CT-Conditioned Diffusion Prior with Physics-Constrained Sampling for PET Super-Resolution

TL;DR

This paper introduces a CT-conditioned diffusion prior with physics-constrained sampling for PET super-resolution, enabling high-quality reconstructions without paired training data and reducing artifacts.

Contribution

It proposes a novel diffusion framework that leverages CT data and physical models for PET super-resolution, addressing the scarcity of paired data and physical constraints.

Findings

Improves PET super-resolution metrics over baselines

Reduces hallucination artifacts in reconstructed images

Enhances structural fidelity and clinical relevance

Abstract

PET super-resolution is highly under-constrained because paired multi-resolution scans from the same subject are rarely available, and effective resolution is determined by scanner-specific physics (e.g., PSF, detector geometry, and acquisition settings). This limits supervised end-to-end training and makes purely image-domain generative restoration prone to hallucinated structures when anatomical and physical constraints are weak. We formulate PET super-resolution as posterior inference under heterogeneous system configurations and propose a CT-conditioned diffusion framework with physics-constrained sampling. During training, a conditional diffusion prior is learned from high-quality PET/CT pairs using cross-attention for anatomical guidance, without requiring paired LR--HR PET data. During inference, measurement consistency is enforced through a scanner-aware forward model with explicit PSF effects and gradient-based data-consistency refinement. Under both standard and OOD settings, the proposed method consistently improves experimental metrics and lesion-level clinical relevance indicators over strong baselines, while reducing hallucination artifacts and improving structural fidelity.