A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.
Identifieur interne : 000144 ( PubMed/Corpus ); précédent : 000143; suivant : 000145A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.
Auteurs : Said Boumaraf ; Xiabi Liu ; Chokri Ferkous ; Xiaohong MaSource :
- BioMed research international [ 2314-6141 ] ; 2020.
English descriptors
- KwdEn :
- MESH :
- diagnostic imaging : Breast, Breast Neoplasms.
- methods : Image Interpretation, Computer-Assisted, Mammography.
- Algorithms, Databases, Factual, Female, Humans, Neural Networks, Computer.
Abstract
Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extracted from the shape, margin, and density of each mass, together with the mass size and the patient's age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database for screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.
DOI: 10.1155/2020/7695207
PubMed: 32462017
PubMed Central: PMC7238352
Links to Exploration step
pubmed:32462017Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.</title>
<author><name sortKey="Boumaraf, Said" sort="Boumaraf, Said" uniqKey="Boumaraf S" first="Said" last="Boumaraf">Said Boumaraf</name>
<affiliation><nlm:affiliation>Beijing Lab of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Liu, Xiabi" sort="Liu, Xiabi" uniqKey="Liu X" first="Xiabi" last="Liu">Xiabi Liu</name>
<affiliation><nlm:affiliation>Beijing Lab of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Ferkous, Chokri" sort="Ferkous, Chokri" uniqKey="Ferkous C" first="Chokri" last="Ferkous">Chokri Ferkous</name>
<affiliation><nlm:affiliation>Laboratoire des Sciences et Technologies de l'Information et de la Communication LabSTIC, Université 8 Mai 1945 Guelma, BP 401, Guelma 24000, Algeria.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Ma, Xiaohong" sort="Ma, Xiaohong" uniqKey="Ma X" first="Xiaohong" last="Ma">Xiaohong Ma</name>
<affiliation><nlm:affiliation>National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.</nlm:affiliation>
</affiliation>
</author>
</titleStmt>
<publicationStmt><idno type="wicri:source">PubMed</idno>
<date when="2020">2020</date>
<idno type="RBID">pubmed:32462017</idno>
<idno type="pmid">32462017</idno>
<idno type="doi">10.1155/2020/7695207</idno>
<idno type="pmc">PMC7238352</idno>
<idno type="wicri:Area/PubMed/Corpus">000144</idno>
<idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000144</idno>
</publicationStmt>
<sourceDesc><biblStruct><analytic><title xml:lang="en">A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.</title>
<author><name sortKey="Boumaraf, Said" sort="Boumaraf, Said" uniqKey="Boumaraf S" first="Said" last="Boumaraf">Said Boumaraf</name>
<affiliation><nlm:affiliation>Beijing Lab of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Liu, Xiabi" sort="Liu, Xiabi" uniqKey="Liu X" first="Xiabi" last="Liu">Xiabi Liu</name>
<affiliation><nlm:affiliation>Beijing Lab of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Ferkous, Chokri" sort="Ferkous, Chokri" uniqKey="Ferkous C" first="Chokri" last="Ferkous">Chokri Ferkous</name>
<affiliation><nlm:affiliation>Laboratoire des Sciences et Technologies de l'Information et de la Communication LabSTIC, Université 8 Mai 1945 Guelma, BP 401, Guelma 24000, Algeria.</nlm:affiliation>
</affiliation>
</author>
<author><name sortKey="Ma, Xiaohong" sort="Ma, Xiaohong" uniqKey="Ma X" first="Xiaohong" last="Ma">Xiaohong Ma</name>
<affiliation><nlm:affiliation>National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.</nlm:affiliation>
</affiliation>
</author>
</analytic>
<series><title level="j">BioMed research international</title>
<idno type="eISSN">2314-6141</idno>
<imprint><date when="2020" type="published">2020</date>
</imprint>
</series>
</biblStruct>
</sourceDesc>
</fileDesc>
<profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms (MeSH)</term>
<term>Breast (diagnostic imaging)</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>Neural Networks, Computer (MeSH)</term>
</keywords>
<keywords scheme="MESH" qualifier="diagnostic imaging" xml:lang="en"><term>Breast</term>
<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>Neural Networks, Computer</term>
</keywords>
</textClass>
</profileDesc>
</teiHeader>
<front><div type="abstract" xml:lang="en">Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extracted from the shape, margin, and density of each mass, together with the mass size and the patient's age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database for screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.</div>
</front>
</TEI>
<pubmed><MedlineCitation Status="MEDLINE" Owner="NLM"><PMID Version="1">32462017</PMID>
<DateCompleted><Year>2021</Year>
<Month>03</Month>
<Day>08</Day>
</DateCompleted>
<DateRevised><Year>2021</Year>
<Month>03</Month>
