3D Wavelet-Based Structural Priors for Controlled Diffusion in Whole-Body Low-Dose PET Denoising

2026-01-11

arXiv.org

AI Summary

This work addresses the challenge of severe noise in low-dose PET imaging, which compromises both image quality and diagnostic reliability, and proposes WCC-Net—a novel framework that explicitly integrates wavelet-domain structural priors into a 3D diffusion model. By employing a lightweight control branch to guide a pretrained backbone, WCC-Net decouples anatomical structures from noise in the frequency domain, effectively preserving three-dimensional anatomical consistency during denoising. Evaluated at an ultra-low dose of 1/20 of the standard, the method achieves a PSNR gain of 1.21 dB and an SSIM improvement of 0.008, while significantly reducing GMSD and NMAE. Furthermore, it demonstrates robust anatomical fidelity and generalization across a broad dose range from 1/50 to 1/4 of the standard clinical dose.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Responsible Web: Data and user privacy-enhancing technologies for the Web
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Low-dose Positron Emission Tomography (PET) imaging reduces patient radiation exposure but suffers from increased noise that degrades image quality and diagnostic reliability. Although diffusion models have demonstrated strong denoising capability, their stochastic nature makes it challenging to enforce anatomically consistent structures, particularly in low signal-to-noise regimes and volumetric whole-body imaging. We propose Wavelet-Conditioned ControlNet (WCC-Net), a fully 3D diffusion-based framework that introduces explicit frequency-domain structural priors via wavelet representations to guide volumetric PET denoising. By injecting wavelet-based structural guidance into a frozen pretrained diffusion backbone through a lightweight control branch, WCC-Net decouples anatomical structure from noise while preserving generative expressiveness and 3D structural continuity. Extensive experiments demonstrate that WCC-Net consistently outperforms CNN-, GAN-, and diffusion-based baselines. On the internal 1/20-dose test set, WCC-Net improves PSNR by +1.21 dB and SSIM by +0.008 over a strong diffusion baseline, while reducing structural distortion (GMSD) and intensity error (NMAE). Moreover, WCC-Net generalizes robustly to unseen dose levels (1/50 and 1/4), achieving superior quantitative performance and improved volumetric anatomical consistency.

Problem

• Low-dose PET
• Denoising
• Structural consistency
• Diffusion models
• 3D imaging

Innovation

• 3D diffusion model
• wavelet-based structural prior
• low-dose PET denoising
• ControlNet
• frequency-domain guidance