FedPerl: Semi-Supervised Peer Learning for Skin Lesion Classification

Abstract

Skin cancer is one of the most deadly cancers worldwide. Yet, it can be reduced by early detection. Recent deep-learning methods have shown a dermatologist-level performance in skin cancer classification. Yet, this success demands a large amount of centralized data, which is oftentimes not available. Federated learning has been recently introduced to train machine learning models in a privacy-preserved distributed fashion demanding annotated data at the clients, which is usually expensive and not available, especially in the medical field. To this end, we propose FedPerl, a semi-supervised federated learning method that utilizes peer learning from social sciences and ensemble averaging from committee machines to build communities and encourage its members to learn from each other such that they produce more accurate pseudo labels. We also propose the peer anonymization (PA) technique as a core component of FedPerl. PA preserves privacy and reduces the communication cost while maintaining the performance without additional complexity. We validated our method on 38,000 skin lesion images collected from 4 publicly available datasets. FedPerl achieves superior performance over the baselines and state-of-the-art SSFL by 15.8%, and 1.8% respectively.

Publication
International Conference on Medical Image Computing and Computer-Assisted Intervention
Tariq Bdair
Tariq Bdair
Researcher

Tariq Bdair is a Software Architect & Technical Leader. He possesses vast experience in software development in the industry for more than 8 years. He has developed a large number of applications using different programming languages using state-of-art technologies, software engineering methodologies, and software-development-life-cycle (SDLC). Since 2018 he is pursuing his Ph.D. at the Chair for Computer Aided Medical Procedures (CAMP), Technical University of Munich (TUM), Germany, under the supervision of Prof. Nassir Navab and Dr. Shadi Albarqouni. His research interest includes Semi-Supervised Learning, Medical Images Segmentation, and Federated Learning.

Shadi Albarqouni
Shadi Albarqouni
Professor of Computational Medical Imaging Research at University of Bonn | AI Young Investigator Group Leader at Helmholtz AI

Related