Differential privacy preserved federated transfer learning for multi-institutional ⁶⁸Ga-PET image artefact detection and disentanglement.

ABSTRACT:

Purpose

Image artefacts continue to pose challenges in clinical molecular imaging, resulting in misdiagnoses, additional radiation doses to patients and financial costs. Mismatch and halo artefacts occur frequently in gallium-68 (⁶⁸Ga)-labelled compounds whole-body PET/CT imaging. Correcting for these artefacts is not straightforward and requires algorithmic developments, given that conventional techniques have failed to address them adequately. In the current study, we employed differential privacy-preserving federated transfer learning (FTL) to manage clinical data sharing and tackle privacy issues for building centre-specific models that detect and correct artefacts present in PET images.

Methods

Altogether, 1413 patients with ⁶⁸Ga prostate-specific

SUBMITTER: Shiri I 

PROVIDER: S-EPMC10684636 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature