Multi-organ Registration Using Adaptive Spatial Support

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing registration algorithms for medical imaging data struggle to accurately model the complex motion and interactions of multiple organs, due to varying degrees of deformation, motion directions, and tissue properties.

Innovation Solution

A system that computes spatial mappings between imaging data using a combination of point distance and feature-based measures, with adaptive spatial support, allowing for registration of multiple organs and their interactions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If B-spline functions or radial basis functions are used to model deformations, then local level deformations can be captured, but large coherent motion cannot be captured effectively

Engineering Contradiction:

Improvelocal deformation modeling precisionVSAvoidcapability to capture large coherent motion

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent divides the deformation field into multiple levels with different spatial supports. Large-scale deformations are modeled using global basis functions, while local deformations are captured using local basis functions. This hierarchical segmentation allows simultaneous capture of both large coherent motion and fine local details without the limitations of single-level approaches.

Inventive Principle:

Principle #1Segmentation

2Adaptability or versatility

If non-parametric deformations are used, then image quality dependence increases, but modeling flexibility improves

Engineering Contradiction:

Improvedeformation modeling flexibilityVSAvoiddependence on image quality

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent transforms the non-parametric deformation problem into a parametric one by representing deformations using basis function expansions with controllable parameters. This allows regularization through parameter constraints, reducing dependence on image quality while maintaining modeling flexibility. The parametric formulation enables stable optimization even with noisy or low-quality images.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If biomechanical finite-element models are used, then tissue property knowledge is required, but registration accuracy for specific tissues improves

Engineering Contradiction:

Improveregistration accuracy for specific tissuesVSAvoiddependence on tissue biomechanical properties

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent develops a universal registration framework using basis functions that can model deformations for any tissue type without requiring specific biomechanical properties. The method is multi-functional, handling both rigid and soft tissue deformations, as well as various organ types, through a unified mathematical formulation that does not depend on tissue-specific mechanical models.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Adaptability or versatility

If large spatial support is used in deformation modeling, then global motion is captured, but sharp local motion changes cannot be resolved

Engineering Contradiction:

Improvecapability to capture global motionVSAvoidsharp local motion change detection

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent segments the deformation field into multiple scales using basis functions with different spatial supports. Global deformations are captured by basis functions with large support, while local sharp changes are resolved by basis functions with small support. This multi-scale segmentation enables simultaneous capture of both global coherent motion and local sharp transitions.

Inventive Principle:

Principle #1Segmentation

5Measurement precision

If small spatial support is used in deformation modeling, then local deformations are captured, but large coherent motion cannot be modeled

Engineering Contradiction:

Improvelocal deformation capture precisionVSAvoidcapability to model large coherent motion

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent implements a hierarchical deformation model where small-support basis functions capture local deformations and large-support basis functions capture global coherent motion. The segmentation of the deformation field into multiple spatial scales allows each basis function to operate at its optimal scale, with local and global components combined to achieve comprehensive deformation modeling.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS20250111526A1Multi-organ registration system and method

Publication Date: 2025.04.03 SIEMENS HEALTHINEERS AG

AI summary

A system comprises: an input module configured to obtain imaging data of a tissue part of an organ of a patient at a time point; a computing module configured to compute at least one spatial mapping between the imaging data and corresponding reference imaging data, wherein the at least one spatial mapping is determined based on a point distance measure and a feature-based measure, wherein the at least one spatial mapping incorporates an adaptive spatial support, and wherein the reference imaging data is obtained from a database or obtained by the input module corresponding to a different time point and/or to a different patient than the imaging data; a registration module configured to process the obtained imaging data and the reference imaging data using the at least one computed spatial mapping and to generate registration information; and an output module configured to output the registration information.