Skin Cancer Detection through Neural Network on Federated Learning
Abstract & Details
Research Area
Computer Science
Keywords
Federated Learning
Skin Cancer Detection
Melanoma Classification
Convolutional
Neural Networks (CNN)
Neural Networks
Deep Learning
Medical Image Analysis
Privacy-Preserving AI
Distributed Learning
Healthcare AI
Edge Computing
ISIC Dataset
Medical Imaging
Secure Machine Learning
Early Cancer Diagnosis
Artificial Intelligence in
Healthcare
Image Classification
Decentralized Training
Patient Data Privacy
Biomedical
Applications.
Abstract
Skin cancer, particularly melanoma, is one of the most aggressive forms of cancer, and early
detection significantly improves survival rates. Traditional machine learning methods for skin lesion
classification often require centralized data collection, raising concerns about patient privacy and
data security, especially in medical domains. This study presents a privacy-preserving approach to
skin cancer detection using Convolutional Neural Networks (CNNs) trained in a Federated Learning
(FL) environment.We propose a system in which multiple clients (e.g., hospitals or mobile devices)
collaboratively train a neural network model on local skin lesion data without sharing raw images.
Using the Flower federated learning framework and a publicly available ISIC skin cancer dataset,
we designed a CNN architecture capable of distinguishing between melanoma and benign skin
lesions. The federated training process is coordinated by a central server using the FedAvg
aggregation algorithm while ensuring that the data remain decentralized.The experimental results
demonstrate that our federated CNN model achieves a high classification performance comparable
to that of a traditionally trained centralized model. The system preserved data privacy without a
significant compromise in accuracy, achieving a detection accuracy of over 85% across multiple
simulated clients. This study showcases the real-world applicability of federated learning in
healthcare, especially in scenarios where data sharing is restricted by legal or ethical constraints.
License
This work is licensed under a Creative
Commons
Attribution-ShareAlike 4.0 International License.
Author Information
| # | Name | Institute / Affiliation |
|---|---|---|
| 1 | Kavya Shree A S | CMR University |
| 2 | Dr. Ashok Kumar T A | Director, CMR University |
| 3 | Dr. Uma Devi Ramamurthi | Assistant Professor CMR University |
How to Cite
Use the following formats to cite this article in your research.
APA Style
S, Kavya Shree A, A, Dr. Ashok Kumar T, & Ramamurthi, Dr. Uma Devi (2025). Skin Cancer Detection through Neural Network on Federated Learning. International Journal of Advance Research and Innovative Ideas In Education, 11(4), 834-840.
MLA Style
S, Kavya Shree A, et al. "Skin Cancer Detection through Neural Network on Federated Learning." International Journal of Advance Research and Innovative Ideas In Education, vol. 11, no. 4, 2025, pp. 834-840.
IEEE Style
Kavya Shree A S, Dr. Ashok Kumar T A, and Dr. Uma Devi Ramamurthi, "Skin Cancer Detection through Neural Network on Federated Learning," International Journal of Advance Research and Innovative Ideas In Education, vol. 11, no. 4, pp. 834-840, 2025.
Vancouver Style
S Kavya Shree A, A Dr. Ashok Kumar T, Ramamurthi Dr. Uma Devi. Skin Cancer Detection through Neural Network on Federated Learning. International Journal of Advance Research and Innovative Ideas In Education. 2025;11(4):834-840.
Harvard Style
S, Kavya Shree A, A, Dr. Ashok Kumar T, & Ramamurthi, Dr. Uma Devi (2025) 'Skin Cancer Detection through Neural Network on Federated Learning', International Journal of Advance Research and Innovative Ideas In Education, 11(4), pp. 834-840.
Chicago Style
S, Kavya Shree A, Dr. Ashok Kumar T A, and Dr. Uma Devi Ramamurthi. "Skin Cancer Detection through Neural Network on Federated Learning." International Journal of Advance Research and Innovative Ideas In Education 11, no. 4 (2025): 834-840.
Turabian Style
S, Kavya Shree A, Dr. Ashok Kumar T A, and Dr. Uma Devi Ramamurthi. "Skin Cancer Detection through Neural Network on Federated Learning." International Journal of Advance Research and Innovative Ideas In Education 11, no. 4 (2025): 834-840.
Related Research
CYBERSECURITY WITH AI
PDF Unavailable
DESIGN AND IMPLEMENTATION OF A SECURE IMAGE STEGANOGRAPHY SYSTEM USING LSB AND CRYPTOGRAPHY
PDF Unavailable
A NOVEL HYBRID IMAGE STEGANOGRAPHY TECHNIQUE BASED ON LSB AND CRYPTOGRAPHIC SECURITY
PDF Unavailable
BioPrint AI: An Intelligent Deep Learning and Computer Vision Based Blood Group Identification System Using Fingerprint Patterns
PDF Unavailable
AnimalAid AI: A Deep Learning Powered Early Warning System for Detecting Skin Infections and Diseases in Stray Dogs
PDF Unavailable
LiverCare AI: Intelligent Medical Imaging Platform for Liver Tumor Detection and Clinical Guidance
PDF Unavailable