Angiographic Vessel Flow Extraction Using Centerline Motion Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for diagnosing coronary artery disease (CAD) and microvascular disease (MVD) are inadequate for early detection due to their invasive nature and inability to provide quantitative assessments of blood flow velocity, especially in smaller vessels, leading to delayed interventions and increased morbidity.
Innovation Solution
A computer-assisted method and system for determining blood flow velocity from angiographic images using computer vision algorithms and machine learning models to segment vessels, track centerline node points, and calculate flow rates, providing quantitative data for vascular health assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If invasive catheter-based pressure measurements are used to determine FFR, then measurement precision is improved, but device complexity and patient risk increase
Solution Approach 1:
The patent replaces the mechanical/invasive catheter-based pressure measurement system with a non-invasive computer vision system that processes angiographic images. The system uses image processing algorithms to track contrast agent flow and calculate blood flow velocity directly from visual data, eliminating the need for physical catheter insertion and pressure sensing.
Solution Approach 2:
The patent introduces computer vision algorithms and image processing techniques as an intermediary between the angiographic imaging system and the blood flow measurement. This intermediary layer extracts flow information from standard angiographic images without requiring additional invasive sensors or devices.
2Ease of operation
If conventional angiography is used for CAD diagnosis, then ease of operation is improved, but measurement precision of blood flow velocity deteriorates
Solution Approach 1:
The patent segments the angiographic image sequence into individual frames and further segments the vessel structures within each frame. This segmentation allows the system to track specific regions of interest (vessels, contrast agent) through the image sequence, enabling precise velocity calculation from standard angiographic data.
Solution Approach 2:
The patent transitions from static angiographic images to dynamic flow analysis by adding the time dimension. By analyzing the temporal progression of contrast agent movement across multiple frames, the system extracts velocity information that was not directly visible in single static images, thereby improving measurement precision without changing the fundamental imaging modality.
3Measurement precision
If invasive imaging modalities are used for early CAD detection, then measurement precision is improved, but ease of operation and patient acceptance worsen
Solution Approach 1:
The patent replaces invasive imaging modalities with a non-invasive analysis approach that processes standard angiographic images using computer vision. This substitution maintains diagnostic precision while eliminating the need for additional invasive procedures, thereby improving ease of operation and patient acceptance for early detection applications.
Data Source
AI summary
A computer-implemented method and system for assessing vascular disease is disclosed. The disclosure provides receiving angiography image data, including a plurality of image frames captured over a sampling time-period for a subject; identifying a representative image frame from the plurality of image frames; segmenting the plurality of image frames to isolate a vessel region; inferring a plurality of centerline node points associated with a centerline of the vessel; tracking movement of the plurality of centerline node points between successive centerline node points of the plurality of angiogram image frames; registering each segmented frame of the plurality of image frames to the representative image frame; and determining a flow rate of the vessel based in part on a change in length of the vessel represented in successive registered image frames.