High-speed acquisition MRI reconstruction method based on residual self-attention image enhancement
An image enhancement and attention technology, applied in image enhancement, 2D image generation, image analysis, etc., can solve problems such as lack of texture details, and achieve the effect of enhancing global information and enriching texture details.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0032] A high-speed MRI reconstruction method based on residual self-attention image enhancement, including the following steps:
[0033] (1) Use Cartesian random high-magnification undersampling to fully sample MR image Y μ Implement the 7 times undersampling strategy, first convert the fully sampled MR image to the frequency domain by Fourier transform, and only retain 14% of the information of the fully sampled image to obtain a 7 times undersampled image X μ :X μ =F -1 (Z(M·(F(Y μ )))), F and F -1 Represents Fourier forward transform and Fourier inverse transform respectively, M represents the undersampling operator, Z represents the zero filling operation, · represents point multiplication;
[0034] (2) The network structure of the present invention is constructed by using a generative confrontation network, wherein the generator is implemented by U-NET, the discriminator is implemented by a convolutional layer, and the feature enhancement module based on residual sel...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com