Histopathological image analysis for centroblasts classification through dimensionality reduction approaches
Identifieur interne : 000433 ( Main/Exploration ); précédent : 000432; suivant : 000434Histopathological image analysis for centroblasts classification through dimensionality reduction approaches
Auteurs : Evgenios N. Kornaropoulos [Grèce] ; M Khalid Khan Niazi ; Gerard Lozanski ; Metin N. GurcanSource :
- Cytometry. Part A : the journal of the International Society for Analytical Cytology [ 1552-4922 ] ; 2013.
Descripteurs français
- KwdFr :
- MESH :
English descriptors
- KwdEn :
- MESH :
- diagnosis : Lymphoma, Follicular.
- methods : Image Enhancement, Image Interpretation, Computer-Assisted, Pattern Recognition, Automated.
- pathology : Lymphoma, Follicular.
- Algorithms, Artificial Intelligence, Humans, Statistics as Topic.
Abstract
We present two novel automated image analysis methods to differentiate centroblast (CB) cells from non-centroblast (Non-CB) cells in digital images of H&E-stained tissues of follicular lymphoma. CB cells are often confused by similar looking cells within the tissue, therefore a system to help their classification is necessary. Our methods extract the discriminatory features of cells by approximating the intrinsic dimensionality from the subspace spanned by CB and Non-CB cells. In the first method, discriminatory features are approximated with the help of Singular Value Decomposition (SVD), whereas in the second method they are extracted using Laplacian Eigenmaps. Five hundred high-power field images were extracted from 17 slides, which are then used to compose a database of 213 CB and 234 Non-CB region of interest images. The recall, precision and overall accuracy rates of the developed methods were measured and compared with existing classification methods. Moreover, the reproducibility of both classification methods was also examined. The average values of the overall accuracy were 99.22% ± 0.75% and 99.07% ± 1.53% for COB and CLEM, respectively. The experimental results demonstrate that both proposed methods provide better classification accuracy of CB/Non-CB in comparison to the state of the art methods.
Url:
DOI: 10.1002/cyto.a.22432
PubMed: 24376080
PubMed Central: 4017952
Affiliations:
Links toward previous steps (curation, corpus...)
- to stream Pmc, to step Corpus: 000412
- to stream Pmc, to step Curation: 000412
- to stream Pmc, to step Checkpoint: 000243
- to stream PubMed, to step Corpus: 000219
- to stream PubMed, to step Curation: 000219
- to stream PubMed, to step Checkpoint: 000219
- to stream Ncbi, to step Merge: 000970
- to stream Ncbi, to step Curation: 000970
- to stream Ncbi, to step Checkpoint: 000970
- to stream Main, to step Merge: 000433
- to stream Main, to step Curation: 000433
Le document en format XML
<record><TEI><teiHeader><fileDesc><titleStmt><title xml:lang="en">Histopathological image analysis for centroblasts classification
through dimensionality reduction approaches</title><author><name sortKey="Kornaropoulos, Evgenios N" sort="Kornaropoulos, Evgenios N" uniqKey="Kornaropoulos E" first="Evgenios N." last="Kornaropoulos">Evgenios N. Kornaropoulos</name><affiliation wicri:level="1"><nlm:aff id="A1">Informatics and Telematics Institute - Centre for Research and Technology Hellas (ITI - CERTH), Thessaloniki, Greece</nlm:aff><country xml:lang="fr">Grèce</country><wicri:regionArea>Informatics and Telematics Institute - Centre for Research and Technology Hellas (ITI - CERTH), Thessaloniki</wicri:regionArea><wicri:noRegion>Thessaloniki</wicri:noRegion></affiliation></author><author><name sortKey="Niazi, M Khalid Khan" sort="Niazi, M Khalid Khan" uniqKey="Niazi M" first="M Khalid Khan" last="Niazi">M Khalid Khan Niazi</name><affiliation><nlm:aff id="A2">Ohio State University, Department of Biomedical Informatics, Columbus, Ohio, United States of America (USA)</nlm:aff><wicri:noCountry code="subfield">United States of America (USA)</wicri:noCountry></affiliation></author><author><name sortKey="Lozanski, Gerard" sort="Lozanski, Gerard" uniqKey="Lozanski G" first="Gerard" last="Lozanski">Gerard Lozanski</name><affiliation><nlm:aff id="A3">Ohio State University, Department of Pathology, Columbus, Ohio, United States of America (USA)</nlm:aff><wicri:noCountry code="subfield">United States of America (USA)</wicri:noCountry></affiliation></author><author><name sortKey="Gurcan, Metin N" sort="Gurcan, Metin N" uniqKey="Gurcan M" first="Metin