Trabecular Node-Link Graph Recovery for Low-Resolution Skeletal Images

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current osteoporosis diagnosis methods rely on bone mineral density (BMD) measurements, which fail to accurately assess bone microstructure, leading to misdiagnosis and over-diagnosis due to low resolution and lack of bony tissue information, and existing high-resolution technologies face limitations in constructing training databases and require excessive calculations.

Innovation Solution

A node-link graph-based bone microstructure post-processing technology that reconstructs skeletal images by representing trabeculae as links and nodes, reinforcing connectivity, and adjusting node locations to minimize structural discontinuity, enabling accurate bone strength evaluation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high-resolution skeletal images are obtained through radiation imaging equipment, then bone microstructure information can be captured, but radiation exposure increases and signal-to-noise ratio decreases

Engineering Contradiction:
Improveimage resolutionVSAvoidradiation exposure
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent applies preliminary action by performing bone microstructure post-processing on low-resolution skeletal images before final diagnosis. The node-link graph representation and connectivity recovery algorithms are applied in advance to enhance microstructure visibility without requiring high-resolution imaging, thereby avoiding the need for high radiation exposure while still enabling accurate bone strength evaluation

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent creates a simplified copy of the bone microstructure using node-link graph representation. Instead of directly imaging at high resolution, the system creates a topological copy of the trabecular structure that captures essential connectivity information, allowing diagnosis without requiring the full detail of high-resolution imaging

Inventive Principle:
Principle #26Copying

2Measurement precision

If artificial neural network-based image high resolution technology is applied, then skeletal image resolution can be improved, but construction of training database becomes difficult

Engineering Contradiction:
Improveimage resolutionVSAvoidtraining database construction
Core Design Contradiction:
Measurement precisionVSEase of manufacture

Solution Approach 1:

The patent introduces node-link graph representation as an intermediary between low-resolution imaging and bone strength evaluation. This intermediate topological representation simplifies the processing requirement, eliminating the need for complex neural network training databases while still enabling high-resolution-like diagnostic capability through graph-based connectivity analysis

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameter space from pixel-based image resolution to graph-based topological parameters (nodes, links, connectivity). This parameter transformation allows the system to work with low-resolution input data while producing high-accuracy bone strength evaluations, bypassing the need for high-resolution training databases

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If phase optimization design-based image high resolution technology is applied, then high-resolution magnification can be achieved, but excessive calculations are required

Engineering Contradiction:
Improvehigh-resolution magnificationVSAvoidcalculation resources
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent segments the bone microstructure into discrete topological elements (nodes and links) rather than attempting full pixel-level reconstruction. This segmentation approach reduces computational complexity by focusing only on critical connectivity information, achieving high-resolution diagnostic capability with minimal calculation resources

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts only the essential connectivity information from the bone microstructure using node-link graph representation. By taking out only the critical topological features needed for bone strength evaluation rather than reconstructing all image details, the system achieves high-resolution magnification效果 with significantly reduced computational burden

Inventive Principle:
Principle #2Taking out (Extraction)

4Productivity

If BMD measurement method is used for bone strength evaluation, then diagnosis can be performed, but accuracy is limited to about 70%

Engineering Contradiction:
Improvediagnosis efficiencyVSAvoidbone strength evaluation accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent combines BMD measurement information with node-link graph-based microstructure connectivity analysis to create a composite evaluation system. This composite approach integrates both quantitative density data and qualitative structural connectivity data, achieving bone strength evaluation accuracy of about 94% while maintaining diagnostic efficiency

Inventive Principle:
Principle #40Composite materials

Data Source

PatentEP4167178B1Computer system for trabecular connectivity recovery of skeletal images through node-link graph-based bone microstructure representation, and methdo thereof
Publication Date: 2025.12.17 KOREA ADVANCED INST OF SCI & TECH
  • EP4167178B1 patent drawingFigure 1
  • EP4167178B1 patent drawingFigure 2(a)~2(c)
  • EP4167178B1 patent drawingFigure 3

AI summary

Various embodiments relate to a computer apparatus for the bone microstructure connectivity recovery of a skeletal image reconstructed through an artificial neural network using the representations of a node-link graph-based bone microstructure and a method thereof. The computer apparatus and the method may be configured to represent a node-link graph from a bone microstructure of an input skeletal image, reinforce a connectivity of the bone microstructure in the node-link graph, and change the node-link graph into a skeletal image.