Literature DB >> 29982919

Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network.

Dongsheng Jiang1, Weiqiang Dou2,3, Luc Vosters4, Xiayu Xu5,6, Yue Sun4, Tao Tan7,8.   

Abstract

PURPOSE: To test if the proposed deep learning based denoising method denoising convolutional neural networks (DnCNN) with residual learning and multi-channel strategy can denoise three dimensional MR images with Rician noise robustly.
MATERIALS AND METHODS: Multi-channel DnCNN (MCDnCNN) method with two training strategies was developed to denoise MR images with and without a specific noise level, respectively. To evaluate our method, three datasets from two public data sources of IXI dataset and Brainweb, including T1 weighted MR images acquired at 1.5 and 3 T as well as MR images simulated with a widely used MR simulator, were randomly selected and artificially added with different noise levels ranging from 1 to 15%. For comparison, four other state-of-the-art denoising methods were also tested using these datasets.
RESULTS: In terms of the highest peak-signal-to-noise-ratio and global of structure similarity index, our proposed MCDnCNN model for a specific noise level showed the most robust denoising performance in all three datasets. Next to that, our general noise-applicable model also performed better than the rest four methods in two datasets. Furthermore, our training model showed good general applicability.
CONCLUSION: Our proposed MCDnCNN model has been demonstrated to robustly denoise three dimensional MR images with Rician noise.

Keywords:  CNN; Deep learning; Denoising; MRI; Rician noise

Mesh:

Year:  2018        PMID: 29982919     DOI: 10.1007/s11604-018-0758-8

Source DB:  PubMed          Journal:  Jpn J Radiol        ISSN: 1867-1071            Impact factor:   2.374


  17 in total

1.  Automatic brain MR image denoising based on texture feature-based artificial neural networks.

Authors:  Yu-Ning Chang; Herng-Hua Chang
Journal:  Biomed Mater Eng       Date:  2015       Impact factor: 1.300

2.  A majorize-minimize framework for Rician and non-central chi MR images.

Authors:  Divya Varadarajan; Justin P Haldar
Journal:  IEEE Trans Med Imaging       Date:  2015-04-28       Impact factor: 10.048

3.  An optimized blockwise nonlocal means denoising filter for 3-D magnetic resonance images.

Authors:  P Coupe; P Yger; S Prima; P Hellier; C Kervrann; C Barillot
Journal:  IEEE Trans Med Imaging       Date:  2008-04       Impact factor: 10.048

4.  MRI noise estimation and denoising using non-local PCA.

Authors:  José V Manjón; Pierrick Coupé; Antonio Buades
Journal:  Med Image Anal       Date:  2015-02-07       Impact factor: 8.545

5.  Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising.

Authors:  Kai Zhang; Wangmeng Zuo; Yunjin Chen; Deyu Meng; Lei Zhang
Journal:  IEEE Trans Image Process       Date:  2017-02-01       Impact factor: 10.856

6.  Denoising of 3D magnetic resonance images by using higher-order singular value decomposition.

Authors:  Xinyuan Zhang; Zhongbiao Xu; Nan Jia; Wei Yang; Qianjin Feng; Wufan Chen; Yanqiu Feng
Journal:  Med Image Anal       Date:  2014-09-18       Impact factor: 8.545

7.  The Rician distribution of noisy MRI data.

Authors:  H Gudbjartsson; S Patz
Journal:  Magn Reson Med       Date:  1995-12       Impact factor: 4.668

8.  The EM Method in a Probabilistic Wavelet-Based MRI Denoising.

Authors:  Marcos Martin-Fernandez; Sergio Villullas
Journal:  Comput Math Methods Med       Date:  2015-05-18       Impact factor: 2.238

9.  3D wavelet subbands mixing for image denoising.

Authors:  Pierrick Coupé; Pierre Hellier; Sylvain Prima; Charles Kervrann; Christian Barillot
Journal:  Int J Biomed Imaging       Date:  2008

10.  Denoising MR images using non-local means filter with combined patch and pixel similarity.

Authors:  Xinyuan Zhang; Guirong Hou; Jianhua Ma; Wei Yang; Bingquan Lin; Yikai Xu; Wufan Chen; Yanqiu Feng
Journal:  PLoS One       Date:  2014-06-16       Impact factor: 3.240

View more
  27 in total

Review 1.  Current applications and future directions of deep learning in musculoskeletal radiology.

Authors:  Pauley Chea; Jacob C Mandell
Journal:  Skeletal Radiol       Date:  2019-08-04       Impact factor: 2.199

Review 2.  Technical and clinical overview of deep learning in radiology.

Authors:  Daiju Ueda; Akitoshi Shimazaki; Yukio Miki
Journal:  Jpn J Radiol       Date:  2018-12-01       Impact factor: 2.374

Review 3.  Improvement of image quality at CT and MRI using deep learning.

Authors:  Toru Higaki; Yuko Nakamura; Fuminari Tatsugami; Takeshi Nakaura; Kazuo Awai
Journal:  Jpn J Radiol       Date:  2018-11-29       Impact factor: 2.374

4.  Improved magnetic resonance myelin water imaging using multi-channel denoising convolutional neural networks (MCDnCNN).

Authors:  Guojun Xu; Yongquan He; Qiurong Yu; Hongjian He; Zhiyong Zhao; Mingxia Fan; Jianqi Li; Dongrong Xu
Journal:  Quant Imaging Med Surg       Date:  2022-03

5.  Fully automatic deep learning trained on limited data for carotid artery segmentation from large image volumes.

Authors:  Tianshu Zhou; Tao Tan; Xiaoyan Pan; Hui Tang; Jingsong Li
Journal:  Quant Imaging Med Surg       Date:  2021-01

6.  Denoising of 3D Brain MR Images with Parallel Residual Learning of Convolutional Neural Network Using Global and Local Feature Extraction.

Authors:  Liang Wu; Shunbo Hu; Changchun Liu
Journal:  Comput Intell Neurosci       Date:  2021-05-04

7.  Improving Diagnostic Accuracy in Low-Dose SPECT Myocardial Perfusion Imaging With Convolutional Denoising Networks.

Authors:  Albert Juan Ramon; Yongyi Yang; P Hendrik Pretorius; Karen L Johnson; Michael A King; Miles N Wernick
Journal:  IEEE Trans Med Imaging       Date:  2020-03-10       Impact factor: 11.037

8.  Deep Learning-Based Ultrasound Combined with Gastroscope for the Diagnosis and Nursing of Upper Gastrointestinal Submucous Lesions.

Authors:  Lima Xia; Suhua Sun; Weijie Dai
Journal:  Comput Math Methods Med       Date:  2022-04-19       Impact factor: 2.809

9.  Applicability of deep learning-based reconstruction trained by brain and knee 3T MRI to lumbar 1.5T MRI.

Authors:  Nobuo Kashiwagi; Hisashi Tanaka; Yuichi Yamashita; Hiroto Takahashi; Yoshimori Kassai; Masahiro Fujiwara; Noriyuki Tomiyama
Journal:  Acta Radiol Open       Date:  2021-06-18

10.  Evaluation of MRI Denoising Methods Using Unsupervised Learning.

Authors:  Marc Moreno López; Joshua M Frederick; Jonathan Ventura
Journal:  Front Artif Intell       Date:  2021-06-04
View more

北京卡尤迪生物科技股份有限公司 © 2022-2023.