Coronary CT Plaque Analysis for Non-Invasive Treatment Decisions
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 more accurate assessment of arterial vessel health to determine the best treatment approach.
Innovation Solution
Utilizing non-invasive medical imaging technologies, including CT scans, and machine learning algorithms to analyze coronary arteries and plaque, with a normalization device to improve image calibration, allowing for personalized treatment plans and risk stratification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If invasive surgical procedures (stents, bypass) are performed, then large blockages in arteries are treated, but the procedures may not be effective for all patients and carry procedural risks
Solution Approach 1:
The system performs preliminary assessment of arterial vessel health using non-invasive medical imaging (CT scans) and machine learning analysis before recommending invasive procedures. By quantifying plaque burden, calcification, and stenosis severity in advance, the system identifies which patients will actually benefit from stents or bypass surgery, preventing unnecessary invasive procedures and their associated risks.
Solution Approach 2:
The patent replaces invasive mechanical procedures (catheter-based stenting, surgical bypass) with non-invasive imaging-based assessment and drug therapy recommendations. The machine learning system analyzes medical images to quantify disease severity and guides pharmacological treatment (statins, lifestyle changes) as an alternative to mechanical intervention for stable heart disease patients.
2Measurement precision
If non-invasive medical imaging and machine learning analysis are used, then accuracy of arterial vessel health assessment is improved, but device complexity increases
Solution Approach 1:
The system integrates multiple functions into a single platform: non-invasive CT imaging, machine learning-based image analysis, automated quantification of plaque and calcification, risk stratification, and treatment recommendation. This multi-functional integration achieves high measurement precision while managing complexity through unified software architecture that processes various image types and clinical parameters through standardized algorithms.
Solution Approach 2:
The machine learning system automatically analyzes medical images, quantifies disease severity, and generates treatment recommendations without requiring manual measurement or interpretation by clinicians. The automated image processing algorithms independently extract features, calculate stenosis percentages, and stratify risk, reducing the complexity burden on healthcare providers while maintaining high assessment accuracy.
3Productivity
If invasive procedures are performed on all patients, then treatment coverage is maximized, but unnecessary procedures and complications increase
Solution Approach 1:
The system applies different treatment recommendations based on locally assessed disease characteristics in each patient's arteries. By analyzing specific plaque composition (calcified vs. non-calcified), location, and stenosis severity in individual arterial segments, the system tailors treatment recommendations to each patient's unique anatomy and pathology, avoiding blanket application of invasive procedures to all patients regardless of actual need.
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.