Automatic OCT TCFA Detection With Gradient and Triangle Thresholding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for detecting thin-cap fibroatheroma (TCFA) in Optical Coherence Tomography (OCT) images are time-consuming, prone to human error, and lack precision, posing a risk of incorrect analysis that can lead to adverse medical outcomes.

Innovation Solution

A method using mathematical algorithms to automatically detect TCFA by processing OCT images, combining 'Gradient Guessing' and 'Triangle Thresholding' algorithms to approximate the fibrous cap border, followed by smoothing and measuring cap thickness, with the option to adjust thresholds for fibrous cap definition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual analysis of OCT images is performed by specialists, then detection accuracy can be maintained, but analysis time becomes excessively long and human error occurs

Engineering Contradiction:
Improvedetection accuracyVSAvoidanalysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical analysis process with an automated image processing system that uses mathematical algorithms (gradient guessing and triangle thresholding) to detect TCFA. This substitution eliminates human labor while maintaining detection accuracy through objective computational methods that can process images rapidly without fatigue or distraction.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the OCT image analysis to be performed automatically without requiring specialist intervention. The automated algorithms independently process the images, detect lipid plaques, measure fibrous cap thickness, and generate diagnostic results, making the system self-sufficient and eliminating dependency on manual analysis.

Inventive Principle:
Principle #25Self-service

2Reliability

If manual analysis is performed, then detailed examination is possible, but human error can lead to incorrect procedures

Engineering Contradiction:
Improvedetection reliabilityVSAvoidhuman error
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent eliminates human error by replacing manual analysis with automated computational algorithms. The system uses objective mathematical methods (gradient guessing and triangle thresholding) that consistently apply the same detection criteria without fatigue, distraction, or subjective bias, thereby eliminating the source of human error entirely.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system incorporates feedback mechanisms where the automated detection results can be reviewed and adjusted. The algorithm provides measurable, quantifiable results (cap thickness measurements, lipid plaque detection) that can be verified and corrected if needed, creating a feedback loop that maintains high reliability while allowing for quality control.

Inventive Principle:
Principle #23Feedback

3Productivity

If automated detection systems are implemented, then analysis time is reduced, but precision and accuracy may be compromised

Engineering Contradiction:
Improveanalysis speedVSAvoiddetection precision
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent achieves both speed and precision by using sophisticated mathematical algorithms that can process images rapidly while maintaining high measurement accuracy. The gradient guessing and triangle thresholding methods are computationally efficient yet produce precise measurements of fibrous cap thickness, eliminating the trade-off between speed and precision that plagues simpler automated systems.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system allows for adjustable parameters and thresholds that can be optimized for different clinical scenarios. By changing detection parameters and threshold values, the system can adapt to maintain precision across various image qualities and patient conditions while consistently delivering fast automated results.

Inventive Principle:
Principle #35Parameter changes

4Stability of the object's composition

If fixed detection criteria are used, then consistency is maintained, but adaptability to changing medical definitions is lost

Engineering Contradiction:
Improvedetection consistencyVSAvoiddefinition adaptability
Core Design Contradiction:
Stability of the object's compositionVSAdaptability or versatility

Solution Approach 1:

The patent implements a dynamic detection system where the algorithms and threshold values can be adjusted to reflect changing medical definitions of TCFA. The system maintains consistency through standardized computational methods while allowing updates to detection criteria, thresholds, and algorithm parameters to accommodate evolving clinical understanding and guidelines.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system enables parameter changes by allowing modification of detection thresholds, cap thickness criteria, and algorithm settings. This flexibility permits the system to adapt to new medical definitions and guidelines while maintaining the structured, consistent approach of automated computational analysis.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4579584A1Method and system for automatic detection and marking of thin-cap fibroatheroma (TCFA) in an oct image
Publication Date: 2025.07.02 DATA JUICE LAB SP ZOO
  • EP4579584A1 patent drawingFigure 1~2
  • EP4579584A1 patent drawingFigure 3~4
  • EP4579584A1 patent drawingFigure 5~6

AI summary

The invention is a method and set-up to detect and mark lipid plaques with thin fibrous cap (TCFA) on Optical Coherence Tomography (OCT) images. Subject of the invention is also a data carrier capable of realizing the invented method.