Dual-Energy Bone Image Processing for Trabecular Osteoporosis Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting osteoporosis, such as DXA and quantitative CT, fail to accurately depict the microstructure of trabeculae due to insufficient spatial resolution, hindering precise osteoporosis detection.
Innovation Solution
An image processing apparatus that acquires two radiation images with different energy distributions, derives a bone part image with a spatial resolution of 0.2 mm/pixel or less, and uses machine learning to extract a partial image of interest, enabling accurate osteoporosis discrimination.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If DXA method or quantitative CT method is used to acquire bone density image, then spatial resolution is improved (0.5-2.0 mm/pixel), but the microstructure of trabeculae cannot be sufficiently depicted
Solution Approach 1:
The patent changes the energy parameter of radiation by acquiring images at multiple energy levels (dual-energy or multi-energy imaging). This allows differentiation of bone components and enhancement of trabecular microstructure visibility beyond what single-energy imaging provides, resolving the contradiction between spatial resolution and microstructure depiction.
Solution Approach 2:
The patent adds the energy dimension to the traditional spatial imaging approach. By incorporating energy discrimination, the system can selectively highlight trabecular structures based on their energy attenuation characteristics, providing microstructure information that complements the spatial resolution capability.
2Measurement precision
If bone density image with high spatial resolution is acquired, then measurement precision is improved, but the image cannot accurately depict trabecular microstructure
Solution Approach 1:
The patent modifies the imaging parameters by using multiple energy levels to capture bone density images. This enables the system to differentiate between cortical and trabecular bone based on their distinct energy attenuation properties, thereby accurately depicting trabecular microstructure even at the same spatial resolution.
Solution Approach 2:
The patent introduces energy discrimination as an intermediary mechanism that enhances the visibility of trabecular structures. By using energy-based segmentation and processing, the system can isolate and emphasize microstructural features that are otherwise indistinguishable in conventional high-resolution images.
3Device complexity
If conventional imaging methods are used, then device complexity is reduced, but osteoporosis detection accuracy is insufficient
Solution Approach 1:
The patent employs dual-energy or multi-energy imaging parameters to improve osteoporosis detection accuracy. By acquiring images at different energy levels and processing them through subtraction or ratio techniques, the system enhances trabecular visibility and provides more accurate osteoporosis assessment without requiring fundamentally new hardware architectures.
Solution Approach 2:
The patent uses dynamic image processing techniques where images acquired at different energy levels are combined through subtraction or other computational methods. This dynamic processing adaptively enhances trabecular structures based on the differential attenuation characteristics, improving detection accuracy while maintaining relatively simple device configuration.
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
The method allows for simple and accurate discrimination of osteoporosis by clearly depicting the trabecular structure of cancellous bone, enhancing the precision of osteoporosis detection.
Implementation Method 1
acquire two radiation images acquired by imaging a subject including a bone part and a soft part with radiation having different energy distributions
Data Source
AI summary
A processor is configured to acquire two radiation images acquired by imaging a subject including a bone part and a soft part with radiation having different energy distributions, derive a bone part image including a microstructure inside the bone part based on the two radiation images, and derive a likelihood of osteoporosis based on the bone part image or a partial image including a bone of interest in the bone part image.