- -

A deep analysis on high resolution dermoscopic image classification

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

  • Estadisticas de Uso

A deep analysis on high resolution dermoscopic image classification

Show simple item record

Files in this item

dc.contributor.author Pollastri, Federico es_ES
dc.contributor.author Parreño Lara, Mario es_ES
dc.contributor.author Maroñas-Molano, Juan es_ES
dc.contributor.author Bolelli, Federico es_ES
dc.contributor.author Paredes Palacios, Roberto es_ES
dc.contributor.author Ramos, Daniel es_ES
dc.contributor.author Grana, Costantino es_ES
dc.date.accessioned 2022-11-07T19:01:32Z
dc.date.available 2022-11-07T19:01:32Z
dc.date.issued 2021-10 es_ES
dc.identifier.issn 1751-9632 es_ES
dc.identifier.uri http://hdl.handle.net/10251/189374
dc.description.abstract [EN] Convolutional neural networks (CNNs) have been broadly employed in dermoscopic image analysis, mainly as a result of the large amount of data gathered by the International Skin Imaging Collaboration (ISIC). As in many other medical imaging domains, state-of-the-art methods take advantage of architectures developed for other tasks, frequently assuming full transferability between enormous sets of natural images (e.g. ImageNet) and dermoscopic images, which is not always the case. A comprehensive analysis on the effectiveness of state-of-the-art deep learning techniques when applied to dermoscopic image analysis is provided. To achieve this goal, the authors consider several CNNs architectures and analyse how their performance is affected by the size of the network, image resolution, data augmentation process, amount of available data, and model calibration. Moreover, taking advantage of the analysis performed, a novel ensemble method to further increase the classification accuracy is designed. The proposed solution achieved the third best result in the 2019 official ISIC challenge, with an accuracy of 0.593. es_ES
dc.description.sponsorship Juan Maroñas is supported by grant FPI-UPV, grant agreement No 825,111 DeepHealth Project, and by the Spanish National Ministry of Education through grant RTI2018-098091-B-I00. The research leading to these results has received funding from the European Union through Programa Operativo del Fondo Europeo de Desarrollo Regional (FEDER) from Comunitat Valencia (2014-2020) under project Sistemas de frabricación inteligentes para la indústria 4.0 (grant agreement IDIFEDER/2018/025). es_ES
dc.language Inglés es_ES
dc.publisher Institution of Electrical Engineers es_ES
dc.relation.ispartof IET Computer Vision es_ES
dc.rights Reconocimiento (by) es_ES
dc.title A deep analysis on high resolution dermoscopic image classification es_ES
dc.type Artículo es_ES
dc.identifier.doi 10.1049/cvi2.12048 es_ES
dc.relation.projectID info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/RTI2018-098091-B-I00/ES/APRENDIZAJE PROFUNDO EN VOZ PARA APLICACIONES FORENSES Y DE SEGURIDAD/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/UPV//825,111/ es_ES
dc.relation.projectID info:eu-repo/grantAgreement/GVA//IDIFEDER%2F2018%2F025//SISTEMAS DE FABRICACIÓN INTELIGENTES PARA LA INDUSTRIA 4.0/ es_ES
dc.rights.accessRights Abierto es_ES
dc.description.bibliographicCitation Pollastri, F.; Parreño Lara, M.; Maroñas-Molano, J.; Bolelli, F.; Paredes Palacios, R.; Ramos, D.; Grana, C. (2021). A deep analysis on high resolution dermoscopic image classification. IET Computer Vision. 15(7):514-526. https://doi.org/10.1049/cvi2.12048 es_ES
dc.description.accrualMethod S es_ES
dc.relation.publisherversion https://doi.org/10.1049/cvi2.12048 es_ES
dc.description.upvformatpinicio 514 es_ES
dc.description.upvformatpfin 526 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.description.volume 15 es_ES
dc.description.issue 7 es_ES
dc.relation.pasarela S\437734 es_ES
dc.contributor.funder Generalitat Valenciana es_ES
dc.contributor.funder Universitat Politècnica de València es_ES
dc.contributor.funder Ministerio de Ciencia, Innovación y Universidades es_ES


This item appears in the following Collection(s)

Show simple item record