Coronary Plaque CT Analysis for Personalized 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 there is a need for a more accurate understanding of arterial vessel health to determine appropriate treatment strategies.
Innovation Solution
Utilizing non-invasive medical imaging technologies, such as CT scans, with machine learning algorithms and normalization devices to analyze coronary arteries and plaque, generating personalized treatment plans and risk assessments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If invasive surgical procedures such as angioplasty and stent placement are performed to treat cardiovascular disease, then arterial blockages can be mechanically opened and blood flow improved, but patients may undergo unnecessary invasive procedures with associated complications and risks
Solution Approach 1:
The system performs preliminary quantitative analysis of arterial blockages using medical imaging and machine learning algorithms before treatment decisions are made. This preliminary characterization of plaque burden and arterial health allows clinicians to determine whether invasive procedures are truly necessary or if less invasive treatments would suffice, thereby preventing unnecessary procedural complications
2Measurement precision
If machine learning algorithms are used to automatically analyze medical images and generate treatment recommendations, then analysis accuracy and personalization improve, but system complexity and computational requirements increase
Solution Approach 1:
The patent employs trained medical professionals as intermediaries who review and validate the machine learning algorithm's quantitative analysis results before final treatment decisions are made. This intermediary human review layer maintains high measurement precision by catching potential algorithm errors while preventing excessive system complexity from fully automating the decision-making process
3Adaptability or versatility
If quantitative analysis of arterial blockages and plaque is performed using medical imaging and machine learning, then personalized treatment planning is enabled, but time and computational resources required for analysis increase
Solution Approach 1:
The system performs preliminary quantitative characterization of arterial anatomy and plaque burden using automated machine learning analysis of routinely acquired medical images. This preliminary quantitative assessment is performed before treatment planning meetings, enabling personalized treatment recommendations to be prepared in advance rather than requiring time-consuming analysis during clinical decision-making
Solution Approach 2:
The machine learning algorithms automatically perform the quantitative analysis without requiring manual measurement or interpretation by clinicians. The system self-services the complex computational tasks of segmenting arteries, quantifying plaque volume, and generating treatment recommendations, freeing clinicians from time-consuming manual analysis while enabling personalized treatment planning
Data Source
Figure 1
Figure 2A
Figure 2B
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.