Four-dimensional motion estimation for CT artifact reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing CT image reconstruction methods struggle to efficiently correct motion artifacts, particularly respiratory and cardiac motion, which degrade image quality and complicate diagnosis, especially in low-dose scans.
Innovation Solution
The method employs feature map-based motion estimation using image registration and deep learning networks to generate a four-dimensional motion field, which is then used for motion-compensated reconstruction to produce artifact-free CT images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional CT image reconstruction methods are used, then the reconstruction process is simple and fast, but motion artifacts severely degrade image quality and diagnostic accuracy
Solution Approach 1:
The patent introduces feature maps as an intermediary representation between projection data and final images. These feature maps capture essential structural information while being more robust to motion artifacts, serving as a mediator that bridges the gap between raw data and high-quality reconstructed images without requiring complex motion correction algorithms
Solution Approach 2:
The patent replaces traditional mechanical motion correction approaches (such as multiple X-ray tubes, faster gantry spinning, or heavier equipment) with a computational approach using feature maps and image registration algorithms, substituting physical complexity with intelligent processing
2Reliability
If brute force approaches are employed to mitigate motion artifacts (e.g., two X-ray tubes, higher power tubes, faster gantry spinning), then motion correction capability is improved, but hardware costs increase and computational time is extended
Solution Approach 1:
The patent performs motion estimation and feature map registration during the reconstruction process itself, rather than requiring preliminary motion correction scans or post-reconstruction correction. The feature maps are generated and registered in advance of final image formation, enabling efficient motion compensation without extending total scan or processing time
Solution Approach 2:
The patent extracts motion information from feature maps through image registration, separating the motion estimation task from the full image reconstruction process. This extraction approach allows efficient computation of motion fields without requiring complete reconstruction of all image data, reducing computational time
3Reliability
If brute force approaches are employed to mitigate motion artifacts (e.g., two X-ray tubes, higher power tubes, faster gantry spinning), then motion correction capability is improved, but hardware costs and device complexity increase
Solution Approach 1:
The patent replaces mechanical motion correction approaches (such as multiple X-ray tubes, faster gantry spinning, or heavier equipment) with a computational approach using feature maps and image registration algorithms, substituting physical complexity with intelligent processing
Solution Approach 2:
The patent uses computationally efficient feature maps that can be rapidly generated and discarded after extracting motion information, replacing the need for expensive, complex hardware systems. The feature maps serve as temporary, low-cost representations that enable motion correction without requiring permanent investment in complex hardware
4Object-affected harmful factors
If low-dose CT scanning is performed to reduce radiation exposure, then patient safety is improved, but image quality degrades due to increased noise and motion artifacts
Solution Approach 1:
The patent converts the harmful effect of motion artifacts in low-dose scans into useful information by using feature map registration to explicitly estimate and compensate for motion. Rather than treating motion artifacts as mere noise to be filtered, the method extracts motion fields from the artifacts themselves, transforming a problem into a solution that enables effective motion correction at low doses
Data Source
AI summary
A medical image processing method includes obtaining a set of projection data acquired in a computed tomography (CT) scan of a three-dimensional region of an object to be examined; generating for each time point of a plurality of time points of the CT scan based on a part of the obtained set of projection data corresponding to the time point, a pair of feature maps for estimating motion at the time point so as to generate a plurality of pairs of feature maps, each feature map representing a feature of an image reconstructed from the part of the obtained set of projection data; estimating, based on the generated plurality of pairs of feature maps, a four-dimensional motion field; and reconstructing, based on the estimated four-dimensional motion field and the obtained set of projection data, a CT image of the object.