Automated Brain Asymmetry Quantification via 3D Surface Projection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current diagnostic methods for dementia, particularly in early stages of Alzheimer's disease, rely heavily on manual comparison of brain metabolism asymmetry in FDG-PET images, which is subjective, inaccurate, and often overlooks subtle asymmetries due to the need for skilled interpretation.

Innovation Solution

An automated system that compares corresponding voxels in brain images to generate an asymmetry map and index, using three-dimensional stereotactic surface projections and a clinical decision support system to quantify and detect asymmetry, facilitating early detection of Alzheimer's disease.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual comparison of brain sections is performed by diagnosticians, then diagnostic evaluation can be conducted, but the process is subjective, inaccurate, and difficult to quantize

Engineering Contradiction:
Improveasymmetry measurement precisionVSAvoiddiagnostic process complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the manual mechanical visual comparison process with an automated computer-based image processing system. The system uses algorithms to automatically compare corresponding voxels in 3D brain images, calculate asymmetry metrics, and generate quantitative results, eliminating the need for subjective manual evaluation while improving measurement precision.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The diagnostic system performs self-evaluation by automatically analyzing brain images without requiring expert intervention. The computerized system independently executes the asymmetry analysis, generates reports, and provides diagnostic support, making the diagnostic process more objective and accessible to non-experts.

Inventive Principle:
Principle #25Self-service

2Reliability

If manual comparison by experienced experts is used, then accurate identification of hypometabolic areas can be achieved, but the process is time-consuming and requires great skill

Engineering Contradiction:
Improvediagnostic reliabilityVSAvoiddiagnosis time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs automated asymmetry analysis without requiring expert time investment. The computerized algorithm independently evaluates brain images, calculates asymmetry indices, and generates diagnostic reports, maintaining reliability while eliminating the time constraint associated with expert manual review.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary automated analysis of brain images to identify asymmetric regions before expert review. This pre-processing step highlights areas of concern, allowing experts to focus their attention on specific regions rather than manually examining entire brain volumes, thereby reducing diagnosis time while maintaining reliability.

Inventive Principle:
Principle #10Preliminary action

3Difficulty of detecting and measuring

If subtle asymmetries are visually inspected, then diagnostic information can be obtained, but asymmetries are often overlooked due to limited visibility

Engineering Contradiction:
Improveasymmetry detection capabilityVSAvoidasymmetry measurement precision
Core Design Contradiction:
Difficulty of detecting and measuringVSMeasurement precision

Solution Approach 1:

The patent replaces human visual inspection with computer-based image processing that can detect subtle intensity differences in brain images. The automated system uses voxel-by-voxel comparison algorithms to identify asymmetries that are imperceptible to the human eye, thereby improving both detection capability and measurement precision simultaneously.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms the brain images into asymmetry maps and calculates asymmetry indices, changing the representation parameters from raw image intensities to standardized asymmetry metrics. This parameter transformation enhances the visibility and measurability of subtle asymmetries, making them detectable and quantifiable.

Inventive Principle:
Principle #35Parameter changes

4Productivity

If automated quantification of asymmetry is implemented, then diagnostic accuracy and efficiency are improved, but device complexity increases

Engineering Contradiction:
Improvediagnostic efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent integrates multiple diagnostic functions into a single automated system that performs image registration, asymmetry calculation, statistical analysis, and report generation. This multi-functional approach increases productivity by consolidating previously separate manual processes into one automated workflow, while the standardized algorithms keep the system manageable despite the increased functionality.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP2661734B1Automatic quantification of asymmetry
Publication Date: 2019.06.05 PHILIPS INTPROP & STANDARDS GMBH
  • EP2661734B1 patent drawingFigure 1
  • EP2661734B1 patent drawingFigure 2
  • EP2661734B1 patent drawingFigure 3

AI summary

An apparatus detects asymmetry in an object, such as a brain. The apparatus includes a processor programmed to fit a three-dimensional image of the object to a preselected shape, such as a standard brain atlas. The processor projects the three- dimensional image of the object to a two-dimensional surface image. The processor compares corresponding mirror image symmetric voxel pairs on the left and right sides of the surface image. The processor generates at least one of an asymmetry map and an asymmetry index based on the deviations in the pixel pairs. The processor can also mask, before the comparison, pixels of the surface image which are asymmetric in a normal brain.