What question did this study set out to answer?

The aim is to improve skin cancer diagnosis using a privacy-preserving approach with federated learning and deep learning.

March 2, 2026Scientific Reports1 citationsOpen Access

Explainable and secure federated learning for privacy-enhancing skin cancer classification using a lightweight multi-scale CNN

ASAbdullah Siddique Mohammad Sayeed SBShaikh Afnan Birahim MUMd. Safik Ullah

Key Points

The aim is to improve skin cancer diagnosis using a privacy-preserving approach with federated learning and deep learning.
Proposed a Lightweight Multi-Scale CNN for skin cancer classification
Implemented Encrypted FedAvg-Based Explainable Federated Learning
Integrated Homomorphic Encryption for privacy
Utilized SHAP and GradCAM for model interpretability
Evaluated on HAM10000 and other benchmark datasets.
Achieved 98.62% accuracy on the HAM10000 dataset
Maintained a 0.3% accuracy drop with encryption
Demonstrated generalization of 96.22% accuracy on ISIC 2019
Achieved 89.84% accuracy on PAD-UFES-20 dataset

Abstract

Skin diseases pose a major public health challenge, with skin cancer being the most prevalent malignancy. Early detection is critical for improving patient outcomes, yet traditional diagnostic methods rely on expert evaluation, which is limited by clinician variability, image quality, and accessibility constraints. Deep learning (DL)-based models offer automated diagnostic capabilities but require large-scale centralized data aggregation, which conflicts with privacy regulations and poses security risks. Federated Learning (FL) enables collaborative training across multiple hospitals without sharing raw patient data, yet it introduces communication overhead, security vulnerabilities, and interpretability challenges, hindering its real-world deployment. To address these issues, an Encrypted FedAvg-Based Explainable Federated Learning approach has been proposed utilizing a Lightweight Deep Learning Multi-Scale Convolutional Neural Network (LWMS-CNN) for efficient, privacy-enhanced, and interpretable skin cancer diagnosis. The proposed method integrates Homomorphic Encryption (HE) in a simulated federated system for secure model aggregation, privacy enhancements while maintaining strong diagnostic performance. Additionally, SHapley Additive exPlanations (SHAP) and GradCAM enhance interpretability, enabling clinicians to understand AI-driven predictions. Experimental evaluations on the HAM10000 dataset demonstrate that the proposed LWMS-CNN-FL model achieves 98.62% accuracy, with only a 0.3% tradeoff when encryption is applied, ensuring robust security without compromising diagnostic reliability. The model’s generalization ability is further confirmed through assessments on additional benchmark datasets, including ISIC 2019, where it achieved an accuracy of 96.22%, and PAD-UFES-20, where it reached 89.84%. By integrating lightweight deep learning, federated learning, encryption, and explainability, this study presents a scalable, privacy-enhanced, computationally efficient, and clinically interpretable AI-driven solution for secure and accurate early skin cancer detection in world healthcare applications.

Ask AI

Helpful

Bookmark

View Full Paper