Vessel Segmentation Using Adaptive Thresholds for Boundary Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current medical imaging techniques for blood vessel segmentation, such as CT and MRI, face challenges in accurately determining vessel boundaries due to variations in contrast medium intensity over time, distance, and vessel size, leading to inaccuracies in 3D reconstruction and visualization.

Innovation Solution

A vessel segmentation method that sets multiple threshold values based on data from a database, considering intensity characteristics and physiological factors, to accurately determine vessel boundaries by adjusting threshold values according to the intensity of the contrast medium in each cross-section, thereby improving segmentation accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single threshold value is used for vessel segmentation, then the segmentation process is simple and fast, but the accuracy of vessel boundary determination deteriorates due to variations in contrast medium intensity

Engineering Contradiction:
Improvevessel boundary determination accuracyVSAvoidthreshold setting complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies local quality by setting different threshold values for different cross-sections of blood vessels based on their specific contrast medium intensity characteristics. Each cross-section receives a customized threshold value tailored to its local intensity profile, thereby improving vessel boundary determination accuracy while accounting for spatial variations in contrast enhancement.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements dynamics by making threshold values adaptive rather than static. The threshold for each cross-section is dynamically determined based on the measured contrast medium intensity at that location, allowing the segmentation process to adapt to varying intensity conditions throughout the vascular structure.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If multiple threshold values are set based on contrast medium intensity data, then vessel segmentation accuracy is improved, but the processing time and computational complexity increase

Engineering Contradiction:
Improvevessel segmentation accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary action by pre-acquiring and storing contrast medium intensity data in a database before performing vessel segmentation. This preparatory step allows the system to quickly retrieve appropriate threshold values during segmentation without performing complex calculations in real-time, thereby reducing processing time while maintaining high accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent uses copying by creating a lookup table or database of pre-computed threshold values based on contrast medium intensity characteristics. During segmentation, the system copies the appropriate threshold value from this database rather than recalculating it, significantly reducing computational overhead and processing time.

Inventive Principle:
Principle #26Copying

3Measurement precision

If higher contrast medium intensity is used to improve vessel visualization, then segmentation accuracy improves, but the amount of contrast medium required increases leading to greater adverse effects

Engineering Contradiction:
Improvesegmentation accuracyVSAvoidadverse effects of contrast medium
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent applies parameter changes by shifting the optimization parameter from contrast medium intensity to threshold value selection. Instead of increasing contrast medium dosage to improve visualization, the system adjusts the threshold parameter based on the actual contrast intensity present, achieving high segmentation accuracy with lower contrast medium amounts and reduced adverse effects.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP2693401B1Vessel segmentation method and apparatus using multiple thresholds values
Publication Date: 2019.01.09 SAMSUNG ELECTRONICS CO LTD
  • EP2693401B1 patent drawingFigure 1
  • EP2693401B1 patent drawingFigure 2
  • EP2693401B1 patent drawingFigure 3

AI summary

A vessel segmentation method includes acquiring an image of a blood vessel, including cross sections, using a contrast medium. The method further includes setting a threshold value for each of the cross sections based on data of an intensity of the contrast medium. The method further includes performing vessel segmentation based on the image and the threshold value for each of the cross sections.