Design of a Skin Cancer Detection Classification with Python GUI and Tensorflow

Skin cancer, which is generally classified into Melanoma Skin Cancer (MSC) and Non-Melanoma Skin Cancer (NMSC) namely Squamous Cell Carcinoma (SCC) and Basal Cell Carcinoma (BCC), is one of the most common types of cancer in humans. In this research, an application based on Python GUI and TensorFlow, known as "Early Detection Skin Cancer", is designed to detect and classify skin cancer. This application uses the Convolutional Neural Network (CNN) classification method to analyse and identify skin lesions that have the potential to become cancerous. CNN is then used to identify whether the lesion is a type of SCC, BCC, or MSC. The test was carried out using validation image data from skin cancer patients at Hasan Sadikin Hospital, Bandung, with a total of 26 image data samples. The test results show that this application is capable of classifying skin cancer with 100% accuracy for MEL, 55.56% for BCC, and 42.86% for SCC. However, the quality of the images of the lesions taken can affect the classification results.