TY - JOUR
T1 - Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network
AU - Jiang, Dongsheng
AU - Dou, Weiqiang
AU - Vosters, Luc
AU - Xu, Xiayu
AU - Sun, Yue
AU - Tan, Tao
PY - 2018/9/1
Y1 - 2018/9/1
N2 - 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.
AB - 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.
KW - CNN
KW - Deep learning
KW - Denoising
KW - MRI
KW - Rician noise
UR - http://www.scopus.com/inward/record.url?scp=85049597662&partnerID=8YFLogxK
U2 - 10.1007/s11604-018-0758-8
DO - 10.1007/s11604-018-0758-8
M3 - Article
C2 - 29982919
AN - SCOPUS:85049597662
VL - 36
SP - 566
EP - 574
JO - Japanese Journal of Radiology
JF - Japanese Journal of Radiology
SN - 1867-1071
IS - 9
ER -