Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation

TL;DR

Privacy-preserving federated learning (FL) addresses HIPAA/GDPR constraints in medical imaging by keeping data local while sharing model updates. The paper surveys FL algorithms, privacy-preserving techniques (DP, HE, and hybrids), and uncertainty estimation methods, with emphasis on non-i.i.d. data and real-world clinical tasks. It highlights real-world FeTS studies, identifies gaps, and proposes future directions to strengthen privacy guarantees and reliable uncertainty quantification in heterogeneous medical imaging data. The findings underscore FL's potential to enable scalable, privacy-compliant, uncertainty-aware medical image analysis.

Abstract

Machine learning (ML) and Artificial Intelligence (AI) have fueled remarkable advancements, particularly in healthcare. Within medical imaging, ML models hold the promise of improving disease diagnoses, treatment planning, and post-treatment monitoring. Various computer vision tasks like image classification, object detection, and image segmentation are poised to become routine in clinical analysis. However, privacy concerns surrounding patient data hinder the assembly of large training datasets needed for developing and training accurate, robust, and generalizable models. Federated Learning (FL) emerges as a compelling solution, enabling organizations to collaborate on ML model training by sharing model training information (gradients) rather than data (e.g., medical images). FL's distributed learning framework facilitates inter-institutional collaboration while preserving patient privacy. However, FL, while robust in privacy preservation, faces several challenges. Sensitive information can still be gleaned from shared gradients that are passed on between organizations during model training. Additionally, in medical imaging, quantifying model confidence\uncertainty accurately is crucial due to the noise and artifacts present in the data. Uncertainty estimation in FL encounters unique hurdles due to data heterogeneity across organizations. This paper offers a comprehensive review of FL, privacy preservation, and uncertainty estimation, with a focus on medical imaging. Alongside a survey of current research, we identify gaps in the field and suggest future directions for FL research to enhance privacy and address noisy medical imaging data challenges.

Figures (5)

• Figure 1: An overview of FL, privacy preservation, and uncertainty estimation is presented.
• Figure 2: Summary of topics covered in this review
• Figure 3: Summary of FL topics
• Figure 4: Summary of privacy preservation methods in FL.
• Figure 5: Summary of uncertainty estimation methods in FL.