<Day>08</Day>
</DateRevised>
<Article PubModel="Electronic-eCollection"><Journal><ISSN IssnType="Electronic">2314-6141</ISSN>
<JournalIssue CitedMedium="Internet"><Volume>2020</Volume>
<PubDate><Year>2020</Year>
</PubDate>
</JournalIssue>
<Title>BioMed research international</Title>
<ISOAbbreviation>Biomed Res Int</ISOAbbreviation>
</Journal>
<ArticleTitle>A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms.</ArticleTitle>
<Pagination><MedlinePgn>7695207</MedlinePgn>
</Pagination>
<ELocationID EIdType="doi" ValidYN="Y">10.1155/2020/7695207</ELocationID>
<Abstract><AbstractText>Mammography remains the most prevalent imaging tool for early breast cancer screening. The language used to describe abnormalities in mammographic reports is based on the Breast Imaging Reporting and Data System (BI-RADS). Assigning a correct BI-RADS category to each examined mammogram is a strenuous and challenging task for even experts. This paper proposes a new and effective computer-aided diagnosis (CAD) system to classify mammographic masses into four assessment categories in BI-RADS. The mass regions are first enhanced by means of histogram equalization and then semiautomatically segmented based on the region growing technique. A total of 130 handcrafted BI-RADS features are then extracted from the shape, margin, and density of each mass, together with the mass size and the patient's age, as mentioned in BI-RADS mammography. Then, a modified feature selection method based on the genetic algorithm (GA) is proposed to select the most clinically significant BI-RADS features. Finally, a back-propagation neural network (BPN) is employed for classification, and its accuracy is used as the fitness in GA. A set of 500 mammogram images from the digital database for screening mammography (DDSM) is used for evaluation. Our system achieves classification accuracy, positive predictive value, negative predictive value, and Matthews correlation coefficient of 84.5%, 84.4%, 94.8%, and 79.3%, respectively. To our best knowledge, this is the best current result for BI-RADS classification of breast masses in mammography, which makes the proposed system promising to support radiologists for deciding proper patient management based on the automatically assigned BI-RADS categories.</AbstractText>
<CopyrightInformation>Copyright © 2020 Said Boumaraf et al.</CopyrightInformation>
</Abstract>
<AuthorList CompleteYN="Y"><Author ValidYN="Y"><LastName>Boumaraf</LastName>
<ForeName>Said</ForeName>
<Initials>S</Initials>
<Identifier Source="ORCID">https://orcid.org/0000-0001-8154-7195</Identifier>
<AffiliationInfo><Affiliation>Beijing Lab of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Liu</LastName>
<ForeName>Xiabi</ForeName>
<Initials>X</Initials>
<Identifier Source="ORCID">https://orcid.org/0000-0003-1633-0648</Identifier>
<AffiliationInfo><Affiliation>Beijing Lab of Intelligent Information Technology, School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Ferkous</LastName>
<ForeName>Chokri</ForeName>
<Initials>C</Initials>
<Identifier Source="ORCID">https://orcid.org/0000-0002-7408-0803</Identifier>
<AffiliationInfo><Affiliation>Laboratoire des Sciences et Technologies de l'Information et de la Communication LabSTIC, Université 8 Mai 1945 Guelma, BP 401, Guelma 24000, Algeria.</Affiliation>
</AffiliationInfo>
</Author>
<Author ValidYN="Y"><LastName>Ma</LastName>
<ForeName>Xiaohong</ForeName>
<Initials>X</Initials>
<Identifier Source="ORCID">https://orcid.org/0000-0002-9048-8374</Identifier>
<AffiliationInfo><Affiliation>National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing 100021, China.</Affiliation>
</AffiliationInfo>
</Author>
</AuthorList>
<Language>eng</Language>
<PublicationTypeList><PublicationType UI="D016428">Journal Article</PublicationType>
</PublicationTypeList>
<ArticleDate DateType="Electronic"><Year>2020</Year>
<Month>05</Month>
<Day>11</Day>
</ArticleDate>
</Article>
<MedlineJournalInfo><Country>United States</Country>
<MedlineTA>Biomed Res Int</MedlineTA>
<NlmUniqueID>101600173</NlmUniqueID>
</MedlineJournalInfo>
<CitationSubset>IM</CitationSubset>
<MeshHeadingList><MeshHeading><DescriptorName UI="D000465" MajorTopicYN="Y">Algorithms</DescriptorName>
</MeshHeading>
<MeshHeading><DescriptorName UI="D001940" MajorTopicYN="N">Breast</DescriptorName>
<QualifierName UI="Q000000981" MajorTopicYN="N">diagnostic imaging</QualifierName>
</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="D016571" MajorTopicYN="N">Neural Networks, Computer</DescriptorName>
</MeshHeading>
</MeshHeadingList>
<CoiStatement>The authors declare that they have no conflicts of interest.</CoiStatement>
</MedlineCitation>
<PubmedData><History><PubMedPubDate PubStatus="received"><Year>2020</Year>
<Month>01</Month>
