Automated Skin Disease Detection Using Deep Learning Algorithms

Skin diseases present a significant challenge in medical diagnosis due to their varied presentation and overlapping symptoms. Deep learning methods, particularly Convolutional Neural Networks (CNN) have emerged as a particular tool for accurately classifying such diseases. The study focuses on classifying nine different diseases such as Actinic Keratosis, Basal Cell Carcinoma, Dermatofibroma, Melanoma, Nevus, Pigmented Benign Keratosis, Seborrheic Keratosis, Squamous Cell Carcinoma and Vascular Lesion that exhibit comparable physical appearances. The study begins with the collection of diverse datasets encompassing images of these diseases. Preprocessing techniques were then applied to prepare the dataset for training and testing. LeNet architecture was used to classify these nine diseases and an accuracy of 95% is obtained. In this study a web application was developed to identify these diseases. This is vital for earning the confidence of healthcare professionals, as it provides them with a reliable tool for diagnosing skin conditions accurately.