Skin Cancer Diagnosis Using Image Processing and Xception-CNN Model

Skin cancer is recognized as one of the most lethal forms of cancer, often resulting in death if not detected early. Its aggressive tendency to spread to other parts of the body makes treatment in later stages particularly difficult, emphasizing the crucial need for early detection. As the incidence of skin cancer continues to rise, along with its associated high mortality rates and treatment expenses, there is an urgent demand for more effective early detection methods. Leveraging deep learning algorithms through a model-driven architecture has emerged as a promising solution for improving skin cancer diagnosis. In this work, present the development and implementation of a deep learning model designed to accurately classify images of skin lesions. The proposed approach uses the Xception model, an advanced convolutional neural network (CNN) architecture. Through training, the Xception model identifies patterns and features in skin lesion images that indicate whether the condition is benign or malignant. Proposed model achieved an accuracy rate of 86% in the classification task.