Vertebral Fracture Quantification via Shape Reconstruction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for diagnosing vertebral fractures in osteoporosis are limited by subjectivity, variability, and limited sensitivity and specificity, as well as the laborious and time-consuming process of manual point placement, which can lead to undiagnosed and untreated fractures.

Innovation Solution

A method that processes images of the spine by segmenting vertebrae, reconstructing their shape using mathematical models of unfractured vertebrae, adapting these models to fit imaged vertebrae, and predicting unfractured shapes to quantify fracture extent by comparing actual and predicted shapes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual point placement is used to measure vertebral heights, then fracture detection can be performed, but the process becomes subjective and variable

Engineering Contradiction:

Improvefracture detection accuracyVSAvoidreproducibility

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces manual mechanical point placement with an automated computer-based system that uses image processing algorithms to identify vertebral boundaries and calculate heights, eliminating human subjectivity and improving reproducibility while maintaining fracture detection accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a digital model of the vertebral body by processing the radiograph image to generate height measurements automatically, replacing the need for manual physical measurement and point marking, thereby reducing variability and improving reliability

Inventive Principle:

Principle #26Copying

2Measurement precision

If manual point placement is used to measure vertebral heights, then fracture detection can be performed, but the process becomes laborious and time consuming

Engineering Contradiction:

Improvefracture detection accuracyVSAvoiddiagnosis speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The patent substitutes manual measurement operations with an automated computer-based image processing system that rapidly calculates vertebral heights and detects fractures, significantly improving diagnosis speed while preserving measurement accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-measurement by automatically identifying vertebral boundaries and calculating heights from the radiograph without requiring manual intervention, thereby eliminating time-consuming manual operations while maintaining diagnostic accuracy

Inventive Principle:

Principle #25Self-service

3Device complexity

If limited height points are marked on each vertebra, then measurement is simplified, but information may be lost

Engineering Contradiction:

Improvemeasurement simplicityVSAvoidvertebral shape information

Core Design Contradiction:

Device complexityVSLoss of information

Solution Approach 1:

The system creates a complete digital representation of the vertebral body by processing the entire radiograph image, capturing all shape information rather than relying on limited manual point markings, thus preserving full vertebral morphology data

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent transitions from one-dimensional point measurements to comprehensive two-dimensional image analysis, allowing the system to capture and analyze the complete vertebral shape and boundaries, thereby preventing information loss while maintaining measurement simplicity through automated processing

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

4Measurement precision

If quantitative methods with fixed point placement are used, then fracture definition is well-defined, but fracture sensitivity and specificity show considerable variants

Engineering Contradiction:

Improvefracture classification accuracyVSAvoidsensitivity and specificity consistency

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The patent replaces manual point placement with automated image processing that consistently identifies vertebral boundaries and calculates heights, eliminating the variability in sensitivity and specificity observed in manual methods while maintaining well-defined fracture classification criteria

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system changes from discrete point measurements to continuous image-based height calculations, allowing for more precise and consistent fracture detection by utilizing the full range of vertebral boundary information rather than relying on subjective point selection, thereby improving sensitivity and specificity consistency

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS8126240B2Vertebral fracture quantification

Publication Date: 2012.02.28 BIOCLINICA

AI summary

A method of deriving an estimate of the extent of fracture in a vertebra shown in an image of part of A spine is provided. The images of at least two vertebrae are segmented to obtain data representative of the shape and size of each of the vertebrae. An approximation of the shape of a first of the vertebrae is reconstructed by comparing the data obtained for a second of the two vertebrae with a mathematical model of at least the same two vertebrae of an unfractured spine. The unfractured shape of the first vertebra is predicted to enable a comparison of the shape and size of the first vertebra as imaged with the predicted unfractured shape and size. The difference between the respective images is subsequently computed to obtain a result representative of the extent of fracture in the first vertebra.