algorithm enhances task-related neuronal activity detection from single subjects fMRI data. In: Proceedings of the International Conference on Machine Learning and Cybernetics (ICMLC), vol. 1, pp. 338–343.
– reference: .
– reference: IMM, 2006. NMF: DTU Toolbox. Collection of NMF algorithms implemented for Matlab. Technical University of Denmark. URL:
– volume: 37
  start-page: 2217
  year: 2004
  end-page: 2232
  ident: b0175
  article-title: Improving non-negative matrix factorizations through structured initialization
  publication-title: Pattern Recognition
– volume: 5
  start-page: 14
  year: 2010
  end-page: 18
  ident: b0115
  article-title: Data mining in cancer research
  publication-title: IEEE Computational Intelligence Magazine
– volume: 13
  year: 2012
  ident: b0130
  article-title: Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours
  publication-title: BMC Bioinformatics
– volume: 11
  start-page: 225
  year: 1998
  end-page: 234
  ident: b0110
  article-title: Assessment of statistical and neural networks methods in NMR spectral classification and metabolite selection
  publication-title: NMR in Biomedicine
– volume: 19
  start-page: 411
  year: 2006
  end-page: 434
  ident: b0150
  article-title: Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra
  publication-title: NMR in Biomedicine
– volume: 17
  start-page: 4
  year: 2010
  end-page: 7
  ident: b0100
  article-title: Semi-supervised nonnegative matrix factorization
  publication-title: IEEE Signal Processing Letters
– start-page: 2803
  year: 2012
  end-page: 2810
  ident: b0160
  article-title: Classifying malignant brain tumours from
  publication-title: Proceedings of the IEEE World Congress on Computational Intelligence (WCCI 2012) International Joint Conference on Artificial Neural Networks (IJCNN 2012)
– volume: 7
  year: 2012
  ident: b0135
  article-title: Convex non-negative matrix factorization for brain tumor delimitation from MRSI data
  publication-title: PLoS ONE
– volume: 50
  start-page: 697
  issue: 4
  year: 2003
  ident: 10.1016/j.patrec.2013.05.023_b0085
  article-title: Independent component analysis for automated decomposition of in vivo magnetic resonance spectra
  publication-title: Magnetic Resonance in Medicine
  doi: 10.1002/mrm.10595
– volume: 7
  issue: 10
  year: 2012
  ident: 10.1016/j.patrec.2013.05.023_b0135
  article-title: Convex non-negative matrix factorization for brain tumor delimitation from MRSI data
  publication-title: PLoS ONE
  doi: 10.1371/journal.pone.0047824
– ident: 10.1016/j.patrec.2013.05.023_b0065
– volume: 25
  start-page: 893
  issue: 8
  year: 2004
  ident: 10.1016/j.patrec.2013.05.023_b0120
  article-title: Non-negative matrix factorization based methods for object recognition
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2004.02.002
– volume: 22
  start-page: 5
  issue: 1
  year: 2009
  ident: 10.1016/j.patrec.2013.05.023_b0035
  article-title: Multiproject–multicenter evaluation of automatic brain tumor classification by magnetic resonance spectroscopy
  publication-title: Magnetic Resonance Materials in Physics, Biology and Medicine (MAGMA)
  doi: 10.1007/s10334-008-0146-y
– volume: 22
  start-page: 147
  issue: 1
  year: 2003
  ident: 10.1016/j.patrec.2013.05.023_b0060
  article-title: Tumour grading from magnetic resonance spectroscopy: a comparison of feature extraction with variable selection
  publication-title: Statistics in Medicine
  doi: 10.1002/sim.1321
– volume: 59
  start-page: 77
  issue: 1
  year: 2004
  ident: 10.1016/j.patrec.2013.05.023_b0030
  article-title: In vivo single-voxel proton MR spectroscopy in the differentiation of high-grade gliomas and solitary metastases
  publication-title: Clinical Radiology
  doi: 10.1016/j.crad.2003.08.006
– volume: 23
