Comparative Image Analysis for Volumetric Change Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Manual comparison of three-dimensional (3D) tomographic images with two-dimensional (2D) or other 3D images is complex, imprecise, and time-consuming, especially when images are acquired using different modalities or at different times, making it difficult for radiologists to detect changes or anomalies effectively.

Innovation Solution

A method for comparative image analysis that involves registering multiple 3D images, normalizing them to account for intensity differences, and using computer-assisted detection algorithms to generate change maps and detect anomalies, which can include registration to an atlas and pairwise or simultaneous registration of images to facilitate accurate comparison and change detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual comparison of 3D tomographic images with 2D or other 3D images is performed, then diagnostic analysis can be conducted, but the process becomes complex, imprecise, and time-consuming

Engineering Contradiction:

Improvediagnostic precisionVSAvoidcomparison time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical comparison process with an automated computer-based image registration and comparison system. The system uses algorithms to automatically register 3D tomographic images with 2D or other 3D images, eliminating the need for manual slice-by-slice comparison while improving both speed and precision through consistent computational analysis

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediate registration process that transforms multiple images into a common coordinate system and representation format. This intermediary step enables accurate comparison by aligning anatomical structures across different modalities and time points, making the comparison process both faster and more precise

Inventive Principle:

Principle #24Intermediary (Mediator)

2Adaptability or versatility

If comparison of images acquired using different imaging modalities is performed, then comprehensive diagnostic information can be obtained, but the comparison becomes difficult and imprecise

Engineering Contradiction:

Improvemulti-modality compatibilityVSAvoidcomparison accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent creates a universal image registration framework that can handle multiple imaging modalities (3D tomographic images, 2D X-ray images, and other 3D images) through a common comparison methodology. The system normalizes different image types into a unified representation, enabling accurate cross-modality comparison while maintaining the unique diagnostic information from each modality

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The patent transforms images from different modalities into a common parameter space through registration operations. By changing the representation parameters of each image type to align with a reference coordinate system and intensity scaling, the system enables precise comparison despite the original modality differences

Inventive Principle:

Principle #35Parameter changes

3Reliability

If longitudinal comparison of images acquired at different times is performed, then disease progression can be detected, but the complexity and time required increase

Engineering Contradiction:

Improvedisease detection reliabilityVSAvoidcomparison system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent performs preliminary registration and normalization of images before comparison, preparing the data in advance for efficient analysis. By pre-aligning the anatomical structures and intensity scales of images from different time points, the system reduces the complexity of the actual comparison process while maintaining high reliability in detecting disease progression

Inventive Principle:

Principle #10Preliminary action

4Measurement precision

If lateral comparison of symmetrically related regions is performed, then asymmetries indicating disease can be identified, but the process becomes more difficult with 3D images

Engineering Contradiction:

Improveasymmetry detection precisionVSAvoidcomparison ease

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces manual lateral comparison with automated computer-based analysis that can process 3D volumetric data. The system automatically identifies symmetrical regions, performs registration, and quantifies asymmetries through computational algorithms, making the process both easier to operate and more precise in detecting subtle pathological differences

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS7653263B2Method and system for volumetric comparative image analysis and diagnosis

Publication Date: 2010.01.26 GE PRECISION HEALTHCARE LLC

AI summary

A technique is provided for comparative image analysis and/or change detection using computer assisted detection and/or diagnosis (CAD) algorithms. The technique includes registering two or more images, comparing the images with one another to generate a change map, and detecting anomalies in the images based on the change map.