Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis

An estimated 60,000 people die annually from skin cancer, predominantly melanoma. The diagnosis of skin lesions primarily relies on visual inspection, but around half of lesions pose diagnostic challenges, often necessitating a biopsy. Non-invasive detection methods like Computer-Aided Diagnosis (CA...

Descripción completa

Detalles Bibliográficos
Autores: Rey Barroso, Laura|||0000-0002-6305-0609, Vilaseca Ricart, Meritxell|||0000-0001-8166-1617, Royo Royo, Santiago|||0000-0003-0136-8301, Díaz Douton, Fernando|||0000-0003-3699-015X, Lihacova, Ilze, Bondarenko, Andrey, Burgos Fernández, Francisco Javier|||0000-0002-3749-6850
Tipo de recurso: artículo
Fecha de publicación:2025
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/424829
Acceso en línea:https://hdl.handle.net/2117/424829
https://dx.doi.org/10.3390/diagnostics15030355
Access Level:acceso abierto
Palabra clave:Skin cancer
Multispectral imaging
Deep learning
Non-invasive diagnosis
Melanoma
Convolutional neural network
Àrees temàtiques de la UPC::Ciències de la salut::Medicina
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
id ES_bdd966b83a73e67d0bc066cb962e4d4e
oai_identifier_str oai:upcommons.upc.edu:2117/424829
network_acronym_str ES
network_name_str España
repository_id_str
spelling Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosisRey Barroso, Laura|||0000-0002-6305-0609Vilaseca Ricart, Meritxell|||0000-0001-8166-1617Royo Royo, Santiago|||0000-0003-0136-8301Díaz Douton, Fernando|||0000-0003-3699-015XLihacova, IlzeBondarenko, AndreyBurgos Fernández, Francisco Javier|||0000-0002-3749-6850Skin cancerMultispectral imagingDeep learningNon-invasive diagnosisMelanomaConvolutional neural networkÀrees temàtiques de la UPC::Ciències de la salut::MedicinaÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeoAn estimated 60,000 people die annually from skin cancer, predominantly melanoma. The diagnosis of skin lesions primarily relies on visual inspection, but around half of lesions pose diagnostic challenges, often necessitating a biopsy. Non-invasive detection methods like Computer-Aided Diagnosis (CAD) using Deep Learning (DL) are becoming more prominent. This study focuses on the use of multispectral (MS) imaging to improve skin lesion classification of DL models. We trained two convolutional neural networks (CNNs)—a simple CNN with six two-dimensional (2D) convolutional layers and a custom VGG-16 model with three-dimensional (3D) convolutional layers—using a dataset of MS images. The dataset included spectral cubes from 327 nevi, 112 melanomas, and 70 basal cell carcinomas (BCCs). We compared the performance of the CNNs trained with full spectral cubes versus using only three spectral bands closest to RGB wavelengths. The custom VGG-16 model achieved a classification accuracy of 71% with full spectral cubes and 45% with RGB-simulated images. The simple CNN achieved an accuracy of 83% with full spectral cubes and 36% with RGB-simulated images, demonstrating the added value of spectral information. These results confirm that MS imaging provides complementary information beyond traditional RGB images, contributing to improved classification performance. Although the dataset size remains a limitation, the findings indicate that MS imaging has significant potential for enhancing skin lesion diagnosis, paving the way for further advancements as larger datasets become available.Peer Reviewed20252025-02-0120252025-02-21journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/424829https://dx.doi.org/10.3390/diagnostics15030355reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengAgencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2023-147541OB-I00 NUEVOS ENFOQUES PARA MEDICIONES ESPECTROSCOPICAS Y MORFOLOGICAS PRECISAS EN APLICACIONES BIOLOGICASopen accesshttp://purl.org/coar/access_right/c_abf2Attribution 4.0 Internationalhttp://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/4248292026-05-27T15:37:01Z
dc.title.none.fl_str_mv Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
title Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
spellingShingle Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
Rey Barroso, Laura|||0000-0002-6305-0609
Skin cancer
Multispectral imaging
