Experimental evaluation of prototype-based deep-learning explainability on skin lesions

Cecilia, Leonardo - Yovine, Sergio

Resumen:

The goal of this work is two-fold. First, it evaluates the application of an explainable computer vision approach based on deep learning in the context of the medical diagnosis of skin lesions. Second, it proposes visualization tools that can be used in clinical settings to help clinicians make better informed decisions.

Detalles Bibliográficos
2024
Agencia Nacional de Investigación e Innovación
Healthcare
Deep learning
Explainability
Ciencias Naturales y Exactas
Ciencias de la Computación e Información
Inglés
Agencia Nacional de Investigación e Innovación
REDI
https://hdl.handle.net/20.500.12381/3737
Acceso abierto
Reconocimiento 4.0 Internacional. (CC BY)
_version_ 1876565325967785984
author Cecilia, Leonardo
author2 Yovine, Sergio
author2_role author
author_facet Cecilia, Leonardo
Yovine, Sergio
author_role author
bitstream.checksum.fl_str_mv a4ce09f01b5dd771727aa05c73851623
79f5b74daeeec783fa3510e317d084d7
bitstream.checksumAlgorithm.fl_str_mv MD5
MD5
bitstream.url.fl_str_mv https://redi.anii.org.uy/jspui/bitstream/20.500.12381/3737/2/license.txt
https://redi.anii.org.uy/jspui/bitstream/20.500.12381/3737/1/skin_lesions.pdf
collection REDI
dc.creator.none.fl_str_mv Cecilia, Leonardo
Yovine, Sergio
dc.date.accessioned.none.fl_str_mv 2024-12-18T18:28:01Z
dc.date.available.none.fl_str_mv 2024-12-18T18:28:01Z
dc.date.issued.none.fl_str_mv 2024-11
dc.description.abstract.none.fl_txt_mv The goal of this work is two-fold. First, it evaluates the application of an explainable computer vision approach based on deep learning in the context of the medical diagnosis of skin lesions. Second, it proposes visualization tools that can be used in clinical settings to help clinicians make better informed decisions.
dc.description.sponsorship.none.fl_txt_mv Agencia Nacional de Investigación e Innovación
dc.identifier.anii.es.fl_str_mv FMV_1_2019_1_155913
dc.identifier.uri.none.fl_str_mv https://hdl.handle.net/20.500.12381/3737
dc.language.iso.none.fl_str_mv eng
dc.rights.*.fl_str_mv Acceso abierto
dc.rights.license.none.fl_str_mv Reconocimiento 4.0 Internacional. (CC BY)
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
dc.source.none.fl_str_mv reponame:REDI
instname:Agencia Nacional de Investigación e Innovación
instacron:Agencia Nacional de Investigación e Innovación
dc.subject.anii.none.fl_str_mv Ciencias Naturales y Exactas
Ciencias de la Computación e Información
dc.subject.es.fl_str_mv Healthcare
Deep learning
Explainability
dc.title.none.fl_str_mv Experimental evaluation of prototype-based deep-learning explainability on skin lesions
dc.type.es.fl_str_mv Preprint
dc.type.none.fl_str_mv info:eu-repo/semantics/preprint
description The goal of this work is two-fold. First, it evaluates the application of an explainable computer vision approach based on deep learning in the context of the medical diagnosis of skin lesions. Second, it proposes visualization tools that can be used in clinical settings to help clinicians make better informed decisions.
eu_rights_str_mv openAccess
format preprint
id REDI_09aac185304209a1d3dd0c50f7987bdc
identifier_str_mv FMV_1_2019_1_155913
instacron_str Agencia Nacional de Investigación e Innovación
institution Agencia Nacional de Investigación e Innovación
instname_str Agencia Nacional de Investigación e Innovación
language eng
network_acronym_str REDI
network_name_str REDI
oai_identifier_str oai:redi.anii.org.uy:20.500.12381/3737
publishDate 2024
reponame_str REDI
repository.mail.fl_str_mv jmaldini@anii.org.uy
repository.name.fl_str_mv REDI - Agencia Nacional de Investigación e Innovación
repository_id_str 9421
rights_invalid_str_mv Reconocimiento 4.0 Internacional. (CC BY)
Acceso abierto
spelling Reconocimiento 4.0 Internacional. (CC BY)Acceso abiertoinfo:eu-repo/semantics/openAccess2024-12-18T18:28:01Z2024-12-18T18:28:01Z2024-11https://hdl.handle.net/20.500.12381/3737FMV_1_2019_1_155913The goal of this work is two-fold. First, it evaluates the application of an explainable computer vision approach based on deep learning in the context of the medical diagnosis of skin lesions. Second, it proposes visualization tools that can be used in clinical settings to help clinicians make better informed decisions.Agencia Nacional de Investigación e InnovaciónengHealthcareDeep learningExplainabilityCiencias Naturales y ExactasCiencias de la Computación e InformaciónExperimental evaluation of prototype-based deep-learning explainability on skin lesionsPreprintinfo:eu-repo/semantics/preprintUniversidad ORT Uruguay, Facultad de Ingeniería//Ciencias Naturales y Exactas/Ciencias de la Computación e Información/Ciencias de la Computación e Informaciónreponame:REDIinstname:Agencia Nacional de Investigación e Innovacióninstacron:Agencia Nacional de Investigación e InnovaciónCecilia, LeonardoYovine, SergioLICENSElicense.txtlicense.txttext/plain; charset=utf-84967https://redi.anii.org.uy/jspui/bitstream/20.500.12381/3737/2/license.txta4ce09f01b5dd771727aa05c73851623MD52ORIGINALskin_lesions.pdfskin_lesions.pdfapplication/pdf9900558https://redi.anii.org.uy/jspui/bitstream/20.500.12381/3737/1/skin_lesions.pdf79f5b74daeeec783fa3510e317d084d7MD5120.500.12381/37372024-12-18 15:28:03.096oai:redi.anii.org.uy:20.500.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Institucionalhttps://redi.anii.org.uy/Gobiernohttps://www.anii.org.uy/https://redi.anii.org.uy/oai/requestjmaldini@anii.org.uyUruguayopendoar:94212024-12-18T18:28:03REDI - Agencia Nacional de Investigación e Innovaciónfalse
spellingShingle Experimental evaluation of prototype-based deep-learning explainability on skin lesions
Cecilia, Leonardo
Healthcare
Deep learning
Explainability
Ciencias Naturales y Exactas
Ciencias de la Computación e Información
title Experimental evaluation of prototype-based deep-learning explainability on skin lesions
title_full Experimental evaluation of prototype-based deep-learning explainability on skin lesions
title_fullStr Experimental evaluation of prototype-based deep-learning explainability on skin lesions
title_full_unstemmed Experimental evaluation of prototype-based deep-learning explainability on skin lesions
title_short Experimental evaluation of prototype-based deep-learning explainability on skin lesions
title_sort Experimental evaluation of prototype-based deep-learning explainability on skin lesions
topic Healthcare
Deep learning
Explainability
Ciencias Naturales y Exactas
Ciencias de la Computación e Información
url https://hdl.handle.net/20.500.12381/3737

Resultados similares