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

Choi D, Kim J, Chae SH, Kim B, Baek J, Maier A, Fahrig R, Park HS, Choi JH (2019)


Publication Type: Conference contribution

Publication year: 2019

Journal

Publisher: SPIE

Book Volume: 10948

Conference Proceedings Title: Progress in Biomedical Optics and Imaging - Proceedings of SPIE

Event location: San Diego, CA US

ISBN: 9781510625433

DOI: 10.1117/12.2512723

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.

Authors with CRIS profile

Involved external institutions

How to cite

APA:

Choi, D., Kim, J., Chae, S.H., Kim, B., Baek, J., Maier, A.,... 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 Hilde Bosmans, Guang-Hong Chen, Taly Gilat Schmidt (Eds.), Progress in Biomedical Optics and Imaging - Proceedings of SPIE. San Diego, CA, US: SPIE.

MLA:

Choi, Dahim, et al. "Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks." Proceedings of the Medical Imaging 2019: Physics of Medical Imaging, San Diego, CA Ed. Hilde Bosmans, Guang-Hong Chen, Taly Gilat Schmidt, SPIE, 2019.

BibTeX: Download