Federated learning for medical image analysis: Methods, challenges, and future directions
Published in Advanced Engineering Informatics, 2026 IF 11.5
Abstract (excerpt). In recent years, rapid technological advances have made artificial intelligence a global trend, significantly advancing the fields of medicine and healthcare. Meanwhile, concerns about information security and medical data privacy have also increased. Although many studies have collected data from hospitals to train centralized models, data sharing between medical facilities is often restricted and protected by law. Federated learning (FL) emerges as a promising solution, enabling model training across different medical facilities without sharing raw data, thereby safeguarding patient privacy and ensuring data security. Our study reviews key works on FL in medical image analysis (MIA) from 2020 to 2025. We systematically analyze major challenges, including data heterogeneity, non-independent and identically distributed data, missing labels, communication costs, and privacy risks during model updates …
Recommended citation: Thu Thuy Le, Phuong-Nam Tran, Nhat Truong Pham, Balachandran Manavalan, Li Shen, Choong Seon Hong, Duc Ngoc Minh Dang. (2026). "Federated learning for medical image analysis: Methods, challenges, and future directions." Advanced Engineering Informatics, 76, 104976.
Download Paper