Respiratory Motion Validation via Conformity Measure

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing motion estimation validation methods often result in erroneous deformation vector fields due to incorrect weighting of forces during image registration, leading to potential misalignment and folding in non-rigid transformations, particularly in respiratory motion compensation.

Innovation Solution

A system that computes a conformity measure based on a vector-field-based metric of local volume change and image intensity, using a hyperbolic function to fit joint distributions, to validate deformation vector fields and detect peaks indicating mis-registration, allowing for local validation and potential updates to the deformation vector field.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If a large weight is applied to the outer force in image registration, then the residuum image becomes smaller (better alignment), but incorrect deformations and folding are introduced into the DVF

Engineering Contradiction:
Improvealignment accuracyVSAvoidDVF validity
Core Design Contradiction:
Manufacturing precisionVSReliability

Solution Approach 1:

The patent implements a feedback mechanism by computing a conformity measure from the DVF and comparing it against expected physiological ranges. This feedback loop allows the system to detect and reject erroneous deformations while preserving accurate alignments, resolving the contradiction between alignment accuracy and DVF validity.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent changes the parameter validation approach by introducing a conformity measure that evaluates whether DVF values fall within physiologically plausible ranges. This parameter-based validation allows the system to accept accurate deformations while rejecting folding artifacts, thereby maintaining both alignment quality and DVF reliability.

Inventive Principle:
Principle #35Parameter changes

2Manufacturing precision

If the residuum image is used for validating DVF, then alignment quality is assessed, but erroneous DVF may be validated due to invariance to deformation in homogeneous regions

Engineering Contradiction:
Improveregistration qualityVSAvoidvalidation accuracy
Core Design Contradiction:
Manufacturing precisionVSMeasurement precision

Solution Approach 1:

The patent introduces a conformity measure as an intermediary validation step between DVF computation and final acceptance. This intermediary assessment evaluates whether the computed deformations are physiologically plausible, adding a layer of validation that overcomes the limitations of residuum-based assessment in homogeneous regions.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Manufacturing precision

If non-rigid transformation is used for respiratory motion compensation, then motion alignment is improved, but folding and incorrect deformations may occur

Engineering Contradiction:
Improvemotion alignmentVSAvoidanatomical structure integrity
Core Design Contradiction:
Manufacturing precisionVSStability of the object's composition

Solution Approach 1:

The patent applies parameter-based validation by checking whether DVF values fall within physiologically expected ranges for respiratory motion. This constraint on deformation parameters prevents folding and unrealistic anatomical transformations while preserving the flexibility of non-rigid registration for accurate motion compensation.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP2591459B1Automatic point-wise validation of respiratory motion estimation
Publication Date: 2016.09.07 PHILIPS INTPROP & STANDARDS GMBH
  • EP2591459B1 patent drawingFigure 1
  • EP2591459B1 patent drawingFigure 2A~2B
  • EP2591459B1 patent drawingFigure 2C~2D

AI summary

A system for validating motion estimation comprising a field unit (110) for obtaining a deformation vector field (DVF) estimating the motion by transforming a first image at a first phase of the motion into a second image at a second phase of the motion, a metric unit (120) for computing a metric of a local volume change at a plurality of locations, and a conformity unit(130) for computing a conformity measure based on the computed metric of the local volume change at the plurality of locations and a local property of the first or second image defined at the plurality of locations. Based on the value of the conformity measure, the DFV estimating the motion is validated. Experiments show that the conformity measure based on the computed metric of a local volume change at a plurality of locations and the local property of the first or second image, defined at the plurality of locations, does not necessarily favor a large weight for the outer force to provide a more accurate registration. One reason for this observation may be that large deformations providing more accurate alignment often lead to deformations resulting in unreasonably large volume changes. DVFs comprising such deformations thus are more likely to be discarded by the system of the invention.