IVUS Object Detection Using Radial Line Probability Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current intravascular ultrasound (IVUS) data representation methods struggle to provide intuitive and comprehensive analysis of vascular structures and implanted objects, often missing details like side branches and stent positions due to limited cross-sectional views.

Innovation Solution

An ultrasound data analysis method that condenses radial scan line data into single representative values, such as maximum intensity or standard deviation, to generate a 2D map for easier detection of intravascular objects like stents, sheaths, and anatomical features by identifying characteristic patterns and contrasts.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional machine learning methods are used for ultrasound image analysis, then computational resources are consumed, but processing speed and real-time capability deteriorate

Engineering Contradiction:
Improveanalysis accuracyVSAvoidprocessing speed
Core Design Contradiction:
Measurement precisionVSSpeed

Solution Approach 1:

The system segments the ultrasound analysis task into two distinct parts: a training phase using traditional machine learning to build a classification model, and an execution phase using the pre-trained model for rapid real-time classification. This segmentation allows computationally intensive operations to be performed only during training, while inference occurs quickly during actual use.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary action by pre-training the machine learning model offline before deployment. The trained model is then deployed to mobile devices where it can perform classification without requiring real-time computational resources, enabling fast processing on resource-constrained devices.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If complex machine learning models are deployed on mobile devices, then analysis capability is improved, but device complexity and resource requirements worsen

Engineering Contradiction:
Improveclassification accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system replaces the need for complex runtime machine learning computations with a pre-trained classification model that can be executed efficiently on mobile devices. The complex training process is performed separately using more powerful computing resources, while the deployed model requires minimal computational overhead.

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

3Productivity

If ultrasound images are processed in real-time, then productivity is improved, but measurement precision may worsen due to reduced processing time

Engineering Contradiction:
Improvereal-time processing capabilityVSAvoidanalysis accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system segments the processing workflow into offline training (high precision, low speed) and online inference (high speed, maintained precision). The pre-trained model captures complex patterns during training, enabling accurate real-time classification without requiring intensive computations during actual processing.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentEP3923818B1Ultrasound analysis method and device
Publication Date: 2026.05.13 KONINKLIJKE PHILIPS NV
  • EP3923818B1 patent drawingFigure 1~3
  • EP3923818B1 patent drawingFigure 4~6
  • EP3923818B1 patent drawingFigure 7~10

AI summary

The invention provides an ultrasound data processing method (30) for detecting presence of an intravascular object in a vessel lumen based on analysis of acquired intravascular ultrasound data of the lumen. The method comprises receiving (32) data comprising multiple frames, and each frame containing data for a plurality of radial lines, corresponding to different circumferential positions around the IVUS device body, and reducing (34) the data to a single representative value for each radial line in each frame. These representative values are subsequently processed to derive (36) values for at least each frame representative of a probability of presence of an object within the given frame. Based on the probability values, a region within the data occupied by an intravascular object, for instance a consecutive set of frames occupied by an object, is determined (38).