Skin Cancer Detection Using Convolutional Neural Networks
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Skin cancer is one of the most frequent types of cancer, and early detection is the only way to ensure successful treatment. However, in rural areas, the traditional method of detection, which is highly dependent on experienced dermatologists, may not be possible. This paper presents a comprehensive web-based skin cancer diagnosis system using Convolutional Neural Networks (CNNs) for the automatic classification of dermatoscopic images into Cancerous or Non-Cancerous. The proposed system consists of a React-based frontend, a Flask REST API backend, and a deep learning model trained on the HAM10000 dataset. The CNN model is designed to process 224x224 RGB images and provide real-time predictions with confidence levels. Although it ensures efficient performance, our model is able to provide 88.08% accuracy, which supports fast and accurate real-time predictions. The system also provides a userfriendly interface with color-coded indicators and progress bars. With a prediction time of 200ms, the experimental results demonstrate the effective classification ability of the system. This work fills the gap between machine learning research and applications, offering an easy-to-use tool for initial skin cancer diagnosis.
Fields of Study & Subjects
Cutaneous Melanoma Detection and Management
AI in cancer detection
Artificial Intelligence in Healthcare
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 30 March 2026
- Language
- EN