Stent Visibility via Image Segmentation and Registration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for producing images of physical objects, such as coronary stents, under fluoroscopy or X-ray exposure runs lack sufficient visibility and information, making it difficult for interventional cardiologists to assess proper deployment and positioning.

Innovation Solution

A method involving the registration and subtraction of two distinct image subsets, one enhanced for the stent and the other for the coronary vessel, using direct registration of predetermined features to generate a final image that improves visibility and provides more information about the stent's placement and apposition to the vessel wall.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Difficulty of detecting and measuring

If image processing techniques are used to enhance stent visibility, then stent visibility is improved, but the generated image does not provide sufficient information about the physical object

Engineering Contradiction:

Improvestent visibilityVSAvoidinformation about physical object

Core Design Contradiction:

Difficulty of detecting and measuringVSLoss of information

Solution Approach 1:

The patent segments the raw images into two distinct subsets: a first subset used to generate an intermediate image enhanced for stent visibility, and a second subset used to generate a mask image enhanced for vessel wall information. This segmentation allows each image type to be optimized for its specific purpose, resolving the contradiction by providing both enhanced stent visibility and comprehensive physical object information through the final composite image.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent merges the intermediate image and mask image through registration and subtraction to produce a final image that combines both stent enhancement and vessel wall information. This merging process integrates the advantages of both image types, simultaneously achieving improved stent visibility and preservation of comprehensive physical object information that neither individual image could provide alone.

Inventive Principle:

Principle #5Merging (Combining)

2Device complexity

If a single image is used to show stent and vessel wall, then the image is simple, but the visibility and information quality are insufficient

Engineering Contradiction:

Improveimage structureVSAvoidstent visibility and apposition assessment

Core Design Contradiction:

Device complexityVSDifficulty of detecting and measuring

Solution Approach 1:

The patent divides the imaging process into separate stages, creating specialized intermediate and mask images from different subsets of raw images. This segmentation allows each image to be optimized for specific detection purposes, with the intermediate image focusing on stent visibility and the mask image focusing on vessel wall characteristics, thereby improving detection capability without excessive complexity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent uses registered feature points as intermediaries to align and combine the intermediate and mask images. These predetermined features serve as mediators that enable accurate registration between the two image types, allowing the final composite image to integrate both stent and vessel wall information with sufficient accuracy for clinical assessment.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of information

If multiple image subsets are processed and registered, then image quality and information are improved, but the processing time and complexity increase

Engineering Contradiction:

Improveinformation completenessVSAvoidprocessing time

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by pre-dividing the raw images into two subsets and pre-processing each subset to generate the intermediate and mask images separately before final registration and subtraction. This preliminary organization and separate processing reduces the computational burden of the final registration step, thereby reducing overall processing time while maintaining information completeness.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent applies different processing qualities to different parts of the imaging process: the first subset undergoes processing optimized for stent visibility enhancement, while the second subset undergoes processing optimized for vessel wall information. This localized optimization of image quality for specific purposes allows efficient processing that maintains information completeness without requiring uniform high-quality processing of all images.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS7941000B2Method for producing an image and system for producing an image

Publication Date: 2011.05.10 KONINKLIJKE PHILIPS NV

AI summary

An image of a physical object is produced by receiving a plurality of raw images, dividing the plurality of raw images into a first subset of primary images and a second subset of secondary images according to a predetermined criterion. From the first subset of primary images an intermediate image is determined while from the second subset of secondary images a mask image is determined. Afterwards a registration of the intermediate image and the mask image is performed by using direct registration of predetermined features present in the intermediate image and the mask image. A fused image of the physical object is generated out of the mask image and the intermediate image.