Static to Dynamic Medical Image Registration via Automated Segmentation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current medical imaging techniques, such as CT and MRI, provide static anatomical information that is difficult for physicians to accurately register with dynamic intra-procedural data during minimally invasive cardiac procedures, leading to mental registration challenges and potential inaccuracies, especially in moving anatomy.

Innovation Solution

An image processing system that automatically segments and registers static pre-procedural data with dynamic intra-procedural data, using a processor module to compare and update annotations, ensuring accurate overlay of static and dynamic information during procedures, reducing systematic errors like landmark drifting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If static pre-procedural imaging (CT/MRI) is used for anatomical detail, then anatomical structure depiction is improved, but dynamic intra-procedural registration accuracy deteriorates due to mental registration requirements

Engineering Contradiction:

Improveanatomical structure depictionVSAvoidregistration accuracy

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent introduces an intermediary registration system that automatically aligns static pre-procedural images with dynamic intra-procedural images. This intermediary computational process mediates between the two imaging modalities, performing automated feature matching and transformation calculations to produce accurate registered images without requiring physician mental registration, thereby resolving the contradiction between anatomical detail and registration accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the mechanical/ cognitive process of mental registration with an automated computational image processing system. The system uses algorithms for feature detection, matching, and geometric transformation to automatically register images, substituting the physician's working memory and manual alignment efforts with a reliable computational mechanism that maintains both anatomical detail and registration accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Adaptability or versatility

If manual mental registration is performed by the physician, then flexibility in handling different imaging modalities is improved, but time consumption and effort increase

Engineering Contradiction:

Improvehandling flexibilityVSAvoidregistration time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent implements a self-service automated registration system that performs image alignment without requiring physician intervention. The system automatically detects features, computes transformations, and generates registered images independently, freeing the physician from time-consuming manual registration tasks while maintaining adaptability to different imaging modalities through configurable processing algorithms

Inventive Principle:

Principle #25Self-service

3Loss of information

If static imaging data is used for planning, then comprehensive anatomical information is improved, but dynamic anatomical changes are lost

Engineering Contradiction:

Improveanatomical information completenessVSAvoiddynamic anatomy adaptation

Core Design Contradiction:

Loss of informationVSAdaptability or versatility

Solution Approach 1:

The patent merges static pre-procedural imaging data with dynamic intra-procedural imaging data through automated registration. By combining the comprehensive anatomical information from static CT/MRI images with the real-time dynamic information from intra-procedural ultrasound, the system creates a fused representation that preserves both complete anatomical detail and dynamic anatomical changes, eliminating the trade-off between information completeness and adaptability

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS11257219B2Registration of static pre-procedural planning data to dynamic intra-procedural segmentation data

Publication Date: 2022.02.22 KONINKLIJKE PHILIPS NV

AI summary

Imaging systems and methods are provided, which involve acquiring static volume data using a first imaging technique; segmenting the static volume data to generate a static segmentation; annotating the static segmentation with at least one annotation; acquiring initial dynamic volume data using a second imaging technique different to the first imaging technique; segmenting the initial dynamic volume data to generate a plurality of dynamic segmentations; comparing the static segmentation to each one of the plurality of dynamic segmentations and determining, using the comparisons, a single dynamic segmentation that most closely corresponds to the static segmentation; storing the corresponding single dynamic segmentation in the memory as a reference segmentation; acquiring subsequent dynamic volume data; segmenting the subsequent dynamic volume data to generate at least one subsequent dynamic segmentation; determining a difference between the reference segmentation and the subsequent dynamic segmentation; updating the at least one annotation using the determined difference; and displaying the at least one updated annotation together with the subsequent dynamic volume data.