Automated Cardiac MRI Phase Classification for Motion Artifact Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current MRI image reconstruction methods require manual identification of cardiac or respiratory events, which is time-consuming and burdensome, especially when trying to reduce motion artifacts in cardiac cine-MRI images.
Innovation Solution
A method implemented on an MRI system that acquires MR signals, generates image data in k-space, classifies the image data into phases and groups, determines reference images, and reconstructs an image sequence based on these reference images and phases, thereby automating the process of reducing motion artifacts.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If manual identification of cardiac or respiratory events is used to reduce motion artifacts, then image quality is improved, but time consumption and operational burden increase
Solution Approach 1:
The system automatically identifies cardiac or respiratory events and performs phase classification without requiring manual operator intervention. The processor autonomously analyzes the MR signals, detects motion events, and reconstructs images with reduced motion artifacts, eliminating the time-consuming manual adjustment of trigger parameters while maintaining high image quality
Solution Approach 2:
The system performs preliminary classification of image data into phases based on detected cardiac or respiratory events before final image reconstruction. By pre-organizing the k-space data into motion-corrected phases, the system prepares the data structure in advance to eliminate motion artifacts, reducing the need for iterative manual adjustments and decreasing overall processing time
2Manufacturing precision
If manual identification of cardiac or respiratory events is used to reduce motion artifacts, then image quality is improved, but operational complexity increases
Solution Approach 1:
The system automatically identifies cardiac or respiratory events and performs phase classification without requiring manual operator intervention. The processor autonomously analyzes the MR signals, detects motion events, and reconstructs images with reduced motion artifacts, eliminating the time-consuming manual adjustment of trigger parameters while maintaining high image quality
Solution Approach 2:
The patent replaces the manual mechanical process of adjusting trigger parameters and identifying cardiac events with an automated computational system. The processor uses algorithmic analysis of MR signals to detect motion events and classify phases, substituting human operator actions with automated electronic processing that reduces operational burden while maintaining or improving image quality
3Productivity
If automated phase classification is implemented, then productivity is improved, but device complexity increases
Solution Approach 1:
The patent segments the image data in k-space into multiple phases based on detected cardiac or respiratory events. Each phase represents a specific temporal window during the cardiac or respiratory cycle, allowing independent processing and reconstruction. This segmentation enables parallel processing of different phases, improving overall reconstruction productivity while managing computational complexity through structured data organization
Solution Approach 2:
The system performs preliminary classification of image data into phases based on detected cardiac or respiratory events before final image reconstruction. By pre-organizing the k-space data into motion-corrected phases, the system prepares the data structure in advance to eliminate motion artifacts, reducing the need for iterative manual adjustments and decreasing overall processing time
Data Source
AI summary
A method may include acquiring MR signals by an MR scanner and generating image data in a k-space according to the MR signals. The method may also include classifying the image data into a plurality of phases. Each of the plurality of phases may have a first count of spokes. A spoke may be defined by a trajectory for filling the k-space. The method may also include classifying the plurality of phases of the image data into a plurality of groups and determining reference images based on the plurality of groups. Each of the reference images may correspond to the at least one of the phases of the image data. The method may further include reconstructing an image sequence based on the reference images and the plurality of phases of the image data.