Disease classification and prediction via semi-supervised dimensionality reduction

We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix dec...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro Ročník 2011; s. 1086 - 1090
Hlavní autoři: Batmanghelich, K N, Ye, D H, Pohl, K M, Taskar, B, Davatzikos, C
Médium: Konferenční příspěvek Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.03.2011
Témata:
Accuracy
Alzheimer's disease
Basis Learning
Biomedical imaging
Laplace equations
Matrix decomposition
Matrix factorization
Mild Cognitive Impairment (MCI)
Optimization
Semi-supervised Learning
Basis Learning
Mild Cognitive Impairment (MCI)
Semi-supervised Learning
Matrix factorization
Alzheimer’s disease
Optimization
ISBN:1424441277, 9781424441273
ISSN:1945-7928, 1945-8452
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix decomposition of to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosed with Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.
AbstractList We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix decomposition of [1] to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosed with Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.
We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix decomposition of [1] to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosed with Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix decomposition of [1] to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosed with Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.
We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of image-based disease classification based on medical images. We perform dimensionality reduction by adopting the formalism of constrained matrix decomposition of to semi-supervised learning. In addition, we add a new regularization term to the objective function to better captur the affinity between labeled and unlabeled data. We apply our method to a data set consisting of medical scans of subjects classified as Normal Control (CN) and Alzheimer (AD). The unlabeled data are scans of subjects diagnosed with Mild Cognitive Impairment (MCI), which are at high risk to develop AD in the future. We measure the accuracy of our algorithm in classifying scans as AD and NC. In addition, we use the classifier to predict which subjects with MCI will converge to AD and compare those results to the diagnosis given at later follow ups. The experiments highlight that unlabeled data greatly improves the accuracy of our classifier.
Author Davatzikos, C
Batmanghelich, K N
Ye, D H
Taskar, B
Pohl, K M
AuthorAffiliation Section of Biomedical Image Analysis (SBIA), Department of Radiology, University of Pennsylvania
Computer and Information Science Department, University of Pennsylvania
AuthorAffiliation_xml – name: Computer and Information Science Department, University of Pennsylvania
– name: Section of Biomedical Image Analysis (SBIA), Department of Radiology, University of Pennsylvania
Author_xml – sequence: 1
  givenname: K N
  surname: Batmanghelich
  fullname: Batmanghelich, K N
  organization: Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
– sequence: 2
  givenname: D H
  surname: Ye
  fullname: Ye, D H
  organization: Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
– sequence: 3
  givenname: K M
  surname: Pohl
  fullname: Pohl, K M
  organization: Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
– sequence: 4
  givenname: B
  surname: Taskar
  fullname: Taskar, B
  organization: Comput. & Inf. Sci. Dept., Univ. of Pennsylvania, Philadelphia, PA, USA
– sequence: 5
  givenname: C
  surname: Davatzikos
  fullname: Davatzikos, C
  organization: Dept. of Radiol., Univ. of Pennsylvania, Philadelphia, PA, USA
BackLink https://www.ncbi.nlm.nih.gov/pubmed/28603581$$D View this record in MEDLINE/PubMed
