Automatic feature generation in endoscopic images
Identifieur interne : 004417 ( Main/Exploration ); précédent : 004416; suivant : 004418Automatic feature generation in endoscopic images
Auteurs : Ulrich Klank [Allemagne] ; Nicolas Padoy [Allemagne, France] ; Hubertus Feussner [Allemagne] ; Nassir Navab [Allemagne]Source :
- International Journal of Computer Assisted Radiology and Surgery [ 1861-6410 ] ; 2008-09-01.
Descripteurs français
- Wicri :
- topic : Classification.
English descriptors
- KwdEn :
Abstract
Abstract: Motivation: Fiber optic endoscopy is essential for minimally invasive surgery, but endoscopic images are very challenging for computer vision algorithms, since they contain many effects like tissue deformations, specular reflections, smoke, variable illumination and field of view. We developed a method to extract features from endoscopic images usable for scene analysis and classification. These features could be used with data from other sensors for workflow analysis and recognition. Materials and methods: Evolutionary reinforcement learning that automatically computes good features, making it possible to classify endoscopic images into their respective surgical phases. It is especially designed to abstract the relevant information from the highly noisy images automatically. Results: Automatic feature extraction was used to classify images from endoscopic cholecystectomies into their respective surgical phases. These automatically computed features perform better than some classical features from computer vision. The automated feature extraction process enables reasonable classification rates for complex and difficult images where no good features are known. Conclusion: We developed an automatic method that extracts features from images for use in classification. The method was applied to endoscopic images yielding promising results and demonstrating its feasibility under demanding conditions.
Url:
DOI: 10.1007/s11548-008-0223-8
Affiliations:
- Allemagne, France
- Bavière, District de Haute-Bavière, Grand Est, Lorraine (région)
- Garching bei München, Munich, Nancy
- Université technique de Munich
Links toward previous steps (curation, corpus...)
- to stream Istex, to step Corpus: 000878
- to stream Istex, to step Curation: 000873
- to stream Istex, to step Checkpoint: 000E45
- to stream Main, to step Merge: 004528
- to stream Main, to step Curation: 004417
Le document en format XML
<record><TEI wicri:istexFullTextTei="biblStruct"><teiHeader><fileDesc><titleStmt><title xml:lang="en">Automatic feature generation in endoscopic images</title><author><name sortKey="Klank, Ulrich" sort="Klank, Ulrich" uniqKey="Klank U" first="Ulrich" last="Klank">Ulrich Klank</name></author><author><name sortKey="Padoy, Nicolas" sort="Padoy, Nicolas" uniqKey="Padoy N" first="Nicolas" last="Padoy">Nicolas Padoy</name></author><author><name sortKey="Feussner, Hubertus" sort="Feussner, Hubertus" uniqKey="Feussner H" first="Hubertus" last="Feussner">Hubertus Feussner</name></author><author><name sortKey="Navab, Nassir" sort="Navab, Nassir" uniqKey="Navab N" first="Nassir" last="Navab">Nassir Navab</name></author></titleStmt><publicationStmt><idno type="wicri:source">ISTEX</idno><idno type="RBID">ISTEX:26AD431C4918106FFCE2E6FC9FF52E9CD598548E</idno><date when="2008" year="2008">2008</date><idno type="doi">10.1007/s11548-008-0223-8</idno><idno type="url">https://api.istex.fr/ark:/67375/VQC-86917SHK-W/fulltext.pdf</idno><idno type="wicri:Area/Istex/Corpus">000878</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Corpus" wicri:corpus="ISTEX">000878</idno><idno type="wicri:Area/Istex/Curation">000873</idno><idno type="wicri:Area/Istex/Checkpoint">000E45</idno><idno type="wicri:explorRef" wicri:stream="Istex" wicri:step="Checkpoint">000E45</idno><idno type="wicri:doubleKey">1861-6410:2008:Klank U:automatic:feature:generation</idno><idno type="wicri:Area/Main/Merge">004528</idno><idno type="wicri:Area/Main/Curation">004417</idno><idno type="wicri:Area/Main/Exploration">004417</idno></publicationStmt><sourceDesc><biblStruct><analytic><title level="a" type="main" xml:lang="en">Automatic feature generation in endoscopic images</title><author><name sortKey="Klank, Ulrich" sort="Klank, Ulrich" uniqKey="Klank U" first="Ulrich" last="Klank">Ulrich Klank</name><affiliation wicri:level="4"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Technische Universität München, Boltzmannstr. 3, 85748, Garching</wicri:regionArea><placeName><region type="land" nuts="1">Bavière</region><region type="district" nuts="2">District de Haute-Bavière</region><settlement type="city">Garching bei München</settlement></placeName><orgName type="university">Université technique de Munich</orgName></affiliation><affiliation wicri:level="1"><country wicri:rule="url">Allemagne</country></affiliation></author><author><name sortKey="Padoy, Nicolas" sort="Padoy, Nicolas" uniqKey="Padoy N" first="Nicolas" last="Padoy">Nicolas Padoy</name><affiliation wicri:level="4"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Technische Universität München, Boltzmannstr. 3, 85748, Garching</wicri:regionArea><placeName><region type="land" nuts="1">Bavière</region><region type="district" nuts="2">District de Haute-Bavière</region><settlement type="city">Garching bei München</settlement></placeName><orgName type="university">Université technique de Munich</orgName></affiliation><affiliation wicri:level="3"><country xml:lang="fr">France</country><wicri:regionArea>LORIA-INRIA Lorraine, Nancy</wicri:regionArea><placeName><region type="region">Grand Est</region><region type="old region">Lorraine (région)</region><settlement type="city">Nancy</settlement></placeName></affiliation></author><author><name sortKey="Feussner, Hubertus" sort="Feussner, Hubertus" uniqKey="Feussner H" first="Hubertus" last="Feussner">Hubertus Feussner</name><affiliation wicri:level="3"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Chirurgische Klinik und Poliklinik, Klinikum Rechts der Isar, TU, München</wicri:regionArea><placeName><region type="land" nuts="1">Bavière</region><region type="district" nuts="2">District de Haute-Bavière</region><settlement type="city">Munich</settlement></placeName></affiliation></author><author><name sortKey="Navab, Nassir" sort="Navab, Nassir" uniqKey="Navab N" first="Nassir" last="Navab">Nassir Navab</name><affiliation wicri:level="4"><country xml:lang="fr">Allemagne</country><wicri:regionArea>Technische Universität München, Boltzmannstr. 3, 85748, Garching</wicri:regionArea><placeName><region type="land" nuts="1">Bavière</region><region type="district" nuts="2">District de Haute-Bavière</region><settlement type="city">Garching bei München</settlement></placeName><orgName type="university">Université technique de Munich</orgName></affiliation></author></analytic><monogr></monogr><series><title level="j">International Journal of Computer Assisted Radiology and Surgery</title><title level="j" type="sub">A journal for interdisciplinary research, development and applications of image guided diagnosis and therapy</title><title level="j" type="abbrev">Int J CARS</title><idno type="ISSN">1861-6410</idno><idno type="eISSN">1861-6429</idno><imprint><publisher>Springer-Verlag</publisher><pubPlace>Berlin/Heidelberg</pubPlace><date type="published" when="2008-09-01">2008-09-01</date><biblScope unit="volume">3</biblScope><biblScope unit="issue">3-4</biblScope><biblScope unit="page" from="331">331</biblScope><biblScope unit="page" to="339">339</biblScope></imprint><idno type="ISSN">1861-6410</idno></series></biblStruct></sourceDesc><seriesStmt><idno type="ISSN">1861-6410</idno></seriesStmt></fileDesc><profileDesc><textClass><keywords scheme="KwdEn" xml:lang="en"><term>Cholecystectomy</term><term>Classification</term><term>Endoscopic images</term><term>Evolutionary reinforcement learning</term><term>Feature generation</term></keywords><keywords scheme="Wicri" type="topic" xml:lang="fr"><term>Classification</term></keywords></textClass><langUsage><language ident="en">en</language></langUsage></profileDesc></teiHeader><front><div type="abstract" xml:lang="en">Abstract: Motivation: Fiber optic endoscopy is essential for minimally invasive surgery, but endoscopic images are very challenging for computer vision algorithms, since they contain many effects like tissue deformations, specular reflections, smoke, variable illumination and field of view. We developed a method to extract features from endoscopic images usable for scene analysis and classification. These features could be used with data from other sensors for workflow analysis and recognition. Materials and methods: Evolutionary reinforcement learning that automatically computes good features, making it possible to classify endoscopic images into their respective surgical phases. It is especially designed to abstract the relevant information from the highly noisy images automatically. Results: Automatic feature extraction was used to classify images from endoscopic cholecystectomies into their respective surgical phases. These automatically computed features perform better than some classical features from computer vision. The automated feature extraction process enables reasonable classification rates for complex and difficult images where no good features are known. Conclusion: We developed an automatic method that extracts features from images for use in classification. The method was applied to endoscopic images yielding promising results and demonstrating its feasibility under demanding conditions.</div></front></TEI><affiliations><list><country><li>Allemagne</li><li>France</li></country><region><li>Bavière</li><li>District de Haute-Bavière</li><li>Grand Est</li><li>Lorraine (région)</li></region><settlement><li>Garching bei München</li><li>Munich</li><li>Nancy</li></settlement><orgName><li>Université technique de Munich</li></orgName></list><tree><country name="Allemagne"><region name="Bavière"><name sortKey="Klank, Ulrich" sort="Klank, Ulrich" uniqKey="Klank U" first="Ulrich" last="Klank">Ulrich Klank</name></region><name sortKey="Feussner, Hubertus" sort="Feussner, Hubertus" uniqKey="Feussner H" first="Hubertus" last="Feussner">Hubertus Feussner</name><name sortKey="Klank, Ulrich" sort="Klank, Ulrich" uniqKey="Klank U" first="Ulrich" last="Klank">Ulrich Klank</name><name sortKey="Navab, Nassir" sort="Navab, Nassir" uniqKey="Navab N" first="Nassir" last="Navab">Nassir Navab</name><name sortKey="Padoy, Nicolas" sort="Padoy, Nicolas" uniqKey="Padoy N" first="Nicolas" last="Padoy">Nicolas Padoy</name></country><country name="France"><region name="Grand Est"><name sortKey="Padoy, Nicolas" sort="Padoy, Nicolas" uniqKey="Padoy N" first="Nicolas" last="Padoy">Nicolas Padoy</name></region></country></tree></affiliations></record>Pour manipuler ce document sous Unix (Dilib)
EXPLOR_STEP=$WICRI_ROOT/Wicri/Lorraine/explor/InforLorV4/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 004417 | SxmlIndent | more
Ou
HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 004417 | SxmlIndent | more
Pour mettre un lien sur cette page dans le réseau Wicri
{{Explor lien
|wiki= Wicri/Lorraine
|area= InforLorV4
|flux= Main
|étape= Exploration
|type= RBID
|clé= ISTEX:26AD431C4918106FFCE2E6FC9FF52E9CD598548E
|texte= Automatic feature generation in endoscopic images
}}
| This area was generated with Dilib version V0.6.33. |  |