Abstract
In computed tomography (CT) images, the presence of metal artifacts leads to contaminated object structures. Theoretically, eliminating metal artifacts in the sinogram domain can correct projection deviation and provide reconstructed images that are more real. Contemporary methods that use deep networks for completing metal-damaged sinogram data are limited to discontinuity at the boundaries of traces, which, however, lead to secondary artifacts. This study modifies the traditional U-net and adds two sinogram feature losses of projection images—namely, continuity and consistency of projection data at each angle, improving the accuracy of the complemented sinogram data. Masking the metal traces also ensures the stability and reliability of the unaffected data during metal artifacts reduction. The projection and reconstruction results and various evaluation metrics reveal that the proposed method can accurately repair missing data and reduce metal artifacts in reconstructed CT images.
Highlights
IntroductionWhen the scanned object contains a high-density structure such as metal, because of the strong attenuation of the metal, the X-rays cannot fully penetrate the object, which causes a dark shadow in the measured sinogram [3]
Mean absolute error (MAE) was introduced as an evaluation metric to quantify the quality of the processed images
With the same dataset and number of training epochs, we compared our model with the following models: LI [12], fully connected neural network (FCN) [25], and U-net [26]
Summary
When the scanned object contains a high-density structure such as metal, because of the strong attenuation of the metal, the X-rays cannot fully penetrate the object, which causes a dark shadow in the measured sinogram [3]. These values no longer satisfy Beer’s law, resulting in information loss in reconstructed CT images because of the presence of metal artifacts. After more than 40 years of research, there is still no general solution for metal artifacts reduction (MAR). MAR is still a common and challenging problem in CT research [4]
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call