Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence

In this paper, we propose a method for optimizing the parameter values in iterative reconstruction algorithms that include adjustable parameters in order to optimize the reconstruction performance. Specifically, we focus on the power divergence-based expectation-maximization algorithm, which include...

Full description

Saved in:
Bibliographic Details
Main Authors: Takeshi Kojima, Yusaku Yamaguchi, Omar M. Abou Al-Ola, Tetsuya Yoshinaga
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/17/11/512
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846154694149275648
author Takeshi Kojima
Yusaku Yamaguchi
Omar M. Abou Al-Ola
Tetsuya Yoshinaga
author_facet Takeshi Kojima
Yusaku Yamaguchi
Omar M. Abou Al-Ola
Tetsuya Yoshinaga
author_sort Takeshi Kojima
collection DOAJ
description In this paper, we propose a method for optimizing the parameter values in iterative reconstruction algorithms that include adjustable parameters in order to optimize the reconstruction performance. Specifically, we focus on the power divergence-based expectation-maximization algorithm, which includes two power indices as adjustable parameters. Through numerical and physical experiments, we demonstrate that optimizing the evaluation function based on the extended power-divergence and weighted extended power-divergence measures yields high-quality image reconstruction. Notably, the optimal parameter values derived from the proposed method produce reconstruction results comparable to those obtained using the true image, even when using distance functions based on differences between forward projection data and measured projection data, as verified by numerical experiments. These results suggest that the proposed method effectively improves reconstruction quality without the need for machine-learning techniques in parameter selection. Our findings also indicate that this approach is useful for enhancing the performance of iterative reconstruction algorithms, especially in medical imaging, where high-accuracy reconstruction under noisy conditions is required.
format Article
id doaj-art-60158e46f26f4a3ea37ca65dface2dd1
institution Kabale University
issn 1999-4893
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-60158e46f26f4a3ea37ca65dface2dd12024-11-26T17:45:28ZengMDPI AGAlgorithms1999-48932024-11-01171151210.3390/a17110512Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power DivergenceTakeshi Kojima0Yusaku Yamaguchi1Omar M. Abou Al-Ola2Tetsuya Yoshinaga3Institute of Biomedical Sciences, Tokushima University, 3-18-15 Kuramoto, Tokushima 770-8509, JapanShikoku Medical Center for Children and Adults, National Hospital Organization, 2-1-1 Senyu, Zentsuji 765-8507, JapanFaculty of Science, Tanta University, El-Giesh St., Tanta 31527, EgyptInstitute of Biomedical Sciences, Tokushima University, 3-18-15 Kuramoto, Tokushima 770-8509, JapanIn this paper, we propose a method for optimizing the parameter values in iterative reconstruction algorithms that include adjustable parameters in order to optimize the reconstruction performance. Specifically, we focus on the power divergence-based expectation-maximization algorithm, which includes two power indices as adjustable parameters. Through numerical and physical experiments, we demonstrate that optimizing the evaluation function based on the extended power-divergence and weighted extended power-divergence measures yields high-quality image reconstruction. Notably, the optimal parameter values derived from the proposed method produce reconstruction results comparable to those obtained using the true image, even when using distance functions based on differences between forward projection data and measured projection data, as verified by numerical experiments. These results suggest that the proposed method effectively improves reconstruction quality without the need for machine-learning techniques in parameter selection. Our findings also indicate that this approach is useful for enhancing the performance of iterative reconstruction algorithms, especially in medical imaging, where high-accuracy reconstruction under noisy conditions is required.https://www.mdpi.com/1999-4893/17/11/512extended power-divergence measurecomputed tomographyiterative reconstructionexpectation-maximization algorithmoptimization
spellingShingle Takeshi Kojima
Yusaku Yamaguchi
Omar M. Abou Al-Ola
Tetsuya Yoshinaga
Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence
Algorithms
extended power-divergence measure
computed tomography
iterative reconstruction
expectation-maximization algorithm
optimization
title Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence
title_full Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence
title_fullStr Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence
title_full_unstemmed Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence
title_short Optimizing Parameters for Enhanced Iterative Image Reconstruction Using Extended Power Divergence
title_sort optimizing parameters for enhanced iterative image reconstruction using extended power divergence
topic extended power-divergence measure
computed tomography
iterative reconstruction
expectation-maximization algorithm
optimization
url https://www.mdpi.com/1999-4893/17/11/512
work_keys_str_mv AT takeshikojima optimizingparametersforenhancediterativeimagereconstructionusingextendedpowerdivergence
AT yusakuyamaguchi optimizingparametersforenhancediterativeimagereconstructionusingextendedpowerdivergence
AT omarmaboualola optimizingparametersforenhancediterativeimagereconstructionusingextendedpowerdivergence
AT tetsuyayoshinaga optimizingparametersforenhancediterativeimagereconstructionusingextendedpowerdivergence