BookMark eNpVkclOwzAQhg0U0YU-AEJCOXJJ8ZrYFyQoW6VKSCznyLUnYJSlxEmlvj2hDQV8GXm-z_9IniHqFWUBCJ0QPCEEq4vZ8_VsQjEhEyFjKhTeQ0PCKeecUCn20YAoLkLJBT34BXHc60CsqOyjsfcfuD0x5wzzI9SnMsJMSDJATzfOg_YQmEx771JndO3KItCFDZYVWGc215XTgYfchb5ZQrVq39jAuhwK31KduXodtHKzkY_RYaozD-OujtDr3e3L9CGcP97Pplfz0DGq6jBNU8GlplpHlhEhsARJrMWCfTdjGgtqsQJueGRSUJYtCDEELDCNUyMWbIQut7nLZpGDNVDUlc6SZeVyXa2TUrvkPynce_JWrhLBo4gT3gacdwFV-dmAr5PceQNZpgsoG58QhWWshBSqVc_-ztoN-fnIVjjdCg4AdrjbGfsCtRuIZQ
ContentType Conference Proceeding
Journal Article
CorporateAuthor ADNI
CorporateAuthor_xml – name: ADNI
DBID 6IE
6IL
CBEJK
RIE
RIL
NPM
7X8
5PM
DOI 10.1109/ISBI.2011.5872590
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
PubMed
MEDLINE - Academic
PubMed Central (Full Participant titles)
DatabaseTitle PubMed
MEDLINE - Academic
DatabaseTitleList
MEDLINE - Academic
PubMed
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 Engineering
EISBN 1424441285
9781424441280
EISSN 1945-8452
EndPage 1090
ExternalDocumentID PMC5466414
28603581
5872590
Genre orig-research
Journal Article
GrantInformation_xml – fundername: NCRR NIH HHS
  grantid: P41 RR013218
GroupedDBID 23N
6IE
6IF
6IK
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
M43
OCL
RIE
RIL
RNS
NPM
7X8
5PM
ID FETCH-LOGICAL-i329t-fff548a2aa6d315508e81dd0538a2a72752d09e4c46cfe9d3b11c1ede3a0fc5b3
IEDL.DBID RIE
ISBN 1424441277
9781424441273
ISICitedReferencesCount 22
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000298849400249&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1945-7928
IngestDate Tue Sep 30 16:56:06 EDT 2025
Fri Jul 11 12:44:40 EDT 2025
Thu Jan 02 22:21:17 EST 2025
Wed Aug 27 02:52:46 EDT 2025
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed false
IsScholarly true
Keywords Basis Learning
Mild Cognitive Impairment (MCI)
Semi-supervised Learning
Matrix factorization
Alzheimer’s disease
Optimization
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i329t-fff548a2aa6d315508e81dd0538a2a72752d09e4c46cfe9d3b11c1ede3a0fc5b3
Notes ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Data used in the preparation of this article were obtained from the Alzheimer Disease Neuroimaging Initiative (ADNI) database (www.loni.ucla.edu/ADNI)
OpenAccessLink http://doi.org/10.1109/ISBI.2011.5872590
PMID 28603581
PQID 1908795859
PQPubID 23479
PageCount 5
ParticipantIDs pubmed_primary_28603581
ieee_primary_5872590
pubmedcentral_primary_oai_pubmedcentral_nih_gov_5466414
proquest_miscellaneous_1908795859
PublicationCentury 2000
PublicationDate 2011 Mar-Apr
PublicationDateYYYYMMDD 2011-03-01
PublicationDate_xml – month: 03
  year: 2011
  text: 2011 Mar-Apr
PublicationDecade 2010
PublicationPlace United States
PublicationPlace_xml – name: United States
PublicationTitle 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro
PublicationTitleAbbrev ISBI
PublicationTitleAlternate Proc IEEE Int Symp Biomed Imaging
PublicationYear 2011
Publisher IEEE
Publisher_xml – name: IEEE
References 19694282 - Inf Process Med Imaging. 2009;21:423-34
18793733 - Neuroimage. 2009 Jan 1;44(1):112-22
10548103 - Nature. 1999 Oct 21;401(6755):788-91
11707092 - Neuroimage. 2001 Dec;14(6):1361-9
12395096 - Neuroreport. 2002 Oct 28;13(15):1939-43
10860804 - Neuroimage. 2000 Jun;11(6 Pt 1):805-21
17243588 - IEEE Trans Med Imaging. 2007 Jan;26(1):93-105
19041946 - Neuroimage. 2009 Mar;45(1 Suppl):S61-72
20580597 - Med Image Anal. 2010 Oct;14(5):633-42
References_xml – reference: 19041946 - Neuroimage. 2009 Mar;45(1 Suppl):S61-72
– reference: 12395096 - Neuroreport. 2002 Oct 28;13(15):1939-43
– reference: 17243588 - IEEE Trans Med Imaging. 2007 Jan;26(1):93-105
– reference: 10860804 - Neuroimage. 2000 Jun;11(6 Pt 1):805-21
– reference: 18793733 - Neuroimage. 2009 Jan 1;44(1):112-22
– reference: 19694282 - Inf Process Med Imaging. 2009;21:423-34
– reference: 10548103 - Nature. 1999 Oct 21;401(6755):788-91
– reference: 11707092 - Neuroimage. 2001 Dec;14(6):1361-9
– reference: 20580597 - Med Image Anal. 2010 Oct;14(5):633-42
SSID ssj0000744304
ssj0000669106
Score 1.9990886
Snippet We present a new semi-supervised algorithm for dimensionality reduction which exploits information of unlabeled data in order to improve the accuracy of...
