Longitudinal Deviation Map for Brain Volumetric Change Assessment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for measuring volumetric changes in brain structures are time-consuming and require extensive interpretation of tabular reports, lacking a concise and precise way to visualize and quantify changes across multiple structures simultaneously, which hinders efficient clinical assessment of neurological disorders.

Innovation Solution

A method and system that generate a longitudinal deviation map using a dense 3D voxel dataset, comparing individual patient data to a reference model, allowing for automatic determination and visualization of volumetric changes in brain structures, enabling fast and precise analysis of volumetric changes across the whole brain.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If tabular reports of annualized percent change values for each segmented brain structure are used, then comprehensive quantitative information is provided, but the analysis becomes time-consuming and complex

Engineering Contradiction:
Improvequantitative accuracyVSAvoidanalysis time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent segments the complex tabular data into a visual map where each brain structure's volumetric change is represented as a distinct visual element. The longitudinal deviation map divides the brain into multiple structures, with each structure's deviation from reference values visually encoded, allowing clinicians to simultaneously assess multiple structures without manually scanning extensive tables.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a visual copy or representation of the volumetric change data through the longitudinal deviation map. Instead of presenting raw numerical data, the system generates a visual map that copies and transforms the quantitative information into an intuitive spatial representation, preserving the quantitative accuracy while dramatically improving interpretability and reducing analysis time.

Inventive Principle:
Principle #26Copying

2Measurement precision

If multiple brain structures are analyzed individually with separate volumetric values, then detailed structure-specific information is obtained, but the overall pattern recognition becomes difficult

Engineering Contradiction:
Improvestructure-specific accuracyVSAvoidpattern recognition
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent merges multiple individual structure assessments into a single integrated longitudinal deviation map. All brain structures are displayed simultaneously in their anatomical context, with each structure's volumetric change visually represented. This merging allows clinicians to recognize overall patterns of atrophy or hypertrophy across the brain while preserving structure-specific quantitative information.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent adds a visual dimension to the data representation by creating a spatial map where volumetric changes are encoded as visual properties (such as color intensity or size) overlaid on the brain anatomy. This dimensional transformation converts one-dimensional numerical values into two-dimensional visual patterns, enabling intuitive pattern recognition across multiple structures while maintaining structure-specific precision.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

3Loss of information

If extensive tabular data and trending plots are provided for volume changes, then complete reference information is available, but the clinical interpretation becomes complex and time-consuming

Engineering Contradiction:
Improveinformation completenessVSAvoidinterpretation ease
Core Design Contradiction:
Loss of informationVSEase of operation

Solution Approach 1:

The patent uses color encoding to represent volumetric deviation values in the longitudinal deviation map. Different colors or color intensities indicate different magnitudes or directions of deviation from reference values, allowing clinicians to quickly interpret the clinical significance of volume changes without reading numerical tables. This visual encoding maintains complete information while dramatically improving interpretation ease.

Inventive Principle:
Principle #32Color changes

4Measurement precision

If traditional volumetric measurement methods are used, then accurate volume calculations are achieved, but the visualization and comparison with reference populations is inefficient

Engineering Contradiction:
Improvevolumetric accuracyVSAvoidassessment efficiency
Core Design Contradiction:
Measurement precisionVSProductivity

Solution Approach 1:

The patent introduces the longitudinal deviation map as an intermediary between raw volumetric measurements and clinical interpretation. This intermediate visual representation automatically compares patient data with reference populations and presents the results in an intuitive format, eliminating the need for manual comparison and interpretation of extensive tabular data while preserving volumetric measurement accuracy.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3712844B1Method and system for fast assessment of brain change normality
Publication Date: 2023.08.09 SIEMENS HEALTHINEERS AG
  • EP3712844B1 patent drawingFigure 1
  • EP3712844B1 patent drawingFigure 2
  • EP3712844B1 patent drawingFigure 3

AI summary

System and method for measuring volumetric changes of brain structures, the method comprising: i. initializing (101) an intensity value of all voxels of a 3D voxel dataset representing the brain of a subject to an initial value preferentially equal to 0; ii. for all voxels that belongs to a segmented brain structure for which reference data of a longitudinal reference model exists, automatically executing (102) the following steps: - calculating (103) a deviation D of a volume change for the segmented brain structure from the longitudinal reference model; - normalizing (104) the deviation D to obtain a quantitative value Q of the volume change on a same scale for voxel's belonging to different brain structures; - sets (107) the intensity value of the voxels to the previously obtained quantitative value Q; - displaying (108) the voxels of the 3D voxel dataset in a longitudinal deviation map.