Related Experiment Video
Updated: Sep 29, 2025
10:12
Synchrotron X-ray Microdiffraction and Fluorescence Imaging of Mineral and Rock Samples
Published on: June 19, 2018
9.2K
Metal Artifact Reduction in Spectral X-ray CT Using Spectral Deep Learning.
Matteo Busi1, Christian Kehl1, Jeppe R Frisvad1
1Department of Physics, Technical University of Denmark, 2800 Kongens Lyngby, Denmark.
Journal of Imaging
|March 24, 2022
Summary
Spectral X-ray computed tomography (SCT) uses deep learning to reduce metal artifacts. This method enhances image quality in low-energy channels, offering near real-time correction for industrial applications.
Area of Science:
- Materials Science
- Medical Imaging
- Computer Vision
Background:
- Spectral X-ray computed tomography (SCT) offers enhanced imaging capabilities over conventional X-ray CT by providing spectral photon energy resolution.
- Despite mitigating some distortions like beam hardening, SCT still suffers from metal artifacts, particularly in low-energy channels due to photon starvation.
- These artifacts significantly degrade the quality of reconstructed images, limiting the technique's utility in certain applications.
Purpose of the Study:
- To develop and present a novel spectral deep learning-based correction method for metal artifact reduction in Spectral X-ray computed tomography (SCT).
- To demonstrate the effectiveness of the proposed method in reducing streaking artifacts across all energy channels.
- To validate the importance of spectral information in restoring image quality in low-energy channels affected by metal artifacts.
Main Methods:
- A spectral deep learning approach was developed for artifact correction.
- The method was applied to Spectral X-ray computed tomography (SCT) data to reduce metal artifacts.
- The correction's performance was evaluated across different energy channels, focusing on low-energy reconstructions.
Main Results:
- The spectral deep learning correction method efficiently reduced streaking artifacts in all measured energy channels.
- The additional spectral information proved crucial for restoring image quality in low-energy channels impacted by metal artifacts.
- The correction method is parameter-free and operates rapidly, processing each energy channel in approximately 15 ms.
Conclusions:
- The proposed spectral deep learning method effectively reduces metal artifacts in Spectral X-ray computed tomography (SCT).
- The energy domain information is vital for artifact correction, especially in low-energy channels.
- The method's speed and parameter-free nature make it suitable for near real-time industrial applications.
Related Concept Videos
01:24X-ray Imaging
8.0K
German physicist Wilhelm Röntgen (1845–1923) was experimenting with electrical current when he discovered that a mysterious and invisible "ray" would pass through his flesh but leave an outline of his bones on a screen coated with a metal compound. In 1895, Röntgen made the first durable record of the internal parts of a living human: an "X-ray" image (as it came to be called) of his wife’s hand. Scientists worldwide quickly began their own experiments with...
8.0K
01:10X-ray Diffraction of Biological Samples
4.1K
X-ray diffraction or XRD is an analytical tool that utilizes X-rays to study ordered structures such as crystalline organic and inorganic samples, polycrystalline materials, proteins, carbohydrates, and drugs.
According to Bragg's law, when X-rays strike the sample positioned on a stage, the rays are scattered by the electron clouds around the sample atoms. The X-ray diffraction or scattering is caused by constructive interference of the X-ray waves that reflect off the internal...
According to Bragg's law, when X-rays strike the sample positioned on a stage, the rays are scattered by the electron clouds around the sample atoms. The X-ray diffraction or scattering is caused by constructive interference of the X-ray waves that reflect off the internal...
4.1K