Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework

Gamma-ray imaging systems are powerful tools in radiographic diagnosis. However, the recorded images suffer from degradations such as noise, blurring, and downsampling, consequently failing to meet high-precision diagnostic requirements. In this paper, we propose a novel single-image super-resolutio...

Full description

Saved in:
Bibliographic Details
Main Authors: Guo-Guang Li, Liang Sheng, Bao-Jun Duan, Yang Li, Yan Song, Zi-Jian Zhu, Wei-Peng Yan, Dong-Wei Hei, Qing-Zi Xing
Format: Article
Language:English
Published: AIP Publishing LLC 2025-03-01
Series:Matter and Radiation at Extremes
Online Access:http://dx.doi.org/10.1063/5.0236541
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849766854494519296
author Guo-Guang Li
Liang Sheng
Bao-Jun Duan
Yang Li
Yan Song
Zi-Jian Zhu
Wei-Peng Yan
Dong-Wei Hei
Qing-Zi Xing
author_facet Guo-Guang Li
Liang Sheng
Bao-Jun Duan
Yang Li
Yan Song
Zi-Jian Zhu
Wei-Peng Yan
Dong-Wei Hei
Qing-Zi Xing
author_sort Guo-Guang Li
collection DOAJ
description Gamma-ray imaging systems are powerful tools in radiographic diagnosis. However, the recorded images suffer from degradations such as noise, blurring, and downsampling, consequently failing to meet high-precision diagnostic requirements. In this paper, we propose a novel single-image super-resolution algorithm to enhance the spatial resolution of gamma-ray imaging systems. A mathematical model of the gamma-ray imaging system is established based on maximum a posteriori estimation. Within the plug-and-play framework, the half-quadratic splitting method is employed to decouple the data fidelity term and the regularization term. An image denoiser using convolutional neural networks is adopted as an implicit image prior, referred to as a deep denoiser prior, eliminating the need to explicitly design a regularization term. Furthermore, the impact of the image boundary condition on reconstruction results is considered, and a method for estimating image boundaries is introduced. The results show that the proposed algorithm can effectively addresses boundary artifacts. By increasing the pixel number of the reconstructed images, the proposed algorithm is capable of recovering more details. Notably, in both simulation and real experiments, the proposed algorithm is demonstrated to achieve subpixel resolution, surpassing the Nyquist sampling limit determined by the camera pixel size.
format Article
id doaj-art-e10f2bd3d919428c8d16b7a248874107
institution DOAJ
issn 2468-080X
language English
publishDate 2025-03-01
publisher AIP Publishing LLC
record_format Article
series Matter and Radiation at Extremes
spelling doaj-art-e10f2bd3d919428c8d16b7a2488741072025-08-20T03:04:26ZengAIP Publishing LLCMatter and Radiation at Extremes2468-080X2025-03-01102027402027402-1510.1063/5.0236541Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play frameworkGuo-Guang Li0Liang Sheng1Bao-Jun Duan2Yang Li3Yan Song4Zi-Jian Zhu5Wei-Peng Yan6Dong-Wei Hei7Qing-Zi Xing8Key Laboratory of Particle and Radiation Imaging (Tsinghua University), Ministry of Education, Beijing 100084, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaState Key Laboratory of Intense Pulsed Radiation Simulation and Effect, Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaKey Laboratory of Particle and Radiation Imaging (Tsinghua University), Ministry of Education, Beijing 100084, ChinaGamma-ray imaging systems are powerful tools in radiographic diagnosis. However, the recorded images suffer from degradations such as noise, blurring, and downsampling, consequently failing to meet high-precision diagnostic requirements. In this paper, we propose a novel single-image super-resolution algorithm to enhance the spatial resolution of gamma-ray imaging systems. A mathematical model of the gamma-ray imaging system is established based on maximum a posteriori estimation. Within the plug-and-play framework, the half-quadratic splitting method is employed to decouple the data fidelity term and the regularization term. An image denoiser using convolutional neural networks is adopted as an implicit image prior, referred to as a deep denoiser prior, eliminating the need to explicitly design a regularization term. Furthermore, the impact of the image boundary condition on reconstruction results is considered, and a method for estimating image boundaries is introduced. The results show that the proposed algorithm can effectively addresses boundary artifacts. By increasing the pixel number of the reconstructed images, the proposed algorithm is capable of recovering more details. Notably, in both simulation and real experiments, the proposed algorithm is demonstrated to achieve subpixel resolution, surpassing the Nyquist sampling limit determined by the camera pixel size.http://dx.doi.org/10.1063/5.0236541
spellingShingle Guo-Guang Li
Liang Sheng
Bao-Jun Duan
Yang Li
Yan Song
Zi-Jian Zhu
Wei-Peng Yan
Dong-Wei Hei
Qing-Zi Xing
Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework
Matter and Radiation at Extremes
title Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework
title_full Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework
title_fullStr Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework
title_full_unstemmed Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework
title_short Single-image super-resolution of gamma-ray imaging system using deep denoiser prior based on plug-and-play framework
title_sort single image super resolution of gamma ray imaging system using deep denoiser prior based on plug and play framework
url http://dx.doi.org/10.1063/5.0236541
work_keys_str_mv AT guoguangli singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT liangsheng singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT baojunduan singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT yangli singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT yansong singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT zijianzhu singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT weipengyan singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT dongweihei singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework
AT qingzixing singleimagesuperresolutionofgammarayimagingsystemusingdeepdenoiserpriorbasedonplugandplayframework