<Day>13</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="revised"><Year>2020</Year>
<Month>03</Month>
<Day>19</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="accepted"><Year>2020</Year>
<Month>04</Month>
<Day>02</Day>
</PubMedPubDate>
<PubMedPubDate PubStatus="entrez"><Year>2020</Year>
<Month>5</Month>
<Day>29</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="pubmed"><Year>2020</Year>
<Month>5</Month>
<Day>29</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
<PubMedPubDate PubStatus="medline"><Year>2021</Year>
<Month>3</Month>
<Day>9</Day>
<Hour>6</Hour>
<Minute>0</Minute>
</PubMedPubDate>
</History>
<PublicationStatus>epublish</PublicationStatus>
<ArticleIdList><ArticleId IdType="pubmed">32462017</ArticleId>
<ArticleId IdType="doi">10.1155/2020/7695207</ArticleId>
<ArticleId IdType="pmc">PMC7238352</ArticleId>
</ArticleIdList>
<ReferenceList><Reference><Citation>J Med Ultrason (2001). 2010 Oct;37(4):181-6</Citation>
<ArticleIdList><ArticleId IdType="pubmed">27278192</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>IEEE J Biomed Health Inform. 2018 May;22(3):826-834</Citation>
<ArticleIdList><ArticleId IdType="pubmed">28622679</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Int J Cancer. 2015 Mar 1;136(5):E359-86</Citation>
<ArticleIdList><ArticleId IdType="pubmed">25220842</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Curr Radiol Rep. 2018;6(2):5</Citation>
<ArticleIdList><ArticleId IdType="pubmed">29399419</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Comput Biol Med. 2015 Sep;64:334-46</Citation>
<ArticleIdList><ArticleId IdType="pubmed">25453323</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Comput Biol Med. 2013 Jan;43(1):32-41</Citation>
<ArticleIdList><ArticleId IdType="pubmed">23182603</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Eur J Radiol. 2013 Mar;82(3):388-97</Citation>
<ArticleIdList><ArticleId IdType="pubmed">22483607</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>CA Cancer J Clin. 2017 Nov;67(6):439-448</Citation>
<ArticleIdList><ArticleId IdType="pubmed">28972651</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Med Phys. 2006 Jun;33(6):1810-7</Citation>
<ArticleIdList><ArticleId IdType="pubmed">16872088</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Acad Radiol. 2012 Feb;19(2):236-48</Citation>
<ArticleIdList><ArticleId IdType="pubmed">22078258</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Lancet Oncol. 2014 Jun;15(7):e279-89</Citation>
<ArticleIdList><ArticleId IdType="pubmed">24872111</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Med Image Anal. 2010 Apr;14(2):87-110</Citation>
<ArticleIdList><ArticleId IdType="pubmed">20071209</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Acad Radiol. 2017 Jan;24(1):60-66</Citation>
<ArticleIdList><ArticleId IdType="pubmed">27793579</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Comput Biol Med. 2018 May 1;96:294-298</Citation>
<ArticleIdList><ArticleId IdType="pubmed">29673997</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Int J Med Inform. 2018 Sep;117:44-54</Citation>
<ArticleIdList><ArticleId IdType="pubmed">30032964</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Gynecol Obstet Fertil. 2005 May;33(5):338-47</Citation>
<ArticleIdList><ArticleId IdType="pubmed">15922646</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Comput Methods Programs Biomed. 2018 Apr;157:19-30</Citation>
<ArticleIdList><ArticleId IdType="pubmed">29477427</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Biomed Res Int. 2017;2017:3640901</Citation>
<ArticleIdList><ArticleId IdType="pubmed">28191461</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Acad Radiol. 1999 Jan;6(1):10-5</Citation>
<ArticleIdList><ArticleId IdType="pubmed">9891147</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Comput Methods Programs Biomed. 2018 Apr;157:85-94</Citation>
<ArticleIdList><ArticleId IdType="pubmed">29477437</ArticleId>
</ArticleIdList>
</Reference>
<Reference><Citation>Comput Biol Med. 2013 May;43(4):259-67</Citation>
<ArticleIdList><ArticleId IdType="pubmed">23414779</ArticleId>
</ArticleIdList>
</Reference>
</ReferenceList>
</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 000144 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd -nk 000144 | 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:32462017 |texte= A New Computer-Aided Diagnosis System with Modified Genetic Feature Selection for BI-RADS Classification of Breast Masses in Mammograms. }}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/PubMed/Corpus/RBID.i -Sk "pubmed:32462017" \ | HfdSelect -Kh $EXPLOR_AREA/Data/PubMed/Corpus/biblio.hfd \ | NlmPubMed2Wicri -a MaghrebDataLibMedV2
![]() | This area was generated with Dilib version V0.6.38. | ![]() |