Intravascular Ultrasound Lumen Border Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current intravascular ultrasound (IVUS) systems require significant manual corrections for accurate lumen border detection, which is time-consuming and lacks sufficient accuracy in large patient datasets, necessitating a fully automated and high-accuracy method for vascular lumen border identification.

Innovation Solution

A method and system that process a sequence of IVUS frames by determining texture and flow features to characterize regions as within or outside the lumen, using processor-executable instructions to derive and display the lumen border, enabling automated and precise lumen border detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual corrections are used for lumen border detection, then accuracy can be improved, but procedural time increases significantly

Engineering Contradiction:
Improvelumen border detection accuracyVSAvoidprocedural time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary automated lumen border detection using texture and flow features before manual review, pre-processing the image sequence to identify candidate borders that reduce the scope of required manual corrections

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system enables semi-automated detection where the automated algorithm performs the primary detection work and the operator only needs to review and correct errors, rather than performing complete manual detection

Inventive Principle:
Principle #25Self-service

2Productivity

If fully automated detection is implemented, then productivity increases, but measurement precision may deteriorate

Engineering Contradiction:
Improvedetection speedVSAvoidlumen border detection accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system incorporates feedback mechanisms where detection results are evaluated and used to refine subsequent detections, with operator corrections feeding back into the automated system to improve future accuracy

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically adjusts detection parameters such as texture analysis thresholds and flow feature weights based on image quality and vessel characteristics, optimizing the balance between speed and accuracy for different clinical scenarios

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If multiple features are analyzed for each region, then detection accuracy improves, but device complexity increases

Engineering Contradiction:
Improveregion characterization accuracyVSAvoidprocessing system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The analysis is segmented into distinct stages: texture feature extraction, flow feature extraction, and integrated border detection. Each stage processes specific features independently, managing complexity through modular organization of the processing pipeline

Inventive Principle:
Principle #1Segmentation

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 a fully automated and accurate lumen border detection, reducing procedural time and improving workflow by exploiting texture and flow features in IVUS frames, enhancing the accuracy of vascular measurements and visualization.

Implementation Method 1

The pulse generator in the control module generates electrical pulses that are delivered to the one or more transducers and transformed to acoustic pulses that are transmitted through patient tissue. Reflected pulses of the transmitted acoustic pulses are absorbed by the one or more transducers and transformed to electric pulses.

Methodology Applied
Scientific EffectPiezoelectric effect: Piezoelectric Effect

Data Source

PatentEP2962283B1Systems and methods for lumen border detection in intravascular ultrasound sequences
Publication Date: 2019.09.25 BOSTON SCIENTIFIC SCIMED INC
  • EP2962283B1 patent drawingFigure 1
  • EP2962283B1 patent drawingFigure 2
  • EP2962283B1 patent drawingFigure 3

AI summary

A method for processing a sequence of ultrasound frames for display includes receiving a sequence of intravascular ultrasound (IVUS) frames of a vessel having a lumen, the sequence including a first frame and a second frame; determining one or more texture features for each of one or more regions of the first frame; determining at least one flow feature for each of the one or more regions by comparing the first and second frames; deriving a lumen border for the first frame using the one or more texture features and the at least one flow feature to characterize the one or more regions as within or outside of the lumen of the vessel; and displaying an ultrasound image of the first frame with the lumen border.