  start-page: 1453
  issue: 12
  year: 2004
  ident: 10.1016/j.patrec.2013.05.023_b0140
  article-title: Nonnegative matrix factorization for rapid recovery of constituent spectra in magnetic resonance chemical shift imaging of the brain
  publication-title: IEEE Transactions on Medical Imaging
  doi: 10.1109/TMI.2004.834626
– start-page: 1
  year: 2008
  ident: 10.1016/j.patrec.2013.05.023_b0165
  article-title: Semi-supervised clustering via matrix factorization
– volume: 401
  start-page: 788
  issue: 6755
  year: 1999
  ident: 10.1016/j.patrec.2013.05.023_b0090
  article-title: Learning the parts of objects by non-negative matrix factorization
  publication-title: Nature
  doi: 10.1038/44565
– volume: 39
  start-page: 1
  issue: 1
  year: 1977
  ident: 10.1016/j.patrec.2013.05.023_b0010
  article-title: Maximum likelihood from incomplete data via the EM algorithm
  publication-title: Journal of the Royal Statistical Society, Series B (Methodological)
  doi: 10.1111/j.2517-6161.1977.tb01600.x
– volume: 12
  start-page: 57
  issue: 1
  year: 2011
  ident: 10.1016/j.patrec.2013.05.023_b0050
  article-title: Multi-resolution independent component analysis for high-performance tumor classification and biomarker discovery
  publication-title: BMC Bioinformatics
– volume: 5
  start-page: 14
  issue: 1
  year: 2010
  ident: 10.1016/j.patrec.2013.05.023_b0115
  article-title: Data mining in cancer research
  publication-title: IEEE Computational Intelligence Magazine
  doi: 10.1109/MCI.2009.935311
– volume: 13
  issue: 38
  year: 2012
  ident: 10.1016/j.patrec.2013.05.023_b0130
  article-title: Non-negative matrix factorisation methods for the spectral decomposition of MRS data from human brain tumours
  publication-title: BMC Bioinformatics
– volume: 37
  start-page: 2217
  issue: 11
  year: 2004
  ident: 10.1016/j.patrec.2013.05.023_b0175
  article-title: Improving non-negative matrix factorizations through structured initialization
  publication-title: Pattern Recognition
  doi: 10.1016/j.patcog.2004.02.013
– volume: 17
  start-page: 683
  issue: 3
  year: 2006
  ident: 10.1016/j.patrec.2013.05.023_b0180
  article-title: Exploiting discriminant information in nonnegative matrix factorization with application to frontal face verification
  publication-title: IEEE Transactions on Neural Networks
  doi: 10.1109/TNN.2006.873291
– ident: 10.1016/j.patrec.2013.05.023_b0095
– volume: 11
  start-page: 225
  issue: 4–5
  year: 1998
  ident: 10.1016/j.patrec.2013.05.023_b0110
  article-title: Assessment of statistical and neural networks methods in NMR spectral classification and metabolite selection
  publication-title: NMR in Biomedicine
  doi: 10.1002/(SICI)1099-1492(199806/08)11:4/5<225::AID-NBM509>3.0.CO;2-Q
– volume: 25
  start-page: 819
  issue: 6
  year: 2012
  ident: 10.1016/j.patrec.2013.05.023_b0155
  article-title: Robust discrimination of glioblastomas from metastatic brain tumors on the basis of single-voxel 1H-MRS
  publication-title: NMR in Biomedicine
  doi: 10.1002/nbm.1797
– volume: 17
  start-page: 4
  issue: 1
  year: 2010
  ident: 10.1016/j.patrec.2013.05.023_b0100
  article-title: Semi-supervised nonnegative matrix factorization
  publication-title: IEEE Signal Processing Letters
  doi: 10.1109/LSP.2009.2027163
– volume: 62
  start-page: 109
  issue: 2
  year: 2007
  ident: 10.1016/j.patrec.2013.05.023_b0145
  article-title: The clinical value of proton magnetic resonance spectroscopy in adult brain tumours
  publication-title: Clinical Radiology
  doi: 10.1016/j.crad.2006.09.012
– volume: 19
  start-page: 411
  issue: 4
  year: 2006
  ident: 10.1016/j.patrec.2013.05.023_b0150
  article-title: Development of a decision support system for diagnosis and grading of brain tumours using in vivo magnetic resonance single voxel spectra
