AI Plaque Analysis From CT Images for Coronary Risk Stratification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current treatments for cardiovascular disease, such as stents and bypass surgeries, may not be effective for patients with stable heart disease, and existing methods like angiography and blood chemistry analysis fail to accurately identify high-risk plaque areas, leading to potential misdiagnosis and invasive procedures.
Innovation Solution
Non-invasive medical imaging technologies, including CT scans, are used with machine learning and AI algorithms to analyze coronary arteries and plaque, generating treatment plans and patient-specific reports, and a normalization device normalizes images for accurate analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If invasive surgical procedures like angioplasty and stenting are performed to treat cardiovascular disease, then arterial blockages can be mechanically opened, but the procedures carry surgical risks and may not be effective for all patient types
Solution Approach 1:
The patent replaces mechanical imaging systems (angiography) with non-invasive imaging technologies (CT, MRI, ultrasound) to visualize arterial blockages without requiring catheter insertion or contrast injection into the heart, thereby eliminating surgical risks while maintaining diagnostic capability
Solution Approach 2:
The patent introduces AI algorithms as an intermediary between image acquisition and clinical decision-making, automatically analyzing medical images to detect and characterize plaque burden, composition, and vulnerability, thereby reducing reliance on invasive procedures for diagnosis
2Measurement precision
If traditional imaging methods like angiography are used to assess cardiovascular health, then large blockages can be identified, but the methods fail to accurately identify high-risk plaque areas and provide comprehensive arterial health assessment
Solution Approach 1:
The patent transitions from two-dimensional angiographic projections to three-dimensional volumetric imaging using CT and MRI, enabling comprehensive assessment of plaque burden, composition (calcified vs. soft plaque), and arterial wall characteristics that cannot be obtained with traditional angiography
Solution Approach 2:
The patent utilizes dual-energy CT and contrast-enhanced MRI to measure multiple parameters simultaneously including plaque density, iodine concentration, vasa vasorum activity, and arterial wall inflammation, providing comprehensive plaque characterization beyond simple luminal narrowing detection
3Loss of information
If non-invasive medical imaging with AI analysis is implemented to assess arterial health, then comprehensive plaque characterization and personalized treatment decisions can be achieved, but the system complexity and computational requirements increase
Solution Approach 1:
The patent performs preliminary processing of medical images including noise reduction, artifact correction, and plaque segmentation using trained AI models before clinical interpretation, thereby simplifying the final diagnostic workflow and reducing the complexity burden on clinicians
Solution Approach 2:
The patent develops multi-functional AI algorithms that can analyze multiple imaging modalities (CT, MRI, ultrasound) and extract various plaque characteristics (burden, composition, vulnerability) using unified computational frameworks, thereby managing system complexity through standardized processing pipelines
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.