3D MRI Reconstruction Based on 2D Generative Adversarial Network Super-Resolution

Abstract

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.

Application of Three-Dimensional Image Reconstruction Technology in Neurogenic Intestinal Nursing Tasks

“…e low resolution of the model grid was the main factor that disturbs the model grid, and also restricts the popularization of the model grid. Based on the 3D reconstruction technology [8], the data feature simulation method was used to optimize the mesh resolution.…”

The role of generative adversarial networks in brain MRI: a scoping review

“…Sorting is done on the basis of the number of studies using the dataset Dataset name URL No. of studies IDs of studies Alzheimer’s Disease Neuroimaging Initiative (ADNI) http://adni.loni.usc.edu/ 16 [ 19 , 27 , 42 , 51 , 65 , 69 , 73 , 84 , 85 , 87 , 92 , 95 , 96 , 139 , 140 , 143 ] BRATS2018 https://www.med.upenn.edu/sbia/brats2018/data.html 8 [ 8 , 10 , 11 , 22 , 55 , 56 , 58 , 78 ] IXI dataset http://brain-development.org/ixi-dataset/ 7 [ 9 , 13 , 86 , 106 , 108 , 110 , 116 ] BRATS2016 https://sites.google.com/site/braintumorsegmentation/home/brats_2016 4 [ 6 , 7 , ...…”

A Systematic Literature Review on Applications of GAN-Synthesized Images for Brain MRI

“…The VGG16 [51] is employed before activation to restore the features, solve over-brightness in SRGAN, and improve performance [52]. The work of [53] is also based on ESR-GAN, where two neural networks complete the super-resolution task. The first network, receiving field block (RFB)-ESRGAN, selects half the number of slices for super-resolution reconstruction and MRI rebuilding and upholds high-frequency information.…”

“…[48] MSGAN Lesion-Focused SR method [49] SRGAN Use of shaping network [50] SRGAN Progressive upscaling method to generate true colors [52] ESRGAN Slices from 3 latitudes are used for SR [53] NESRGAN Noise and interpolated sampling [54] MedSRGAN Residual whole map attention to interpolate [55] GAN Medical image arbitrary-scale super-resolution method [57] GAN Improving resolution of through-plane slices [58] GAN The image resolution of 1.5-T scanner is made equivalent to 3-T scanner. [59] FPGAN Use a divide-and-conquer manner with multiple subbands in the wavelet domain [60] End-to-end GAN Uses a hierarchical structure A. Modality Translation:…”