MRI Image Correction Using Coordinate-Based Deformation Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for correcting image deformations caused by gradient nonlinearity in magnetic resonance imaging (MRI) are inaccurate due to high requirements and measurement errors associated with field measurement tools.
Innovation Solution
A method using a deformation prediction model to obtain deformation information based on pixel coordinates, determining second coordinates, and correcting the image based on these coordinates, eliminating the need for field measurement tools.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If field measurement tools are used to obtain deformation information, then measurement can be performed, but measurement errors and mechanical errors occur leading to inaccurate image correction
Solution Approach 1:
The patent replaces the mechanical field measurement tool with a magnetic resonance imaging system that uses magnetic field encoding to obtain deformation information. Instead of mechanical measurement on spherical surfaces, the system encodes spatial positions using magnetic field gradients and reconstructs deformation from image data, eliminating mechanical errors and improving both measurement precision and reliability
Solution Approach 2:
The patent introduces a calibration phantom with known geometric structures as an intermediary object. This phantom serves as a reference to establish the relationship between magnetic field encoding and actual spatial positions, enabling accurate deformation measurement without direct mechanical measurement tools
2Measurement precision
If field measurement tools are used to obtain deformation information, then deformation can be measured, but high requirements are placed on the measurement tools
Solution Approach 1:
The patent replaces complex mechanical field measurement tools with a magnetic resonance imaging system that uses standard magnetic field encoding sequences. The deformation measurement function is integrated into the imaging system itself, eliminating the need for separate, highly specialized measurement devices
Solution Approach 2:
The patent makes the magnetic resonance imaging system multi-functional by enabling it to perform both standard imaging and deformation measurement tasks. The same imaging system and data processing pipeline are used for both purposes, eliminating the need for dedicated measurement tools and reducing device complexity
Data Source
AI summary
A method for correcting an image is provided, which includes obtaining deformation information of pixels in the image based on first coordinates of the pixels through a deformation prediction model, where the deformation information includes target deformation information caused by gradient nonlinearity of a gradient magnetic field, determining second coordinates corresponding to the first coordinates based on the target deformation information and the first coordinates, and correcting the image based on pixel values corresponding to the second coordinates.


