Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng por |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.5935/scd1984-8773.2021130015 http://hdl.handle.net/11449/229427 |
Resumo: | Introduction: With the advancement of digital image analysis, predictive analysis, and machine learning methods, studies have emerged regarding the use of artificial intelligence in imaging tests such as dermoscopy. Objective: Construction, testing, and implementation of an artificial neural network based on characteristics of dermoscopic images. Methods: 1949 images of melanocytic nevi and melanomas were included, both from the authors’ files and from dermoscopic image banks available on the internet, and routines and plugins were developed to extract 58 features applied to a multilayered neural network construction algorithm. Also, 52 dermatologists assessed 40 random images and compared the results compared. Results: The training and testing of the neural network obtained a correct percentage of classification of 78.5% and 79.1%, respectively, with a ROC curve covering 86.5% of the area. The sensitivity and specificity of dermatologists were 71.8% and 52%. For the same images and a cutoff point of 0.4 (40%) of the output value, the application obtained 62% and 56% values, respectively Conclusions: Multilayer neural network models can assist in the dermoscopic evaluation of melanocytic nevi and melanomas regarding the differential diagnosis between them. |
id |
UNSP_2d3f6a0ce85bbac0962511f9f517f583 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/229427 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic imagesDesenvolvimento e validação de rede neural artificial para suporte ao diagnóstico de melanoma em imagens dermatoscópicasArtificial intelligenceDiagnosisMelanomaNevusIntroduction: With the advancement of digital image analysis, predictive analysis, and machine learning methods, studies have emerged regarding the use of artificial intelligence in imaging tests such as dermoscopy. Objective: Construction, testing, and implementation of an artificial neural network based on characteristics of dermoscopic images. Methods: 1949 images of melanocytic nevi and melanomas were included, both from the authors’ files and from dermoscopic image banks available on the internet, and routines and plugins were developed to extract 58 features applied to a multilayered neural network construction algorithm. Also, 52 dermatologists assessed 40 random images and compared the results compared. Results: The training and testing of the neural network obtained a correct percentage of classification of 78.5% and 79.1%, respectively, with a ROC curve covering 86.5% of the area. The sensitivity and specificity of dermatologists were 71.8% and 52%. For the same images and a cutoff point of 0.4 (40%) of the output value, the application obtained 62% and 56% values, respectively Conclusions: Multilayer neural network models can assist in the dermoscopic evaluation of melanocytic nevi and melanomas regarding the differential diagnosis between them.Hospital de Clínicas Dermatology Service Medical School São Paulo State UniversityDepartment of Infectology Medical School São Paulo State UniversityHospital de Clínicas Dermatology Service Medical School São Paulo State UniversityDepartment of Infectology Medical School São Paulo State UniversityUniversidade Estadual Paulista (UNESP)Ferreira, César Augusto Zago [UNESP]de Souza, Vinícius [UNESP]Miot, Hélio Amante [UNESP]Schmitt, Juliano Vilaverde [UNESP]2022-04-29T08:32:32Z2022-04-29T08:32:32Z2021-01-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article1-4http://dx.doi.org/10.5935/scd1984-8773.2021130015Surgical and Cosmetic Dermatology, v. 13, p. 1-4.1984-87731984-5510http://hdl.handle.net/11449/22942710.5935/scd1984-8773.20211300152-s2.0-85113853584Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengporSurgical and Cosmetic Dermatologyinfo:eu-repo/semantics/openAccess2022-04-29T08:32:32Zoai:repositorio.unesp.br:11449/229427Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462022-04-29T08:32:32Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images Desenvolvimento e validação de rede neural artificial para suporte ao diagnóstico de melanoma em imagens dermatoscópicas |
title |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images |
spellingShingle |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images Ferreira, César Augusto Zago [UNESP] Artificial intelligence Diagnosis Melanoma Nevus |
title_short |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images |
title_full |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images |
title_fullStr |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images |
title_full_unstemmed |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images |
title_sort |
Development and validation of an artificial neural network to support the diagnosis of melanoma from dermoscopic images |
author |
Ferreira, César Augusto Zago [UNESP] |
author_facet |
Ferreira, César Augusto Zago [UNESP] de Souza, Vinícius [UNESP] Miot, Hélio Amante [UNESP] Schmitt, Juliano Vilaverde [UNESP] |
author_role |
author |
author2 |
de Souza, Vinícius [UNESP] Miot, Hélio Amante [UNESP] Schmitt, Juliano Vilaverde [UNESP] |
author2_role |
author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Ferreira, César Augusto Zago [UNESP] de Souza, Vinícius [UNESP] Miot, Hélio Amante [UNESP] Schmitt, Juliano Vilaverde [UNESP] |
dc.subject.por.fl_str_mv |
Artificial intelligence Diagnosis Melanoma Nevus |
topic |
Artificial intelligence Diagnosis Melanoma Nevus |
description |
Introduction: With the advancement of digital image analysis, predictive analysis, and machine learning methods, studies have emerged regarding the use of artificial intelligence in imaging tests such as dermoscopy. Objective: Construction, testing, and implementation of an artificial neural network based on characteristics of dermoscopic images. Methods: 1949 images of melanocytic nevi and melanomas were included, both from the authors’ files and from dermoscopic image banks available on the internet, and routines and plugins were developed to extract 58 features applied to a multilayered neural network construction algorithm. Also, 52 dermatologists assessed 40 random images and compared the results compared. Results: The training and testing of the neural network obtained a correct percentage of classification of 78.5% and 79.1%, respectively, with a ROC curve covering 86.5% of the area. The sensitivity and specificity of dermatologists were 71.8% and 52%. For the same images and a cutoff point of 0.4 (40%) of the output value, the application obtained 62% and 56% values, respectively Conclusions: Multilayer neural network models can assist in the dermoscopic evaluation of melanocytic nevi and melanomas regarding the differential diagnosis between them. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-01-01 2022-04-29T08:32:32Z 2022-04-29T08:32:32Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.5935/scd1984-8773.2021130015 Surgical and Cosmetic Dermatology, v. 13, p. 1-4. 1984-8773 1984-5510 http://hdl.handle.net/11449/229427 10.5935/scd1984-8773.2021130015 2-s2.0-85113853584 |
url |
http://dx.doi.org/10.5935/scd1984-8773.2021130015 http://hdl.handle.net/11449/229427 |
identifier_str_mv |
Surgical and Cosmetic Dermatology, v. 13, p. 1-4. 1984-8773 1984-5510 10.5935/scd1984-8773.2021130015 2-s2.0-85113853584 |
dc.language.iso.fl_str_mv |
eng por |
language |
eng por |
dc.relation.none.fl_str_mv |
Surgical and Cosmetic Dermatology |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
1-4 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1799965431835918336 |