Spectral CT Monoenergetic Imaging for Complex Metal Artifact Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing metal artifact reduction algorithms for virtual monoenergetic images in spectral CT are ineffective for irregular metal shapes and complex artifact distributions, often introducing new artifacts and failing to achieve comparable suppression effects at lower energies as at higher energies.
Innovation Solution
A method involving the extraction of artifact and non-artifact regions from virtual monoenergetic images, constructing a relational model between these regions and basis material images, and synthesizing corrected basis material images to reduce metal artifacts across various energies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional MAR algorithms based on projection and interpolation are used, then metal artifacts can be reduced in regular shapes with simple artifact distributions, but the correction effect deteriorates for irregular metal shapes and complex artifact distributions, and new artifacts may be introduced
Solution Approach 1:
The patent segments the image into artifact regions and non-artifact regions using masks, then processes each region differently. The artifact regions are corrected using learned transformations while non-artifact regions are preserved, allowing the method to handle complex artifact distributions without introducing new artifacts.
Solution Approach 2:
The patent uses deep learning models to copy and transform artifact-free image regions to correspond artifact regions, creating corrected images by composing transformed non-artifact regions with corrected artifact regions. This copying approach enables effective correction for irregular shapes and complex distributions.
2Object-affected harmful factors
If virtual monoenergetic images at higher energies are used, then metal artifact suppression effect is improved, but the images still contain obvious metal artifacts at lower energies
Solution Approach 1:
The patent processes virtual monoenergetic images across multiple energy levels by applying energy-specific masks and learned transformations. The method adjusts processing parameters for different energy levels, enabling effective artifact correction at lower energies where traditional high-energy images show obvious artifacts.
3Object-affected harmful factors
If deep learning methods are applied to metal artifact reduction, then artifact suppression can be achieved, but the computational complexity and processing time increase
Solution Approach 1:
The patent performs preliminary actions by pre-processing images to generate masks identifying artifact and non-artifact regions before applying the deep learning correction. This segmentation step simplifies the subsequent learning process and reduces computational complexity by focusing only on relevant regions.
Data Source
AI summary
The present invention provides a metal artifact reduction method in an image domain for spectral CT, and belongs to the technical field of CT imaging. During imaging of a target (e.g., a patient) with a metal implant, metal artifacts can be observed in virtual monoenergetic images obtained by current devices, in particular, it is more obvious at a low energy (low keV). According to the method, by extraction of non-artifact regions (or low-artifact regions) in the virtual monoenergetic images in which artifacts exist and decomposition of basis materials, a relational model between basis materials and artifact-free (or low-artifact) images is constructed, then pixel (voxel) CT values in the artifact-free monoenergetic images corresponding to artifact regions in the above images with artifacts are substituted into the above relational model, and new decomposition of the basis materials is acquired, so that virtual monoenergetic images after artifact correction under arbitrary energy are synthesized.