CL3: A Collaborative Learning Framework for the Medical Data Ensuring Data Privacy in the Hyperconnected Environment

TL;DR

This paper introduces CL3, a collaborative learning framework that combines transfer, federated, and incremental learning to detect COVID-19 from chest X-ray images while preserving patient data privacy and adapting to data changes.

Contribution

The paper proposes a novel collaborative learning framework, CL3, integrating transfer, federated, and incremental learning for privacy-preserving medical data analysis.

Findings

Achieved 89.99% accuracy in COVID-19 detection.

Demonstrated effective model adaptation to data drift.

Validated the framework's scalability and privacy preservation.

Abstract

In a hyperconnected environment, medical institutions are particularly concerned with data privacy when sharing and transmitting sensitive patient information due to the risk of data breaches, where malicious actors could intercept sensitive information. A collaborative learning framework, including transfer, federated, and incremental learning, can generate efficient, secure, and scalable models while requiring less computation, maintaining patient data privacy, and ensuring an up-to-date model. This study aims to address the detection of COVID-19 using chest X-ray images through a proposed collaborative learning framework called CL3. Initially, transfer learning is employed, leveraging knowledge from a pre-trained model as the starting global model. Local models from different medical institutes are then integrated, and a new global model is constructed to adapt to any data drift observed in the local models. Additionally, incremental learning is considered, allowing continuous adaptation to new medical data without forgetting previously learned information. Experimental results demonstrate that the CL3 framework achieved a global accuracy of 89.99% when using Xception with a batch size of 16 after being trained for six federated communication rounds. A demo of the CL3 framework is available at https://github.com/zavidparvez/CL3-Collaborative-Approach to ensure reproducibility.