cs.CVNov 18, 2026

Image-Condition-Controlled Diffusion Network with Large-Scale CT Pretraining for CT-Free Attenuation Correction in Dynamic Cardiac PET

Authors: Zhejia Zhang, Scott M. Leonard, Jinkui Hao, Ryan J. Avery, Richard L. Weinberg, Bo Zhou

Organizations: Department of Radiology, Northwestern University, Chicago, IL 60611 USA · Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL 60208 USA · Division of Cardiology, Department of Medicine, Northwestern University, Chicago, IL 60611 USA

Abstract

Positron emission tomography (PET) provides quantitative information on myocardial perfusion. In dynamic PET, tracer kinetics are tracked through a series of reconstructed time frames. Reliable attenuation correction is essential for accurate measurements. Clinical attenuation maps (μμ-maps) are typically derived from computed tomography (CT), which adds radiation exposure and may introduce PET-CT misregistration due to respiratory and cardiac motion. Moreover, supervised CT-free methods rely on paired non-attenuation-corrected (NAC) PET and CT data, which are scarce, whereas large-scale unpaired CT data are more readily available. To address these challenges, we propose Large-scale Unpaired CT-Informed Diffusion (LUCID), a framework that transfers anatomical priors learned from 10,000 chest CT volumes in the public CT-RATE dataset to μμ-map synthesis for dynamic cardiac 82^{82}Rb PET. First, a convolutional neural network (CNN) predicts an initial μμ-map from each NAC PET frame. Second, the CT-pretrained diffusion backbone refines a low-noise perturbation of the CNN prediction through a single denoising step, conditioned on the corresponding NAC PET frame via ControlNet. Finally, frame-wise predictions are averaged voxel-wise to obtain the final μμ-map. We further introduce the voxel-wise temporal standard deviation (TSD) to quantify inter-frame variability without requiring a reference μμ-map. We evaluated LUCID on an in-house dataset of 102 patients and found that it achieved the best quantitative accuracy while maintaining competitive inter-frame consistency. Ablation studies showed that refinement with a diffusion backbone pretrained on in-house CT data from the training patients was less accurate than the CNN prediction alone, highlighting the importance of large-scale CT pretraining.

Figures & tables

Explore similar work

CardsList
  1. DECADE: A Temporally-Consistent Unsupervised Diffusion Model for Enhanced Rb-82 Dynamic Cardiac PET Image Denoising

    Mar 8, 2026Yinchi Zhou, Liang Guo, Huidong Xie +14Image DenoisingMedical Imaging

  2. Region-Weighted Losses and Model Fusion for Cross-Modal PET Attenuation Correction

    Aug 22, 2026Khoa Tuan Nguyen, Joris Vankerschaver, Wesley De NeveMedical Image SynthesisMultimodal Generation

  3. AnF-DiffPET: Anatomy- and Frequency-Guided Diffusion for PET/CT Denoising

    Jul 1, 2026Xuepeng Liu, Ruili Li, Zetong Liu +5Diffusion Models for Image RestorationDiffusion Model Guidance