Generative Super-Resolution PET Imaging with Fourier Diffusion Models

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Tivnan, Matthew, Li, Quanzheng
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910837929672704
author Tivnan, Matthew
Li, Quanzheng
author_facet Tivnan, Matthew
Li, Quanzheng
contents 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 Schrödinger 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15055
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Super-Resolution PET Imaging with Fourier Diffusion Models
Tivnan, Matthew
Li, Quanzheng
Medical Physics
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 Schrödinger 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.
title Generative Super-Resolution PET Imaging with Fourier Diffusion Models
topic Medical Physics
url https://arxiv.org/abs/2502.15055