Trabecular Bone MRI Texture Metrics for Fragility Risk Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current methods for screening osteoporosis, such as dual energy x-ray absorptiometry (DXA), are underutilized, and opportunistic imaging methods are needed to identify individuals at risk for osteoporosis, as traditional techniques are limited to prospective applications and fail to account for structural and material properties beyond bone mineral density (BMD).

Innovation Solution

A method involving magnetic resonance imaging (MRI) is used to analyze trabecular bone texture by calculating metrics like inverse difference moment, angular second moment, entropy, and contrast to assess bone health and risk, which can be performed on clinical MRI scans without additional protocols, enabling opportunistic screening.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional osteoporosis screening methods like DXA are used, then bone mineral density can be measured, but many high-risk patients are never screened and structural properties beyond BMD are not assessed

Engineering Contradiction:
Improvebone quality assessmentVSAvoidscreening application
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent applies texture analysis to MRI images obtained for various clinical indications (back pain, radiculopathy, tumor evaluation) to simultaneously assess bone quality and detect osteoporosis, making the MRI scan serve multiple purposes beyond its primary indication

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Measurement precision

If prospective bone quality measurement techniques like QCT or bone biopsy are used, then detailed bone structure can be measured, but they are limited to prospective applications and cannot be used for screening

Engineering Contradiction:
Improvetrabecular microarchitectureVSAvoidscreening feasibility
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The patent performs bone quality assessment in advance during routine MRI scans before fractures occur, enabling early identification of osteoporosis risk in high-risk individuals who would otherwise never be screened

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The method uses the MRI scan itself (already performed for other clinical reasons) to provide both the primary indication evaluation and the bone quality assessment, eliminating the need for separate screening procedures

Inventive Principle:
Principle #25Self-service

3Reliability

If DXA-based Trabecular Bone Score is used, then fracture risk can be predicted independently of BMD, but it requires additional DXA imaging and is not available on commonly obtained images

Engineering Contradiction:
Improvefracture risk predictionVSAvoidimaging protocol
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent uses texture analysis of MRI images as an intermediary method that bridges the gap between commonly obtained MRI scans and the need for bone quality assessment, providing fracture risk prediction without requiring dedicated DXA imaging

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4125673B1MRI-based textural analysis of trabecular bone
Publication Date: 2026.02.18 NEW YORK SOC FOR THE RUPTURED & CRIPPLED MAINTAINING THE HOSPITAL FOR SPECIAL SURGERY
  • EP4125673B1 patent drawingFigure 1
  • EP4125673B1 patent drawingFigure 2
  • EP4125673B1 patent drawingFigure 3

AI summary

In an example method, a computer system receives one or more images of one or more bones of a patient. The one or more images are generated by a magnetic resonance imaging (MRI). The computer system determines one or more metrics indicative of an image texture of the one or more images; and determines at least one of a bone risk or a bone health of the patient based on the one or more metrics.