  publication-title: NMR in Biomedicine
  doi: 10.1002/nbm.1016
– volume: 32
  start-page: 45
  year: 2010
  ident: 10.1016/j.patrec.2013.05.023_b0015
  article-title: Convex and semi-nonnegative matrix factorizations
  publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence
  doi: 10.1109/TPAMI.2008.277
– volume: 19
  start-page: 22
  issue: 1
  year: 2006
  ident: 10.1016/j.patrec.2013.05.023_b0075
  article-title: A multi-centre, web-accessible and quality control-checked database of in vivo MR spectra of brain tumour patients
  publication-title: Magnetic Resonance Materials in Physics, Biology and Medicine (MAGMA)
  doi: 10.1007/s10334-005-0023-x
– volume: 13
  start-page: 129
  issue: 3
  year: 2000
  ident: 10.1016/j.patrec.2013.05.023_b0045
  article-title: Proton NMR chemical shifts and coupling constants for brain metabolites
  publication-title: NMR in Biomedicine
  doi: 10.1002/1099-1492(200005)13:3<129::AID-NBM619>3.0.CO;2-V
– volume: 19
  start-page: 2756
  year: 2007
  ident: 10.1016/j.patrec.2013.05.023_b0105
  article-title: Projected gradient methods for nonnegative matrix factorization
  publication-title: Neural Computation
  doi: 10.1162/neco.2007.19.10.2756
– volume: 27
  start-page: 1404
  issue: 7
  year: 2006
  ident: 10.1016/j.patrec.2013.05.023_b0055
  article-title: A systematic literature review of magnetic resonance spectroscopy for the characterization of brain tumors
  publication-title: American Journal of Neuroradiology
– volume: 73
  start-page: 622
  issue: 4–6
  year: 2010
  ident: 10.1016/j.patrec.2013.05.023_b0040
  article-title: Feature and model selection with discriminatory visualization for diagnostic classification of brain tumors
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2009.07.018
– volume: 114
  start-page: 97
  year: 2007
  ident: 10.1016/j.patrec.2013.05.023_b0125
  article-title: The 2007 WHO classification of tumours of the central nervous system
  publication-title: Acta Neuropathologica
  doi: 10.1007/s00401-007-0243-4
– volume: 10
  start-page: 99
  issue: 3
  year: 1997
  ident: 10.1016/j.patrec.2013.05.023_b0025
  article-title: Pattern recognition approaches in biomedical and clinical magnetic resonance spectroscopy: a review
  publication-title: NMR in Biomedicine
  doi: 10.1002/(SICI)1099-1492(199705)10:3<99::AID-NBM461>3.0.CO;2-#
– volume: 2
  start-page: 588
  issue: 3
  year: 2007
  ident: 10.1016/j.patrec.2013.05.023_b0080
  article-title: A novel discriminant non-negative matrix factorization algorithm with applications to facial image characterization problems
  publication-title: IEEE Transactions on Information Forensics and Security
  doi: 10.1109/TIFS.2007.902017
– volume: 19
  start-page: 1
  issue: 4
  year: 2005
  ident: 10.1016/j.patrec.2013.05.023_b0170
  article-title: Non-negative matrix factorization framework for face recognition
  publication-title: International Journal of Pattern Recognition and Artificial Intelligence
  doi: 10.1142/S0218001405004198
– start-page: 2803
  year: 2012
  ident: 10.1016/j.patrec.2013.05.023_b0160
  article-title: Classifying malignant brain tumours from 1H-MRS data using breadth ensemble learnings
– ident: 10.1016/j.patrec.2013.05.023_b0020
  doi: 10.1109/ICMLC.2011.6016680
– ident: 10.1016/j.patrec.2013.05.023_b0005
  doi: 10.1109/ICPR.2010.764
– volume: 31
  start-page: 651
  year: 2010
  ident: 10.1016/j.patrec.2013.05.023_b0070
  article-title: Data clustering: 50 years beyond K-means
  publication-title: Pattern Recognition Letters
  doi: 10.1016/j.patrec.2009.09.011
SSID ssj0006398
Score 2.149567
Snippet •Brain tumours can be diagnosed on the basis of magnetic resonance spectroscopy (MRS).•A new method to introduce class information into a convex variant of NMF...
