Enhancing melanoma skin cancer classification through data augmentation

Abstract

Skin cancer is a dangerous and prevalent cancer illness. It is the abnormal growth of cells in the outermost of the skin. Currently, it has received tremendous attention, highlighting an urgent need to address this worldwide public health crisis. The purpose of this study is to propose a convolutional neural network (CNN) to help dermatology physicians in the inspection, identification, and diagnosis of skin cancer. More precisely, we offer an automated method that leverages deep learning techniques to categorize binary categories of skin lesions. Our technique enlarges skin cancer by utilizing data pre-processing and augmentation to address the imbalanced class problem. Subsequently, fine-tuning is conducted on the pre-trained models visual geometry group (VGG-19) and MobileNetV2 to extract and classify the image features using transfer learning. The model is tested on the society for imaging informatics in medicine international skin imaging collaboration (SIIM-ISIC) 2020 dataset and achieved an accuracy of 95.16%, sensitivity of 90.83%, specificity of 99.2%, area under curve (AUC) of 97.57%, and precision of 99.06%. The proposed model based on MobileNetV2 outperforms the other techniques.