Skin Cancer Detection Using Machine Learning
Usman Ibrahim Musa1, Apash Roy2, Musa Ibrahim Musa3, Umar Muhammad Babani4, Aminu Ibrahim Musa5
1Usman Ibrahim Musa, Faculty of Science and Technology, Islamic Science University of Malaysia, Nilai, Malaysia.
2Apash Roy, Professor, School of Computer Applications, Lovely Professional University, Punjab, India.
3Musa Ibrahim Musa, Faculty of Computer Science and IT, Bayero University Kano, Kano, Nigeria.
4Umar Muhammad Babani, Department of Computer Science & Engineering, Integral University, Lucknow (U.P), India.
5Aminu Ibrahim Musa, Head of the Department of Information Technology, ESGT Benin University, Cotonou, Benin Republic.
Manuscript received on 16 June 2024 | Revised Manuscript received on 20 October 2024 | Manuscript Accepted on 15 November 2024 | Manuscript published on 30 November 2024 | PP: 10-16 | Volume-5 Issue-1, November 2024 | Retrieval Number: 100.1/ijpmh.C72640911322 | DOI: 10.54105/ijpmh.C7264.05011124
Open Access | Ethics and Policies | Cite | Zenodo | OJS | Indexing and Abstracting
© The Authors. Published by Lattice Science Publication (LSP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Skin-related issues often serve as indicators of underlying health problems in other parts of the human body, adversely affecting an individual’s overall fitness and well-being. However, such issues are frequently ignored, as they are perceived to be either painless or have minimal to no impact on daily life. To address this challenge, this system was developed with the aim of early detection of skin cancer. The system enables users to upload images or videos of the affected area in real-time, utilising a skin cancer detector to identify existing conditions, determine the type of cancer (if present), and provide instant feedback. The system is precisely configured to deliver highperformance results, offering real-time recommendations for medications or treatments based on its findings. By reducing the stress and inconvenience associated with dermatological consultations, this system empowers individuals to accurately identify skin-related issues and make informed decisions about seeking further medical attention from a qualified dermatologist. Powered by image processing using OpenCV, a convolutional neural network (CNN), and machine learning techniques, the system excels in accurately recognising various skin conditions. It can detect conditions such as nevus, vascular lesions, seborrheic keratosis, basal cell carcinoma, melanoma, pigmented benign keratosis, squamous cell carcinoma, dermatofibroma, and actinic keratosis, while also recommending appropriate remedial health solutions.
Keywords: Skin Cancer, Machine Learning, CNN
Scope of the Article: Health Care Management