MRI Reconstruction Using Enhanced Image Priors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Magnetic Resonance Imaging (MRI) technologies face challenges in balancing imaging speed with signal-to-noise ratio and artifact reduction, with partial sampling methods increasing speed but compromising image quality, and existing reconstruction methods like compressed sensing requiring iterative processes that are time-consuming and incomplete in noise elimination.
Innovation Solution
The method involves collecting undersampled MRI data, performing parallel imaging reconstruction using SENSE or GRAPPA algorithms, enhancing images to include distributional information of supporting points, and using these enhanced images as priors for constrained reconstruction with SENSE-based coil sensitivity to produce high-quality images with reduced noise and artifacts, eliminating the need for iterative reconstruction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If partial sampling methods are used to increase imaging speed, then imaging speed is improved, but image quality deteriorates due to increased noise and artifacts
Solution Approach 1:
The patent performs preliminary image enhancement processing on the initial reconstructed image to obtain an enhanced image with better quality features. This enhanced image is then used as a prior constraint in the subsequent reconstruction process, preparing quality information in advance to guide the final image reconstruction and reduce noise/artifacts while maintaining fast imaging speed
Solution Approach 2:
The patent introduces an enhanced image as an intermediary element between the undersampled k-space data and the final reconstructed image. This enhanced image serves as a prior constraint that mediates the reconstruction process, allowing the system to achieve both fast imaging (from undersampling) and high image quality (from the constraint)
Solution Approach 3:
The patent changes the parameter of image quality by applying enhancement processing that modifies the enhanced image's characteristics (such as using total variation minimization or other enhancement techniques). This parameter change in the prior image quality allows the constrained reconstruction to produce high-quality images even from undersampled data
2Manufacturing precision
If compressed sensing iterative reconstruction is used to reduce noise, then noise elimination is improved, but imaging time increases due to iterative processes
Solution Approach 1:
The patent performs preliminary enhancement processing on an initial reconstructed image to create an enhanced prior image before conducting the final constrained reconstruction. This preliminary action prepares quality information in advance, allowing the final reconstruction to achieve good noise elimination without requiring multiple iterative refinements
Solution Approach 2:
The patent skips the time-consuming iterative reconstruction process by using a constrained reconstruction approach with a pre-enhanced prior image. The enhancement processing followed by constrained reconstruction with the enhanced prior allows the system to rush through to a high-quality result without the prolonged iterative refinement process
3Manufacturing precision
If existing reconstruction methods are used to eliminate noise, then noise elimination is improved, but artifact reduction remains incomplete
Solution Approach 1:
The patent performs preliminary enhancement processing that specifically addresses both noise and artifact characteristics. The enhancement step prepares an improved prior image that contains corrected features, which then constrains the final reconstruction to maintain both noise elimination and artifact reduction simultaneously
Solution Approach 2:
The enhanced prior image acts as an intermediary that carries corrected information about both noise and artifacts. This intermediary image guides the constrained reconstruction process to simultaneously address both noise elimination and artifact reduction, achieving more complete reliability than methods that only address noise
Data Source
AI summary
Methods, devices, systems and apparatus for determining emphysema thresholds for controlling magnetic resonance imaging are provided. In one aspect, a magnetic resonance imaging method includes: collecting magnetic resonance imaging data as first k-space data by undersampling a magnetic resonance signal, performing parallel imaging reconstruction on the first k-space data to obtain a first image, performing enhancement processing on the first image to obtain a second image that comprises distributional information of image supporting points, and performing constrained reconstruction on the first k-space data by using the second image as a prior image to obtain a third image as a magnetic resonance image to be displayed.