Coronary Plaque CT Characterization for Stable Vs. Unstable Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current treatments for cardiovascular disease, such as stents and bypass surgeries, may not be effective for all patients, particularly those with stable heart disease, and there is a need for better understanding of arterial vessel health to determine appropriate treatment plans.
Innovation Solution
Utilizing non-invasive medical imaging technologies, such as CT scans, combined with machine learning and artificial intelligence algorithms to analyze coronary arteries and plaque, and employing a normalization device to calibrate medical images for accurate analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If invasive surgical procedures such as angioplasty and stenting are performed to treat cardiovascular disease, then large blockages in arteries can be opened to increase blood flow, but the procedures carry risks of complications and may not be more effective than drugs for stable heart disease
Solution Approach 1:
The system performs preliminary analysis of arterial plaque characteristics using CT imaging and machine learning algorithms before treatment decisions are made. By预先 identifying plaque vulnerability, composition, and location, the system enables clinicians to determine whether invasive procedures are truly necessary or if medical management would be sufficient, thereby avoiding unnecessary procedural risks
Solution Approach 2:
The invention introduces an intermediate diagnostic step between detecting cardiovascular disease and selecting treatment. The automated plaque analysis system serves as an intermediary that provides detailed characterization of arterial pathology, enabling more informed treatment decisions that balance procedural benefits against potential complications
2Ease of operation
If macro-level biochemical analysis is used to assess cardiovascular health, then treatment decisions can be made based on blood markers, but the analysis lacks detailed information about arterial vessel health and plaque characteristics
Solution Approach 1:
The system segments the arterial tree into individual vessels and further segments plaque into distinct compositional regions (calcified, soft, intermediate). This segmentation provides detailed spatial and compositional information about plaque that is lost in macro-level biochemical analysis, enabling more precise treatment planning
Solution Approach 2:
The invention transitions from one-dimensional biochemical markers to three-dimensional spatial mapping of plaque within arteries. By providing volumetric assessment of plaque burden, composition, and location, the system recovers critical anatomical information that was previously unavailable from blood tests alone
3Measurement precision
If automated machine learning algorithms are used to analyze medical images, then analysis precision and consistency are improved, but the system complexity increases
Solution Approach 1:
The system employs self-training mechanisms where the machine learning algorithms improve automatically through exposure to labeled data. The automated plaque characterization provides ground truth labels that can be used to retrain and refine the models, enabling the system to self-improve precision without proportionally increasing operational complexity
Solution Approach 2:
The invention combines multiple analysis functions (plaque detection, segmentation, characterization, and risk assessment) into a single integrated automated pipeline. By merging these functions, the system achieves high measurement precision through comprehensive analysis while managing complexity through unified processing rather than separate sequential steps
Data Source
AI summary
The disclosure herein relates to systems, methods, and devices for medical image analysis, diagnosis, risk stratification, decision making and/or disease tracking. In some embodiments, the systems, devices, and methods described herein are configured to analyze non-invasive medical images of a subject to automatically and/or dynamically identify one or more features, such as plaque and vessels, and/or derive one or more quantified plaque parameters, such as radiodensity, radiodensity composition, volume, radiodensity heterogeneity, geometry, location, and/or the like. In some embodiments, the systems, devices, and methods described herein are further configured to generate one or more assessments of plaque-based diseases from raw medical images using one or more of the identified features and/or quantified parameters.