AI Bone Texture Analysis for Opportunistic Osteoporosis Screening

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for identifying individuals at risk of osteoporosis are inadequate, with 70% of those at risk undiagnosed and a decline in osteoporosis treatment after fractures, due to lack of awareness and inefficient screening tools like BMD testing, which is not cost-effective for widespread use.

Innovation Solution

A method using artificial intelligence to analyze bone texture from digitized x-ray images, incorporating trabecular bone score (TBS) and bone mineral density (BMD) to identify individuals at risk, utilizing neural networks for image analysis.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If BMD testing is used for widespread osteoporosis screening, then bone density measurement is obtained, but cost-effectiveness deteriorates and accessibility is reduced

Engineering Contradiction:

Improvebone density measurementVSAvoidscreening efficiency

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent uses standard digital x-ray images (copies of routine imaging) instead of requiring specialized DXA equipment, allowing bone texture analysis to be performed on existing medical images without additional testing resources

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The AI system performs multiple functions by analyzing the same x-ray image for both routine diagnostic purposes and osteoporosis screening, eliminating the need for separate specialized testing

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If AI-based texture analysis is implemented, then screening coverage and identification accuracy improve, but system complexity increases

Engineering Contradiction:

Improveosteoporosis risk identificationVSAvoidanalysis system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces complex manual assessment mechanisms with automated AI algorithms that analyze bone texture patterns, reducing the need for specialized expertise and simplifying the screening process

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The AI system automatically performs texture analysis and generates osteoporosis risk assessments without requiring manual intervention or interpretation by healthcare professionals

Inventive Principle:

Principle #25Self-service

3Productivity

If opportunistic screening of x-ray images is performed, then undiagnosed individuals are identified, but false positives may increase

Engineering Contradiction:

Improvescreening throughputVSAvoiddiagnosis accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system provides structured output reports with osteoporosis risk assessments that can be reviewed and verified by healthcare professionals, allowing for feedback and correction of potential false positives

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The AI analysis focuses specifically on bone texture characteristics in the x-ray image, concentrating the assessment on relevant local features rather than general image analysis, improving diagnostic precision

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20260051391A1Method for analyzing a texture of a bone from a digitized image

Publication Date: 2026.02.19 MEDIMAPS GRP

AI summary

A method for analyzing a texture of a bone, including: receiving an input x-ray image showing an input bone, and a bone score analysis of the received input x-ray image by a bone score artificial intelligence implemented by a technical element. The bone score artificial intelligence provides as a result of this bone score analysis: a global score depending at least on a trabecular bone score depending on a texture of the trabecular part of the input bone showed on the received input x-ray image, and/or a trabecular bone score depending on a texture of the trabecular part of the input bone showed on the received input x-ray image. Also, a corresponding device for carrying out the method.