Deep Learning-Based Skin Cancer Identification

Abstract

Amongst different types of cancer, skin cancer has shown an increasing trend over the decade. Skin cancer is mainly caused due to exposure of human skin to ultraviolet rays, due to overexposure to the sun. Early diagnosis of skin cancer can help in preventing the further spread of the deadly disease. But there is a lack of clinical services and expertise, and this situation has worsened due to the ongoing pandemic. An automated system to guide the clinicians is the need of the hour. There are a lot of AI-based systems developed using datasets that are publicly available. Especially, deep learning-based solutions are available which detect the malignancy and classify it into a particular type of malignancy. CNN is a proven technology in the diagnosis of skin cancer. Various models based on transfer learning have been developed. The various systems that have been developed are still in the early stages of clinical deployment. There are still many challenges and open issues. It is proposed to investigate the work done so far and to develop a model with matching or improved performance. HAM 10000 dataset containing dermoscopic images is used for the research work. Dataset preprocessing is done to resize the images and to augment the dataset. The class imbalance has been addressed using data augmentation. Three models have been trained and tested. CNN-based, MobileNet V2 and Resnet50 based models have been built and tested. Achieved a validation accuracy of 86% for CNN, 96% for MobileNet and 89% for ResNet50.