CT-Conditioned Diffusion Prior with Physics-Constrained Sampling for PET Super-Resolution
This addresses PET super-resolution for medical imaging, which is incremental as it builds on diffusion models with specific constraints.
The paper tackled PET super-resolution by formulating it as posterior inference under heterogeneous system configurations and proposed a CT-conditioned diffusion framework with physics-constrained sampling, resulting in consistent improvements in experimental metrics and lesion-level clinical relevance indicators while reducing hallucination artifacts and improving structural fidelity.
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.