RELICT-NI: Replica Detection in Synthetic Neuroimaging-A Study on Noncontrast CT and Time-of-Flight MRA.

ABSTRACT:

Background

Synthetic neuroimaging data has the potential to augment and improve the generalizability of deep learning models. However, memorization in generative models can lead to unintended leakage of sensitive patient information, limiting model utility and jeopardizing patient privacy.

Methods

We propose RELICT-NI (REpLIca deteCTion-NeuroImaging), a framework for detecting replicas in synthetic neuroimaging datasets. RELICT-NI evaluates image similarity using three complementary approaches: (1) image-level analysis, (2) feature-level analysis via a pretrained medical foundation model, and (3) segmentation-level analysis. RELICT-NI was validated on two clinically relevant neuroimaging use cases: non-contrast head CT with intracerebral hemorrhage (N = 774) and time-of-flig

SUBMITTER: Aydin OU 

PROVIDER: S-EPMC12602640 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature