DC FieldValueLanguage
dc.contributor.authorBengs, Marcel-
dc.contributor.authorWestermann, Stephan-
dc.contributor.authorGessert, Nils Thorben-
dc.contributor.authorEggert, Dennis-
dc.contributor.authorGerstner, Andreas O. H.-
dc.contributor.authorMueller, Nina A.-
dc.contributor.authorBetz, Christian Stephan-
dc.contributor.authorLaffers, Wiebke-
dc.contributor.authorSchlaefer, Alexander-
dc.date.accessioned2020-06-04T05:56:10Z-
dc.date.available2020-06-04T05:56:10Z-
dc.date.issued2020-02-
dc.identifier.citationProgress in Biomedical Optics and Imaging - Proceedings of SPIE (11314): 113141L (2020-02)de_DE
dc.identifier.isbn978-151063395-7de_DE
dc.identifier.issn1605-7422de_DE
dc.identifier.urihttp://hdl.handle.net/11420/6237-
dc.description.abstractEarly detection of head and neck tumors is crucial for patient survival. Often, diagnoses are made based on endoscopic examination of the larynx followed by biopsy and histological analysis, leading to a high interobserver variability due to subjective assessment. In this regard, early non-invasive diagnostics independent of the clinician would be a valuable tool. A recent study has shown that hyperspectral imaging (HSI) can be used for non-invasive detection of head and neck tumors, as precancerous or cancerous lesions show specific spectral signatures that distinguish them from healthy tissue. However, HSI data processing is challenging due to high spectral variations, various image interferences, and the high dimensionality of the data. Therefore, performance of automatic HSI analysis has been limited and so far, mostly ex-vivo studies have been presented with deep learning. In this work, we analyze deep learning techniques for in-vivo hyperspectral laryngeal cancer detection. For this purpose we design and evaluate convolutional neural networks (CNNs) with 2D spatial or 3D spatio-spectral convolutions combined with a state-of-the-art Densenet architecture. For evaluation, we use an in-vivo data set with HSI of the oral cavity or oropharynx. Overall, we present multiple deep learning techniques for in-vivo laryngeal cancer detection based on HSI and we show that jointly learning from the spatial and spectral domain improves classification accuracy notably. Our 3D spatio-spectral Densenet achieves an average accuracy of 81%.en
dc.language.isoende_DE
dc.relation.ispartofProgress in Biomedical Optics and Imaging - Proceedings of SPIEde_DE
dc.subjectconvolutional neural networksde_DE
dc.subjecthead and neck cancerde_DE
dc.subjecthyperspectral imagingde_DE
dc.subjectintraoperative imagingde_DE
dc.subjectoptical biopsyde_DE
dc.titleSpatio-spectral deep learning methods for in-vivo hyperspectral laryngeal cancer detectionde_DE
dc.typeinProceedingsde_DE
dc.type.dinicontributionToPeriodical-
dcterms.DCMITypeText-
tuhh.abstract.englishEarly detection of head and neck tumors is crucial for patient survival. Often, diagnoses are made based on endoscopic examination of the larynx followed by biopsy and histological analysis, leading to a high interobserver variability due to subjective assessment. In this regard, early non-invasive diagnostics independent of the clinician would be a valuable tool. A recent study has shown that hyperspectral imaging (HSI) can be used for non-invasive detection of head and neck tumors, as precancerous or cancerous lesions show specific spectral signatures that distinguish them from healthy tissue. However, HSI data processing is challenging due to high spectral variations, various image interferences, and the high dimensionality of the data. Therefore, performance of automatic HSI analysis has been limited and so far, mostly ex-vivo studies have been presented with deep learning. In this work, we analyze deep learning techniques for in-vivo hyperspectral laryngeal cancer detection. For this purpose we design and evaluate convolutional neural networks (CNNs) with 2D spatial or 3D spatio-spectral convolutions combined with a state-of-the-art Densenet architecture. For evaluation, we use an in-vivo data set with HSI of the oral cavity or oropharynx. Overall, we present multiple deep learning techniques for in-vivo laryngeal cancer detection based on HSI and we show that jointly learning from the spatial and spectral domain improves classification accuracy notably. Our 3D spatio-spectral Densenet achieves an average accuracy of 81%.de_DE
tuhh.publisher.doi10.1117/12.2549251-
tuhh.publication.instituteMedizintechnische Systeme E-1de_DE
tuhh.type.opusInProceedings (Aufsatz / Paper einer Konferenz etc.)-
dc.type.drivercontributionToPeriodical-
dc.type.casraiConference Paper-
tuhh.container.volume11314de_DE
dc.relation.conferenceProgress in Biomedical Optics and Imaging, SPIE (2020-02)de_DE
tuhh.container.articlenumber113141Lde_DE
item.creatorGNDBengs, Marcel-
item.creatorGNDWestermann, Stephan-
item.creatorGNDGessert, Nils Thorben-
item.creatorGNDEggert, Dennis-
item.creatorGNDGerstner, Andreas O. H.-
item.creatorGNDMueller, Nina A.-
item.creatorGNDBetz, Christian Stephan-
item.creatorGNDLaffers, Wiebke-
item.creatorGNDSchlaefer, Alexander-
item.openairecristypehttp://purl.org/coar/resource_type/c_5794-
item.grantfulltextnone-
item.languageiso639-1en-
item.openairetypeinProceedings-
item.cerifentitytypePublications-
item.creatorOrcidBengs, Marcel-
item.creatorOrcidWestermann, Stephan-
item.creatorOrcidGessert, Nils Thorben-
item.creatorOrcidEggert, Dennis-
item.creatorOrcidGerstner, Andreas O. H.-
item.creatorOrcidMueller, Nina A.-
item.creatorOrcidBetz, Christian Stephan-
item.creatorOrcidLaffers, Wiebke-
item.creatorOrcidSchlaefer, Alexander-
item.fulltextNo Fulltext-
crisitem.author.deptMedizintechnische Systeme E-1-
crisitem.author.deptMedizintechnische Systeme E-1-
crisitem.author.deptMedizintechnische Systeme E-1-
crisitem.author.orcid0000-0002-2229-9547-
crisitem.author.orcid0000-0001-6325-5092-
crisitem.author.parentorgStudiendekanat Elektrotechnik, Informatik und Mathematik-
crisitem.author.parentorgStudiendekanat Elektrotechnik, Informatik und Mathematik-
crisitem.author.parentorgStudiendekanat Elektrotechnik, Informatik und Mathematik-
Appears in Collections:Publications without fulltext
Show simple item record

Page view(s)

19
Last Week
2
Last month
3
checked on Aug 11, 2020

Google ScholarTM

Check

Add Files to Item

Note about this record

Export

Items in TORE are protected by copyright, with all rights reserved, unless otherwise indicated.