Breast cancer diagnosis in digitized mammograms using curvelet moments.
Identifieur interne : 000532 ( PubMed/Corpus ); précédent : 000531; suivant : 000533Breast cancer diagnosis in digitized mammograms using curvelet moments.
Auteurs : Sami Dhahbi ; Walid Barhoumi ; Ezzeddine ZagroubaSource :
- Computers in biology and medicine [ 1879-0534 ] ; 2015.
English descriptors
- KwdEn :
- MESH :
- diagnostic imaging : Breast Neoplasms.
- methods : Image Interpretation, Computer-Assisted, Mammography.
- Algorithms, Databases, Factual, Female, Humans, Reproducibility of Results.
Abstract
BACKGROUND
Feature extraction is a key issue in designing a computer aided diagnosis system. Recent researches on breast cancer diagnosis have reported the effectiveness of multiscale transforms (wavelets and curvelets) for mammogram analysis and have shown the superiority of curvelet transform. However, the curse of dimensionality problem arises when using the curvelet coefficients and therefore a reduction method is required to extract a reduced set of discriminative features.
METHODS
This paper deals with this problem and proposes a feature extraction method based on curvelet transform and moment theory for mammogram description. First, we performed discrete curvelet transform and we computed the four first-order moments from curvelet coefficients distribution. Hence, two feature sets can be obtained: moments from each band and moments from each level. In this work, both sets are studied. Then, the t-test ranking technique was applied to select the best features from each set. Finally, a k-nearest neighbor classifier was used to distinguish between normal and abnormal breast tissues and to classify tumors as malignant or benign. Experiments were performed on 252 mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on 11553 mammograms from the Digital Database for Screening Mammography (DDSM) database using 2×5-fold cross validation.
RESULTS
Experimental results prove the effectiveness and the superiority of curvelet moments for mammogram analysis. Indeed, results on the mini-MIAS database show that curvelet moments yield an accuracy of 91.27% (resp. 81.35 %) with 10 (resp. 8) features for abnormality (resp. malignancy) detection. In addition, empirical comparisons of the proposed method against state-of-the-art curvelet-based methods on the DDSM database show that the suggested method does not only lead to a more reduced feature set, but it also statistically outperforms all the compared methods in terms of accuracy.
CONCLUSIONS
In summary, curvelet moments are an efficient and effective way to extract a reduced set of discriminative features for breast cancer diagnosis.
DOI: 10.1016/j.compbiomed.2015.06.012
PubMed: 26151831
Links to Exploration step
pubmed:26151831Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Breast cancer diagnosis in digitized mammograms using curvelet moments.</title>
<author><name sortKey="Dhahbi, Sami" sort="Dhahbi, Sami" uniqKey="Dhahbi S" first="Sami" last="Dhahbi">Sami Dhahbi</name>
<affiliation><nlm:affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: sami_dhahbi@yahoo.fr.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Barhoumi, Walid" sort="Barhoumi, Walid" uniqKey="Barhoumi W" first="Walid" last="Barhoumi">Walid Barhoumi</name>
<affiliation><nlm:affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: walid.barhoumi@esti.rnu.tn.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Zagrouba, Ezzeddine" sort="Zagrouba, Ezzeddine" uniqKey="Zagrouba E" first="Ezzeddine" last="Zagrouba">Ezzeddine Zagrouba</name>
<affiliation><nlm:affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: e.zagrouba@gmail.com.</nlm:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2015">2015</date>
<idno type="RBID">pubmed:26151831</idno>
<idno type="pmid">26151831</idno>
<idno type="doi">10.1016/j.compbiomed.2015.06.012</idno>
<idno type="wicri:Area/PubMed/Corpus">000532</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000532</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">Breast cancer diagnosis in digitized mammograms using curvelet moments.</title>
<author><name sortKey="Dhahbi, Sami" sort="Dhahbi, Sami" uniqKey="Dhahbi S" first="Sami" last="Dhahbi">Sami Dhahbi</name>
<affiliation><nlm:affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: sami_dhahbi@yahoo.fr.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Barhoumi, Walid" sort="Barhoumi, Walid" uniqKey="Barhoumi W" first="Walid" last="Barhoumi">Walid Barhoumi</name>
<affiliation><nlm:affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: walid.barhoumi@esti.rnu.tn.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Zagrouba, Ezzeddine" sort="Zagrouba, Ezzeddine" uniqKey="Zagrouba E" first="Ezzeddine" last="Zagrouba">Ezzeddine Zagrouba</name>
<affiliation><nlm:affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: e.zagrouba@gmail.com.</nlm:affiliation>
</affiliation>
</author>
</analytic>
<series><title level="j">Computers in biology and medicine</title>
<idno type="eISSN">1879-0534</idno>
<imprint><date when="2015" type="published">2015</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms (MeSH)</term>
<term>Breast Neoplasms (diagnostic imaging)</term>