SourceID pubmedcentral
proquest
pubmed
ieee
SourceType Open Access Repository
Aggregation Database
Index Database
Publisher
StartPage 1086
SubjectTerms Accuracy
Alzheimer's disease
Basis Learning
Biomedical imaging
Laplace equations
Matrix decomposition
Matrix factorization
Mild Cognitive Impairment (MCI)
Optimization
Semi-supervised Learning
Title Disease classification and prediction via semi-supervised dimensionality reduction
URI https://ieeexplore.ieee.org/document/5872590
https://www.ncbi.nlm.nih.gov/pubmed/28603581
https://www.proquest.com/docview/1908795859
https://pubmed.ncbi.nlm.nih.gov/PMC5466414
Volume 2011
WOSCitedRecordID wos000298849400249&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
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDLYAcYALj_EYj6lIHCnrO-mVxwQSmiZe2m1KE1f0QDetG78fu-0KQ7twa9pUTe20-RzbnwEuE0NGALpcNMM4dhDr1E7cRNsJpko4UjlpSWD6_iT6fTkcxoM1uGpyYRCxDD7Daz4sfflmrOe8VdYNpSC0Tgb6uhBRlavV7KfQ0hkvPIZlWwSB71RO5YBZGT25yOsKXE-IBd1T3fZrj6frxN3Hl5vHityzfmBdeWUVCP0bS_lrcert_O-1duHgJ8vPGjTr1x6sYb4P278IClvwfFf5byzNIJujikpFWio31mTKPp6y-ZUpq8DPzC7mE_73FGgsw2UDKsoPAvrWlCliufMBvPXuX28f7LoKg535Xjyz0zQlq0Z5SkXGZ4NGImFcQx8vnyT4E5KWYwx0EOkUY-MnrqtdNOiTonWY-IewkY9zPAbLED4IPS0crTUJPZKKrCUTKRGiQhOaNrRYOqNJRbQxqgXThouF3Ec0-dmjoXIcz4sRoRkuli7DuA1HlR6amz0ZOUzu1gaxpKGmAxNrL1_Js4-SYDtkzn03OFk9nFPYqjaWORDtDDZm0zmew6b-mmXFtENzcyg75dz8BubK4Bw
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT4NAEJ4YNVEvPuqjPjHxKMpjl4Wrr9hYG6PVeCPL7hA5SJvS-vvdAYrW9OKNhSUsMwv7zc7MNwBniTZGALpUNEM7NotUaiduouwEUymcUDppSWD61hW9Xvj-Hj0twHmTC4OIZfAZXtBh6cvXAzWhrbJLHgqD1o2BvsQZ85wqW6vZUTGLZzT1GZZtwZjvVG5lRryMXjjN7GKuJ8SU8Klu-7XP03Wiy87LVaei96wfWddemQdD_0ZT_lqe7tb_92IbsP2T52c9NSvYJixgvgVrvygKW_B8U3lwLEUwm-KKSlVaMtfWcERenrL5lUmrwM_MLiZD-vsUqC1NhQMq0g8D9a0RkcRS5214vbvtX9_bdR0GO_O9aGynaWrsGulJGWifTJoQDcrV5vOlkwYAcaPnCJligUox0n7iuspFjb5RteKJvwOL-SDHPbC0QQjcU8JRShmhB6E09pIOpOAoUXPdhhZJJx5WVBtxLZg2nE7lHpvpTz4NmeNgUsQGz1C59JBHbdit9NDc7IWBQ_RubRAzGmo6ELX27JU8-ygptjmx7rtsf_5wTmDlvv_Yjbud3sMBrFbbzBSWdgiL49EEj2BZfY2zYnRcztBvbKjiew
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%3Abook&rft.genre=proceeding&rft.title=2011+IEEE+International+Symposium+on+Biomedical+Imaging%3A+From+Nano+to+Macro&rft.atitle=Disease+classification+and+prediction+via+semi-supervised+dimensionality+reduction&rft.au=Batmanghelich%2C+K+N&rft.au=Ye%2C+D+H&rft.au=Pohl%2C+K+M&rft.au=Taskar%2C+B&rft.date=2011-03-01&rft.pub=IEEE&rft.isbn=9781424441273&rft.issn=1945-7928&rft.spage=1086&rft.epage=1090&rft_id=info:doi/10.1109%2FISBI.2011.5872590&rft.externalDocID=5872590
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1945-7928&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1945-7928&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1945-7928&client=summon