JavaScript is disabled for your browser. Some features of this site may not work without it.

    Listar

    Todo RIUMAComunidades & ColeccionesPor fecha de publicaciónAutoresTítulosMateriasTipo de publicaciónCentrosEsta colecciónPor fecha de publicaciónAutoresTítulosMateriasTipo de publicaciónCentros

    Mi cuenta

    AccederRegistro

    Estadísticas

    Ver Estadísticas de uso

    DE INTERÉS

    Datos de investigaciónReglamento de ciencia abierta de la UMAPolítica de RIUMAPolitica de datos de investigación en RIUMASHERPA/RoMEODulcinea
    Preguntas frecuentesManual de usoDerechos de autorContacto/Sugerencias
    Ver ítem 
    •   RIUMA Principal
    • Investigación
    • Lenguajes y Ciencias de la Computación - (LCC)
    • LCC - Artículos
    • Ver ítem
    •   RIUMA Principal
    • Investigación
    • Lenguajes y Ciencias de la Computación - (LCC)
    • LCC - Artículos
    • Ver ítem

    Skin lesion classification by ensembles of deep convolutional networks and regularly spaced shifting

    • Autor
      Thurnhofer Hemsi, Karl; López-Rubio, EzequielAutoridad Universidad de Málaga; Domínguez, Enrique; Elizondo, David A.
    • Fecha
      2021
    • Palabras clave
      Piel - Enfermedades
    • Resumen
      Skin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions. Melanoma is one of the best-known types of skin lesions due to the vast majority of skin cancer deaths. In this work, we propose an ensemble of improved convolutional neural networks combined with a test-time regularly spaced shifting technique for skin lesion classification. The shifting technique builds several versions of the test input image, which are shifted by displacement vectors that lie on a regular lattice in the plane of possible shifts. These shifted versions of the test image are subsequently passed on to each of the classifiers of an ensemble. Finally, all the outputs from the classifiers are combined to yield the final result. Experiment results show a significant improvement on the well-known HAM10000 dataset in terms of accuracy and Fscore. In particular, it is demonstrated that our combination of ensembles with test-time regularly spaced shifting yields better performance than any of the two methods when applied alone.
    • URI
      https://hdl.handle.net/10630/22741
    • DOI
      https://dx.doi.org/10.1109/ACCESS.2021.3103410
    • Compartir
      RefworksMendeley
    Mostrar el registro completo del ítem
    Ficheros
    IEEEAccessKarl.pdf (4.997Mb)
    Colecciones
    • LCC - Artículos

    Estadísticas

    Ver Estadísticas de uso
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
     

     

    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA
    REPOSITORIO INSTITUCIONAL UNIVERSIDAD DE MÁLAGA