AnF-DiffPET: Anatomy- and Frequency-Guided Diffusion for PET/CT Denoising
2026-07-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created a new way to improve noisy PET scan images taken with less radiation or shorter times by using a special technique called diffusion models. Their method, AnF-DiffPET, uses information from CT scans and focuses on anatomy and frequency details to make the images clearer and more accurate. They tested it on several datasets and found it works better than other popular methods for cleaning up PET images. This helps doctors get better information without exposing patients to more radiation.
Positron Emission Tomography (PET)Computed Tomography (CT)Diffusion ModelsImage DenoisingAnatomical GuidanceFrequency DomainCross-TransformerLow-Dose ImagingQuantitative Fidelity
Authors
Xuepeng Liu, Ruili Li, Zetong Liu, Renyiming Li, Yan Li, Yin Dai, Chao Li, Yueyang Teng
Abstract
Positron emission tomography (PET) provides essential functional information for disease assessment, however reducing injected activity or acquisition time produces low-dose (LD) PET with stronger count dependent noise and less reliable uptake quantification. Diffusion models offer a promising solution for PET denoising by progressively recovering high-dose (HD) PET images from LD inputs. However, LD-to-HD PET denoising is still challenging due to insufficient anatomical guidance, unstable multi-scale feature propagation, and uncertain frequency domain uptake recovery. We propose AnF-DiffPET, an anatomy- and frequency-guided diffusion framework for computed tomography (CT) conditioned LD PET denoising. The framework integrates Anatomical-Frequency Guidance (AFG), Multi-Scale Cross-Transformer Reconstruction (MSCTR), and Frequency-Contrastive Hard Mining (FCHM) to enhance anatomy aware feature modulation and frequency domain consistency during denoising. Experimental results across four PET/CT datasets show that the proposed method improves image fidelity, anatomical consistency, and quantitative fidelity over representative CNN-based, GAN-based, transformer-based, and diffusion-based methods. The code and trained models will be publicly released upon acceptance.