Skin Disease Classification Using Deep Learning Techniques

Department of Computer Science and Engineering, B V Raju Institute of Technology, Narsapur, Medak, India

Abstract

Skin conditions are becoming increasingly prevalent, and many of these ailments carry concealed risks that can elevate the likelihood of developing skin cancer. Given the low quality of images associated with such conditions, diagnosing these diseases traditionally required advanced medical expertise and specialized equipment. Furthermore, manually detecting skin disorders is often subjective, time-consuming, and demands considerable human effort. This highlights the need for an automated, computer-assisted system capable of diagnosing skin conditions without human intervention. To achieve this, Deep Learning techniques, particularly Convolutional Neural Networks (CNNs), will be employed to classify skin diseases using dermoscopic images. The dataset for this study comes from the MNIST HAM10000 collection, which contains 10,015 images and was made available by the International Skin Imaging Collaboration (ISIC). The data is divided into seven categories, including skin cancer. For image classification, a pre-trained CNN model will be utilized. One key challenge is the imbalanced nature of the dataset. To mitigate this, data augmentation techniques were applied, helping to reduce class imbalance and ensure that classification accuracy across categories was not dominated by the majority class.