FedDermaSeg: Federated Learning for Dermatological Image Segmentation

2026-10-06

AI Summary

This study addresses the privacy leakage and computational bottlenecks inherent in centralized training for skin lesion segmentation by proposing a distributed collaborative segmentation framework based on federated learning. By simulating a multi-center environment on the ISIC and PH2 datasets and integrating deep learning-based segmentation networks, this work presents the first validation of federated learning for this task, overcoming the limitations of traditional centralized data aggregation. Experimental results demonstrate that the proposed model achieves performance comparable to centralized training while significantly outperforming local models. These findings confirm that high-precision collaborative diagnosis can be realized without sharing raw images, thereby establishing a novel paradigm for privacy-preserving and efficient collaboration in medical artificial intelligence.

Abstract

Skin cancer is a major global health concern, and early detection and accurate lesion delineation are important for effective diagnosis and treatment planning. Automated skin lesion analysis can assist dermatologists, with lesion segmentation serving as a fundamental step in computer-aided diagnostic systems. Conventional deep learning-based segmentation models typically rely on centralized training, where images and their corresponding segmentation masks are collected on a central server. Such data aggregation raises privacy concerns in medical applications and requires substantial centralized computational resources. To address these limitations, we investigate the feasibility of federated learning for privacy-preserving skin lesion segmentation. The training and validation sets of the ISIC 2018 Skin Lesion Segmentation Challenge dataset are used to simulate a distributed learning environment and develop a federated segmentation model. The resulting model is evaluated on the ISIC 2018 test set and the PH2 dataset to assess its performance and generalizability. Experimental results demonstrate that the federated model achieves performance comparable to centralized training while consistently improving upon the locally trained models. These findings demonstrate the potential of federated learning for collaborative skin lesion segmentation without requiring centralized aggregation of medical images.

Problem

• skin lesion segmentation
• federated learning
• privacy preservation
• decentralized training
• dermatological imaging

Innovation

• Federated Learning
• Skin Lesion Segmentation
• Privacy-Preserving
• Distributed Learning
• Medical Image Analysis