Bone Image Evaluation Excluding Fractures and Artificial Objects

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing bone density evaluation methods fail to accurately assess fracture risk due to the inclusion of fractured bones or artificial objects, leading to incorrect bone density calculations and ineffective drug efficacy determination for osteoporosis treatment.

Innovation Solution

An image processing device that utilizes energy subtraction imaging and neural networks to exclude fractures and artificial objects from bone part images, enabling accurate evaluation of bone state by specifying target bones and deriving relevant indicators such as bone density and microstructure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If bone density evaluation is performed using conventional methods that include all visible bones in the image, then the evaluation process is simple and fast, but the bone density calculation becomes incorrect when fractures or artificial objects are present

Engineering Contradiction:
Improvebone density calculation accuracyVSAvoidimage processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts and removes fracture regions and artificial object regions from the bone image before performing bone density evaluation. By separating these problematic regions from the evaluation area, the system achieves accurate bone density measurement without being influenced by high-density artifacts that would otherwise skew the calculation results.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent segments the bone image into multiple regions: evaluation regions (normal bone areas), fracture regions, and artificial object regions. This segmentation allows the system to selectively process only the appropriate regions for bone density calculation, improving measurement precision while managing processing complexity through targeted region analysis.

Inventive Principle:
Principle #1Segmentation

2Measurement precision

If the evaluation region is restricted to exclude fractured bones and artificial objects, then bone density measurement accuracy improves, but the evaluation cannot be performed when all target bones are affected

Engineering Contradiction:
Improvebone state evaluation accuracyVSAvoidevaluation availability
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent extends the evaluation capability by selecting alternative bones for assessment when the primary target bones are completely affected by fractures or artificial objects. The system can switch between different bone evaluation targets (e.g., from lumbar vertebrae to femoral neck or other available bones), ensuring that bone state evaluation remains reliable and available across various clinical scenarios.

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

3Measurement precision

If artificial objects and fractures are excluded from the evaluation region, then correct bone density values are obtained, but the processing time and computational load increase

Engineering Contradiction:
Improvebone density value accuracyVSAvoidimage processing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary identification and marking of fracture regions and artificial object regions before the actual bone density calculation. By pre-processing the image to define exclusion zones in advance, the system avoids repeated analysis of problematic areas during the main evaluation process, thereby reducing overall computational load and processing time while maintaining measurement precision.

Inventive Principle:
Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables correct evaluation of bone state, allowing for precise fracture risk assessment and effective drug efficacy determination by excluding fractures and artificial objects from bone images.

Implementation Method 1

a bone part image showing a bone part of the subject is derived from first and second radiation images acquired by imaging the subject with radiation having different energy distributions

Methodology Applied
Scientific EffectX-Ray: X-Ray

Data Source

PatentEP4527297B1Image processing device, image processing method, and image processing program
Publication Date: 2026.04.15 FUJIFILM CORP
  • EP4527297B1 patent drawingFigure 1~2
  • EP4527297B1 patent drawingFigure 3
  • EP4527297B1 patent drawingFigure 4

AI summary

A processor (11) specifies a target bone, which is a target of state evaluation of a bone, from a radiation image (Gb) of a subject, determines whether or not the state evaluation of the bone is possible based on a specification result of the target bone, derives an evaluation result by performing the state evaluation of the bone using the target bone in a case in which it is determined that the state evaluation of the bone is possible, and performs the state evaluation of the bone by changing an evaluation method in a case in which it is determined that the state evaluation of the bone is not possible.