1 March 2019 Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks
Author Affiliations +
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.
© (2019) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Dahim Choi, Juhee Kim, Seung-Hoon Chae, Byeongjoon Kim, Jongduk Baek, Andreas Maier, Rebecca Fahrig, Hyun-Seok Park, and Jang-Hwan Choi "Multidimensional noise reduction in C-arm cone-beam CT via 2D-based Landweber iteration and 3D-based deep neural networks ", Proc. SPIE 10948, Medical Imaging 2019: Physics of Medical Imaging, 1094837 (1 March 2019); doi: 10.1117/12.2512723; https://doi.org/10.1117/12.2512723
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top