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
Y2 - 17 February 2019 through 20 February 2019
ER -