Hypernetwork-Based Physics-Driven Personalized Federated Learning for CT Imaging

In clinical practice, computed tomography (CT) is an important noninvasive inspection technology to provide patients’ anatomical information. However, its potential radiation risk is an unavoidable problem that raises people’s concerns. Recently, deep learning (DL)-based methods have achieved promising results in CT reconstruction, but these methods usually require the centralized collection of large amounts of data for training from specific scanning protocols, which leads to serious domain shift and privacy concerns. To relieve these problems, in this article, we propose a hypernetwork-based physics-driven personalized federated learning method (HyperFed) for CT imaging. The basic assumption of the proposed HyperFed is that the optimization problem for each domain can be divided into two subproblems: local data adaption and global CT imaging problems, which are implemented by an institution-specific physics-driven hypernetwork and a global-sharing imaging network, respectively. Learning stable and effective invariant features from different data distributions is the main purpose of global-sharing imaging network. Inspired by the physical process of CT imaging, we carefully design physics-driven hypernetwork for each domain to obtain hyperparameters from specific physical scanning protocol to condition the global-sharing imaging network, so that we can achieve personalized local CT reconstruction. Experiments show that HyperFed achieves competitive performance in comparison with several other state-of-the-art methods. It is believed as a promising direction to improve CT imaging quality and personalize the needs of different institutions or scanners without data sharing. Related codes have been released at https://github.com/Zi-YuanYang/HyperFed.

I. Introduction

Computed tomography (CT) is an important imaging modality in clinical diagnosis since it can noninvasively visualize anatomical information inside the patient’s body. However, with the popularization of CT, related concerns have been expressed about the potential radiation risk that may lead to genetic, cancerous, and other diseases. In practice, switching the voltage/current of X-ray tube and reducing the scanning views are two typically used strategies to lower the radiation dose [1]. However, the above strategies will unavoidably degrade the imaging quality, which produces negative impacts on the subsequent image analysis and diagnosis [2], [3], [4].