A privacy-preserving federated learning framework for generalizable CBCT to synthetic CT translation in head and neck - Summary - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

A Federated Learning Approach for Privacy-Enhanced Translation of CBCT to Synthetic CT in Head and Neck Imaging

  • By

  • Ciro Benito Raggio

  • Paolo Zaffino

  • Maria Francesca Spadea

  • June 15, 2026

Share

Objective:

To propose a federated learning approach for synthesizing synthetic CT from cone-beam computed tomography while preserving data privacy across multiple institutions.

Key Findings:
  • Include specific numerical values for MAE, SSIM, and PSNR as mentioned in the source.
Interpretation:

Remove this section as it adds unsupported conclusions.

Limitations:
  • 1
Conclusion:

Revise to avoid implications of collaboration without data sharing unless directly supported by the source.

Original Source(s)

Related Content