Coronary Stenosis Assessment via Myocardial Perfusion Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for assessing coronary artery stenosis, such as X-ray angiography and Fractional Flow Reserve (FFR), face challenges including invasive procedures, high costs, and limitations in accurately determining the functional significance of stenosis without relying on detailed anatomical vessel geometry, leading to potential over- or under-treatment of patients.
Innovation Solution
A machine learning-based approach using a feature-perfusion classification (FPC) model that classifies patients based on myocardial texture characteristics from a single coronary computed tomography angiography (CCTA) dataset, without requiring detailed anatomical segmentation, to identify functionally significant stenosis, incorporating features like texture and morphologic features, and accounting for myocardial microvasculature and collateral flow.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If X-ray angiography is used for anatomical assessment of coronary arteries, then anatomical visualization is improved, but functional significance of stenosis cannot be determined
Solution Approach 1:
The patent segments the coronary artery tree into multiple vessels and segments the myocardium into multiple regions, then establishes correspondence between them. This segmentation enables the system to assess functional significance for specific vessel segments by analyzing perfusion in corresponding myocardial regions, rather than treating the entire artery as a single unit.
Solution Approach 2:
The patent transitions from two-dimensional X-ray angiography images to three-dimensional volumetric assessment by integrating CCTA anatomical data with myocardial perfusion information. This dimensional expansion allows simultaneous visualization of anatomical structure and functional perfusion data in 3D space, providing comprehensive assessment of stenosis functional significance.
2Measurement precision
If FFR measurement is performed to assess functional severity, then functional assessment accuracy is improved, but invasiveness and procedure complexity increase
Solution Approach 1:
The patent uses myocardial perfusion imaging as an intermediary to assess coronary stenosis functional significance. Instead of directly measuring pressure gradients with invasive wires, the system indirectly assesses functional impact by evaluating myocardial perfusion deficits in regions supplied by stenotic vessels, using the perfusion signal as a mediator between anatomical stenosis and functional outcome.
Solution Approach 2:
The patent replaces the mechanical FFR measurement system (pressure wires, catheters, direct pressure gradient measurement) with a non-invasive imaging-based assessment system. The mechanical intrusion of FFR wires is substituted by computational analysis of perfusion images, eliminating the need for invasive pressure measurement while providing functional severity assessment.
3Manufacturing precision
If detailed anatomical segmentation is performed for vessel assessment, then anatomical precision is improved, but processing time and complexity increase
Solution Approach 1:
The patent performs automated segmentation of the coronary artery tree and myocardium as a preliminary step before functional assessment. By pre-segmenting the anatomy and establishing vessel-myocardium correspondence in advance, the system eliminates the need for manual segmentation during the assessment phase, significantly reducing processing time while maintaining anatomical precision.
Solution Approach 2:
The patent changes the assessment parameters from detailed anatomical measurements to perfusion-based functional parameters. Instead of focusing on precise anatomical dimensions and stenosis geometry, the system uses perfusion signal intensity and distribution as assessment parameters, which can be extracted more quickly from imaging data while providing functional significance information.
Data Source
AI summary
Methods and systems are provided for assessing the presence of functionally significant stenosis in one or more coronary arteries, further known as a severity of vessel obstruction. The methods and systems can implement a prediction phase that comprises segmenting at least a portion of a contrast enhanced volume image data set into data segments corresponding to wall regions of the target organ, and analyzing the data segments to extract features that are indicative of an amount of perfusion experiences by wall regions of the target organ. The methods and systems can obtain a feature-perfusion classification (FPC) model derived from a training set of perfused organs, classify the data segments based on the features extracted and based on the FPC model, and provide, as an output, a prediction indicative of a severity of vessel obstruction based on the classification of the features.