Image Processing for 3D–2D Medical Registration Validation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

The registration between three-dimensional and two-dimensional medical images, such as in a transbronchial lung biopsy, often results in reduced accuracy due to local optimal solutions and increases the user's burden, particularly in operations requiring superimposition of these images.

Innovation Solution

An image processing apparatus and method that derives multiple transformation parameters using different registration methods, allows user input to validate initial composite images, and displays alternative composite images for selection, thereby improving accuracy while reducing user burden.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If a single transformation parameter is derived by performing registration between the first image and the second image, then the processing time is reduced, but the registration accuracy decreases due to local optimal solutions

Engineering Contradiction:
Improveprocessing timeVSAvoidregistration accuracy
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The patent segments the registration process into multiple independent registration operations, each deriving a different transformation parameter. Instead of performing one comprehensive registration, the system performs multiple registrations with different settings or algorithms, generating multiple transformation parameters that are then evaluated to select the most accurate one, thereby resolving the contradiction between speed and accuracy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent changes registration parameters such as algorithm type, initialization points, or optimization settings across multiple registration operations. By varying these parameters, the system explores different solution spaces and avoids local optima, improving registration accuracy while maintaining reasonable processing time through efficient parameter selection.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If multiple transformation parameters are derived by performing registration multiple times, then the registration accuracy is improved, but the processing time increases

Engineering Contradiction:
Improveregistration accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary actions by deriving multiple transformation parameters in advance through multiple registration operations. These parameters are pre-computed and stored, allowing the system to quickly select from pre-evaluated options during actual use, thereby improving accuracy while managing processing time through advance preparation.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system performs self-service by automatically evaluating multiple transformation parameters and selecting the optimal one without requiring extensive user intervention. The automated selection process efficiently balances accuracy and processing time by using objective criteria to choose from multiple pre-derived parameters.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If the user is caused to perform the registration between the images, then the registration accuracy can be verified, but the burden on the user increases

Engineering Contradiction:
Improveregistration accuracy verificationVSAvoiduser burden
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent implements self-service by enabling the system to automatically verify and select transformation parameters without requiring user intervention. The system autonomously evaluates multiple transformation parameters using automated metrics and selection criteria, maintaining accuracy verification while eliminating the burden of manual user operation.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent incorporates feedback mechanisms where the system automatically evaluates the quality of registration results using objective criteria. This feedback loop allows the system to verify accuracy automatically by comparing registration outcomes against predefined standards, replacing manual user verification with automated quality assessment.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP4621714A1Image processing apparatus, image processing method, and image processing program
Publication Date: 2025.09.24 FUJIFILM CORP
  • EP4621714A1 patent drawingFigure 1
  • EP4621714A1 patent drawingFigure 2~3
  • EP4621714A1 patent drawingFigure 4~6

AI summary

An image processing apparatus acquires a first image and a second image, derives a first transformation parameter by performing registration between the first image and the second image, performs a control of displaying a first composite image in which the first image is superimposed on the second image using the first transformation parameter, acquires a second transformation parameter different from the first transformation parameter in a case where a user input represents that the first composite image is not valid, and performs a control of displaying a second composite image obtained by composing a plurality of images using one or more of the first transformation parameter and the second transformation parameter.