<term>Databases, Factual (MeSH)</term>
<term>Female (MeSH)</term>
<term>Humans (MeSH)</term>
<term>Image Interpretation, Computer-Assisted (methods)</term>
<term>Mammography (methods)</term>
<term>Reproducibility of Results (MeSH)</term>
</keywords>
<keywords scheme="MESH" qualifier="diagnostic imaging" xml:lang="en"><term>Breast Neoplasms</term>
</keywords>
<keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Image Interpretation, Computer-Assisted</term>
<term>Mammography</term>
</keywords>
<keywords scheme="MESH" xml:lang="en"><term>Algorithms</term>
<term>Databases, Factual</term>
<term>Female</term>
<term>Humans</term>
<term>Reproducibility of Results</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en"><p><b>BACKGROUND</b>
</p>
<p>Feature extraction is a key issue in designing a computer aided diagnosis system. Recent researches on breast cancer diagnosis have reported the effectiveness of multiscale transforms (wavelets and curvelets) for mammogram analysis and have shown the superiority of curvelet transform. However, the curse of dimensionality problem arises when using the curvelet coefficients and therefore a reduction method is required to extract a reduced set of discriminative features.</p>
</div>
<div type="abstract" xml:lang="en"><p><b>METHODS</b>
</p>
<p>This paper deals with this problem and proposes a feature extraction method based on curvelet transform and moment theory for mammogram description. First, we performed discrete curvelet transform and we computed the four first-order moments from curvelet coefficients distribution. Hence, two feature sets can be obtained: moments from each band and moments from each level. In this work, both sets are studied. Then, the t-test ranking technique was applied to select the best features from each set. Finally, a k-nearest neighbor classifier was used to distinguish between normal and abnormal breast tissues and to classify tumors as malignant or benign. Experiments were performed on 252 mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on 11553 mammograms from the Digital Database for Screening Mammography (DDSM) database using 2×5-fold cross validation.</p>
</div>
<div type="abstract" xml:lang="en"><p><b>RESULTS</b>
</p>
<p>Experimental results prove the effectiveness and the superiority of curvelet moments for mammogram analysis. Indeed, results on the mini-MIAS database show that curvelet moments yield an accuracy of 91.27% (resp. 81.35 %) with 10 (resp. 8) features for abnormality (resp. malignancy) detection. In addition, empirical comparisons of the proposed method against state-of-the-art curvelet-based methods on the DDSM database show that the suggested method does not only lead to a more reduced feature set, but it also statistically outperforms all the compared methods in terms of accuracy.</p>
</div>
<div type="abstract" xml:lang="en"><p><b>CONCLUSIONS</b>
</p>
<p>In summary, curvelet moments are an efficient and effective way to extract a reduced set of discriminative features for breast cancer diagnosis.</p>
</div>
</front>
</TEI>
<pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">26151831</PMID>
<DateCompleted><Year>2016</Year>
<Month>05</Month>
<Day>25</Day>
</DateCompleted>
<DateRevised><Year>2016</Year>
<Month>11</Month>
<Day>25</Day>
</DateRevised>
<Article PubModel="Print-Electronic"><Journal><ISSN IssnType="Electronic">1879-0534</ISSN>
<JournalIssue CitedMedium="Internet"><Volume>64</Volume>
<PubDate><Year>2015</Year>
<Month>Sep</Month>
</PubDate>
</JournalIssue>
<Title>Computers in biology and medicine</Title>
<ISOAbbreviation>Comput Biol Med</ISOAbbreviation>
</Journal>
<ArticleTitle>Breast cancer diagnosis in digitized mammograms using curvelet moments.</ArticleTitle>
<Pagination><MedlinePgn>79-90</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1016/j.compbiomed.2015.06.012</ELocationID>
<ELocationID EIdType="pii" ValidYN="Y">S0010-4825(15)00220-6</ELocationID>
<Abstract><AbstractText Label="BACKGROUND" NlmCategory="BACKGROUND">Feature extraction is a key issue in designing a computer aided diagnosis system. Recent researches on breast cancer diagnosis have reported the effectiveness of multiscale transforms (wavelets and curvelets) for mammogram analysis and have shown the superiority of curvelet transform. However, the curse of dimensionality problem arises when using the curvelet coefficients and therefore a reduction method is required to extract a reduced set of discriminative features.</AbstractText>
<AbstractText Label="METHODS" NlmCategory="METHODS">This paper deals with this problem and proposes a feature extraction method based on curvelet transform and moment theory for mammogram description. First, we performed discrete curvelet transform and we computed the four first-order moments from curvelet coefficients distribution. Hence, two feature sets can be obtained: moments from each band and moments from each level. In this work, both sets are studied. Then, the t-test ranking technique was applied to select the best features from each set. Finally, a k-nearest neighbor classifier was used to distinguish between normal and abnormal breast tissues and to classify tumors as malignant or benign. Experiments were performed on 252 mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on 11553 mammograms from the Digital Database for Screening Mammography (DDSM) database using 2×5-fold cross validation.</AbstractText>
