Convolutional neural networks are used to classify dermoscopic skin lesion images. The high accuracy of deep learning models is well documented; however, those models do not perform very well on testing (unseen data) sets due to imbalanced classes of images. To tackle this problem, over-sampling and under-sampling methods are explored in this study. Part 1 of the study focuses on the details of these sampling techniques, while Part 2 highlights the architecture of the deep learning model and its performance when using both sampling approaches. The results of Part 1 show that through the use of unsupervised learning techniques, namely, Hierarchical Clustering, Self-Organizing Maps, and K-Means, similar images are clustered, based on the skin lesions’ shape and color. Using augmentation for oversampling, 32,731 images are included for the training task in total. For undersampling, unsupervised learning techniques suggested 3 or 4 sub-groups of melanocytic nevi. Going through those clusters, the image background color also affects the way unsupervised learning techniques group similar images together.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Sampling Methods to Balance Classes in Dermoscopic Skin Lesion Images


    Weitere Titelangaben:

    Lect. Notes Electrical Eng.


    Beteiligte:
    Ahmad, Nur Syazreen (Herausgeber:in) / Mohamad-Saleh, Junita (Herausgeber:in) / Teh, Jiashen (Herausgeber:in) / Nguyen, Quynh T. (Autor:in) / Jancic-Turner, Tanja (Autor:in) / Kaur, Avneet (Autor:in) / Naguib, Raouf N. G. (Autor:in) / Sakim, Harsa Amylia Mat (Autor:in)

    Kongress:

    International Conference on Robotics, Vision, Signal Processing and Power Applications ; 2021 April 05, 2021 - April 06, 2021



    Erscheinungsdatum :

    31.03.2024


    Format / Umfang :

    7 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Domain Shifts in Dermoscopic Datasets

    Chamarthi, Sireesha / Fogelberg, Katharina / Niebling, Julia | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2022

    Freier Zugriff

    Deep Learning Ensemble Methods for Skin Lesion Analysis towards Melanoma Detection

    Ali, Redha / Hardie, Russell C. / Narayanan Narayanan, Barath et al. | IEEE | 2019


    Parameterization of Dermoscopic Findings for the Internet-based Melanoma Screening System

    Iyatomi, Hitoshi / Oka, Hiroshi / Celebi, M. Emre et al. | IEEE | 2007


    Measuring Lesion Growth from 3D Medical Images

    Thirion, J.-P. / Calmon, G. / IEEE; Computer Society | British Library Conference Proceedings | 1997


    Measuring lesion growth from 3D medical images

    Thirion, J.-P. / Calmon, G. | IEEE | 1997