Less Is More: Training-Free Acceleration Framework of 3D Diffusion Models for Low-Count PET Denoising via Global-Local Trajectory Reduction
Researchers have developed a novel framework to accelerate 3D diffusion models for low-count PET image denoising. This training-free approach, called the Global-Local Skipping Strategy, significantly reduces inference latency without requiring model retraining. The method employs a global denoising step skipping strategy and a local feature reuse shortcut to achieve over an order of magnitude acceleration while maintaining or improving reconstruction quality. Blinded reader studies confirmed enhanced clinical confidence and diagnostic quality. AI
IMPACT Accelerates AI model inference for medical imaging, potentially enabling faster and more accurate diagnoses from lower-radiation PET scans.