The medical analysis of human brain tumours commonly relies on indirect measurements. Among these, magnetic resonance imaging (MRI) and spectroscopy (MRS)...
SourceID csuc
crossref
elsevier
SourceType Open Access Repository
Enrichment Source
Index Database
Publisher
StartPage 1734
SubjectTerms Aplicacions de la informàtica
Bioinformàtica
Brain tumours
Diagnosis
Discriminant Convex Non-negative Matrix Factorization
Informàtica
Magnetic resonance spectroscopy
Models matemàtics
Source separation
Tumors
Àrees temàtiques de la UPC
Title Discriminant Convex Non-negative Matrix Factorization for the classification of human brain tumours
URI https://dx.doi.org/10.1016/j.patrec.2013.05.023
https://recercat.cat/handle/2072/219235
Volume 34
WOSCitedRecordID wos000323794200020&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: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1872-7344
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0006398
  issn: 0167-8655
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFLZKxwM8cBkgOi7yA09UqZI4qZPHCTZgGtUkRtU3y7GdqVNJpvSi_rH9P86JnSxl0mAPPDRq0sZ1c774fD455zMhHwKjJNB47fmZZl409o2XJj7zYiaNjMcmkPVaBNNTPpkks1l61utdN7UwmwUvimS7Ta_-q6nhGBgbS2fvYe62UTgA78HosAWzw_afDP95jiOBzXDBgr6N2Q4nZeEV5sKKfH9HVf7t8LheaceVYbbZhgrZNKYP3VDJOsyf4VISw9X6F3Rh2WW0Z7VAJxbFuEwkOGtR1wi1bH06B9jJhY3goqZWm2pzClPMUjYZiuXwZPRl1IZ9qxX02EOdg7JyT0d-yEJXrSOZopiodnU6OSqfdmMYQZ0NZ6s4m7AmDNdYItsdl12Q0-Ev6oyyAXefGbdrRTtveQMbmLgc4WMFg3qVAatlWm2F86749h9OsU1VbLLgLoVtRWArwo8FtPKA7IU8TpM-2Tv8djQ7aSkA0L6kEZXHv9XUbNaJhbd7s8OJ-mq5Vh1q1KE758_IEzdPoYcWX89JzxT75GmzBgh1LmGfPO4IWr4gqgs-asFHu-CjFnx0B3wUwEcBfHQXfLTMaQ0-WoOPOvC9JD-Pj84_ffXcMh6eYlGy8rQJw5wp6WseSDM2SernWZZnwHyZNuA_ZMaU5iYNEsNlyDKf6TgKQiD-Og8jzl6RflEW5jWhKA4YRXkeB1yCs1GSqyiVKg01TNylNgPCmgsplNO4x6VWFuIuMw6I1551ZTVe_vL9j2gjAYdNBVdEoER7u4Ov0OehCHHyFA8IbywpHKm1ZFUASu_8mYN7dusNeXRzb70l_VW1Nu_IQ7VZzZfVewfR36jsyo0
linkProvider Elsevier
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=Discriminant+Convex+Non-negative+Matrix+Factorization+for+the+classification+of+human+brain+tumours&rft.jtitle=Pattern+recognition+letters&rft.au=Vilamala%2C+Albert&rft.au=Lisboa%2C+Paulo+J.G.&rft.au=Ortega-Martorell%2C+Sandra&rft.au=Vellido%2C+Alfredo&rft.date=2013-10-15&rft.issn=0167-8655&rft.volume=34&rft.issue=14&rft.spage=1734&rft.epage=1747&rft_id=info:doi/10.1016%2Fj.patrec.2013.05.023&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_patrec_2013_05_023
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0167-8655&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0167-8655&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0167-8655&client=summon