Side Branch Detection for Angiographic Image Co-Registration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current co-registration techniques for CT coronary angiography and intravascular imaging modalities require manual adjustment of side branch locations, which is time-consuming and prone to errors, and do not allow for live co-registration.

Innovation Solution

The implementation of a cross-modality side branch matching system using machine learning models to automatically identify side branch locations and characteristics from angiographic images, enabling precise alignment with intravascular images.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual adjustment of side branch locations is used for co-registration, then flexibility in handling complex cases is maintained, but time consumption increases and error probability rises

Engineering Contradiction:

Improveco-registration accuracyVSAvoidtime for manual adjustment

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs automatic side branch detection and co-registration without requiring manual physician intervention. The machine learning models automatically identify side branches in angiographic images and match them with intravascular images, allowing the system to serve itself rather than requiring continuous human operation.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces the manual mechanical adjustment process with an automated computational system. Machine learning models detect side branch locations and characteristics, and a computing device performs the co-registration matching, substituting the manual mechanical adjustment process with an automated information processing system.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If manual co-registration techniques are used, then existing imaging modalities can be integrated, but live co-registration capability is lost

Engineering Contradiction:

Improveintegration of imaging modalitiesVSAvoidlive co-registration capability

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system performs preliminary detection of side branch locations and characteristics from angiographic images before the actual co-registration process. By pre-identifying these key anatomical landmarks, the system prepares the necessary information in advance, enabling rapid real-time matching with intravascular images during live procedures.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses side branch locations and characteristics as intermediary elements that bridge different imaging modalities. These detected features serve as common reference points that facilitate the matching and co-registration between angiographic and intravascular images, enabling real-time integration.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If automated machine learning models are used for side branch detection, then time efficiency and consistency improve, but system complexity increases

Engineering Contradiction:

Improvedetection efficiencyVSAvoidmachine learning system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments the complex detection task into distinct components handled by specialized machine learning models. One model detects side branch locations while another detects characteristics such as diameter and orientation. This segmentation of functionality manages complexity by dividing the overall system into modular, specialized components.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250117962A1Side branch detection from angiographic images

Publication Date: 2025.04.10 BOSTON SCIENTIFIC SCIMED INC

AI summary

The present disclosure provides to generate a 3D visualization of a vessel from intravascular ultrasound (IVUS) images. In particular, the present disclosure provides to reduce jitter between frames of an IVUS recording to provide a smoother appearance of a longitudinal view of the vessel from the IVUS image frames and to construct a 3D visualization of the vessel from the jitter compensated IVUS image frames.