Automated Plaque Classification in Intravascular Ultrasound
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current intravascular ultrasound (IVUS) systems rely on manual analysis by clinicians, leading to variability in plaque classification and potential differences in treatment approaches among observers due to the subjective interpretation of tissue types and their compositions within vascular images.
Innovation Solution
An automated plaque classification system that applies a classification criterion to IVUS images, analyzing the amount and location of characterized tissue types to render standardized plaque classifications such as adaptive intimal thickening, pathological intimal thickening, fibroatheroma, thin-cap fibroatheroma, and fibro-calcific plaques, enabling real-time identification of vulnerable plaque events and risk assessment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If manual analysis by clinicians is used, then flexibility in interpretation is maintained, but variability in plaque classification and treatment approaches increases
Solution Approach 1:
The patent introduces an automated analysis system as an intermediary between the IVUS imaging system and clinical decision-making. This system processes tissue characterization data through predefined algorithms and classification criteria, producing standardized plaque classifications that reduce observer variability while maintaining clinical relevance. The automated system acts as a mediator that translates raw imaging data into consistent diagnostic categories.
Solution Approach 2:
The patent replaces the manual mechanical process of clinician interpretation with an automated computational system. Instead of relying on human observers to manually analyze tissue characteristics and assign classifications, the system uses automated image processing, spectral analysis, and algorithmic classification to generate standardized results, thereby eliminating inter-observer variability.
2Measurement precision
If automated classification is implemented, then classification consistency is improved, but system complexity increases
Solution Approach 1:
The automated classification system is divided into distinct functional modules: tissue characterization module, plaque classification module, and vulnerability assessment module. Each module performs a specific function and processes data in a structured sequence. This segmentation allows the complex overall task to be broken down into manageable components that can be developed, validated, and maintained independently.
Solution Approach 2:
The system incorporates automated quality control and self-validation mechanisms that reduce the need for manual intervention. The classification algorithm automatically adjusts parameters based on image quality metrics, and the system provides built-in consistency checks to ensure reliable results without requiring constant operator calibration or adjustment.
3Measurement precision
If detailed tissue characterization is performed, then diagnostic accuracy is improved, but analysis time increases
Solution Approach 1:
The system performs preliminary tissue characterization during the IVUS imaging acquisition phase, extracting spectral features and tissue properties in real-time as the catheter pulls back through the vessel. This preliminary processing allows the detailed analysis to be completed before the clinician needs to make treatment decisions, eliminating delays in the diagnostic workflow.
Solution Approach 2:
The automated classification system operates continuously during the IVUS pull-back procedure, analyzing tissue characteristics in real-time as each cross-sectional image is acquired. This continuous processing eliminates the need for batch processing or post-acquisition analysis, providing immediate diagnostic results without interrupting the procedural flow.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system provides consistent and objective plaque classification, enabling immediate interventional actions and reducing variability in diagnosis, thereby improving patient outcomes by accurately identifying high-risk plaque lesions and their locations within blood vessels.
Implementation Method 1
Acoustic signals are transmitted and echoes (or backscatter) from these acoustic signals are received. The backscatter data is used to identify the type or density of a scanned tissue.
Data Source
AI summary
A system and method are disclosed for automatically classifying plaque lesions. A plaque classification application applies a plaque classification criterion to at least one graphical image, comprising a map of spectrally-analyzed characterized tissue of a vessel cross-section, to render an overall plaque classification for the slice or set of slices, covering a 3D volume. The plaque classification is based upon the amount and location of each characterized tissue type (e.g., necrotic core—NC). In an exemplary embodiment the set of potential plaque classifications, not to be confused with characterized tissue types—from which the plaque classifications are derived—include, for example: adaptive intimal thickening (AIT), pathological intimal thickening (PIT), fibroatheroma (FA), thin-cap fibroatheroma (TCFA), and fibro-calcific (FC).