N." last="Gurcan">Metin N. Gurcan</name><affiliation><nlm:aff id="A2">Ohio State University, Department of Biomedical Informatics, Columbus, Ohio, United States of America (USA)</nlm:aff><wicri:noCountry code="subfield">United States of America (USA)</wicri:noCountry></affiliation></author></titleStmt><publicationStmt><idno type="wicri:source">PMC</idno><idno type="pmid">24376080</idno><idno type="pmc">4017952</idno><idno type="url">http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4017952</idno><idno type="RBID">PMC:4017952</idno><idno type="doi">10.1002/cyto.a.22432</idno><date when="2013">2013</date><idno type="wicri:Area/Pmc/Corpus">000412</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Corpus" wicri:corpus="PMC">000412</idno><idno type="wicri:Area/Pmc/Curation">000412</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Curation">000412</idno><idno type="wicri:Area/Pmc/Checkpoint">000243</idno><idno type="wicri:explorRef" wicri:stream="Pmc" wicri:step="Checkpoint">000243</idno><idno type="wicri:source">PubMed</idno><idno type="wicri:Area/PubMed/Corpus">000219</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Corpus" wicri:corpus="PubMed">000219</idno><idno type="wicri:Area/PubMed/Curation">000219</idno><idno type="wicri:explorRef" wicri:stream="PubMed" wicri:step="Curation">000219</idno><idno type="wicri:Area/PubMed/Checkpoint">000219</idno><idno type="wicri:explorRef" wicri:stream="Checkpoint" wicri:step="PubMed">000219</idno><idno type="wicri:Area/Ncbi/Merge">000970</idno><idno type="wicri:Area/Ncbi/Curation">000970</idno><idno type="wicri:Area/Ncbi/Checkpoint">000970</idno><idno type="wicri:doubleKey">1552-4922:2013:Kornaropoulos E:histopathological:image:analysis</idno><idno type="wicri:Area/Main/Merge">000433</idno><idno type="wicri:Area/Main/Curation">000433</idno><idno type="wicri:Area/Main/Exploration">000433</idno></publicationStmt><sourceDesc><biblStruct><analytic><title xml:lang="en" level="a" type="main">Histopathological image analysis for centroblasts classification
through dimensionality reduction approaches</title><author><name sortKey="Kornaropoulos, Evgenios N" sort="Kornaropoulos, Evgenios N" uniqKey="Kornaropoulos E" first="Evgenios N." last="Kornaropoulos">Evgenios N. Kornaropoulos</name><affiliation wicri:level="1"><nlm:aff id="A1">Informatics and Telematics Institute - Centre for Research and Technology Hellas (ITI - CERTH), Thessaloniki, Greece</nlm:aff><country xml:lang="fr">Grèce</country><wicri:regionArea>Informatics and Telematics Institute - Centre for Research and Technology Hellas (ITI - CERTH), Thessaloniki</wicri:regionArea><wicri:noRegion>Thessaloniki</wicri:noRegion></affiliation></author><author><name sortKey="Niazi, M Khalid Khan" sort="Niazi, M Khalid Khan" uniqKey="Niazi M" first="M Khalid Khan" last="Niazi">M Khalid Khan Niazi</name><affiliation><nlm:aff id="A2">Ohio State University, Department of Biomedical Informatics, Columbus, Ohio, United States of America (USA)</nlm:aff><wicri:noCountry code="subfield">United States of America (USA)</wicri:noCountry></affiliation></author><author><name sortKey="Lozanski, Gerard" sort="Lozanski, Gerard" uniqKey="Lozanski G" first="Gerard" last="Lozanski">Gerard Lozanski</name><affiliation><nlm:aff id="A3">Ohio State University, Department of Pathology, Columbus, Ohio, United States of America (USA)</nlm:aff><wicri:noCountry code="subfield">United States of America (USA)</wicri:noCountry></affiliation></author><author><name sortKey="Gurcan, Metin N" sort="Gurcan, Metin N" uniqKey="Gurcan M" first="Metin N." last="Gurcan">Metin N. Gurcan</name><affiliation><nlm:aff id="A2">Ohio State University, Department of Biomedical Informatics, Columbus, Ohio, United States of America (USA)</nlm:aff><wicri:noCountry code="subfield">United States of America (USA)</wicri:noCountry></affiliation></author></analytic><series><title level="j">Cytometry. Part A : the journal of the International Society for Analytical Cytology</title><idno type="ISSN">1552-4922</idno><idno type="eISSN">1552-4930</idno><imprint><date when="2013">2013</date></imprint></series></biblStruct></sourceDesc></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Algorithms</term><term>Artificial Intelligence</term><term>Humans</term><term>Image Enhancement (methods)</term><term>Image Interpretation, Computer-Assisted (methods)</term><term>Lymphoma, Follicular (diagnosis)</term><term>Lymphoma, Follicular (pathology)</term><term>Pattern