Meta-information Guided Cross-domain Synergistic Diffusion Model for Low-dose PET Reconstruction

2025-12-23

AI Summary

Low-dose PET imaging suffers from severe noise, low contrast, and loss of physiological details; existing methods often neglect projection-domain physical priors and patient-specific metadata (e.g., administered dose, clinical parameters, semi-quantitative indices). To address this, we propose a physics-informed, semantically guided cross-domain collaborative diffusion model. First, we encode textual metadata as semantic prompts to enable functional–anatomical alignment. Second, we design a dual-path diffusion architecture jointly operating in the sinogram and image domains to integrate physical constraints and anatomical semantics. Third, we introduce a sinogram adapter and a multi-scale collaborative denoising mechanism. Evaluated on the UDPET dataset and a multi-center clinical cohort, our method achieves a 2.1 dB PSNR gain and a 0.032 SSIM improvement over state-of-the-art methods, with significantly enhanced fidelity in reconstructing key lesions and metabolic texture features.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Search and Optimization: Learning to Search

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Low-dose PET imaging is crucial for reducing patient radiation exposure but faces challenges like noise interference, reduced contrast, and difficulty in preserving physiological details. Existing methods often neglect both projection-domain physics knowledge and patient-specific meta-information, which are critical for functional-semantic correlation mining. In this study, we introduce a meta-information guided cross-domain synergistic diffusion model (MiG-DM) that integrates comprehensive cross-modal priors to generate high-quality PET images. Specifically, a meta-information encoding module transforms clinical parameters into semantic prompts by considering patient characteristics, dose-related information, and semi-quantitative parameters, enabling cross-modal alignment between textual meta-information and image reconstruction. Additionally, the cross-domain architecture combines projection-domain and image-domain processing. In the projection domain, a specialized sinogram adapter captures global physical structures through convolution operations equivalent to global image-domain filtering. Experiments on the UDPET public dataset and clinical datasets with varying dose levels demonstrate that MiG-DM outperforms state-of-the-art methods in enhancing PET image quality and preserving physiological details.

Problem

• Reconstructs low-dose PET images with reduced noise and enhanced contrast
• Integrates patient-specific meta-information to preserve physiological details
• Combines projection-domain physics with image-domain processing for cross-modal alignment

Innovation

• Meta-information encoding transforms clinical parameters into semantic prompts
• Cross-domain architecture combines projection and image-domain processing
• Sinogram adapter captures global physical structures via convolution operations