Metal Artifact Reduction for X-Ray Computed Tomography Using U-Net in Image Domain

Metal artifacts seriously degrade the quality of the CT data and bring great difficulties to subsequent image processing and analysis, which nowadays become a great concern in X-ray CT applications. In this paper, we introduce a U-net-based metal artifact reduction method into CT image domain. The proposed network reduces metal artifacts by learning an end-to-end mapping of images from metal-corrupted CT images to their corresponding artifact-free ground truth images. We design and optimize the network through the simulation experiments. The experimental results show that the proposed method can well reduce metal artifacts of CT images, and this method has higher computational efficiency and greatly shortens the processing time. It avoids complex image preprocessing and can accept input images of any size. Therefore, it can be a more automated way to handle large amounts of data, making it ideal for existing CT workflows.

[1]  Chang-Ock Lee,et al.  A CT metal artifact reduction algorithm based on sinogram surgery. , 2018, Journal of X-ray science and technology.

[2]  S. Dwivedi,et al.  Obesity May Be Bad: Compressed Convolutional Networks for Biomedical Image Segmentation , 2020 .

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Toby P. Breckon,et al.  Materials-based 3D segmentation of unknown objects from dual-energy computed tomography imagery in baggage security screening , 2015, Pattern Recognit..

[5]  Johan Nuyts,et al.  An experimental survey of metal artefact reduction in computed tomography. , 2013, Journal of X-ray science and technology.

[6]  C. McCollough,et al.  Dual- and Multi-Energy CT: Principles, Technical Approaches, and Clinical Applications. , 2015, Radiology.

[7]  J. Hsieh,et al.  An iterative approach to the beam hardening correction in cone beam CT. , 2000, Medical physics.

[8]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[9]  Jin Keun Seo,et al.  Sinogram-consistency learning in CT for metal artifact reduction , 2017, ArXiv.

[10]  D E Raeside,et al.  A pattern recognition method for the removal of streaking artifact in computed tomography. , 1981, Radiology.

[11]  Rainer Raupach,et al.  Normalized metal artifact reduction (NMAR) in computed tomography. , 2010, Medical physics.

[12]  Jin Keun Seo,et al.  Metal Artifact Reduction for Polychromatic X-ray CT Based on a Beam-Hardening Corrector , 2016, IEEE Transactions on Medical Imaging.

[13]  Francesco C Stingo,et al.  An evaluation of three commercially available metal artifact reduction methods for CT imaging , 2015, Physics in medicine and biology.

[14]  Yannan Jin,et al.  Reducing Metal Streak Artifacts in CT Images via Deep Learning : Pilot Results , 2017 .

[15]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[16]  Ge Wang,et al.  Metal Artifact Reduction in CT: Where Are We After Four Decades? , 2016, IEEE Access.

[17]  L. Xing,et al.  Metal artifact reduction in x-ray computed tomography (CT) by constrained optimization. , 2011, Medical physics.

[18]  Shuai Leng,et al.  dual- and multi- energy C t : Principles, Technical Approaches, and , 2015 .

[19]  Yanbo Zhang,et al.  Metal artifact reduction based on the combined prior image , 2014, 1408.5198.

[20]  Bruno De Man,et al.  Deep learning methods for CT image-domain metal artifact reduction , 2017, Optical Engineering + Applications.

[21]  Hai Zhang,et al.  Realization of Industry 4.0 with high speed CT in high volume production , 2018, CIRP Journal of Manufacturing Science and Technology.

[22]  Jiang Hsieh,et al.  Computed Tomography: Principles, Design, Artifacts, and Recent Advances, Fourth Edition , 2022 .

[23]  Emil Y. Sidky,et al.  Spectral CT metal artifact reduction with an optimization-based reconstruction algorithm , 2017, Medical Imaging.

[24]  Ge Wang,et al.  Deep learning methods to guide CT image reconstruction and reduce metal artifacts , 2017, Medical Imaging.

[25]  Jin Keun Seo,et al.  Machine-learning-based nonlinear decomposition of CT images for metal artifact reduction , 2017, 1708.00244.

[26]  Patrick Dupont,et al.  An iterative maximum-likelihood polychromatic algorithm for CT , 2001, IEEE Transactions on Medical Imaging.

[27]  David Faul,et al.  Suppression of Metal Artifacts in CT Using a Reconstruction Procedure That Combines MAP and Projection Completion , 2009, IEEE Transactions on Medical Imaging.

[28]  Benoit Hamelin,et al.  Iterative CT reconstruction of real data with metal artifact reduction , 2008, 2008 5th IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[29]  Ge Wang,et al.  A Perspective on Deep Imaging , 2016, IEEE Access.

[30]  Rainer Raupach,et al.  A new algorithm for metal artifact reduction in computed tomography: in vitro and in vivo evaluation after total hip replacement. , 2003, Investigative radiology.

[31]  W. Kalender,et al.  Reduction of CT artifacts caused by metallic implants. , 1987 .

[32]  S. Zhao,et al.  X-ray CT metal artifact reduction using wavelets: an application for imaging total hip prostheses , 2000, IEEE Transactions on Medical Imaging.

[33]  Xuanqin Mou,et al.  Beam hardening correction for fan-beam CT imaging with multiple materials , 2010, IEEE Nuclear Science Symposuim & Medical Imaging Conference.

[34]  W. Kalender,et al.  Generalized multi-dimensional adaptive filtering for conventional and spiral single-slice, multi-slice, and cone-beam CT. , 2001, Medical physics.

[35]  F. Boas,et al.  CT artifacts: Causes and reduction techniques , 2012 .

[36]  Jin Keun Seo,et al.  CT sinogram‐consistency learning for metal‐induced beam hardening correction , 2017, Medical physics.

[37]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).