X-Ray Projection Pose Metrics for Fewer Repeat Acquisitions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for positioning anatomical structures in projection X-ray imaging systems are inefficient, leading to increased X-ray dose and workflow disruptions due to the need for repeated image acquisitions when unsuitable poses are used.
Innovation Solution
A computer-implemented method that segments X-ray projection images to identify projected sub-regions and generates a pose metric based on their relative sizes, providing feedback to adjust the imaging system's pose for improved image acquisition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual positioning by radiographer is used, then positioning experience can be applied, but the amount of X-ray dose increases and workflow is hampered due to repeated image acquisitions
Solution Approach 1:
The system automatically analyzes the X-ray projection image to generate a pose metric that provides feedback on the positioning quality. This feedback loop enables real-time assessment of whether the anatomical structure is correctly positioned, eliminating the need for repeated acquisitions and reducing X-ray dose while maintaining positioning accuracy.
Solution Approach 2:
The patent replaces the manual mechanical positioning process performed by radiographers with an automated computer-implemented system. The system uses image processing algorithms to automatically assess pose quality, substituting human experience-based positioning with objective, quantifiable metrics derived from the X-ray images themselves.
2Measurement precision
If manual positioning by radiographer is used, then positioning experience can be applied, but workflow efficiency decreases due to repeated image acquisitions
Solution Approach 1:
The automated pose metric provides immediate feedback on positioning quality, allowing radiographers to know within seconds whether an image is acceptable. This eliminates the iterative process of acquiring images, manually reviewing them, and re-positioning if necessary, thereby significantly improving workflow efficiency while maintaining positioning accuracy.
Solution Approach 2:
The system performs self-assessment of the image quality by automatically analyzing the projection images to generate pose metrics. This self-service capability eliminates the need for time-consuming manual review and decision-making, enabling rapid determination of whether re-positioning is necessary and thus improving overall workflow efficiency.
3Measurement precision
If repeated image acquisitions are performed to achieve acceptable pose, then positioning accuracy can be improved, but X-ray dose to subject increases
Solution Approach 1:
The system performs preliminary assessment of the pose quality immediately after image acquisition using automated pose metric generation. This preliminary action allows for immediate determination of whether the image is suitable, preventing the need for repeated acquisitions and thereby reducing cumulative X-ray dose while ensuring pose suitability is achieved.
Solution Approach 2:
The patent replaces the iterative mechanical process of repeated image acquisitions with a single acquisition followed by automated digital assessment. The computer-implemented pose metric system substitutes for the physical act of re-acquiring images, achieving the same goal of ensuring pose suitability while minimizing X-ray exposure.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A computer-implemented method of providing pose information for X-ray projection images, is provided. The method includes segmenting an X-ray projection image (120) to identify a plurality of projected sub-regions (1501..m) of an anatomical structure, generating a pose metric for the X- ray projection image (120) based on a relative size of two or more of the projected sub-regions (1501..m) in the segmented X-ray projection image (120), and outputting the pose metric to provide the pose information for the X-ray projection image (120).