Automated WMH Quantification via Intensity Thresholding

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for evaluating white matter hyperintensities (WMH) in brain imaging are imprecise and biased, relying on patient interviews, which can lead to inadequate assessments for cognitive and neurological disorders.

Innovation Solution

A computer-based method for selecting an intensity threshold value, defining hyperintensities, extracting voxels, and determining the regional distribution of WMH using anatomical atlases, which includes image analysis and correction for under- or over-labeling based on voxel location and light intensity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If patient interviews are used for evaluation, then assessment can be obtained, but precision and objectivity deteriorate due to bias and imprecision

Engineering Contradiction:

Improveassessment precisionVSAvoidevaluation complexity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces manual patient interviews and subjective assessments with an automated computer-based image analysis system. The computer automatically processes MRI images to detect and quantify WMH, substituting human evaluation with machine-based measurement that eliminates interviewer bias and improves precision while maintaining ease of operation through automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If automated image analysis is implemented, then measurement precision improves, but device complexity increases

Engineering Contradiction:

ImproveWMH quantification precisionVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a self-service system where the computer automatically performs image preprocessing, threshold selection, WMH detection, and quantification without requiring manual intervention. The system selects its own intensity threshold values, automatically processes images, and generates reports, thereby improving precision while managing complexity through automation rather than manual procedures.

Inventive Principle:

Principle #25Self-service

3Measurement precision

If intensity threshold values are manually selected, then operation simplicity is maintained, but measurement precision deteriorates due to subjectivity

Engineering Contradiction:

Improvehyperintensity detection precisionVSAvoidthreshold selection complexity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces manual threshold selection with automated computer-based threshold determination. The computer analyzes the image data and automatically selects intensity threshold values that optimize WMH detection, substituting subjective human judgment with objective algorithmic processing that improves detection precision while managing the complexity of threshold selection through automation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS9867566B2Technologies for white matter hyperintensity quantification

Publication Date: 2018.01.16 THE TRUSTEES OF COLUMBIA UNIV IN THE CITY OF NEW YORK

AI summary

A method comprises selecting, via a computer, an intensity threshold value. The method also comprises defining, via the computer, a plurality of hyperintensities on imaging data based on the intensity threshold value. The method further comprises extracting, via the computer, a plurality of voxels from the imaging data based on the defining. The method additionally comprises determining, via the computer, a total volume of the voxels based on the extracting. The method also comprises determining, via the computer, a regional distribution of WMH based on an anatomical atlas and the total volume.