As a malignant form of skin disease, skin carcinoma requires early identification and treatment. Development, implementation, and calibration of an advanced deep learning model for automated classification of skin types in multiple categories of lesions are the main objective. In the proposed approach, Convolutional Neural Network (CNN) models are utilized that efficiently extract pertinent information from the input images. The objective of this research work includes developing a CNN model with a detection accuracy of >80% for skin cancer, lowering the false negative rate to below 10%, achieving a precision of >80%, and performing data visualization. The ResNet model combined with the VGGNet achieved an accuracy of 87% for the detection.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Performance Analysis of Deep Learning Algorithms in Skin Lesion Classification


    Beteiligte:
    Dhanasekar, S. (Autor:in) / Kuraloviya, K. (Autor:in) / Rajashree, S. (Autor:in) / Renuka Devi, J.M. (Autor:in) / Malin Bruntha, P. (Autor:in) / Naveenkumar, R. (Autor:in)


    Erscheinungsdatum :

    2023-11-22


    Format / Umfang :

    783886 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Learning Ensemble Methods for Skin Lesion Analysis towards Melanoma Detection

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


    Multiclass skin lesion classification using image augmentation technique and transfer learning models

    Swetha R, Naga / Shrivastava, Vimal K. / Parvathi, K. | Emerald Group Publishing | 2024


    Photometric space object classification via deep learning algorithms

    Liu, Tong / Schreiber, K. Ulrich | Elsevier | 2021



    Real Time Bearing Defect Classification Using Time Domain Analysis and Deep Learning Algorithms

    Gorantiwar, Anish / Moslehi, Bijan / Zahiri, Feraidoon et al. | SAE Technical Papers | 2023