Individualized Brain Functional Atlas Iterative Refinement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for drawing high-precision individualized brain functional atlases suffer from poor stability, noise immunity, and unreliable results, making them unsuitable for clinical applications.

Innovation Solution

A method involving iterative calculations to adjust the functional area of each voxel based on connection degrees, using a brain functional atlas template, and employing structural and functional magnetic resonance imaging data to refine the partitioning of the brain into functional areas.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If an individualized brain functional atlas is drawn using existing methods, then the atlas can be created for individual patients, but the results suffer from poor stability, poor noise immunity, and high noise

Engineering Contradiction:
ImprovestabilityVSAvoidnoise level
Core Design Contradiction:
ReliabilityVSManufacturing precision

Solution Approach 1:

The patent divides the brain into multiple large-scale functional areas first, then performs iterative optimization within each area. This segmentation approach stabilizes the atlas drawing process by breaking down the complex whole-brain problem into manageable regional sub-problems, reducing noise and improving reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements an iterative optimization process where the atlas is repeatedly refined based on functional connectivity data. Each iteration uses feedback from correlation calculations to adjust voxel assignments, progressively improving stability and reducing noise until convergence is achieved.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If a high-precision individualized brain functional atlas is drawn, then accurate functional areas are obtained, but the results become unreliable and noisy

Engineering Contradiction:
Improvefunctional area accuracyVSAvoidresult reliability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

By segmenting the brain into large-scale functional areas first, the patent achieves a balance between precision and reliability. The hierarchical approach allows accurate functional area delineation within stable regional boundaries, avoiding the noise and unreliability associated with attempting to define all boundaries simultaneously at high precision.

Inventive Principle:
Principle #1Segmentation

3Quantity of substance

If a group level brain atlas is used, then commonalities and patterns are revealed, but the uniqueness of individuals is obliterated and clinical relevance is limited

Engineering Contradiction:
Improvecommonality detectionVSAvoidindividual uniqueness
Core Design Contradiction:
Quantity of substanceVSAdaptability or versatility

Solution Approach 1:

The patent applies local quality by using a group-level atlas as a template for initialization, then performing individualized iterative optimization for each patient. This allows the atlas to capture both group-level commonalities (from the template) and individual uniqueness (from the personalized optimization), making it adaptable to individual patients while preserving population-level patterns.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4071765B1Method and system for drawing brain functional atlas
Publication Date: 2026.02.25 BEIJING GALAXY CIRCUMFERENCE TECHNOLOGIESCO LTD
  • EP4071765B1 patent drawingFigure 1
  • EP4071765B1 patent drawingFigure 2
  • EP4071765B1 patent drawingFigure 3

AI summary

A method and system for drawing a brain functional atlas. The method comprises: initializing a brain functional atlas of an individual by using a brain functional atlas template to obtain an initial individualized brain functional atlas; dividing the initial individualized brain functional atlas into a plurality of large areas, each large area comprising a plurality of functional areas; entering iteration, each iteration process comprising calculating the connection degree between each voxel in each large area and each functional area in the large area in sequence, and adjusting each voxel to the functional area having the highest connection degree with the voxel until all voxels are adjusted; and when an ending condition is satisfied, ending the iteration to obtain a final individualized brain functional atlas. According to the present method, a high-precision individualized brain functional atlas can be drawn, and high stability, high reliability, and low noise can be achieved under different precisions or resolutions.