PET Image Reconstruction Using Deep Diffusion Image Prior

arXiv — cs.CVWednesday, December 10, 2025 at 5:00:00 AM
  • A new method for Positron Emission Tomography (PET) image reconstruction has been proposed, utilizing diffusion models to enhance image quality while addressing challenges such as tracer-specific contrast variability and high computational demands. This approach employs an anatomical prior-guided framework that alternates between diffusion sampling and model fine-tuning, resulting in improved image reconstruction from various PET tracers.
  • The development of this method is significant as it enhances the capability of PET imaging, which is crucial for accurate diagnostics in medical settings. By leveraging a pretrained score function and optimizing computational efficiency through the half-quadratic splitting algorithm, this technique could lead to more reliable imaging outcomes, ultimately benefiting patient care and treatment planning.
  • This advancement reflects a broader trend in the application of diffusion models across various imaging and generative tasks, highlighting their potential to solve complex inverse problems in medical imaging. The integration of frameworks like Measurement-Aware Consistency Sampling and innovations in fine-grained image generation further underscores the growing importance of diffusion models in enhancing imaging technologies and their applications in fields such as drug discovery and AI-enhanced diagnostics.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
CHIMERA: Adaptive Cache Injection and Semantic Anchor Prompting for Zero-shot Image Morphing with Morphing-oriented Metrics
PositiveArtificial Intelligence
CHIMERA has been introduced as a zero-shot diffusion-based framework aimed at improving image morphing by addressing challenges in achieving smooth and semantically consistent transitions. The framework employs Adaptive Cache Injection and Semantic Anchor Prompting to enhance feature fusion and alignment during the denoising process.
Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions
NeutralArtificial Intelligence
A new study introduces Prompt-Conditioned Intervention (PCI) to analyze the dynamics of concept formation in diffusion models, focusing on how noise transitions into specific concepts during the image generation process. This framework evaluates Concept Insertion Success (CIS), which measures the likelihood that an inserted concept is preserved in the final output, providing insights into the controllability and reliability of these models.
Refining Visual Artifacts in Diffusion Models via Explainable AI-based Flaw Activation Maps
PositiveArtificial Intelligence
A novel framework called self-refining diffusion has been introduced to enhance image generation quality in diffusion models by detecting artifacts and unrealistic regions. This framework utilizes explainable AI-based flaw activation maps (FAMs) to identify and improve flawed areas during the image synthesis process, achieving significant performance improvements across various datasets.