Recognition, Automated (methods)</term><term>Statistics as Topic</term></keywords><keywords scheme="KwdFr" xml:lang="fr"><term>Algorithmes</term><term>Amélioration d'image ()</term><term>Humains</term><term>Intelligence artificielle</term><term>Interprétation d'image assistée par ordinateur ()</term><term>Lymphome folliculaire (anatomopathologie)</term><term>Lymphome folliculaire (diagnostic)</term><term>Reconnaissance automatique des formes ()</term><term>Statistiques comme sujet</term></keywords><keywords scheme="MESH" qualifier="anatomopathologie" xml:lang="fr"><term>Lymphome folliculaire</term></keywords><keywords scheme="MESH" qualifier="diagnosis" xml:lang="en"><term>Lymphoma, Follicular</term></keywords><keywords scheme="MESH" qualifier="diagnostic" xml:lang="fr"><term>Lymphome folliculaire</term></keywords><keywords scheme="MESH" qualifier="methods" xml:lang="en"><term>Image Enhancement</term><term>Image Interpretation, Computer-Assisted</term><term>Pattern Recognition, Automated</term></keywords><keywords scheme="MESH" qualifier="pathology" xml:lang="en"><term>Lymphoma, Follicular</term></keywords><keywords scheme="MESH" xml:lang="en"><term>Algorithms</term><term>Artificial Intelligence</term><term>Humans</term><term>Statistics as Topic</term></keywords><keywords scheme="MESH" xml:lang="fr"><term>Algorithmes</term><term>Amélioration d'image</term><term>Humains</term><term>Intelligence artificielle</term><term>Interprétation d'image assistée par ordinateur</term><term>Reconnaissance automatique des formes</term><term>Statistiques comme sujet</term></keywords></textClass></profileDesc></teiHeader><front><div type="abstract" xml:lang="en"><p id="P1">We present two novel automated image analysis methods to differentiate
centroblast (CB) cells from non-centroblast (Non-CB) cells in digital images of
H&E-stained tissues of follicular lymphoma. CB cells are often confused
by similar looking cells within the tissue, therefore a system to help their
classification is necessary. Our methods extract the discriminatory features of
cells by approximating the intrinsic dimensionality from the subspace spanned by
CB and Non-CB cells. In the first method, discriminatory features are
approximated with the help of Singular Value Decomposition (SVD), whereas in the
second method they are extracted using Laplacian Eigenmaps. Five hundred
high-power field images were extracted from 17 slides, which are then used to
compose a database of 213 CB and 234 Non-CB region of interest images. The
recall, precision and overall accuracy rates of the developed methods were
measured and compared with existing classification methods. Moreover, the
reproducibility of both classification methods was also examined. The average
values of the overall accuracy were 99.22% ± 0.75% and
99.07% ± 1.53% for COB and CLEM, respectively. The
experimental results demonstrate that both proposed methods provide better
classification accuracy of CB/Non-CB in comparison to the state of the art
methods.</p></div></front></TEI><affiliations><list><country><li>Grèce</li></country></list><tree><noCountry><name sortKey="Gurcan, Metin N" sort="Gurcan, Metin N" uniqKey="Gurcan M" first="Metin N." last="Gurcan">Metin N. Gurcan</name><name sortKey="Lozanski, Gerard" sort="Lozanski, Gerard" uniqKey="Lozanski G" first="Gerard" last="Lozanski">Gerard Lozanski</name><name sortKey="Niazi, M Khalid Khan" sort="Niazi, M Khalid Khan" uniqKey="Niazi M" first="M Khalid Khan" last="Niazi">M Khalid Khan Niazi</name></noCountry><country name="Grèce"><noRegion><name sortKey="Kornaropoulos, Evgenios N" sort="Kornaropoulos, Evgenios N" uniqKey="Kornaropoulos E" first="Evgenios N." last="Kornaropoulos">Evgenios N. Kornaropoulos</name></noRegion></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/TelematiV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000433 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000433 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Ticri/CIDE
|area= TelematiV1
|flux= Main
|étape= Exploration
|type= RBID
|clé= PMC:4017952
|texte= Histopathological image analysis for centroblasts classification
through dimensionality reduction approaches
}}
Pour générer des pages wiki
HfdIndexSelect -h $EXPLOR_AREA/Data/Main/Exploration/RBID.i -Sk "pubmed:24376080" \
| HfdSelect -Kh $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd \
| NlmPubMed2Wicri -a TelematiV1
| This area was generated with Dilib version V0.6.31. |  |