Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks

Dahim Choi; Juhee Kim; Seung Hoon Chae; Byeongjoon Kim; Jongduk Baek; Andreas Maier; Rebecca Fahrig; Hyun Seok Park; Jang Hwan Choi

doi:10.1117/12.2512723

Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks

Dahim Choi, Juhee Kim, Seung Hoon Chae, Byeongjoon Kim, Jongduk Baek, Andreas Maier, Rebecca Fahrig, Hyun Seok Park, Jang Hwan Choi

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Scopus citations

Abstract

Recently, the necessity of using low-dose CT imaging with reduced noise has come to the forefront due to the risks involved in radiation. In order to acquire a high-resolution image from a low-resolution image which produces a relatively small amount of radiation, various algorithms including deep learning-based methods have been proposed. However, the current techniques have shown limited performance, especially with regard to losing fine details and blurring high-frequency edges. To enhance the previously suggested 2D patch-based denoising model, we have suggested the 3D block-based REDCNN model, employing convolution layers paired with deconvolution layers, shortcuts, and residual mappings. This process allows us to preserve the image structure and diagnostic features of an image, increasing image resolution by smoothing noise. Finally, we applied a bilateral filter in 3D and utilized a 2D-based Landweber iteration method to reduce remaining noise under a certain amplitude and prevent the edges from blurring. As a result, our proposed method effectively reduced Poisson noise level without losing diagnostic features and showed high performance in both qualitative and quantitative evaluation methods compared to ResNet2D, ResNet3D, REDCNN2D, and REDCNN3D.

Original language	English
Title of host publication	Medical Imaging 2019
Subtitle of host publication	Physics of Medical Imaging
Editors	Taly Gilat Schmidt, Guang-Hong Chen, Hilde Bosmans
Publisher	SPIE
ISBN (Electronic)	9781510625433
DOIs	https://doi.org/10.1117/12.2512723
State	Published - 2019
Event	Medical Imaging 2019: Physics of Medical Imaging - San Diego, United States Duration: 17 Feb 2019 → 20 Feb 2019

Publication series

Name	Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume	10948
ISSN (Print)	1605-7422

Conference

Conference	Medical Imaging 2019: Physics of Medical Imaging
Country/Territory	United States
City	San Diego
Period	17/02/19 → 20/02/19

Bibliographical note

Funding Information:
This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government, MSIP (grant no: NRF-2015M3A9A7029725 and NRF-2017M2A2A6A02070522, URL: http://nrf.re.kr). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. This work was never submitted, published, or presented before.

Publisher Copyright:
© SPIE. Downloading of the abstract is permitted for personal use only.

Keywords

Bilateral filtering
C-arm cone-beam CT
Deep neural networks
Imaging of lower extremities
Landweber type iteration
Medical image processing
Noise reduction

Access to Document

10.1117/12.2512723

Cite this

Choi, D., Kim, J., Chae, S. H., Kim, B., Baek, J., Maier, A., Fahrig, R., Park, H. S., & Choi, J. H. (2019). Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks. In T. G. Schmidt, G-H. Chen, & H. Bosmans (Eds.), Medical Imaging 2019: Physics of Medical Imaging Article 1094837 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10948). SPIE. https://doi.org/10.1117/12.2512723

@inproceedings{9fb69ec4db5049f895eed19bb4968bd1,

title = "Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks",

abstract = "Recently, the necessity of using low-dose CT imaging with reduced noise has come to the forefront due to the risks involved in radiation. In order to acquire a high-resolution image from a low-resolution image which produces a relatively small amount of radiation, various algorithms including deep learning-based methods have been proposed. However, the current techniques have shown limited performance, especially with regard to losing fine details and blurring high-frequency edges. To enhance the previously suggested 2D patch-based denoising model, we have suggested the 3D block-based REDCNN model, employing convolution layers paired with deconvolution layers, shortcuts, and residual mappings. This process allows us to preserve the image structure and diagnostic features of an image, increasing image resolution by smoothing noise. Finally, we applied a bilateral filter in 3D and utilized a 2D-based Landweber iteration method to reduce remaining noise under a certain amplitude and prevent the edges from blurring. As a result, our proposed method effectively reduced Poisson noise level without losing diagnostic features and showed high performance in both qualitative and quantitative evaluation methods compared to ResNet2D, ResNet3D, REDCNN2D, and REDCNN3D.",

keywords = "Bilateral filtering, C-arm cone-beam CT, Deep neural networks, Imaging of lower extremities, Landweber type iteration, Medical image processing, Noise reduction",

author = "Dahim Choi and Juhee Kim and Chae, {Seung Hoon} and Byeongjoon Kim and Jongduk Baek and Andreas Maier and Rebecca Fahrig and Park, {Hyun Seok} and Choi, {Jang Hwan}",

