1
|
Xie K, Gao L, Lu Z, Li C, Qianyi X, Fan Z, Sun J, Tao L, Jianfeng S, Ni X. Inpainting the metal artifact region in MRI images by using generative adversarial networks with gated convolution. Med Phys 2022; 49:6424-6438. [PMID: 35982470 DOI: 10.1002/mp.15931] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/29/2021] [Revised: 03/23/2022] [Accepted: 08/04/2022] [Indexed: 11/09/2022] Open
Abstract
PURPOSE Magnetic resonance imaging (MRI) plays an important role in clinical diagnosis, but it is susceptible to metal artifacts. The generative adversarial network GatedConv with gated convolution (GC) and contextual attention (CA) was used to inpaint the metal artifact region in MRI images. METHODS MRI images containing or near the teeth of 70 patients were collected, and the scanning sequence was a T1-weighted high-resolution isotropic volume examination sequence. A total of 10,000 slices were obtained after data enhancement, of which 8,000 slices were used for training. MRI images were normalized to [-1,1]. Based on the randomly generated mask, U-Net, pix2pix, PConv with partial convolution, and GatedConv were used to inpaint the artifact region of MRI images. The mean absolute error (MAE) and peak signal-to-noise ratio (PSNR) for the mask were used to compare the results of these methods. The inpainting effect on the test data set using dental masks was also evaluated. Besides, the artifact area of clinical MRI images was inpainted based on the mask sketched by physicians. Finally, the earring artifacts and artifacts caused by abnormal signal foci were inpainted to verify the generalization of the models. RESULTS GatedConv could directly and effectively inpaint the incomplete MRI images generated by masks in the image domain. For the results of U-Net, pix2pix, PConv, and Gatedconv, the masked MAEs were 0.1638, 0.1812, 0.1688, and 0.1596, respectively, and the masked PSNRs were 18.2136, 17.5692, 18.2258, and 18.3035 dB, respectively. Using dental masks, the results of U-Net, pix2pix, and PConv differed more from the real images in terms of alveolar shape and surrounding tissue compared with GatedConv. GatedConv could inpaint the metal artifact region in clinical MRI images more effectively than the other models, but the increase in the mask area could reduce the inpainting effect. Inpainted MRI images by GatedConv and CT images with metal artifact reduction coincided with alveolar and tissue structure, and GatedConv could successfully inpaint artifacts caused by abnormal signal foci while the other models failed. The ablation study demonstrated that GC and CA increased the reliability of the inpainting performance of GatedConv. CONCLUSION MRI images are affected by metal, and signal void areas appear near metal. GatedConv can inpaint the MRI metal artifact region in the image domain directly and effectively and improve image quality. Medical image inpainting by GatedConv has potential value for tasks such as PET attenuation correction in PET/MRI and adaptive radiotherapy of synthetic CT based on MRI. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Kai Xie
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Liugang Gao
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Zhengda Lu
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China.,School of biomedical engineering and informatics, Nanjing Medical University, Nanjing, 213000, China
| | - Chunying Li
- Radiotherapy Department, Second People's Hospital of Changzhou, Nanjing Medical University, Changzhou, 213003, China.,Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Xi Qianyi
- Radiotherapy Department, Second People's Hospital of Changzhou, Nanjing Medical University, Changzhou, 213003, China.,Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Zhang Fan
- Radiotherapy Department, Second People's Hospital of Changzhou, Nanjing Medical University, Changzhou, 213003, China.,Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Jiawei Sun
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Lin Tao
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Sui Jianfeng
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| | - Xinye Ni
- Center for Medical Physics, Nanjing Medical University, Changzhou, 213003, China
| |
Collapse
|
2
|
Seo S, Do W, Luu HM, Kim KH, Choi SH, Park S. Artificial neural network for Slice Encoding for Metal Artifact Correction (SEMAC) MRI. Magn Reson Med 2019; 84:263-276. [DOI: 10.1002/mrm.28126] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/11/2019] [Revised: 11/21/2019] [Accepted: 11/21/2019] [Indexed: 01/09/2023]
Affiliation(s)
- Sunghun Seo
- Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology Daejeon Korea
| | - Won‐Joon Do
- Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology Daejeon Korea
| | - Huan Minh Luu
- Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology Daejeon Korea
| | - Ki Hwan Kim
- Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology Daejeon Korea
| | - Seung Hong Choi
- Department of Radiology Seoul National University College of Medicine Seoul Korea
| | - Sung‐Hong Park
- Department of Bio and Brain Engineering Korea Advanced Institute of Science and Technology Daejeon Korea
| |
Collapse
|
3
|
Kwon K, Kim D, Kim B, Park H. Unsupervised learning of a deep neural network for metal artifact correction using dual‐polarity readout gradients. Magn Reson Med 2019; 83:124-138. [DOI: 10.1002/mrm.27917] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/16/2019] [Revised: 07/03/2019] [Accepted: 07/05/2019] [Indexed: 12/24/2022]
Affiliation(s)
- Kinam Kwon
- School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea
| | - Dongchan Kim
- College of Medicine Gachon University Incheon Republic of Korea
| | - Byungjai Kim
- School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea
| | - HyunWook Park
- School of Electrical Engineering Korea Advanced Institute of Science and Technology Daejeon Republic of Korea
| |
Collapse
|