Deep learning
Non-invasive diagnosis
Melanoma
Convolutional neural network
Àrees temàtiques de la UPC::Ciències de la salut::Medicina
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
title_short Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
title_full Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
title_fullStr Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
title_full_unstemmed Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
title_sort Training state-of-the-art deep learning algorithms with visible and extended near-infrared multispectral images of skin lesions for the improvement of skin cancer diagnosis
dc.creator.none.fl_str_mv Rey Barroso, Laura|||0000-0002-6305-0609
Vilaseca Ricart, Meritxell|||0000-0001-8166-1617
Royo Royo, Santiago|||0000-0003-0136-8301
Díaz Douton, Fernando|||0000-0003-3699-015X
Lihacova, Ilze
Bondarenko, Andrey
Burgos Fernández, Francisco Javier|||0000-0002-3749-6850
author Rey Barroso, Laura|||0000-0002-6305-0609
author_facet Rey Barroso, Laura|||0000-0002-6305-0609
Vilaseca Ricart, Meritxell|||0000-0001-8166-1617
Royo Royo, Santiago|||0000-0003-0136-8301
Díaz Douton, Fernando|||0000-0003-3699-015X
Lihacova, Ilze
Bondarenko, Andrey
Burgos Fernández, Francisco Javier|||0000-0002-3749-6850
author_role author
author2 Vilaseca Ricart, Meritxell|||0000-0001-8166-1617
Royo Royo, Santiago|||0000-0003-0136-8301
Díaz Douton, Fernando|||0000-0003-3699-015X
Lihacova, Ilze
Bondarenko, Andrey
Burgos Fernández, Francisco Javier|||0000-0002-3749-6850
author2_role author
author
author
author
author
author
dc.subject.none.fl_str_mv Skin cancer
Multispectral imaging
Deep learning
Non-invasive diagnosis
Melanoma
Convolutional neural network
Àrees temàtiques de la UPC::Ciències de la salut::Medicina
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
topic Skin cancer
Multispectral imaging
Deep learning
Non-invasive diagnosis
Melanoma
Convolutional neural network
Àrees temàtiques de la UPC::Ciències de la salut::Medicina
Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
description An estimated 60,000 people die annually from skin cancer, predominantly melanoma. The diagnosis of skin lesions primarily relies on visual inspection, but around half of lesions pose diagnostic challenges, often necessitating a biopsy. Non-invasive detection methods like Computer-Aided Diagnosis (CAD) using Deep Learning (DL) are becoming more prominent. This study focuses on the use of multispectral (MS) imaging to improve skin lesion classification of DL models. We trained two convolutional neural networks (CNNs)—a simple CNN with six two-dimensional (2D) convolutional layers and a custom VGG-16 model with three-dimensional (3D) convolutional layers—using a dataset of MS images. The dataset included spectral cubes from 327 nevi, 112 melanomas, and 70 basal cell carcinomas (BCCs). We compared the performance of the CNNs trained with full spectral cubes versus using only three spectral bands closest to RGB wavelengths. The custom VGG-16 model achieved a classification accuracy of 71% with full spectral cubes and 45% with RGB-simulated images. The simple CNN achieved an accuracy of 83% with full spectral cubes and 36% with RGB-simulated images, demonstrating the added value of spectral information. These results confirm that MS imaging provides complementary information beyond traditional RGB images, contributing to improved classification performance. Although the dataset size remains a limitation, the findings indicate that MS imaging has significant potential for enhancing skin lesion diagnosis, paving the way for further advancements as larger datasets become available.
publishDate 2025
dc.date.none.fl_str_mv 2025
2025-02-01
2025
2025-02-21
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/424829
https://dx.doi.org/10.3390/diagnostics15030355
url https://hdl.handle.net/2117/424829
https://dx.doi.org/10.3390/diagnostics15030355
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 PID2023-147541OB-I00 NUEVOS ENFOQUES PARA MEDICIONES ESPECTROSCOPICAS Y MORFOLOGICAS PRECISAS EN APLICACIONES BIOLOGICAS
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution 4.0 International
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869418235509604352
score 15.811543

Similares en LA Referencia