phat 24(1):

Research Article

Deep Learning Framework for Identification of Skin Lesions

Download137 downloads
  • @ARTICLE{10.4108/eetpht.9.3900,
        author={Nonita Sharma and Monika Mangla and M Mohamed Iqbal and Sachi Nandan Mohanty},
        title={Deep Learning Framework for Identification of Skin Lesions},
        journal={EAI Endorsed Transactions on Pervasive Health and Technology},
        volume={9},
        number={1},
        publisher={EAI},
        journal_a={PHAT},
        year={2023},
        month={9},
        keywords={Convolutional Neural Network, Grey Level Co-occurrence Matrix, Rectilinear Unit, Stochastic Gradient Descent},
        doi={10.4108/eetpht.9.3900}
    }
    
  • Nonita Sharma
    Monika Mangla
    M Mohamed Iqbal
    Sachi Nandan Mohanty
    Year: 2023
    Deep Learning Framework for Identification of Skin Lesions
    PHAT
    EAI
    DOI: 10.4108/eetpht.9.3900
Nonita Sharma1,*, Monika Mangla2, M Mohamed Iqbal3, Sachi Nandan Mohanty4
  • 1: Indira Gandhi Delhi Technical University for Women
  • 2: Dwarkadas J. Sanghvi College of Engineering
  • 3: Vellore Institute of Technology University
  • 4: Vardhaman College of Engineering
*Contact email: nonitasharma@igdtuw.ac.in

Abstract

Skin ailments don't just affect the physical appearance of an individual but also lead to psychological issues. Vitiligo and discoloration patches are such conditions that can negatively impact one's self-assurance. Here, authors have designed 14 distinct models to classify skin lesions using the HAM10000 dataset which is sorted into 7 classes including Actinic Keratosis, Melanocytic nevi, Actinic keratoses, Melanoma, Benign keratosis-like lesions, Basal cell carcinoma, and Vascular lesions. Further, authors compared their model against other state-of-the-art models, and additional-ly employed various pre-trained models like Resnet50, InceptionV3, MobileNetV2, Densenet201, VGG16, VGG19, InceptionResnetv2, Xception, EfficientNetB0, EfficientNetB1, EfficientNetB2, EfficientNetB3, Effi-cientNetB4, EfficientNetB5 that were trained on image net datasets. Their primary aim was to develop a framework that can be implemented in real-world applications using Efficient Nets. Experimental evaluations have shown that their proposed models have outperformed traditional pre-trained models like ResNets and VGG16 in terms of accuracy, precision, re-call, and validation loss, despite being lightweight. Interestingly, this im-provement was achieved without any data augmentation techniques. The authors achieved accuracy above 90% for all the EfficientNet models (B0-B5), which was far better than the existing pre-trained models, thus establishing the supremacy of proposed model.