Medical Image Deformation Correction via Deviation Feedback

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for deformation correction in medical imaging, such as using deformation models based on material parameters or manual adjustments, are inadequate for accurately representing anatomical structures and medical objects within vessels, particularly at orifices and vessel bifurcations, due to insufficient correction of vessel and tissue deformation during procedures.

Innovation Solution

A method involving the reception of preoperative 3D image data, segmentation of anatomical structures, registration with intraoperative image data, and application of a deformation rule to correct deviations, allowing for intuitive and precise correction of anatomical structure deformations using trained functions and deformable models.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If deformation models based on material parameters or manual adjustments are used, then the correction process can be performed, but the accuracy of anatomical structure representation deteriorates, particularly at orifices and vessel bifurcations

Engineering Contradiction:

Improveaccuracy of anatomical structure representationVSAvoidinsufficiency of correction at orifices and vessel bifurcations

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system automatically detects deviations between preoperative and intraoperative images and uses this feedback to iteratively optimize deformation rules. The deviation detection mechanism continuously monitors correction accuracy and adjusts deformation parameters to improve representation at critical locations like orifices and bifurcations.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system dynamically adjusts deformation rules by changing parameters based on detected deviations. Material parameters and deformation coefficients are modified iteratively to improve the accuracy of anatomical structure representation, particularly at complex regions such as orifices and vessel bifurcations where traditional methods fail.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If traditional deformation correction methods are used, then the process can be completed, but the time consumption increases due to manual adjustments based on multiple projection images

Engineering Contradiction:

Improvecorrection speedVSAvoidtime-consuming manual adjustment

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs automatic deformation correction by self-detecting deviations between preoperative and intraoperative images and autonomously optimizing deformation rules. This eliminates the need for time-consuming manual adjustments by multiple projection images, allowing the correction process to serve itself without extensive human intervention.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces manual mechanical adjustment processes with automated image processing and deviation detection algorithms. Instead of manually comparing multiple projection images and adjusting deformation parameters, the system uses computational methods to automatically detect deviations and optimize correction, significantly reducing time loss.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Ease of operation

If preoperative image data set is used without deformation correction, then the workflow is simple, but the representation accuracy of medical objects and anatomical structures deteriorates

Engineering Contradiction:

Improveworkflow simplicityVSAvoidrepresentation accuracy of medical objects

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system performs preliminary deformation correction by automatically detecting deviations between preoperative and intraoperative images and optimizing deformation rules before final medical object representation. This preliminary action ensures accurate representation of medical objects and anatomical structures while maintaining workflow simplicity through automation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system replaces complex manual deformation correction procedures with automated image processing algorithms. The deviation detection and optimization mechanisms automatically adjust deformation parameters to improve medical object representation accuracy without requiring complex manual workflows, thus maintaining ease of operation while enhancing precision.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS11657519B2Method for deformation correction

Publication Date: 2023.05.23 SIEMENS HEALTHINEERS AG

AI summary

A method for deformation correction includes receiving a preoperative 3D image data set from an examination region of an examination object, generating a segmented 3D image data set by segmenting an anatomical structure in the preoperative 3D image data set, and acquiring image data from the examination region. A medical object is arranged in the examination region. The medical object is identified in the image data, and the segmented 3D image data set is registered with the image data. An overlay data set is generated and displayed based on the segmented 3D image data set and the image data. A position of a deviation between the image data and the segmented 3D image data set is defined, and a deformation rule is determined for the reduction of the deviation between the image data and the segmented 3D image data set. The corrected overlay data set is generated and provided.