CT Image Correction via Dynamic Weighting and Pre-Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Computed tomography (CT) images often suffer from artifacts such as metal and streak artifacts, which degrade image quality and hinder accurate medical diagnosis.
Innovation Solution
A method and system for image correction that involves pre-correction of original images, generation of correction data, and weighting of images based on artifact regularity, using techniques like interpolation and weighting coefficients to generate a corrected image, and compensation to enhance image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If pre-correction and weighting methods are applied to remove artifacts, then image quality is improved, but device complexity and processing time increase
Solution Approach 1:
The patent applies pre-correction processing to the original image before final reconstruction, generating a pre-corrected image that removes artifacts in advance. This preliminary action reduces the burden on subsequent processing steps while maintaining image quality.
Solution Approach 2:
The patent uses weighted fusion where the weighting coefficient dynamically adjusts the contribution of pre-corrected and original images based on local artifact characteristics. This partial application of correction—applying it more strongly where artifacts exist and less where they don't—optimizes the balance between artifact removal and processing efficiency.
2Measurement precision
If dynamic weighting coefficients are used based on information entropy, then artifact removal accuracy is improved, but calculation complexity increases
Solution Approach 1:
The patent calculates information entropy of the pre-corrected image and uses it as feedback to dynamically adjust the weighting coefficient. This feedback mechanism allows the system to adaptively optimize artifact removal accuracy by comparing the entropy-based metric with actual artifact characteristics and adjusting parameters accordingly.
Solution Approach 2:
The patent changes the weighting parameter dynamically based on information entropy calculations. By adjusting the weighting coefficient according to entropy values, the system adapts to different local image characteristics, improving artifact removal precision without requiring completely different processing approaches for each region.
3Manufacturing precision
If multiple threshold levels are applied for weighting intensity, then correction accuracy is improved, but processing time increases
Solution Approach 1:
The patent segments the weighting process into multiple threshold levels, where different weighting intensities are applied to different regions based on their artifact severity. This segmentation allows accurate correction of severe artifacts while using lighter processing for mild cases, improving overall efficiency.
Solution Approach 2:
The patent applies different weighting intensities to different local regions of the image based on their specific artifact characteristics. Rather than applying a uniform correction strength across the entire image, the system tailors the correction intensity to local needs, improving accuracy where required while saving processing time where not needed.
Data Source
AI summary
A system and method for image correction is provided. The method includes: receiving an original image; obtaining an image relating to a region of interest (ROI); detecting an artifact in the image relating to the ROI; generating an artifact image based on the artifact; and correcting the original image based on the artifact image.