CT Artifact Correction Using Difference Image Reconstruction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CT image processing technologies struggle to correct artifacts with high accuracy, as they primarily focus on metal-induced artifacts without addressing other causes.
Innovation Solution
An image processing apparatus and method that extracts specific artifact generation sources, performs subtraction and projection operations on these sources, and generates difference images to correct artifacts in CT images, utilizing threshold value processing and machine learning for enhanced accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing CT image processing technology focuses only on metal-induced artifacts, then the processing method is simple, but the artifact correction accuracy is insufficient
Solution Approach 1:
The patent segments the artifact correction process into multiple distinct steps: extracting artifact generation sources, performing subtraction operations, conducting forward and back projection, generating difference images, and applying corrections. This segmentation allows each step to target specific artifact types (metal, bone, contrast medium) independently, improving correction accuracy while maintaining manageable processing complexity through systematic decomposition of the overall task.
Solution Approach 2:
The patent changes the parameter approach by using threshold values to identify and extract different artifact generation sources based on their CT values. By adjusting threshold parameters, the system can selectively process different types of artifacts (metal, bone, contrast medium) with appropriate correction methods, enabling accurate multi-type artifact correction without requiring a completely complex new processing framework.
2Reliability
If multiple artifact generation sources are processed separately, then the artifact correction comprehensiveness is improved, but the calculation cost increases
Solution Approach 1:
The patent merges the processing of multiple artifact generation sources (metal, bone, contrast medium) into a unified correction framework. By combining the difference images from multiple sources and applying a single correction operation to the CT image, the system achieves comprehensive artifact correction while avoiding the excessive calculation cost of completely separate processing pipelines for each artifact type.
Solution Approach 2:
The patent applies partial action by selectively processing only the regions containing artifact generation sources identified through threshold-based extraction. Rather than processing the entire CT image uniformly, the system focuses computational resources on specific regions of interest (artifact sources and their surrounding areas), reducing overall calculation cost while maintaining comprehensive correction coverage.
Data Source
AI summary
An image processing apparatus generates a first image by extracting a first region which is a first artifact generation source from a CT image, generates a second image by subtracting a value determined according to a specific part from the first image, generates a third image by performing forward projection and back projection on the second image, generates a fourth image which is a difference image between the second image and the third image, and generates a fifth image by correcting an artifact in the CT image using the fourth image.