Categorical and phenotypic image synthetic learning as an alternative to federated learning

Nghi C. D. Truong (), Chandan Ganesh Bangalore Yogananda, Benjamin C. Wagner, James M. Holcomb, Divya D. Reddy, Niloufar Saadat, Jason Bowerman, Kimmo J. Hatanpaa, Toral R. Patel, Baowei Fei, Matthew D. Lee, Rajan Jain, Richard J. Bruce, Ananth J. Madhuranthakam, Marco C. Pinho and Joseph A. Maldjian ()
Additional contact information
Nghi C. D. Truong: University of Texas Southwestern Medical Center
Chandan Ganesh Bangalore Yogananda: University of Texas Southwestern Medical Center
Benjamin C. Wagner: University of Texas Southwestern Medical Center
James M. Holcomb: University of Texas Southwestern Medical Center
Divya D. Reddy: University of Texas Southwestern Medical Center
Niloufar Saadat: University of Texas Southwestern Medical Center
Jason Bowerman: University of Texas Southwestern Medical Center
Kimmo J. Hatanpaa: University of Texas Southwestern Medical Center
Toral R. Patel: University of Texas Southwestern Medical Center
Baowei Fei: University of Texas Southwestern Medical Center
Matthew D. Lee: NYU Grossman School of Medicine
Rajan Jain: NYU Grossman School of Medicine
Richard J. Bruce: University of Wisconsin-Madison
Ananth J. Madhuranthakam: Mayo Clinic
Marco C. Pinho: University of Texas Southwestern Medical Center
Joseph A. Maldjian: University of Texas Southwestern Medical Center

Nature Communications, 2025, vol. 16, issue 1, 1-11

Abstract: Abstract Multi-center collaborations are crucial in developing robust and generalizable machine learning models in medical imaging. Traditional methods, such as centralized data sharing or federated learning (FL), face challenges, including privacy issues, communication burdens, and synchronization complexities. We present CATegorical and PHenotypic Image SyntHetic learnING (CATphishing), an alternative to FL using Latent Diffusion Models (LDM) to generate synthetic multi-contrast three-dimensional magnetic resonance imaging data for downstream tasks, eliminating the need for raw data sharing or iterative inter-site communication. Each institution trains an LDM to capture site-specific data distributions, producing synthetic samples aggregated at a central server. We evaluate CATphishing using data from 2491 patients across seven institutions for isocitrate dehydrogenase mutation classification and three-class tumor-type classification. CATphishing achieves accuracy comparable to centralized training and FL, with synthetic data exhibiting high fidelity. This method addresses privacy, scalability, and communication challenges, offering a promising alternative for collaborative artificial intelligence development in medical imaging.

Date: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-64385-z Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-64385-z

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-64385-z

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().