CXR-FL: Deep Learning-Based Chest X-ray Image Analysis Using Federated Learning

Abstract

Federated learning enables building a shared model from multicentre data while storing the training data locally for privacy. In this paper, we present an evaluation (called CXR-FL) of deep learningbased models for chest X-ray image analysis using the federated learning method. We examine the impact of federated learning parameters on the performance of central models. Additionally, we show that classification models perform worse if trained on a region of interest reduced to segmentation of the lung compared to the full image. However, focusing training of the classification model on the lung area may result in improved pathology interpretability during inference. We also find that federated learning helps maintain model generalizability. The pre-trained weights and code are publicly available at (https://github.com/SanoScience/ CXR-FL).

Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions

“…The authors in [160] introduced a collaborative FL framework that allows multiple medical institutions to use DL to screen COVID-19 from chest X-ray images without sharing/exchanging the patient data. Similarly, there have been several studies that propose the use of FL for COVID-19 X-ray data training and deploy experiments to verify the FL effectiveness [161,162,163,164,165,166,167,168,169,58,170,171,172,173].…”