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

Jpn J Radiol. 2018 Sep;36(9):566-574. doi: 10.1007/s11604-018-0758-8. Epub 2018 Jul 7.


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 terms

  • Algorithms
  • Brain / anatomy & histology*
  • Datasets as Topic
  • Humans
  • Imaging, Three-Dimensional / methods*
  • Magnetic Resonance Imaging / methods*
  • Neural Networks, Computer*
  • Reference Values
  • Signal-To-Noise Ratio