Brain Cortex Shape Analysis for Developmental Disorder Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional computer-aided diagnostic systems for identifying developmental brain disorders, such as autism and dyslexia, rely on volumetric analysis which is not accurate due to brain volume differences caused by age and gender, and lacks objectivity in diagnosis.

Innovation Solution

A computer-aided diagnostic system that classifies brains using shape analysis by generating a 3D mesh model of the brain cortex, mapping it to a unit sphere, and computing spherical harmonics to differentiate between normal and developmental disorder brains based on gyrification patterns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If volumetric analysis is used to classify brains for developmental disorders, then the diagnostic process is simplified, but the classification accuracy deteriorates due to confounding factors like age and gender

Engineering Contradiction:

Improvediagnostic process simplicityVSAvoidclassification accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The patent transitions from using volume as the sole discriminating parameter to using shape descriptors (spherical harmonics coefficients) that capture gyrification patterns. This parameter change eliminates the confounding effects of age and gender on classification accuracy while maintaining computational simplicity

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent moves from 1D volumetric measurements to 3D shape analysis using spherical harmonics decomposition. By analyzing the brain surface in multiple dimensional aspects (gyrification patterns, cortical folding), the system achieves higher accuracy without sacrificing operational simplicity

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If human observation is used for diagnosing brain disorders, then flexibility in assessing various symptoms is improved, but objectivity and consistency deteriorate due to human error

Engineering Contradiction:

Improveassessment flexibilityVSAvoiddiagnostic objectivity

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent replaces the human observational system with an automated computer-aided diagnosis system that uses spherical harmonics analysis. This substitution maintains versatility in assessing different disorders while dramatically improving objectivity and consistency by eliminating human perceptual errors

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces spherical harmonics coefficients as an intermediary between raw MRI data and diagnostic conclusions. This mathematical representation serves as an objective mediator that quantifies shape characteristics, enabling consistent and reproducible diagnoses across different cases

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS9230321B2Computer aided diagnostic system incorporating 3D shape analysis of the brain for identifying developmental brain disorders

Publication Date: 2016.01.05 UNIVERSITY OF LOUISVILLE RESEARCH FOUNDATION INC

AI summary

A computer aided diagnostic system and automated method classify a brain through modeling and analyzing the shape of a brain cortex, e.g., to detect a brain cortex that is indicative of a developmental disorder such as ADHD, autism or dyslexia. A model used in such analysis describes the shape of brain cortices in terms of spherical harmonics required to delineate a unit sphere corresponding to the brain cortex to a model of the brain cortex.