3D Brain MRI Reconstruction based on 2D Super-Resolution Technology

Magnetic resonance imaging (MRI) is one of the most important diagnostic imaging methods, which is widely used in diagnosis and image-guided therapy, especially imaging diagnosis of the brain. However, MRI images have the characteristics of low resolution, and there are limitations such as long imaging time and noise. Super-resolution techniques have been studied on three-dimensional MRI images using three-dimensional convolutional neural network. Based on some related techniques of super-resolution reconstruction of two-dimensional MRI slices, we evaluated the capability of several super-resolution technologies. We utilize the super-resolution algorithm based on generative adversarial network ESRGAN to realize super-resolution reconstruction of two-dimensional MRI slices, and then we further demonstrate that frequent details can be obtained from ESRGAN. In the aspect of two-dimensional to three-dimensional reconstruction, we use the technique of two-dimensional super-resolution on slices from three different latitudes. We rebuild reconstructed two-dimensional images into a three-dimensional form. Then based on the principle of linear interpolation, we use the surrounding effective pixel values to interpolate the null value of each slice, and realize the reconstruction of three-dimensional brain MRI.