Early Identification of Skin Cancer Lesions with CNN Model

Abstract

Skin cancer is considered to be the most common and dangerous type of cancer. Information technology techniques are required to identify the possibility of skin cancer. Therefore, there is a need for an early and accurate skin cancer detection by employing an efficient deep learning technique. This research work proposes automatic diagnosis of skin cancer by employing Convolution Neural Network (CNN) model. The purposed model is able to classify the image as benign and malignant skin lesions and obtained an accuracy of 86.74%. Moreover, a notable characteristic of this research lies in its utilization of the CNN model integrated within a Graphical User Interface (GUI) application developed using the Tkinter toolkit. The GUI application are designed to be user-friendly, allowed user to experience enhanced and simplified interaction. The work implemented is expected to be helpful model in the early detection of skin cancer in the field of medicine and healthcare.