Coronary Artery Plaque Scoring With Spatial Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for calculating coronary artery disease scores, such as Agatston's method and CAD-RADS, do not account for the pattern or distribution of calcified and non-calcified plaque, leading to inadequate risk assessment for cardiovascular events.
Innovation Solution
A method and system using machine learning to analyze cardiac CT data, identify plaque volumes, determine key points on coronary arteries, and calculate a plaque score based on plaque volume, distance from key points, and heart dimension, incorporating both calcified and non-calcified plaque types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Agatston's method or CAD-RADS scoring is used, then calcified plaque can be detected, but the pattern and distribution of plaque cannot be assessed
Solution Approach 1:
The patent segments the coronary artery into multiple sections based on anatomical landmarks (ostia, bifurcations, segments) and assigns plaque scores to each section. This segmentation allows assessment of plaque distribution patterns while maintaining overall detection accuracy through systematic evaluation of each segment's characteristics
Solution Approach 2:
The patent adds a spatial distribution dimension to traditional plaque scoring by evaluating plaque location relative to coronary artery segments and calculating scores that reflect both presence and distribution. This transforms the assessment from a single aggregate value to a multi-dimensional evaluation incorporating spatial information
2Quantity of substance
If traditional plaque scoring methods are used, then overall calcified plaque burden can be measured, but non-calcified plaque is not accounted for
Solution Approach 1:
The patent creates a unified scoring system that can evaluate multiple plaque types (calcified, non-calcified, mixed) using the same methodological framework. The system adapts to different plaque compositions while maintaining consistent scoring principles, making it universally applicable to various plaque presentations
3Measurement precision
If manual expert delineation is used, then accurate differentiation of calcification types is achieved, but the process is time-consuming and requires trained experts
Solution Approach 1:
The patent implements an automated system that performs plaque identification, segmentation, and scoring without requiring manual expert intervention. The system uses image processing algorithms to automatically differentiate plaque types and calculate scores, making the process self-service and eliminating dependency on trained experts while maintaining accuracy
4Productivity
If automated machine learning plaque identification is used, then processing speed increases, but accuracy in differentiating plaque types may decrease
Solution Approach 1:
The patent replaces manual mechanical analysis with automated image processing and machine learning algorithms. The system uses computational methods to identify and characterize plaque, substituting human expert analysis with automated computational processes that maintain accuracy while dramatically increasing processing speed
Data Source
AI summary
A method of automatically determining a plaque score for coronary arteries of a patient is disclosed. The method involves receiving cardiac CT data indicative of a cardiac CT scan carried out on the patient, and analysing the cardiac CT data to identify plaque volumes to be included in the plaque score, the plaque volumes located on the coronary arteries. The method also includes determining locations of the identified plaque volumes on the coronary arteries, applying machine learning to the cardiac CT data to identify a plurality of primary key points on the coronary arteries, determining a distance between each identified plaque volume and an associated primary key point, and determining a plaque score based on a heart dimension value and, for each identified plaque volume, the determined distance from the identified plaque volume to the associated primary key point.