ROI Position Tracking for Motion-Adaptive Imaging Scans
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical imaging technologies face inaccuracies in positioning a region of interest (ROI) due to factors like rigid and respiratory motion of the object, which affects the accuracy of contrast agent concentration monitoring.
Innovation Solution
A system and method using a positioning model to determine the ROI's position based on image and feature information, incorporating machine learning or regression models to dynamically track the ROI's changes during sequential scans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a user manually marks the ROI on a locator image and records the position, then the initial ROI position is obtained, but the ROI position accuracy deteriorates due to rigid motion and respiratory motion of the object during scanning
Solution Approach 1:
The system performs a locator scan before the main scanning procedure to obtain initial ROI position information. This preliminary action allows the system to establish a reference position for the ROI before motion occurs during the actual scanning process, enabling subsequent dynamic tracking and compensation of position changes.
Solution Approach 2:
The system continuously monitors the object's position during scanning using the positioning model and compares it with the initial ROI position. Based on the detected position deviations caused by rigid motion and respiratory motion, the system dynamically adjusts the ROI position through feedback control, thereby maintaining accurate positioning throughout the scanning procedure.
2Measurement precision
If sequential tracker scans are performed to monitor contrast agent concentration, then the concentration monitoring is enabled, but the monitoring accuracy deteriorates when the ROI position changes due to object motion
Solution Approach 1:
The system transitions from a static ROI positioning approach to a dynamic positioning approach by implementing real-time position tracking during sequential scans. The positioning model continuously updates the ROI position based on detected motion, allowing the system to adapt to changing conditions and maintain accurate concentration monitoring throughout the scanning procedure.
Solution Approach 2:
The system uses feedback from the positioning model to continuously correct the ROI position during sequential tracker scans. By comparing the current position with the expected position and applying corrections based on detected motion, the system ensures that concentration measurements remain accurate even when the object moves during scanning.
3Device complexity
If a static ROI position is assumed throughout the scanning procedure, then the scanning process is simplified, but the positioning accuracy deteriorates due to rigid motion and respiratory motion
Solution Approach 1:
The system introduces a positioning model as an intermediary component that bridges the simple static positioning approach and the need for accurate dynamic positioning. This positioning model processes motion information and generates corrected ROI positions, enabling accurate tracking without requiring complex manual intervention or significantly complicating the scanning workflow.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to systems and methods for positioning a region of interest (ROI). The methods may include obtaining an image of an object captured by an imaging device. The methods may extracting image information of the image. The methods may obtaining feature information of a region of interest (ROI) in the object. The methods may determining position information of the ROI in the image using a positioning model based on the image information of the image and the feature information of the ROI.