DermaKNet: Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for Skin Lesion Diagnosis

e-Archivo Repository

Show simple item record González Díaz, Iván 2022-09-06T08:27:23Z 2022-09-06T08:27:23Z 2019-03-01
dc.identifier.bibliographicCitation IEEE Journal of Biomedical and Health Informatics, (2019), 23(2), pp.: 547-559.
dc.identifier.issn 2168-2194
dc.description.abstract Traditional approaches to automatic diagnosis of skin lesions consisted of classifiers working on sets of hand-crafted features, some of which modeled lesion aspects of special importance for dermatologists. Recently, the broad adoption of convolutional neural networks (CNNs) in most computer vision tasks has brought about a great leap forward in terms of performance. Nevertheless, with this performance leap, the CNN-based computer-aided diagnosis (CAD) systems have also brought a notable reduction of the useful insights provided by hand-crafted features. This paper presents DermaKNet, a CAD system based on CNNs that incorporates specific subsystems modeling properties of skin lesions that are of special interest to dermatologists aiming to improve the interpretability of its diagnosis. Our results prove that the incorporation of these subsystems not only improves the performance, but also enhances the diagnosis by providing more interpretable outputs.
dc.description.sponsorship This work was supported in part by the National Grant TEC2014-53390-P and National Grant TEC2014-61729-EXP of the Spanish Ministry of Economy and Competitiveness, and in part by NVIDIA Corporation with the donation of the TITAN X GPU
dc.format.extent 8
dc.language.iso eng
dc.publisher IEEE
dc.rights © 2018 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
dc.subject.other Skin lesion analysis
dc.subject.other Cancer
dc.subject.other Melanoma
dc.subject.other Convolutional
dc.subject.other Neural Networks
dc.subject.other Dermoscopy
dc.subject.other CAD
dc.subject.other CNN-based Computer Aided Diagnosis
dc.title DermaKNet: Incorporating the Knowledge of Dermatologists to Convolutional Neural Networks for Skin Lesion Diagnosis
dc.type article
dc.description.status Publicado
dc.subject.eciencia Biología y Biomedicina
dc.subject.eciencia Informática
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. TEC2014-53390-P
dc.relation.projectID Gobierno de España. TEC2014-61729-EXP
dc.type.version acceptedVersion
dc.identifier.publicationfirstpage 547
dc.identifier.publicationissue 2
dc.identifier.publicationlastpage 559
dc.identifier.publicationtitle IEEE Journal of Biomedical and Health Informatics
dc.identifier.publicationvolume 23
dc.identifier.uxxi AR/0000023385
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.affiliation.dpto UC3M. Departamento de Teoría de la Señal y Comunicaciones
dc.affiliation.grupoinv UC3M. Grupo de Investigación: Procesado Multimedia
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)

This item appears in the following Collection(s)

Show simple item record