The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Cet article propose une méthode de reconstruction d’images de tomodensitométrie (CT) de haute qualité à partir de données de projection de rayons X à faible dose. Une méthode de pointe, proposée par Xu et al., exploite l'apprentissage par dictionnaire pour les correctifs d'image. Cette méthode génère un dictionnaire surcomplet à partir de parcelles d'images CT à dose standard et reconstruit des images CT à faible dose en minimisant la somme d'une fidélité de données et d'un terme de régularisation basé sur des représentations clairsemées avec le dictionnaire. Cependant, cette méthode ne prend pas en compte les caractéristiques de chaque patch, telles que les textures ou les bords. Dans cet article, nous proposons de classer tous les correctifs en plusieurs classes et d'utiliser un dictionnaire individuel avec un paramètre de régularisation individuel pour chaque classe. De plus, pour un calcul rapide, nous introduisons l’orthogonalité aux vecteurs colonnes de chaque dictionnaire. Étant donné que des correctifs similaires sont collectés dans le même cluster, la dégradation de la précision due à l'orthogonalité se produit rarement. Nos simulations montrent que la méthode proposée surpasse l’état de l’art en termes de précision et de rapidité.
Hiryu KAMOSHITA
Ritsumeikan University
Daichi KITAHARA
Ritsumeikan University
Ken'ichi FUJIMOTO
Kagawa University
Laurent CONDAT
King Abdullah University of Science and Technology
Akira HIRABAYASHI
Ritsumeikan University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copier
Hiryu KAMOSHITA, Daichi KITAHARA, Ken'ichi FUJIMOTO, Laurent CONDAT, Akira HIRABAYASHI, "Multiclass Dictionary-Based Statistical Iterative Reconstruction for Low-Dose CT" in IEICE TRANSACTIONS on Fundamentals,
vol. E104-A, no. 4, pp. 702-713, April 2021, doi: 10.1587/transfun.2020EAP1020.
Abstract: This paper proposes a high-quality computed tomography (CT) image reconstruction method from low-dose X-ray projection data. A state-of-the-art method, proposed by Xu et al., exploits dictionary learning for image patches. This method generates an overcomplete dictionary from patches of standard-dose CT images and reconstructs low-dose CT images by minimizing the sum of a data fidelity and a regularization term based on sparse representations with the dictionary. However, this method does not take characteristics of each patch, such as textures or edges, into account. In this paper, we propose to classify all patches into several classes and utilize an individual dictionary with an individual regularization parameter for each class. Furthermore, for fast computation, we introduce the orthogonality to column vectors of each dictionary. Since similar patches are collected in the same cluster, accuracy degradation by the orthogonality hardly occurs. Our simulations show that the proposed method outperforms the state-of-the-art in terms of both accuracy and speed.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2020EAP1020/_p
Copier
@ARTICLE{e104-a_4_702,
author={Hiryu KAMOSHITA, Daichi KITAHARA, Ken'ichi FUJIMOTO, Laurent CONDAT, Akira HIRABAYASHI, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Multiclass Dictionary-Based Statistical Iterative Reconstruction for Low-Dose CT},
year={2021},
volume={E104-A},
number={4},
pages={702-713},
abstract={This paper proposes a high-quality computed tomography (CT) image reconstruction method from low-dose X-ray projection data. A state-of-the-art method, proposed by Xu et al., exploits dictionary learning for image patches. This method generates an overcomplete dictionary from patches of standard-dose CT images and reconstructs low-dose CT images by minimizing the sum of a data fidelity and a regularization term based on sparse representations with the dictionary. However, this method does not take characteristics of each patch, such as textures or edges, into account. In this paper, we propose to classify all patches into several classes and utilize an individual dictionary with an individual regularization parameter for each class. Furthermore, for fast computation, we introduce the orthogonality to column vectors of each dictionary. Since similar patches are collected in the same cluster, accuracy degradation by the orthogonality hardly occurs. Our simulations show that the proposed method outperforms the state-of-the-art in terms of both accuracy and speed.},
keywords={},
doi={10.1587/transfun.2020EAP1020},
ISSN={1745-1337},
month={April},}
Copier
TY - JOUR
TI - Multiclass Dictionary-Based Statistical Iterative Reconstruction for Low-Dose CT
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 702
EP - 713
AU - Hiryu KAMOSHITA
AU - Daichi KITAHARA
AU - Ken'ichi FUJIMOTO
AU - Laurent CONDAT
AU - Akira HIRABAYASHI
PY - 2021
DO - 10.1587/transfun.2020EAP1020
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E104-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 2021
AB - This paper proposes a high-quality computed tomography (CT) image reconstruction method from low-dose X-ray projection data. A state-of-the-art method, proposed by Xu et al., exploits dictionary learning for image patches. This method generates an overcomplete dictionary from patches of standard-dose CT images and reconstructs low-dose CT images by minimizing the sum of a data fidelity and a regularization term based on sparse representations with the dictionary. However, this method does not take characteristics of each patch, such as textures or edges, into account. In this paper, we propose to classify all patches into several classes and utilize an individual dictionary with an individual regularization parameter for each class. Furthermore, for fast computation, we introduce the orthogonality to column vectors of each dictionary. Since similar patches are collected in the same cluster, accuracy degradation by the orthogonality hardly occurs. Our simulations show that the proposed method outperforms the state-of-the-art in terms of both accuracy and speed.
ER -