MRI Quantitative Value Computation via Localized Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current MRI technologies face challenges in efficiently computing quantitative value images, which are time-consuming and burdensome for operators, especially when determining the success or failure of imaging, as they require global optimization algorithms and manual adjustments.
Innovation Solution
An MRI apparatus that utilizes a localized optimization technique to compute quantitative values by predicting pixel values from multiple images acquired with different imaging parameter values, reducing calculation costs and improving operability by shortening the time to image checking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a global optimization algorithm is used to compute quantitative values, then the accuracy of quantitative value estimation is improved, but the calculation cost and time are significantly increased
Solution Approach 1:
The patent applies preliminary action by performing a preliminary optimization calculation to generate initial value data before the main quantitative value computation. This initial value data serves as a starting point for the subsequent localized optimization, avoiding the need to start from scratch and significantly reducing the overall calculation time while maintaining accuracy
Solution Approach 2:
The patent segments the optimization process into two distinct stages: (1) a preliminary optimization stage that generates initial value data, and (2) a main computation stage that uses localized optimization with the pre-computed initial values. This segmentation allows each stage to be optimized independently, reducing the total computational burden
2Measurement precision
If a global optimization algorithm is used to compute quantitative values, then the accuracy of quantitative value estimation is improved, but the device complexity and operational burden are increased
Solution Approach 1:
By pre-computing and storing initial value data from a preliminary optimization, the system avoids the need to execute complex global optimization algorithms during the main quantitative value computation. This preliminary action simplifies the main computation process while preserving accuracy
Solution Approach 2:
The patent creates a copy of the optimization results in the form of initial value data that can be reused for multiple quantitative value computations. This copying approach eliminates the need to repeatedly execute complex optimization algorithms, reducing computational complexity while maintaining result accuracy
3Measurement precision
If multiple images with different imaging parameters are acquired, then the quality of quantitative value computation is improved, but the imaging time and productivity are reduced
Solution Approach 1:
The patent maintains continuity of useful action by performing the preliminary optimization calculation during the imaging acquisition phase, so that when the actual quantitative value computation is needed, the initial value data is already available. This continuous preparation eliminates idle time and maintains imaging efficiency
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach significantly reduces calculation costs and time, allowing for faster quantitative value computation and improved operability by enabling quicker determination of imaging success or failure, thus enhancing the efficiency of MRI operations.
Implementation Method 1
A magnetic resonance imaging (hereinafter, MRI) apparatus is a medical diagnostic imaging apparatus that mainly uses a nuclear magnetic resonance phenomenon of protons
Data Source
AI summary
An MRI apparatus in which, when a quantitative value, which does not depend on imaging parameter values, is computed from a plurality of image data having different pixel values that are acquired by performing imaging the plurality of times with different imaging parameter values in the same pulse sequence, pixel values which are acquired from the imaging parameter values are predicted for each of a plurality of predetermined quantitative-value candidate group, and an initial value of the quantitative value is selected from the quantitative-value candidate groups with reference to the predicted pixel values. The optimal quantitative value is computed through a localized optimization technique using the selected initial value.