| ZHAO Bin,LIU Zhiyang,DING Shuxue,LIU Guohua,CAO Chen,WU Hong.Motion artifact correction for MR images based on convolutional neural network[J].Optoelectronics Letters,2022,(1):54-58 |
| Motion artifact correction for MR images based on convolutional neural network |
| Author Name | Affiliation | | ZHAO Bin | College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China
Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin300350, China | | LIU Zhiyang | College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China
Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin300350, China | | DING Shuxue | College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China
Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin300350, China
School of Artificial Intelligence, Guilin University of Electronic Technology, Guilin 541004, China | | LIU Guohua | College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China
Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin300350, China | | CAO Chen | Department of Medical Imaging, Tianjin Huanhu Hospital, Tianjin 300350, China | | WU Hong | College of Electronic Information and Optical Engineering, Nankai University, Tianjin 300350, China
Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology, Nankai University, Tianjin300350, China |
|
| Abstract: |
| Magnetic resonance imaging (MRI) is a common way to diagnose related diseases. However, the magnetic resonance (MR) images are easily defected by motion artifacts in their acquisition process, which affects the clinicians' diagnosis. In order to correct the motion artifacts of MR images, we propose a convolutional neural network (CNN)-based method to solve the problem. Our method achieves a mean peak signal-to-noise ratio (PSNR) of (35.212±3.321) dB and a mean structural similarity (SSIM) of 0.974 ± 0.015 on the test set, which are better than those of the comparison methods. |
| Hits: 360 |
| Download times: 9 |
|
| View Full Text Download reader |
|
|
|
