DC FieldValueLanguage
dc.contributor.authorGessert, Nils Thorben-
dc.contributor.authorBengs, Marcel-
dc.contributor.authorSchlaefer, Alexander-
dc.date.accessioned2020-06-04T05:52:25Z-
dc.date.available2020-06-04T05:52:25Z-
dc.date.issued2020-02-
dc.identifier.citationProgress in Biomedical Optics and Imaging - Proceedings of SPIE (11314): 1131414 (2020-02)de_DE
dc.identifier.isbn978-151063395-7de_DE
dc.identifier.issn1605-7422de_DE
dc.identifier.urihttp://hdl.handle.net/11420/6235-
dc.description.abstractThe initial assessment of skin lesions is typically based on dermoscopic images. As this is a difficult and time-consuming task, machine learning methods using dermoscopic images have been proposed to assist human experts. Other approaches have studied electrical impedance spectroscopy (EIS) as a basis for clinical decision support systems. Both methods represent different ways of measuring skin lesion properties as dermoscopy relies on visible light and EIS uses electric currents. Thus, the two methods might carry complementary features for lesion classification. Therefore, we propose joint deep learning models considering both EIS and dermoscopy for melanoma detection. For this purpose, we first study machine learning methods for EIS that incorporate domain knowledge and previously used heuristics into the design process. As a result, we propose a recurrent model with state-max-pooling which automatically learns the relevance of different EIS measurements. Second, we combine this new model with different convolutional neural networks that process dermoscopic images. We study ensembling approaches and also propose a cross-attention module guiding information exchange between the EIS and dermoscopy model. In general, combinations of EIS and dermoscopy clearly outperform models that only use either EIS or dermoscopy. We show that our attention-based, combined model outperforms other models with specificities of 34:4% (CI 31:3-38:4), 34:7% (CI 31:0-38:8) and 53:7% (CI 50:1-57:6) for dermoscopy, EIS and the combined model, respectively, at a clinically relevant sensitivity of 98 %.en
dc.language.isoende_DE
dc.relation.ispartofProgress in Biomedical Optics and Imaging - Proceedings of SPIEde_DE
dc.subjectdeep learningde_DE
dc.subjectdermoscopyde_DE
dc.subjectelectrical impedance spectroscopyde_DE
dc.subjectmelanomade_DE
dc.titleMelanoma detection with electrical impedance spectroscopy and dermoscopy using joint deep learning modelsde_DE
dc.typeinProceedingsde_DE
dc.type.dinicontributionToPeriodical-
dcterms.DCMITypeText-
tuhh.abstract.englishThe initial assessment of skin lesions is typically based on dermoscopic images. As this is a difficult and time-consuming task, machine learning methods using dermoscopic images have been proposed to assist human experts. Other approaches have studied electrical impedance spectroscopy (EIS) as a basis for clinical decision support systems. Both methods represent different ways of measuring skin lesion properties as dermoscopy relies on visible light and EIS uses electric currents. Thus, the two methods might carry complementary features for lesion classification. Therefore, we propose joint deep learning models considering both EIS and dermoscopy for melanoma detection. For this purpose, we first study machine learning methods for EIS that incorporate domain knowledge and previously used heuristics into the design process. As a result, we propose a recurrent model with state-max-pooling which automatically learns the relevance of different EIS measurements. Second, we combine this new model with different convolutional neural networks that process dermoscopic images. We study ensembling approaches and also propose a cross-attention module guiding information exchange between the EIS and dermoscopy model. In general, combinations of EIS and dermoscopy clearly outperform models that only use either EIS or dermoscopy. We show that our attention-based, combined model outperforms other models with specificities of 34:4% (CI 31:3-38:4), 34:7% (CI 31:0-38:8) and 53:7% (CI 50:1-57:6) for dermoscopy, EIS and the combined model, respectively, at a clinically relevant sensitivity of 98 %.de_DE
tuhh.publisher.doi10.1117/12.2548974-
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.articlenumber1131414de_DE
item.creatorGNDGessert, Nils Thorben-
item.creatorGNDBengs, Marcel-
item.creatorGNDSchlaefer, Alexander-
item.openairecristypehttp://purl.org/coar/resource_type/c_5794-
item.grantfulltextnone-
item.languageiso639-1en-
item.openairetypeinProceedings-
item.cerifentitytypePublications-
item.creatorOrcidGessert, Nils Thorben-
item.creatorOrcidBengs, Marcel-
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.orcid0000-0001-6325-5092-
crisitem.author.orcid0000-0002-2229-9547-
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)

15
Last Week
3
Last month
0
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.