Future-Proofing Medical Imaging with Privacy-Preserving Federated Learning and Uncertainty Quantification: A Review

TL;DR

This review discusses how federated learning can enable privacy-preserving AI in medical imaging, emphasizing the importance of uncertainty quantification to improve model reliability amidst data heterogeneity.

Contribution

It provides a comprehensive overview of federated learning, privacy-preserving techniques, and uncertainty quantification in medical imaging, highlighting current gaps and future research directions.

Findings

Federated learning enables collaborative model training without sharing sensitive data.

Challenges include privacy risks from gradient sharing and data heterogeneity.

Future research should focus on enhancing privacy and model trustworthiness.

Abstract

Artificial Intelligence (AI) has demonstrated significant potential in automating various medical imaging tasks, which could soon become routine in clinical practice for disease diagnosis, prognosis, treatment planning, and post-treatment surveillance. However, the privacy concerns surrounding patient data present a major barrier to the widespread adoption of AI in medical imaging, as large, diverse training datasets are essential for developing accurate, generalizable, and robust Artificial intelligence models. Federated Learning (FL) offers a solution that enables organizations to train AI models collaboratively without sharing sensitive data. federated learning exchanges model training information, such as gradients, between the participating sites. Despite its promise, federated learning is still in its developmental stages and faces several challenges. Notably, sensitive information can still be inferred from the gradients shared during model training. Quantifying AI models' uncertainty is vital due to potential data distribution shifts post-deployment, which can affect model performance. Uncertainty quantification (UQ) in FL is particularly challenging due to data heterogeneity across participating sites. This review provides a comprehensive examination of FL, privacy-preserving FL (PPFL), and UQ in FL. We identify key gaps in current FL methodologies and propose future research directions to enhance data privacy and trustworthiness in medical imaging applications.