Projection Data Correction for Beam Hardening and Detector Artifacts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Multi-energy imaging/spectral radiography is affected by beam hardening and artifacts due to detector position deviations and obstructions, leading to inaccuracies in reconstructed images.
Innovation Solution
A method and system for correcting projection data using a trained correction model that incorporates transform projection data, including first projection data related to detector shading and second projection data related to detector position, to improve image quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multi-energy imaging/spectral radiography is used to exploit different absorption rates of radiation, then image differentiation capability is improved, but beam hardening artifacts occur during ray transmission
Solution Approach 1:
The patent applies preliminary action by performing artifact correction before image reconstruction. A correction model is trained using projection data from a calibration object to predict and remove beam hardening artifacts and detector-related artifacts from the projection data before it is used for image reconstruction, thereby preventing artifacts from appearing in the final image
Solution Approach 2:
The patent introduces an intermediary correction model that acts as a mediator between the raw projection data and the final reconstructed image. This correction model, trained on calibration data, processes the projection data to eliminate artifacts caused by beam hardening and detector imperfections, allowing the useful diagnostic information to pass through while blocking harmful artifacts
2Adaptability or versatility
If broadband spectrum rays are used for imaging, then imaging capability is improved, but beam hardening occurs during transmission
Solution Approach 1:
The correction model is trained in advance using projection data acquired with a broadband spectrum from a calibration object. This preliminary training enables the model to learn the characteristics of beam hardening artifacts specific to the imaging system and spectrum, allowing it to effectively correct these artifacts when processing actual patient or object data
3Ease of operation
If detector position deviates from reference position, then device assembly is simplified, but installation position artifacts occur in projection data
Solution Approach 1:
The correction model performs self-service by automatically detecting and correcting for detector position deviations and other detector-related artifacts. During training with a calibration object, the model learns the relationship between detector position variations and resulting artifacts, enabling it to self-correct projection data without requiring manual detector repositioning or complex mechanical alignment procedures
Solution Approach 2:
The correction model serves as an intermediary that compensates for detector position deviations. Rather than requiring the detector to be precisely positioned, the correction model processes the projection data to remove artifacts caused by position deviations, allowing the system to tolerate easier mechanical assembly while maintaining high measurement precision
4Device complexity
If imaging device components obstruct rays, then device structure is simplified, but radiation obstruction artifacts occur in projection data
Solution Approach 1:
The correction model is trained in advance using projection data that includes artifacts from radiation obstruction by imaging device components. This preliminary training enables the model to learn the specific patterns of obstruction artifacts produced by the device structure, allowing it to effectively identify and correct these artifacts in subsequent imaging sessions
Solution Approach 2:
The patent converts the harmful effect of radiation obstruction into a beneficial correction process. By training the correction model with calibration data that includes obstruction artifacts, the model learns to recognize these patterns and transform them into corrected projection data, effectively turning the previously harmful obstruction effects into opportunities for artifact removal and image improvement
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 correction model effectively addresses beam hardening and detector-related artifacts, enhancing the accuracy and quality of reconstructed images.
Implementation Method 1
beam hardening may occur during the ray transmission process, resulting in different attenuation at different positions
Implementation Method 2
a detector, or a portion thereof, used to acquire the projection data
Data Source
AI summary
The present disclosure provides a method and system for correction projection data. The method includes: obtaining the entity projection data and the transformed projection data related to the imaging object, the transformed projection data includes the first projection data related to the pixel shading generated by the detector components; inputting the entity projection data, the transformed projection data to the trained correction model and obtaining the correction projection data. The correction model obtained through training realizes the efficient and accurate correction of multi-energy imaging/spectral radiography, so that the obtained correction projection data may be more in line with the complexity of the actual system, and the correction effect may be better.