Generative Super-Resolution PET Imaging with Fourier Diffusion Models

TL;DR

This paper introduces Fourier Diffusion Models for super-resolution PET imaging, significantly improving image resolution and noise reduction over existing methods, with promising simulation results for neurodegenerative disease diagnosis.

Contribution

The paper presents a novel Fourier Diffusion Model approach that leverages MTF and NPS for PET super-resolution, outperforming traditional diffusion and Schrödinger bridge methods.

Findings

FDMs outperform existing super-resolution techniques in structural similarity.

FDMs effectively reduce noise in high-resolution PET reconstructions.

Simulation results show successful 2mm resolution from 4mm input PET data.

Abstract

Neurological Positron Emission Tomography (PET) is a critical imaging modality for diagnosing and studying neurodegenerative diseases like Alzheimer's disease. However, the inherent low spatial resolution of PET images poses significant challenges in clinical settings. This work introduces a novel Generative Super-Resolution (GSR) approach using Fourier Diffusion Models (FDMs) to enhance the spatial resolution of PET images. Unlike traditional methods, FDMs leverage the time-dependent Modulation Transfer Function (MTF) and Noise Power Spectrum (NPS) to generate high-resolution, low-noise images from low-resolution inputs. Our method was evaluated using simulated data derived from High-Resolution Research Tomograph (HRRT) PET images with 2 mm resolution. The results demonstrate that FDMs significantly outperform existing techniques, including conditional diffusion models and image-to-image Schr\"odinger bridge, across several metrics, including structural similarity and noise suppression. Our simulation results highlight the potential of FDMs to generate high-quality 2mm resolution reconstructions given 4mm resolution input PET data.