Privacy‐Preserving Federated Learning in Medical Imaging: A Systematic Review

ABSTRACT Integrating artificial intelligence (AI) into medical imaging is often hindered by privacy regulations, fragmented data sources, and institutional reluctance to share patient information. Federated learning (FL) has emerged as a promising solution, enabling collaborative model training without the need to centralize data. This review critically examines the role of FL in medical imaging, with a particular focus on privacy‐preserving approaches. We analyze developments in FL architectures, privacy‐enhancing techniques, and challenges specific to medical imaging, such as data heterogeneity, modality‐specific constraints, optimization strategies to reduce communication overhead, and fairness issues related to modality drift. The review also provides insights into various privacy‐preserving techniques and discusses the impact of global health regulations, including the Health Insurance Portability and Accountability Act (HIPAA), the General Data Protection Regulation (GDPR), and India's Digital Personal Data Protection (DPDP) Act. Overall, this review aims to guide the development of secure, privacy‐aware, and practical FL systems tailored for real‐world medical imaging applications. This article is categorized under: Technologies > Artificial Intelligence Technologies > Machine Learning Commercial, Legal, and Ethical Issues > Security and Privacy