• Qianqian Zhang, Guohui Ruan, Wei Yang, Yilong Liu, Kaixuan Zhao, Qianjin Feng, Wufan Chen, Ed X Wu, and Yanqiu Feng.
• School of Biomedical Engineering, Southern Medical University, Guangzhou, China.
• Magn Reson Med. 2019 Dec 1; 82 (6): 2133-2145.

PurposeTo develop a machine learning approach using convolutional neural network for reducing MRI Gibbs-ringing artifact.Theory And MethodsGibbs-ringing artifact in MR images is caused by insufficient sampling of the high frequency data. Existing methods exploit smooth constraints to reduce intensity oscillations near sharp edges at the cost of blurring details. In this work, we developed a machine learning approach for removing the Gibbs-ringing artifact from MR images. The ringing artifact was extracted from the original image using a deep convolutional neural network and then subtracted from the original image to obtain the artifact-free image. Finally, its low-frequency k-space data were replaced with measured counterparts to enforce data fidelity further. We trained the convolutional neural network using 17,532 T2-weighted (T2W) normal brain images and evaluated its performance on T2W images of normal and tumor brains, diffusion-weighted brain images, and T2W knee images.ResultsThe proposed method effectively removed the ringing artifact without noticeable smoothing in T2W and diffusion-weighted images. Quantitatively, images produced by the proposed method were closer to the fully-sampled reference images in terms of the root-mean-square error, peak signal-to-noise ratio, and structural similarity index, compared with current state-of-the-art methods.ConclusionThe proposed method presents a novel and effective approach for Gibbs-ringing reduction in MRI. The convolutional neural network-based approach is simple, computationally efficient, and highly applicable in routine clinical MRI.© 2019 International Society for Magnetic Resonance in Medicine.

27 keywords...

hide…