LegoPET: Hierarchical Feature Guided Conditional Diffusion for PET Image Reconstruction

TL;DR

LegoPET is a hierarchical feature guided conditional diffusion model that significantly improves PET image reconstruction quality from sinograms, outperforming existing deep learning methods in visual fidelity and quantitative metrics.

Contribution

We propose LegoPET, a novel hierarchical feature guided cDPM that enhances PET image reconstruction quality and addresses domain correspondence and convergence issues.

Findings

LegoPET outperforms recent DL-based methods in PSNR and SSIM.

LegoPET produces higher perceptual quality PET images.

The model demonstrates improved consistency between input sinograms and reconstructed images.

Abstract

Positron emission tomography (PET) is widely utilized for cancer detection due to its ability to visualize functional and biological processes in vivo. PET images are usually reconstructed from histogrammed raw data (sinograms) using traditional iterative techniques (e.g., OSEM, MLEM). Recently, deep learning (DL) methods have shown promise by directly mapping raw sinogram data to PET images. However, DL approaches that are regression-based or GAN-based often produce overly smoothed images or introduce various artifacts respectively. Image-conditioned diffusion probabilistic models (cDPMs) are another class of likelihood-based DL techniques capable of generating highly realistic and controllable images. While cDPMs have notable strengths, they still face challenges such as maintain correspondence and consistency between input and output images when they are from different domains (e.g., sinogram vs. image domain) as well as slow convergence rates. To address these limitations, we introduce LegoPET, a hierarchical feature guided conditional diffusion model for high-perceptual quality PET image reconstruction from sinograms. We conducted several experiments demonstrating that LegoPET not only improves the performance of cDPMs but also surpasses recent DL-based PET image reconstruction techniques in terms of visual quality and pixel-level PSNR/SSIM metrics. Our code is available at https://github.com/yransun/LegoPET.