CT Metal Artifact Reduction via Voxel Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current CT imaging techniques struggle to effectively correct metal artifacts caused by high density regions, such as metal implants and dental fillings, especially in composite imaging subjects with multiple high and medium density regions, leading to significant image degradation and measurement errors.
Innovation Solution
An automated method that clusters and classifies pixels in the uncorrected tomographic image into metal, bone, tissue, and air classes, replaces metal class pixels with values from another class, and uses forward projection to generate model projection data, identifying and replacing corrupted regions to produce corrected projection data for improved image reconstruction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If filtered backprojection is used to reconstruct images from projection data, then image reconstruction is achieved, but metal artifacts and streaks appear that deteriorate image quality
Solution Approach 1:
The patent applies preliminary action by performing clustering and classification of pixels before the reconstruction process. The method identifies and segments metal regions in the projection data before filtered backprojection, allowing for preprocessing that prevents metal artifacts from deteriorating the final image quality. This preliminary segmentation enables the system to handle high attenuating objects before they cause harmful artifacts.
2Loss of information
If projection data passing through high density regions is used for reconstruction, then complete data coverage is achieved, but measurement errors increase due to high attenuation
Solution Approach 1:
The patent applies segmentation by dividing the projection data into different regions based on attenuation characteristics. Using clustering algorithms, the method segments projection data into regions affected by high density objects and regions that are not affected. This segmentation allows the system to identify and handle corrupted data portions separately, preventing measurement errors from propagating through the reconstruction process while maintaining completeness of the overall data set.
3Measurement precision
If automated artifact correction is implemented, then diagnostic accuracy improves, but processing complexity and computational cost increase
Solution Approach 1:
The patent applies self-service by implementing automated clustering and classification algorithms that perform artifact correction without requiring manual intervention. The system automatically identifies metal regions, segments corrupted projection data, and reconstructs images with reduced artifacts. This automation improves diagnostic accuracy while managing processing complexity through efficient algorithms that adapt to different imaging scenarios without requiring complex manual 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
This approach effectively compensates for metal artifacts, enhancing image quality by reducing streaks and improving diagnostic accuracy, particularly in medical imaging applications with multiple density regions, and supports accurate radiation therapy planning.
Implementation Method 1
high absorbing objects such as metal bodies may cause significant artifacts... Metal artifacts arise when the imaged region of interest contains metal implants, dental fillings, bullets, or other articles of high radiation absorption which prevent the x-rays from fully penetrating the subject
Data Source
AI summary
A reconstruction processor (34) reconstructs acquired projection data (S) into an uncorrected reconstructed image (T). A classifying algorithm (66) classifies pixels of the uncorrected reconstructed image (T) at least into metal, bone, tissue, and air pixel classes. A clustering algorithm (60) iteratively assigns pixels to best fit classes. A pixel replacement algorithm (70) replaces metal class pixels of the uncorrected reconstructed image (T) with pixel values of the bone density class to generate a metal free image. A morphological algorithm (80) applies prior knowledge of the subject's anatomy to the metal free image to correct the shapes of the class regions to generate a model tomogram image. A forward projector (88) forward projects the model tomogram image to generate model projection data (Smodel). A corrupted rays identifying algorithm (100) identifies the rays in the original projection data (S) which lie through the regions containing metal objects. A corrupted rays replacement algorithm (102) replaces the corrupted regions with corresponding regions of the model projection data to generate corrected projection data (S′). The reconstruction processor (34) reconstructs the corrected projection data (S) into a corrected reconstructed 3D image (T′).