Dynamic ROI Positioning for Motion-Affected Medical Imaging
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, leading to decreased accuracy in contrast agent concentration monitoring.
Innovation Solution
A system and method for dynamic ROI positioning using a positioning model that determines ROI position based on image and feature information, incorporating machine learning or regression models to track ROI changes across multiple scans.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a locator scan is performed to determine ROI position and subsequent tracker scans are performed under the premise that ROI position remains unchanged, then the workflow is simple and efficient, but the positioning accuracy deteriorates due to rigid motion and respiratory motion of the object
Solution Approach 1:
The patent implements dynamic ROI positioning by automatically updating the ROI position in each tracker scan based on the positioning model, transforming the static ROI approach into a dynamic one that adapts to object motion, thereby resolving the contradiction between workflow efficiency and positioning accuracy
Solution Approach 2:
The patent employs feedback mechanisms where the positioning model continuously receives tracker scan data and updates the ROI position accordingly, creating a closed-loop system that maintains accurate positioning throughout the scanning process without compromising workflow efficiency
2Ease of operation
If manual marking of ROI is performed on locator image, then user control and flexibility are improved, but the complexity of the operation increases and automation is reduced
Solution Approach 1:
The patent enables the system to automatically perform ROI positioning using the positioning model and tracker scan data, eliminating the need for manual marking in each scan, thereby reducing operational complexity while maintaining user control through the initial ROI definition and model configuration
Solution Approach 2:
The patent performs preliminary ROI definition and positioning model configuration during the locator scan phase, preparing the system in advance so that subsequent tracker scans can automatically track the ROI without requiring repeated manual intervention, thus balancing user control with operational simplicity
Data Source
AI summary
The present disclosure relates to systems and methods for positioning a region of interest (ROI). The systems may obtain an image of an object captured by an imaging device. The systems may extract image information of the image. The systems may obtain feature information of a region of interest (ROI) in the object. The systems may determine 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.