<AbstractText Label="RESULTS" NlmCategory="RESULTS">Experimental results prove the effectiveness and the superiority of curvelet moments for mammogram analysis. Indeed, results on the mini-MIAS database show that curvelet moments yield an accuracy of 91.27% (resp. 81.35 %) with 10 (resp. 8) features for abnormality (resp. malignancy) detection. In addition, empirical comparisons of the proposed method against state-of-the-art curvelet-based methods on the DDSM database show that the suggested method does not only lead to a more reduced feature set, but it also statistically outperforms all the compared methods in terms of accuracy.</AbstractText>
<AbstractText Label="CONCLUSIONS" NlmCategory="CONCLUSIONS">In summary, curvelet moments are an efficient and effective way to extract a reduced set of discriminative features for breast cancer diagnosis.</AbstractText>
<CopyrightInformation>Copyright © 2015 Elsevier Ltd. All rights reserved.</CopyrightInformation>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Dhahbi</LastName>
<ForeName>Sami</ForeName>
<Initials>S</Initials>
<AffiliationInfo><Affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: sami_dhahbi@yahoo.fr.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Barhoumi</LastName>
<ForeName>Walid</ForeName>
<Initials>W</Initials>
<AffiliationInfo><Affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: walid.barhoumi@esti.rnu.tn.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Zagrouba</LastName>
<ForeName>Ezzeddine</ForeName>
<Initials>E</Initials>
<AffiliationInfo><Affiliation>Research Team on Intelligent Systems in Imaging and Artificial Vision (SIIVA) - RIADI Laboratory, ISI, 2 Street Abou Rayhane Bayrouni, 2080 Ariana, Tunisia. Electronic address: e.zagrouba@gmail.com.</Affiliation>
</AffiliationInfo>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic"><Year>2015</Year>
<Month>06</Month>
<Day>26</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>Comput Biol Med</MedlineTA>
<NlmUniqueID>1250250</NlmUniqueID>
<ISSNLinking>0010-4825</ISSNLinking>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
<MeshHeadingList><MeshHeading><DescriptorName UI="D000465" MajorTopicYN="N">Algorithms</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D001943" MajorTopicYN="N">Breast Neoplasms</DescriptorName>
<QualifierName UI="Q000000981" MajorTopicYN="Y">diagnostic imaging</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D016208" MajorTopicYN="N">Databases, Factual</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D005260" MajorTopicYN="N">Female</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D006801" MajorTopicYN="N">Humans</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D007090" MajorTopicYN="N">Image Interpretation, Computer-Assisted</DescriptorName>
<QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D008327" MajorTopicYN="N">Mammography</DescriptorName>
<QualifierName UI="Q000379" MajorTopicYN="Y">methods</QualifierName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D015203" MajorTopicYN="N">Reproducibility of Results</DescriptorName>
</MeshHeading>
</MeshHeadingList>
<KeywordList Owner="NOTNLM"><Keyword MajorTopicYN="N">Breast cancer diagnosis</Keyword>
<Keyword MajorTopicYN="N">Curvelet moments</Keyword>
<Keyword MajorTopicYN="N">Curvelet transform</Keyword>
<Keyword MajorTopicYN="N">Feature reduction</Keyword>
<Keyword MajorTopicYN="N">Mammography</Keyword>
</KeywordList>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="received"><Year>2015</Year>
<Month>04</Month>
<Day>27</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="revised"><Year>2015</Year>
<Month>06</Month>
<Day>16</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="accepted"><Year>2015</Year>
<Month>06</Month>
<Day>17</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2015</Year>
<Month>7</Month>
<Day>8</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed"><Year>2015</Year>
<Month>7</Month>
<Day>8</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2016</Year>
<Month>5</Month>
<Day>26</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>ppublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="pubmed">26151831</ArticleId>
<ArticleId IdType="pii">S0010-4825(15)00220-6</ArticleId>
<ArticleId IdType="doi">10.1016/j.compbiomed.2015.06.012</ArticleId>
</ArticleIdList>
</PubmedData>
</pubmed>
</record>
Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Sante/explor/MaghrebDataLibMedV2/Data/PubMed/Corpus
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000532 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000532 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien |wiki= Wicri/Sante |area= MaghrebDataLibMedV2 |flux= PubMed |étape= Corpus |type= RBID |clé= pubmed:26151831 |texte= Breast cancer diagnosis in digitized mammograms using curvelet moments. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:26151831" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \ | NlmPubMed2Wicri -a MaghrebDataLibMedV2
This area was generated with Dilib version V0.6.38. |