Proj2Proj: self-supervised low-dose CT reconstruction
In Computed Tomography (CT) imaging, one of the most serious concerns has always been ionizing radiation. Several approaches have been proposed to reduce the dose level without compromising the image quality. With the emergence of deep learning, thanks to the increasing availability of computational...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
PeerJ Inc.
2024-02-01
|
Series: | PeerJ Computer Science |
Subjects: | |
Online Access: | https://peerj.com/articles/cs-1849.pdf |
_version_ | 1797284194343190528 |
---|---|
author | Mehmet Ozan Unal Metin Ertas Isa Yildirim |
author_facet | Mehmet Ozan Unal Metin Ertas Isa Yildirim |
author_sort | Mehmet Ozan Unal |
collection | DOAJ |
description | In Computed Tomography (CT) imaging, one of the most serious concerns has always been ionizing radiation. Several approaches have been proposed to reduce the dose level without compromising the image quality. With the emergence of deep learning, thanks to the increasing availability of computational power and huge datasets, data-driven methods have recently received a lot of attention. Deep learning based methods have also been applied in various ways to address the low-dose CT reconstruction problem. However, the success of these methods largely depends on the availability of labeled data. On the other hand, recent studies showed that training can be done successfully without the need for labeled datasets. In this study, a training scheme was defined to use low-dose projections as their own training targets. The self-supervision principle was applied in the projection domain. The parameters of a denoiser neural network were optimized through self-supervised training. It was shown that our method outperformed both traditional and compressed sensing-based iterative methods, and deep learning based unsupervised methods, in the reconstruction of analytic CT phantoms and human CT images in low-dose CT imaging. Our method’s reconstruction quality is also comparable to a well-known supervised method. |
first_indexed | 2024-03-07T17:45:37Z |
format | Article |
id | doaj.art-0e03bb828f8c486aa7d9442d7e29f57c |
institution | Directory Open Access Journal |
issn | 2376-5992 |
language | English |
last_indexed | 2024-03-07T17:45:37Z |
publishDate | 2024-02-01 |
publisher | PeerJ Inc. |
record_format | Article |
series | PeerJ Computer Science |
spelling | doaj.art-0e03bb828f8c486aa7d9442d7e29f57c2024-03-02T15:05:12ZengPeerJ Inc.PeerJ Computer Science2376-59922024-02-0110e184910.7717/peerj-cs.1849Proj2Proj: self-supervised low-dose CT reconstructionMehmet Ozan Unal0Metin Ertas1Isa Yildirim2Department of Electronics and Communication Engineering, Istanbul Technical University, Istanbul, TurkeyDepartment of Electrical and Electronics Engineering, Istanbul University-Cerrahpasa, Istanbul, TurkeyDepartment of Electronics and Communication Engineering, Istanbul Technical University, Istanbul, TurkeyIn Computed Tomography (CT) imaging, one of the most serious concerns has always been ionizing radiation. Several approaches have been proposed to reduce the dose level without compromising the image quality. With the emergence of deep learning, thanks to the increasing availability of computational power and huge datasets, data-driven methods have recently received a lot of attention. Deep learning based methods have also been applied in various ways to address the low-dose CT reconstruction problem. However, the success of these methods largely depends on the availability of labeled data. On the other hand, recent studies showed that training can be done successfully without the need for labeled datasets. In this study, a training scheme was defined to use low-dose projections as their own training targets. The self-supervision principle was applied in the projection domain. The parameters of a denoiser neural network were optimized through self-supervised training. It was shown that our method outperformed both traditional and compressed sensing-based iterative methods, and deep learning based unsupervised methods, in the reconstruction of analytic CT phantoms and human CT images in low-dose CT imaging. Our method’s reconstruction quality is also comparable to a well-known supervised method.https://peerj.com/articles/cs-1849.pdfDeep learningLow-dose CTImage reconstructionSelf-supervised learning |
spellingShingle | Mehmet Ozan Unal Metin Ertas Isa Yildirim Proj2Proj: self-supervised low-dose CT reconstruction PeerJ Computer Science Deep learning Low-dose CT Image reconstruction Self-supervised learning |
title | Proj2Proj: self-supervised low-dose CT reconstruction |
title_full | Proj2Proj: self-supervised low-dose CT reconstruction |
title_fullStr | Proj2Proj: self-supervised low-dose CT reconstruction |
title_full_unstemmed | Proj2Proj: self-supervised low-dose CT reconstruction |
title_short | Proj2Proj: self-supervised low-dose CT reconstruction |
title_sort | proj2proj self supervised low dose ct reconstruction |
topic | Deep learning Low-dose CT Image reconstruction Self-supervised learning |
url | https://peerj.com/articles/cs-1849.pdf |
work_keys_str_mv | AT mehmetozanunal proj2projselfsupervisedlowdosectreconstruction AT metinertas proj2projselfsupervisedlowdosectreconstruction AT isayildirim proj2projselfsupervisedlowdosectreconstruction |