AI Bone Density Assessment From Existing X-Ray Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for acquiring bone density require separate physical examinations and expose subjects to excess radiation, necessitating a method to conveniently determine bone density from existing X-ray images without additional radiation.
Innovation Solution
An X-ray image-based method using a trained learning network to analyze X-ray images, outputting bone density, abnormality position, and probability, utilizing an X-ray imaging system and computer-readable storage medium to process and display the results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a dedicated bone density measuring instrument is used to acquire T-score, then measurement precision is improved, but device complexity and examination time increase
Solution Approach 1:
The X-ray imaging system is enhanced with AI capabilities to perform multiple functions: standard X-ray imaging and bone density assessment. The learning network enables the system to analyze existing X-ray images for bone density evaluation, transforming a single-function device into a multi-functional one that eliminates the need for separate dedicated bone density instruments
Solution Approach 2:
Instead of requiring physical interaction with a dedicated bone density measuring instrument, the system creates a virtual model of bone density assessment by training the learning network on X-ray images with corresponding T-scores from dedicated instruments. This allows the X-ray system to replicate bone density measurement capabilities through image analysis
2Measurement precision
If a dedicated bone density measuring instrument is used, then measurement precision is improved, but loss of time increases due to separate physical examination
Solution Approach 1:
The system merges bone density assessment with standard X-ray imaging procedures. By integrating the learning network into the existing X-ray workflow, the system processes both imaging and bone density analysis in a single examination session, eliminating the need for separate dedicated bone density measurement appointments
Solution Approach 2:
The learning network is pre-trained on datasets containing X-ray images and corresponding T-scores before deployment. This preliminary training enables the system to perform accurate bone density assessment during routine X-ray examinations without requiring additional calibration or setup time during patient examinations
3Measurement precision
If additional dedicated bone density examination is performed, then measurement precision is improved, but object-affected harmful factors increase due to excess radiation exposure
Solution Approach 1:
The system extracts bone density information by analyzing the existing X-ray image data that has already captured radiation attenuation patterns. The learning network learns to derive T-scores from the image pixel values and attenuation characteristics, copying the measurement capability without requiring additional radiation exposure
Solution Approach 2:
Instead of discarding the existing X-ray image after standard imaging, the system recovers additional diagnostic information by applying the learning network to extract bone density metrics from the same image data, maximizing the utility of the radiation already received
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 accurate determination of bone density and abnormality without additional radiation exposure, providing T-scores and classification for improved diagnostic efficiency.
Implementation Method 1
radiation from an X-ray source is emitted toward a subject
Implementation Method 2
the subject under examination is usually a patient in a medical diagnosis application. Some of the radiation passes through the subject under examination and impacts a detector
Data Source
AI summary
The present application provides a method for acquiring bone density, an X-ray imaging system, and a storage medium. The method for acquiring bone density includes acquiring at least one X-ray image of a subject under examination using an X-ray imaging system, wherein the at least one X-ray image is a raw image or a medical image following image processing, and on the basis of a trained learning network, performing processing on the at least one X-ray image, and at least one of position of bone with abnormality, probability of abnormality, and prompt of abnormality, the result including at least one of T-score and classification of bone density, and the abnormality denoting that the T-score exceeds a threshold value range.