Dynamic-Fusion-Based Federated Learning for COVID-19 Detection

Abstract

Medical diagnostic image analysis (e.g., CT scan or X-Ray) using machine learning is an efficient and accurate way to detect COVID-19 infections. However, the sharing of diagnostic images across medical institutions is usually prohibited due to patients' privacy concerns. This causes the issue of insufficient datasets for training the image classification model. Federated learning is an emerging privacy-preserving machine learning paradigm that produces an unbiased global model based on the received local model updates trained by clients without exchanging clients' local data. Nevertheless, the default setting of federated learning introduces a huge communication cost of transferring model updates and can hardly ensure model performance when severe data heterogeneity of clients exists. To improve communication efficiency and model performance, in this paper, we propose a novel dynamic fusion-based federated learning approach for medical diagnostic image analysis to detect COVID-19 infections. First, we design an architecture for dynamic fusion-based federated learning systems to analyse medical diagnostic images. Further, we present a dynamic fusion method to dynamically decide the participating clients according to their local model performance and schedule the model fusion based on participating clients' training time. In addition, we summarise a category of medical diagnostic image datasets for COVID-19 detection, which can be used by the machine learning community for image analysis. The evaluation results show that the proposed approach is feasible and performs better than the default setting of federated learning in terms of model performance, communication efficiency, and fault tolerance.

Learning to learn by yourself: Unsupervised meta‐learning with self‐knowledge distillation for COVID‐19 diagnosis from pneumonia cases

“…Most patients have an air bronchogram 60 . The distribution characteristics of the abnormalities on X‐ray images about these five types of pneumonia are similar to those of CT images (slices) 52,61‐73 . Although the collected 2D data (e.g., X‐ray images) in our proposed data set misses lots of information (original intensity level, spacing, etc.)…”

Blockchain and AI-Based Solutions to Combat Coronavirus (COVID-19)-Like Epidemics: A Survey

“…Four state-of-the-art CNN models, e.g., MobileNet, ResNet18, MoblieNet and COVID-Net, are used in the federated setting for evaluation, where ResNet18 is proven with the best COVID-19 detection performance (98.06%) in federated X-ray image learning settings. Moreover, a dynamic fusion-based FL method is proposed in [138] for CT scan image analysis to diagnose COVID-19 infections via two stages, including client participation and client selection. First, each client such as a medical institution make a decision to participate in the FL round based on the performance of the newly trained model.…”

COVID-19 detection using federated machine learning

“…Weishan Zhang et al [ 4 ] proposed a novel dynamic fusion-based federated learning approach to enhance federated learning model performance metrics. They found that all the recent studies on federated learning used the default federated learning settings which may introduce huge communication overhead and underperforms when there is data heterogeneity between clients.…”

“…The concept of federated learning was proposed by Google in 2016 as a new machine learning paradigm. The objective of federated learning is to build a machine learning model based on distributed datasets without sharing raw data while preserving data privacy [ 4 , 5 ].…”

“…Each client trains the local machine learning model locally on a dataset and shares the model parameters or wights to the global model. The global model makes iteration of rounds to collect the distributed clients model updates without sharing raw data [ 4 , 5 ] as shown in Fig 1 .…”