X-Ray Vascular Feature Detection And Registration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing x-ray imaging technologies face challenges in achieving accurate visualization and registration of vascular structures during intravascular imaging, particularly due to the obscuration of imaging probes by contrast solutions and the interference of guidewires and catheters.

Innovation Solution

The disclosure presents methods for detecting the position and size of contrast clouds in x-ray images, extracting metallic guidewires, and registering vascular trees across multiple frames, which enhances image processing and feature detection, thereby improving cross-frame registration accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Illumination intensity

If contrast solution is injected to enhance imaging of blood vessels via angiography, then vascular structure visualization is improved, but optical and acoustic imaging probes are obscured

Engineering Contradiction:
Improvevascular structure visualizationVSAvoidimaging probe visibility
Core Design Contradiction:
Illumination intensityVSLoss of information

Solution Approach 1:

The system separates the imaging modalities by using x-ray imaging for vascular structure visualization during contrast injection, while using intravascular optical/acoustic imaging probes for complementary tissue characterization. The segmentation allows each modality to operate in its optimal performance range without mutual interference.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces image registration and co-registration algorithms as intermediaries to integrate data from multiple imaging modalities. These computational methods correlate x-ray angiographic images with intravascular optical coherence tomography (OCT) or ultrasound images, allowing the system to overcome the obscuration problem by fusing information from different sources.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If guidewires and catheters are used in the vasculature, then procedural intervention capability is improved, but certain landmarks are obscured and imaging analysis is interfered with

Engineering Contradiction:
Improveprocedural intervention capabilityVSAvoidlandmark detection
Core Design Contradiction:
Adaptability or versatilityVSDifficulty of detecting and measuring

Solution Approach 1:

The system applies different image processing techniques to different regions of the image. Areas obscured by guidewires or catheters are processed using specialized algorithms that can detect landmarks in less obstructed regions, while maintaining procedural intervention capability in the obscured areas.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent uses multiple imaging modalities (x-ray angiography, intravascular OCT, ultrasound) that provide information from different dimensions and perspectives. By co-registering these multi-dimensional datasets, the system can identify landmarks that may be obscured in one modality but visible in another.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Loss of information

If multiple imaging modalities are combined for intravascular imaging, then diagnostic information is improved, but imaging and co-registration challenges become more complex

Engineering Contradiction:
Improvediagnostic information completenessVSAvoidimaging and co-registration complexity
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The system employs universal image registration algorithms that can handle multiple imaging modalities (x-ray, OCT, ultrasound) through a unified computational framework. This multi-functional approach allows the same core algorithms to process and co-register different types of imaging data, reducing overall system complexity despite the diversity of modalities.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent implements feedback mechanisms in the image registration process, where the system continuously refines the alignment between different imaging modalities by comparing anatomical features and adjusting transformation parameters. This iterative feedback approach improves co-registration accuracy while providing a systematic method to manage the complexity of multiple imaging sources.

Inventive Principle:
Principle #23Feedback

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

These methods enable more accurate detection of vascular features, reduce registration errors, and enhance the accuracy of cross-frame registration, facilitating better diagnostic and procedural outcomes in vascular imaging.

Implementation Method 1

An injection or other delivery contrast solution renders the artery radiopaque for angiography or other x-ray related imaging methods

Methodology Applied
Scientific EffectX-ray attenuation: X-Ray

Implementation Method 2

The injection of contrast solution to enhance imaging of blood vessels via angiography

Methodology Applied
Scientific EffectRadiopaque contrast absorption: Absorption (EM radiation)

Data Source

PatentUS20250127475A1X-Ray Image Feature Detection And Registration Systems And Methods
Publication Date: 2025.04.24 LIGHTLAB IMAGING LLC
  • US20250127475A1 patent drawing
  • US20250127475A1 patent drawing
  • US20250127475A1 patent drawing

AI summary

The disclosure relates generally to the field of vascular system and peripheral vascular system data collection, imaging, image processing and feature detection relating thereto. In part, the disclosure more specifically relates to methods for detecting position and size of contrast cloud in an x-ray image including with respect to a sequence of x-ray images during intravascular imaging. Methods of detecting and extracting metallic wires from x-ray images are also described herein such as guidewires used in coronary procedures. Further, methods for of registering vascular trees for one or more images, such as in sequences of x-ray images, are disclosed. In part, the disclosure relates to processing, tracking and registering angiography images and elements in such images. The registration can be performed relative to images from an intravascular imaging modality such as, for example, optical coherence tomography (OCT) or intravascular ultrasound (IVUS).