APSIPA Transactions on Signal and Information Processing > Vol 13 > Issue 1

When Federated Learning Meets Medical Image Analysis: A Systematic Review with Challenges and Solutions

Tian Yang, University of British Columbia, Canada, tianyang@ece.ubc.ca , Xinhui Yu, University of British Columbia, Canada, Martin J. McKeown, University of British Columbia, Canada, Z. Jane Wang, University of British Columbia, Canada
 
Suggested Citation
Tian Yang, Xinhui Yu, Martin J. McKeown and Z. Jane Wang (2024), "When Federated Learning Meets Medical Image Analysis: A Systematic Review with Challenges and Solutions", APSIPA Transactions on Signal and Information Processing: Vol. 13: No. 1, e38. http://dx.doi.org/10.1561/116.20240048

Publication Date: 17 Dec 2024
© 2024 T. Yang, X. Yu, M. J. McKeown and Z. J. Wang
 
Subjects
Classification and prediction,  Deep learning,  Artificial intelligence methods in security and privacy,  Privacy-preserving systems
 
Keywords
Federated learningdeep learningmedical image analysis
 

Share

Open Access

This is published under the terms of CC BY-NC.

Downloaded: 59 times

In this article:
Introduction 
Background 
Challenges and Solutions 
Future Directions 
Conclusion 
References 

Abstract

Deep learning has been a powerful tool for medical image analysis, but large amount of high-quality labeled datasets are generally required to train deep learning models with satisfactory performance and generalization capability. In medical applications, collecting such large-scale datasets involves specific challenges: data annotation is time-consuming and expert-requisite, and privacy restrictions make it impractical for different institutions to share their own data to construct single large datasets. Federated learning (FL) is an effective method for addressing such concerns since it allows multiple institutions to collaboratively train deep learning models, without sharing individual data samples directly, in line with privacy protection requirements. However, there are numerous challenges when applying FL in medical image analysis, including data heterogeneity and low label quality, that may impede FL from being implemented effectively. This paper conducts a systematic literature review of the challenges and solutions when applying FL in medical image analysis. We present a novel taxonomy of FL-specific challenges in medical image analysis research and summarize representative solutions for these challenges. We anticipate this review will be proved helpful for researchers to have better knowledge of challenges and existing solutions in related fields, and provide inspiration for developing more advanced solutions in the future.

DOI:10.1561/116.20240048