AI-Based Coronary Plaque Analysis for Non-Invasive Risk Assessment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for treating cardiovascular disease, such as angioplasty and heart bypass surgeries, may not be the most effective for all patients, as evidenced by a recent study showing that stents and bypass procedures are no more effective than drug combinations with lifestyle changes for those with stable heart disease, leading to a need for more accurate and non-invasive analysis of arterial plaque to determine appropriate treatment plans.
Innovation Solution
The development of non-invasive image-based systems and methods for analyzing coronary plaque using CT images and AI/machine learning algorithms to quantify and classify plaque, allowing for the generation of personalized treatment plans and risk assessments based on plaque characteristics, such as distance, volume, shape, and morphology.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If invasive procedures such as angioplasty and bypass surgeries are performed, then treatment effectiveness for cardiovascular disease is improved, but patient risk and invasiveness increase
Solution Approach 1:
The system performs preliminary plaque analysis using CT imaging and AI algorithms to assess plaque characteristics, vulnerability, and risk factors before treatment decisions are made. This advance assessment allows clinicians to determine which patients truly need invasive procedures versus those who can be managed with less invasive approaches, thereby reducing unnecessary patient risk while maintaining treatment effectiveness for those who require it.
Solution Approach 2:
The patent introduces an intermediary assessment system that bridges the gap between initial diagnosis and treatment decision-making. This intermediate plaque characterization system provides detailed information about plaque composition, morphology, and stability, enabling more informed treatment decisions that balance effectiveness with patient safety and minimize unnecessary invasive procedures.
2Reliability
If invasive procedures are used for all patients, then treatment coverage is improved, but resource utilization and unnecessary surgeries increase
Solution Approach 1:
The system applies local quality assessment by analyzing specific plaque characteristics in different locations and contexts. Rather than applying a uniform treatment approach to all patients, the system evaluates local plaque features such as composition, morphology, and vulnerability to determine the appropriate level of intervention for each specific case, thereby optimizing resource utilization while maintaining adequate treatment coverage.
Solution Approach 2:
The patent utilizes parameter changes in plaque characteristics as the basis for treatment stratification. By measuring and analyzing multiple plaque parameters (composition, volume, morphology, vulnerability indicators), the system transforms these measurements into actionable treatment recommendations that match intervention intensity to disease severity, reducing unnecessary procedures while ensuring adequate coverage for high-risk patients.
3Measurement precision
If detailed plaque analysis is performed, then treatment accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments the plaque analysis process into distinct functional modules: CT image acquisition, image preprocessing, plaque segmentation, characteristic extraction, and risk assessment. Each module performs a specific function and can be independently optimized or validated. This segmentation allows for high measurement precision in each component while managing overall system complexity through modular architecture.
Solution Approach 2:
The patent replaces manual plaque analysis with automated AI-based image analysis systems. The mechanical/manual process of visual inspection and measurement by clinicians is substituted with computational algorithms that automatically extract plaque characteristics from CT images. This substitution maintains high measurement precision while reducing the complexity burden on the clinical workflow.
Data Source
AI summary
Various embodiments described herein relate to systems, devices, and methods for non-invasive image-based plaque analysis and risk determination. In particular, in some embodiments, the systems, devices, and methods described herein are related to analysis of one or more regions of plaque, such as for example coronary plaque, using non-invasively obtained images that can be analyzed using computer vision or machine learning to identify, diagnose, characterize, treat and/or track coronary artery disease.