note = "Funding Information: This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government, MSIP (grant no: NRF-2015M3A9A7029725 and NRF-2017M2A2A6A02070522, URL: http://nrf.re.kr). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. This work was never submitted, published, or presented before. Publisher Copyright: {\textcopyright} SPIE. Downloading of the abstract is permitted for personal use only.; Medical Imaging 2019: Physics of Medical Imaging ; Conference date: 17-02-2019 Through 20-02-2019",

year = "2019",

doi = "10.1117/12.2512723",

language = "English",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

editor = "Schmidt, {Taly Gilat} and Guang-Hong Chen and Hilde Bosmans",

booktitle = "Medical Imaging 2019",

}

Choi, D, Kim, J, Chae, SH, Kim, B, Baek, J, Maier, A, Fahrig, R, Park, HS & Choi, JH 2019, Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks. in TG Schmidt, G-H Chen & H Bosmans (eds), Medical Imaging 2019: Physics of Medical Imaging., 1094837, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10948, SPIE, Medical Imaging 2019: Physics of Medical Imaging, San Diego, United States, 17/02/19. https://doi.org/10.1117/12.2512723

Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks. / Choi, Dahim; Kim, Juhee; Chae, Seung Hoon et al.
Medical Imaging 2019: Physics of Medical Imaging. ed. / Taly Gilat Schmidt; Guang-Hong Chen; Hilde Bosmans. SPIE, 2019. 1094837 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10948).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks

AU - Choi, Dahim

AU - Kim, Juhee

AU - Chae, Seung Hoon

AU - Kim, Byeongjoon

AU - Baek, Jongduk

AU - Maier, Andreas

AU - Fahrig, Rebecca

AU - Park, Hyun Seok

AU - Choi, Jang Hwan

N1 - Funding Information: This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government, MSIP (grant no: NRF-2015M3A9A7029725 and NRF-2017M2A2A6A02070522, URL: http://nrf.re.kr). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. This work was never submitted, published, or presented before. Publisher Copyright: © SPIE. Downloading of the abstract is permitted for personal use only.

PY - 2019

Y1 - 2019

N2 - Recently, the necessity of using low-dose CT imaging with reduced noise has come to the forefront due to the risks involved in radiation. In order to acquire a high-resolution image from a low-resolution image which produces a relatively small amount of radiation, various algorithms including deep learning-based methods have been proposed. However, the current techniques have shown limited performance, especially with regard to losing fine details and blurring high-frequency edges. To enhance the previously suggested 2D patch-based denoising model, we have suggested the 3D block-based REDCNN model, employing convolution layers paired with deconvolution layers, shortcuts, and residual mappings. This process allows us to preserve the image structure and diagnostic features of an image, increasing image resolution by smoothing noise. Finally, we applied a bilateral filter in 3D and utilized a 2D-based Landweber iteration method to reduce remaining noise under a certain amplitude and prevent the edges from blurring. As a result, our proposed method effectively reduced Poisson noise level without losing diagnostic features and showed high performance in both qualitative and quantitative evaluation methods compared to ResNet2D, ResNet3D, REDCNN2D, and REDCNN3D.

AB - Recently, the necessity of using low-dose CT imaging with reduced noise has come to the forefront due to the risks involved in radiation. In order to acquire a high-resolution image from a low-resolution image which produces a relatively small amount of radiation, various algorithms including deep learning-based methods have been proposed. However, the current techniques have shown limited performance, especially with regard to losing fine details and blurring high-frequency edges. To enhance the previously suggested 2D patch-based denoising model, we have suggested the 3D block-based REDCNN model, employing convolution layers paired with deconvolution layers, shortcuts, and residual mappings. This process allows us to preserve the image structure and diagnostic features of an image, increasing image resolution by smoothing noise. Finally, we applied a bilateral filter in 3D and utilized a 2D-based Landweber iteration method to reduce remaining noise under a certain amplitude and prevent the edges from blurring. As a result, our proposed method effectively reduced Poisson noise level without losing diagnostic features and showed high performance in both qualitative and quantitative evaluation methods compared to ResNet2D, ResNet3D, REDCNN2D, and REDCNN3D.

KW - Bilateral filtering

KW - C-arm cone-beam CT

KW - Deep neural networks

KW - Imaging of lower extremities

KW - Landweber type iteration

KW - Medical image processing

KW - Noise reduction

UR - http://www.scopus.com/inward/record.url?scp=85068412785&partnerID=8YFLogxK

U2 - 10.1117/12.2512723

DO - 10.1117/12.2512723

M3 - Conference contribution

AN - SCOPUS:85068412785

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Medical Imaging 2019

A2 - Schmidt, Taly Gilat

A2 - Chen, Guang-Hong

A2 - Bosmans, Hilde

PB - SPIE

T2 - Medical Imaging 2019: Physics of Medical Imaging

Y2 - 17 February 2019 through 20 February 2019

ER -

Choi D, Kim J, Chae SH, Kim B, Baek J, Maier A et al. Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks. In Schmidt TG, Chen G-H, Bosmans H, editors, Medical Imaging 2019: Physics of Medical Imaging. SPIE. 2019. 1094837. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2512723

Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Fingerprint

Cite this