MRI denoising using progressively distribution-based neural network |
| |
Institution: | 1. School of Information Science and Technology, Northwest University, Xi''an 710127, China;2. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, NC 27599, USA;3. Shanghai United Imaging Intelligence Co., Ltd., Shanghai 201807, China;4. Department of Brain and Cognitive Engineering, Korea University, Seoul 136713, South Korea;1. Department of Imaging and Interventional Radiology, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, P.R. China;2. Research Center for Medical Image Computing, The Chinese University of Hong Kong Shatin, New Territories, Hong Kong SAR, P.R. China;3. Department of Medicine and Therapeutics, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, P.R. China;4. Department of Biomedical Engineering and Shun Hing Institute of Advanced Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong SAR, P.R. China;5. CUHK Shenzhen Research Institute, Shenzhen, Guangdong, P.R. China;6. Institute of Clinical Anatomy, Southern Medical University, Guangzhou, Guangdong, P.R. China |
| |
Abstract: | Magnetic Resonance (MR) images often suffer from noise pollution during image acquisition and transmission, which limits the accuracy of quantitative measurements from the data. Noise in magnitude MR images is usually governed by Rician distribution, due to the existence of uncorrelated Gaussian noise with zero-mean and equal variance in both the real and imaginary parts of the complex K-space data. Different from the existing MRI denoising methods that utilizing the spatial neighbor information around the pixels or patches, this work turns to capture the pixel-level distribution information by means of supervised network learning. A progressive network learning strategy is proposed via fitting the distribution of pixel-level and feature-level intensities. The proposed network consists of two residual blocks, one is used for fitting pixel domain without batch normalization layer and another one is applied for matching feature domain with batch normalization layer. Experimental results under synthetic, complex-valued and clinical MR brain images demonstrate great potential of the proposed network with substantially improved quantitative measures and visual inspections. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|