Overall architecture of FedM2CT for all-in-one CT reconstruction. (IMAGE)

Beijing Institute of Technology Press Co., Ltd

Overall architecture of FedM2CT for all-in-one CT reconstruction.

Caption

FedM2CT consists of 3 modules, i.e., task-specific iRadonMAP (TS-iRadonMAP), condition-prompted mutual learning (CPML), and federated metadata learning (FMDL). TS-iRadonMAP performs the local CT image reconstruction task using a private model with any architecture, facilitating information exchange with the server. CPML is designed to share the knowledge in the local parameter-sharing submodule in TS-iRadonMAP via mutual learning. High-quality metadata are collected on the server to train the metamodel. FMDL adaptively combines the parameters of the metamodel on the server with the parameters of CPML to mitigate the effect of data heterogeneity. In particular, the imaging geometry and scanning protocol parameters of each client are employed to modulate the client-specific reconstruction task.

Credit

Hao Wang, Southern Medical University

Usage Restrictions

News organizations may use or redistribute this image, with proper attribution, as part of news coverage of this paper only.

License

Licensed content

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.