A Peer-to-peer Federated Continual Learning Network for Improving CT Imaging from Multiple Institutions

TL;DR

This paper introduces a peer-to-peer federated continual learning approach for multi-institutional CT imaging that enhances low-dose image quality without sharing raw data, outperforming traditional federated learning methods.

Contribution

The paper proposes a novel peer-to-peer continual federated learning method with intermediate controllers, eliminating the need for a central server and improving collaborative CT imaging models.

Findings

Outperforms other federated learning methods in CT imaging quality.

Achieves accuracy comparable to centralized data pooling.

Demonstrates effectiveness on multiple datasets.

Abstract

Deep learning techniques have been widely used in computed tomography (CT) but require large data sets to train networks. Moreover, data sharing among multiple institutions is limited due to data privacy constraints, which hinders the development of high-performance DL-based CT imaging models from multi-institutional collaborations. Federated learning (FL) strategy is an alternative way to train the models without centralizing data from multi-institutions. In this work, we propose a novel peer-to-peer federated continual learning strategy to improve low-dose CT imaging performance from multiple institutions. The newly proposed method is called peer-to-peer continual FL with intermediate controllers, i.e., icP2P-FL. Specifically, different from the conventional FL model, the proposed icP2P-FL does not require a central server that coordinates training information for a global model. In the proposed icP2P-FL method, the peer-to-peer federated continual learning is introduced wherein the DL-based model is continually trained one client after another via model transferring and inter institutional parameter sharing due to the common characteristics of CT data among the clients. Furthermore, an intermediate controller is developed to make the overall training more flexible. Numerous experiments were conducted on the AAPM low-dose CT Grand Challenge dataset and local datasets, and the experimental results showed that the proposed icP2P-FL method outperforms the other comparative methods both qualitatively and quantitatively, and reaches an accuracy similar to a model trained with pooling data from all the institutions.