CT Image Motion Artifact Correction via Region Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for correcting motion artifacts in medical images, such as those from CT scans, either increase radiation dose or lack stability and safety, and often fail to effectively retain detailed features.
Innovation Solution
A method that preprocesses initial images by segmenting them into uniform regions based on CT values and homogenizing these values, followed by data generation and correction using motion information to generate a second image that reduces motion artifacts while retaining image details.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If existing methods for correcting motion artifacts are used, then motion artifacts are reduced, but detailed features are lost or image quality deteriorates
Solution Approach 1:
The patent segments the image into multiple types of regions (first type, second type, third type) based on CT value thresholds. This segmentation allows different processing strategies to be applied to different regions, preserving detailed features in regions where they are important while correcting motion artifacts in regions where they are less critical.
Solution Approach 2:
The patent applies homogenization processing specifically to CT values within each segmented region, creating uniform quality characteristics within each region. This local quality adjustment reduces motion artifacts while maintaining the overall image structure and important details.
2Stability of the object's composition
If motion artifacts are corrected using existing techniques, then image stability improves, but radiation dose increases or safety decreases
Solution Approach 1:
The patent replaces physical re-scanning (which would increase radiation dose) with computational image processing methods. By using segmentation, homogenization, and weighted fusion of multiple images, the system achieves motion artifact correction and improved image stability without additional radiation exposure.
3Object-affected harmful factors
If image preprocessing is performed to reduce motion artifacts, then motion artifacts are corrected, but detailed features are lost
Solution Approach 1:
The patent performs preliminary segmentation and homogenization processing on the image before final reconstruction. This preliminary action prepares the image data in a way that facilitates motion artifact correction while preserving important features for subsequent processing stages.
Solution Approach 2:
The patent changes the CT value parameters within each segmented region through homogenization processing. By adjusting these parameters uniformly within regions, motion artifacts are reduced while the overall image information and detailed features are preserved through the region-based approach.
Data Source
AI summary
A method and an apparatus for correcting an image, an electronic device, and a non-transitory computer-readable storage medium. The method includes following steps. Initial data are acquired, and an initial image is generated to be processed based on the initial data. The initial image is preprocessed to generate a first image, and the first image includes multiple types of image regions. First data are generated based on the first image, and second data are generated based on the first data and the initial data. A second image is generated based on the second data.