3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution
The diagnosis of brain pathologies usually involves imaging to analyze the condition of the brain. Magnetic resonance imaging (MRI) technology is widely used in brain disorder diagnosis. The image quality of MRI depends on the magnetostatic field strength and scanning time. Scanners with lower field...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/9/2978 |
| _version_ | 1827694286222655488 |
|---|---|
| author | Hongtao Zhang Yuki Shinomiya Shinichi Yoshida |
| author_facet | Hongtao Zhang Yuki Shinomiya Shinichi Yoshida |
| author_sort | Hongtao Zhang |
| collection | DOAJ |
| description | The diagnosis of brain pathologies usually involves imaging to analyze the condition of the brain. Magnetic resonance imaging (MRI) technology is widely used in brain disorder diagnosis. The image quality of MRI depends on the magnetostatic field strength and scanning time. Scanners with lower field strengths have the disadvantages of a low resolution and high imaging cost, and scanning takes a long time. The traditional super-resolution reconstruction method based on MRI generally states an optimization problem in terms of prior information. It solves the problem using an iterative approach with a large time cost. Many methods based on deep learning have emerged to replace traditional methods. MRI super-resolution technology based on deep learning can effectively improve MRI resolution through a three-dimensional convolutional neural network; however, the training costs are relatively high. In this paper, we propose the use of two-dimensional super-resolution technology for the super-resolution reconstruction of MRI images. In the first reconstruction, we choose a scale factor of 2 and simulate half the volume of MRI slices as input. We utilize a receiving field block enhanced super-resolution generative adversarial network (RFB-ESRGAN), which is superior to other super-resolution technologies in terms of texture and frequency information. We then rebuild the super-resolution reconstructed slices in the MRI. In the second reconstruction, the image after the first reconstruction is composed of only half of the slices, and there are still missing values. In our previous work, we adopted the traditional interpolation method, and there was still a gap in the visual effect of the reconstructed images. Therefore, we propose a noise-based super-resolution network (nESRGAN). The noise addition to the network can provide additional texture restoration possibilities. We use nESRGAN to further restore MRI resolution and high-frequency information. Finally, we achieve the 3D reconstruction of brain MRI images through two super-resolution reconstructions. Our proposed method is superior to 3D super-resolution technology based on deep learning in terms of perception range and image quality evaluation standards. |
| first_indexed | 2024-03-10T12:01:00Z |
| format | Article |
| id | doaj.art-84a447e64fdf419585b63298018cd192 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T12:01:00Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-84a447e64fdf419585b63298018cd1922023-11-21T16:55:36ZengMDPI AGSensors1424-82202021-04-01219297810.3390/s210929783D MRI Reconstruction Based on 2D Generative Adversarial Network Super-ResolutionHongtao Zhang0Yuki Shinomiya1Shinichi Yoshida2Graduate School of Engineering, Kochi University of Technology, Kami, Kochi 782-8502, JapanSchool of Information, Kochi University of Technology, Kami, Kochi 782-8502, JapanSchool of Information, Kochi University of Technology, Kami, Kochi 782-8502, JapanThe diagnosis of brain pathologies usually involves imaging to analyze the condition of the brain. Magnetic resonance imaging (MRI) technology is widely used in brain disorder diagnosis. The image quality of MRI depends on the magnetostatic field strength and scanning time. Scanners with lower field strengths have the disadvantages of a low resolution and high imaging cost, and scanning takes a long time. The traditional super-resolution reconstruction method based on MRI generally states an optimization problem in terms of prior information. It solves the problem using an iterative approach with a large time cost. Many methods based on deep learning have emerged to replace traditional methods. MRI super-resolution technology based on deep learning can effectively improve MRI resolution through a three-dimensional convolutional neural network; however, the training costs are relatively high. In this paper, we propose the use of two-dimensional super-resolution technology for the super-resolution reconstruction of MRI images. In the first reconstruction, we choose a scale factor of 2 and simulate half the volume of MRI slices as input. We utilize a receiving field block enhanced super-resolution generative adversarial network (RFB-ESRGAN), which is superior to other super-resolution technologies in terms of texture and frequency information. We then rebuild the super-resolution reconstructed slices in the MRI. In the second reconstruction, the image after the first reconstruction is composed of only half of the slices, and there are still missing values. In our previous work, we adopted the traditional interpolation method, and there was still a gap in the visual effect of the reconstructed images. Therefore, we propose a noise-based super-resolution network (nESRGAN). The noise addition to the network can provide additional texture restoration possibilities. We use nESRGAN to further restore MRI resolution and high-frequency information. Finally, we achieve the 3D reconstruction of brain MRI images through two super-resolution reconstructions. Our proposed method is superior to 3D super-resolution technology based on deep learning in terms of perception range and image quality evaluation standards.https://www.mdpi.com/1424-8220/21/9/2978magnetic resonance imagingdeep learningsuper-resolutionthree-dimensional reconstructionRFB-ESRGANnESRGAN |
| spellingShingle | Hongtao Zhang Yuki Shinomiya Shinichi Yoshida 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution Sensors magnetic resonance imaging deep learning super-resolution three-dimensional reconstruction RFB-ESRGAN nESRGAN |
| title | 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution |
| title_full | 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution |
| title_fullStr | 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution |
| title_full_unstemmed | 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution |
| title_short | 3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution |
| title_sort | 3d mri reconstruction based on 2d generative adversarial network super resolution |
| topic | magnetic resonance imaging deep learning super-resolution three-dimensional reconstruction RFB-ESRGAN nESRGAN |
| url | https://www.mdpi.com/1424-8220/21/9/2978 |
| work_keys_str_mv | AT hongtaozhang 3dmrireconstructionbasedon2dgenerativeadversarialnetworksuperresolution AT yukishinomiya 3dmrireconstructionbasedon2dgenerativeadversarialnetworksuperresolution AT shinichiyoshida 3dmrireconstructionbasedon2dgenerativeadversarialnetworksuperresolution |