Brain Segment Analysis Correlation Algorithm

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for analyzing three-dimensional medical image data sets, particularly for brain morphometry, are laborious and prone to errors when evaluating degeneration in brain segments, especially in diagnosing neurodegenerative diseases.

Innovation Solution

A computer-implemented method that correlates brain segment analysis with patient symptoms using a correlation algorithm, determining parameters for brain segments and comparing them with patient data records to provide correlation information for atrophy or degeneration, aiding in accurate detection and validation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automatic brain region segmentation is used, then analysis speed and simplicity are improved, but evaluation accuracy and reliability deteriorate due to laborious and error-prone assessment of degeneration

Engineering Contradiction:
Improveanalysis speedVSAvoidevaluation accuracy
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system implements feedback by comparing automatically determined brain segment parameters against a database of reference values from healthy subjects and previous patient data. This feedback mechanism validates the automatic segmentation results and provides confidence levels for each assessment, thereby maintaining high productivity while improving evaluation reliability through automated validation.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces an intermediary computational layer that acts as a bridge between automatic segmentation and final diagnosis. This intermediary system performs automated assessment of degeneration by comparing segmented brain regions against reference databases and correlation algorithms, reducing human error while maintaining analysis speed.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If manual or automatic segmentation with traditional evaluation is performed, then brain morphometry analysis is achieved, but the process remains laborious and error-prone

Engineering Contradiction:
Improvebrain morphometry analysis capabilityVSAvoidoperational simplicity
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system implements self-service by enabling automated self-assessment of brain segment degeneration. The computational system automatically compares determined parameters against reference databases, generates confidence levels, and provides diagnostic support without requiring manual evaluation, thereby maintaining measurement precision while dramatically improving ease of operation.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent replaces the mechanical manual evaluation process with an automated computational system. Traditional manual assessment of brain segment degeneration is substituted by automated algorithms that compare imaging data against reference databases, eliminating laborious operations while preserving measurement precision through systematic computational analysis.

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

3Reliability

If correlation analysis with patient symptoms is implemented, then diagnostic accuracy is improved, but computational complexity increases

Engineering Contradiction:
Improvediagnostic accuracyVSAvoidcomputational complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system applies segmentation by dividing the complex correlation analysis into distinct modular components: brain segment segmentation, parameter determination, symptom data processing, and correlation computation. Each module handles a specific aspect of the analysis independently, reducing overall computational complexity while maintaining diagnostic accuracy through systematic processing of multiple data dimensions.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent utilizes parameter changes by transforming complex correlation analysis into manageable computational steps. The system converts raw imaging data and symptom data into standardized parameters, then applies correlation algorithms that compare these parameters against reference databases. This parameter transformation approach simplifies the computational complexity while preserving diagnostic accuracy through systematic data normalization and comparison.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4227896B1Computer-implemented method for processing a three-dimensional medical image data set, device, computer program and computer-readable storage medium
Publication Date: 2026.01.07 SIEMENS HEALTHINEERS AG
  • EP4227896B1 patent drawingFigure 1
  • EP4227896B1 patent drawingFigure 2~3
  • EP4227896B1 patent drawingFigure 4

AI summary

Computer-implemented method for processing a respective three-dimensional medical image data set (1) for at least one patient (21), wherein the image data set (1) at least partially depicts the brain (22) of the respective patient (21), comprising the steps performed for each patient: - receiving or acquiring the image data set (1) for the respective patient (21), - selecting a respective image segment (2) in the image data set (1) that corresponds to a respective one of multiple given brain segments (3), - determining at least one respective parameter (7) for each selected image segment (2), - selecting a selected group (8) of brain segments (2) for which a selection condition (9) is fulfilled, wherein the selection condition (9) depends on the parameter (7) determined for the respective image segment (2) corresponding to the respective brain segment (3), - receiving a patient data record (11) describing the presence of at least one registered symptom (12) for the respective patient (21), - for each brain segment (3) in the selected group (8) determine a respective correlation result (16) for each registered symptom (12) using a given correlation algorithm (15, 20), and - determining a correlation information (17) based on the determined correlation results (16).