Enhanced dermatology Image Quality Assessment via cross-domain training

Vista sencilla de ítem
dc.contributor.authorHernández Montilla, Ignacio
dc.contributor.authorMedela, Alfonso
dc.contributor.authorPasquali, Paola
dc.contributor.authorAguilar, Andy
dc.contributor.authorMac Carthy, Taig
dc.contributor.authorFernández, Gerardo
dc.contributor.authorMartorell, Antonio
dc.contributor.authorOnieva Caracuel, Enrique
dc.date.accessioned2026-04-20T06:46:23Z
dc.date.available2026-04-20T06:46:23Z
dc.date.issued2025-12-22
dc.date.updated2026-04-20T06:46:23Z
dc.descriptionPonencia presentada en la ICBRA 2025: The 12th International Conference on Bioinformatics Research and Applications, celebrada en Praga, entre el 19 y el 21 de septiembre de 2025es
dc.description.abstractTeledermatology has become a widely accepted communication method in daily clinical practice, enabling remote care while showing strong agreement with in-person visits. Poor image quality remains an unsolved problem in teledermatology and is a major concern to practitioners, as bad-quality images reduce the usefulness of the remote consultation process. However, research on Image Quality Assessment (IQA) in dermatology is sparse, and does not leverage the latest advances in non-dermatology IQA, such as using larger image databases with ratings from large groups of human observers. In this work, we propose cross-domain training of IQA models, combining dermatology and non-dermatology IQA datasets. For this purpose, we created a novel dermatology IQA database, Legit.Health-DIQA-Artificial, using dermatology images from several sources and having them annotated by a group of human observers. We demonstrate that cross-domain training yields optimal performance across domains and overcomes one of the biggest limitations in dermatology IQA, which is the small scale of data, and leads to models trained on a larger pool of image distortions, resulting in a better management of image quality in the teledermatology process.en
dc.description.sponsorshipThis project has been funded by the Department of Industry, Energy Transition and Sustainability of the Basque Government (BIKAINTEK Program).We also acknowledge the financial support provided by the European Union NextGenerationEU and the Centro para el Desarrollo Tecnológico y la Innovación (CDTI) through the support program PYME con Sello de Excelencia del Acelerador del EIC de Horizonte Europa (SoE-20221020), and the annotation services provided by LinkedAIen
dc.identifier.citationHernández Montilla, I., Medela, A., Pasquali, P., Aguilar, A., Mac Carthy, T., Fernández, G., Martorell, A., & Onieva, E. (2025). Enhanced dermatology Image Quality Assessment via cross-domain training. ICBRA 2025 - Proceedings of the 12th International Conference on Bioinformatics Research and Applications, 1-9. https://doi.org/10.1145/3774976.3774977
dc.identifier.doi10.1145/3774976.3774977
dc.identifier.isbn9798400715808
dc.identifier.urihttps://hdl.handle.net/20.500.14454/5692
dc.language.isoeng
dc.publisherAssociation for Computing Machinery, Inc
dc.rights© 2025 Copyright held by the owner/author(s)
dc.subject.otherComputer vision
dc.subject.otherDermatology
dc.subject.otherImage Quality Assessment
dc.subject.otherTeledermatology
dc.titleEnhanced dermatology Image Quality Assessment via cross-domain trainingen
dc.typeconference paper
dcterms.accessRightsopen access
oaire.citation.endPage9
oaire.citation.startPage1
oaire.citation.titleICBRA 2025 - Proceedings of the 12th International Conference on Bioinformatics Research and Applications
oaire.licenseConditionhttps://creativecommons.org/licenses/by/4.0/
oaire.versionVoR
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
hernandez_enhanced_2025.pdf
Tamaño:
5.35 MB
Formato:
Adobe Portable Document Format
Descargar
Colecciones
Ponencias