Improving Performance of Federated Learning based Medical Image Analysis in Non-IID Settings using Image Augmentation

TL;DR

This paper proposes a novel image augmentation method to balance data distribution in federated learning, significantly improving model accuracy for medical image analysis under non-IID data conditions while preserving privacy.

Contribution

It introduces a dynamic image augmentation technique that stabilizes federated learning training and enhances accuracy in non-IID data scenarios, especially for medical imaging.

Findings

Test accuracy improved from 83.22% to 89.43%.

Method stabilizes training in highly non-IID settings.

Applicable to healthcare and other privacy-sensitive fields.

Abstract

Federated Learning (FL) is a suitable solution for making use of sensitive data belonging to patients, people, companies, or industries that are obligatory to work under rigid privacy constraints. FL mainly or partially supports data privacy and security issues and provides an alternative to model problems facilitating multiple edge devices or organizations to contribute a training of a global model using a number of local data without having them. Non-IID data of FL caused from its distributed nature presents a significant performance degradation and stabilization skews. This paper introduces a novel method dynamically balancing the data distributions of clients by augmenting images to address the non-IID data problem of FL. The introduced method remarkably stabilizes the model training and improves the model's test accuracy from 83.22% to 89.43% for multi-chest diseases detection of chest X-ray images in highly non-IID FL setting. The results of IID, non-IID and non-IID with proposed method federated trainings demonstrated that the proposed method might help to encourage organizations or researchers in developing better systems to get values from data with respect to data privacy not only for healthcare but also other fields.