Interactive MR Image Non-uniformity Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for correcting image non-uniformity and intensity non-standardness in magnetic resonance (MR) images are inadequate, particularly in automated approaches, which fail to accurately identify tissue types and introduce residual non-standardness, affecting image quality and segmentation performance.
Innovation Solution
Interactive non-uniformity correction (iNC) and intensity standardization (iIS) methods that require operator specification of sample tissue regions, estimating non-uniformity at each voxel, building a global correction function, and performing a calibration and transformation step using piecewise linear intensity mapping to standardize image intensities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated methods are used for non-uniformity correction and intensity standardization, then productivity is improved, but measurement precision deteriorates due to failure to accurately identify tissue types
Solution Approach 1:
The patent introduces an operator as an intermediary to manually specify sample tissue regions, bridging the gap between automated processing and accurate tissue identification. The operator's expertise serves as a mediator to guide the automated algorithms toward correct tissue type identification, resolving the contradiction between automation efficiency and precision.
Solution Approach 2:
The patent requires preliminary manual specification of tissue regions before automated correction and standardization can proceed. This preliminary action by the operator ensures that subsequent automated processing operates on correctly identified tissue types, thereby maintaining measurement precision while still benefiting from automated processing in later stages.
2Ease of operation
If automated methods are used for non-uniformity correction, then ease of operation is improved, but manufacturing precision deteriorates due to introduction of residual non-standardness
Solution Approach 1:
The patent implements a feedback mechanism where the operator reviews and specifies tissue regions based on preliminary automated results, and the system iteratively refines the correction and standardization based on this feedback. This closed-loop approach ensures that residual non-standardness is minimized while maintaining ease of operation through automated iteration.
Solution Approach 2:
The patent employs dynamic adjustment of correction parameters based on operator specifications. The system adapts its correction function and intensity mapping based on the manually identified tissue regions, allowing precision to be optimized for each specific case while maintaining overall ease of operation through automated parameter adjustment.
3Measurement precision
If interactive methods with operator specification are used, then measurement precision is improved, but loss of time increases due to manual region specification
Solution Approach 1:
The patent requires the operator to specify only sample tissue regions rather than complete segmentation of all tissues. This partial action approach captures the essential information needed for accurate correction and standardization without requiring exhaustive manual processing, thereby reducing time loss while maintaining precision.
Solution Approach 2:
The system performs preliminary automated processing to generate initial correction results before requiring operator input. This preliminary action reduces the amount of manual work needed by providing a good starting point, thereby minimizing time loss while still enabling precise tissue identification through operator guidance.
4Manufacturing precision
If complex correction algorithms are used, then manufacturing precision is improved, but device complexity increases
Solution Approach 1:
The patent divides the complex correction process into distinct segments: non-uniformity correction, intensity standardization, and tissue-specific mapping. Each segment uses specialized algorithms optimized for its specific task, making the overall complex system more manageable and interpretable while maintaining high precision through specialized processing at each stage.
Data Source
AI summary
Interactive non-uniformity correction (NC) and interactive intensity standardization (IS) require sample tissue regions to be specified for several different types of tissues. Interactive NC estimates the degree of non-uniformity at each voxel in a given image, builds a global function for non-uniformity correction, and then corrects the image to improve quality. Interactive IS includes two steps: a calibration step and a transformation step. In the first step, tissue intensity signatures of each tissue from a few subjects are utilized to set up key landmarks in a standardized intensity space. In the second step, a piecewise linear intensity mapping function is built between the same tissue signatures derived from the given image and those in the standardized intensity space to transform the intensity of the given image into standardized intensity. Interactive IS for MR images combined with interactive NC can substantially improve numeric characterization of tissues.