Diagnosis of skin cancer using VGG16 and VGG19 based transfer learning models

Today, skin cancer is considered one of the most dangerous and common cancers in the world, demanding special attention. Skin cancer can be developed in different types, including melanoma, actinic keratosis, basal cell carcinoma, squamous cell carcinoma, and Merkel cell carcinoma. Among them, melanoma is considered to be more unpredictable. However, melanoma cancer can be diagnosed at early stages, which increases the possibility of successful treatment. Automatic classification of skin lesions is a challenging task due to diverse forms and grades of the disease, which demands the implementation of novel methods. Deep convolutional neural networks (CNNs) have shown an excellent potential for data and image classification. In this article, we examine the problem of skin lesion classification using CNN techniques. Remarkably, we present that prominent classification accuracy of lesion detection can be achieved through proper design and application of transfer learning framework on pre-trained neural networks. This can be accomplished without the need for data augmentation techniques; specifically, we merged the core architectures of VGG16 and VGG19, which were pretrained on a generic dataset, into a modified AlexNet network. We then fine-tuned this combined architecture using a subject-specific dataset consisting of dermatology images. The convolutional neural network was trained using 2541 images. In particular, dropout was employed to mitigate overfitting. Finally, we assessed the model’s performance by applying the K-fold cross validation method. The proposed model improved classification accuracy with an increase of 3% (from 94.2% to 98.18%) compared to other methods.