Abstract
Purpose
In X-ray CT systems, ring artifacts caused by the nonuniform response of detector elements degrades the reconstruction quality and affects the subsequent processing and quantitative analysis of the image.
Method
In this paper, a novel method is proposed to remove the ring artifacts in CT image by applying deep learning algorithm based on convolutional neural network (CNN) and recurrent neural network (RNN). First, the reconstructed CT images is transformed into polar coordinate system to make rings appear as stripes. Then, a CNN is constructed to detect the stripes, and a RNN is utilized to process the line artifact correction. After that, by retransforming the corrected image from polar coordinate system to Cartesian coordinate system, a ring artifact removal image can be achieved.
Results
The presented method can successfully reduce the CT ring artifact on simulated and real data. Specifically, in the experiment with real water phantom, the center and peripheral standard deviations reduced 46% and 24%, respectively.
Conclusions
The proposed method is potential to be widely deployed in industrial and medical CT systems, due to the excellent results on correction and the real-time performance without adjusting parameters manually.
Similar content being viewed by others
References
M.K. Hasan, F. Sadi, S.Y. Lee, Removal of ring artifacts in micro-CT imaging using iterative morphological filters. Sig. Image Video Proc. 6(1), 41–53 (2012)
Raven and C. J. R. o. S. Instruments, "Numerical removal of ring artifacts in microtomography," 69(8), 2978–2980, (1998).
M. Boin and A. J. O. E. Haibel, "Compensation of ring artefacts in synchrotron tomographic images," 14(25) 12071–5, (2006).
B. Muench, P. Trtik, F. Marone, M. Stampanoni, Stripe and ring artifact removal with combined wavelet—Fourier filtering. Opt. Express 17(10), 8567–8591 (2009)
J. Sijbers, A. Postnov, Reduction of ring artefacts in high resolution micro-CT reconstructions. Phys. Med. Biol. 49(14), N247 (2004)
F. Brun, G. Kourousias, D. Dreossi, and L. Mancini, An improved method for ring artifacts removing in reconstructed tomographic images. World Congress on Medical Physics and Biomedical Engineering, September 7 - 12, 2009, Munich, Germany, (2009).
Y. W. Chen, G. Duan, A. Fujita, K. Hirooka, and Y. Ueno, "Ring artifacts reduction in cone-beam CT images based on independent component analysis," in IEEE Instrumentation & Measurement Technology Conference, (2009).
Z. Wei, S. Wiebe, D. Chapman, Ring artifacts removal from synchrotron CT image slices. J. Instrument. 8(06), C06006 (2013)
L. Yan, W. Tao, Z. Sheng, Q. J. P. I. M. Zhang, and Biology, "A variation-based ring artifact correction method with sparse constraint for flat-detector CT," 61(3), 1278–1292, (2016).
S. Ioffe and C. J. J. O. Szegedy, "Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift," (2015).
A. Krizhevsky, I. Sutskever, and G. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," in NIPS, (2012).
O. Ronneberger, P. Fischer, and T. J. S. Brox, Cham, "U-Net: Convolutional Networks for Biomedical Image Segmentation," (2015).
Z. Kai, W. Zuo, Y. Chen, D. Meng, and Z. J. I. T. o. I. P. Lei, "Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising," vol. 26, no. 7, pp. 3142–3155, (2016).
J. Kim, J. K. Lee, and K. M. Lee, "Accurate Image Super-Resolution Using Very Deep Convolutional Networks," (2015).
W. Shi, J. Caballero, F. Huszár, J. Totz, and Z. Wang, "Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network," in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), (2016).
Hu, Chen, Yi, Zhang, Weihua, Zhang, Peixi, Liao, Ke, Li, Jiliu, Zhou,Ge, Wang, "Low-dose CT via convolutional neural network %J Biomedical Optics Express," (2017).
Y. Ma, P. Feng, P. He, Z. Long, and B. Wei, "A Deep Learning Based Method for Low Dose Lung CT Noise Reduction," Singapore, (2020), pp. 649–657: Springer Singapore.
W. Xia, Z. Lu, Y. Huang, Y. Liu, and Y. Zhang, "CT Reconstruction with PDF: Parameter-Dependent Framework for Multiple Scanning Geometries and Dose Levels," (2020).
W. Xia, Z. Lu, Y. Huang, Z. Shi, and Y. Zhang, "MAGIC: Manifold and Graph Integrative Convolutional Network for Low-Dose CT Reconstruction," (2020).
S. Zhao, J. Li, Q. Huo, and Ieee, REMOVING RING ARTIFACTS IN CBCT IMAGES VIA GENERATIVE ADVERSARIAL NETWORK (2018 Ieee International Conference on Acoustics, Speech and Signal Processing). (2018), pp. 1055–1059.
W. Yang et al., "Deep Joint Rain Detection and Removal from a Single Image," in 30th Ieee Conference on Computer Vision and Pattern Recognition(IEEE Conference on Computer Vision and Pattern Recognition, (2017), pp. 1685–1694.
X. Li, J. Wu, Z. Lin, H. Liu, and H. Zha, "Recurrent Squeeze-and-Excitation Context Aggregation Net for Single Image Deraining," in Computer Vision - Eccv 2018, Pt Vii, vol. 11211, V. Ferrari, M. Hebert, C. Sminchisescu, and Y. Weiss, Eds. (Lecture Notes in Computer Science, (2018), pp. 262–277.
"A CNN based Hybrid Ring Artifact Reduction Algorithm for CT Images %J IEEE Transactions on Radiation and Plasma Medical Sciences," vol. PP, no. 99, pp. 1–1, (2020).
H. Jie, S. Li, S. Gang, S. J. I. T. o. P. A. Albanie, and M. Intelligence, "Squeeze-and-Excitation Networks," vol. PP, no. 99, (2017).
Available: https://www.aapm.org/grandchallenge/lowdosect/#trainingData
D. Prell, Y. Kyriakou, W.A. Kalender, Comparison of ring artifact correction methods for flat-detector CT. Phys. Med. Biol. 54(12), 3881–3895 (2009)
W. Fang, L. Li, and Z. J. I. A. Chen, "Removing Ring Artefacts for Photon-Counting Detectors Using Neural Networks in Different Domains," vol. PP, no. 99, pp. 1–1, (2020).
Acknowledgements
This work is partially supported by National Key R&D Program of China (No. 2017YFF0107201) and CAS Interdisciplinary Innovation Team (No. JCTD-2019-02), National Natural Science Foundation of China (NSFC) (No. 11975250), the Science and Technology Service Network Initiative of Chinese Academy of Sciences (No. KFJ-STS-QYZD-193) and the Key Technology Research and Development Team Project of Chinese Academy of Sciences (No. GJJSTD20200004).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared that there is no conflict of interest.
Rights and permissions
About this article
Cite this article
Yuan, L., Xu, Q., Liu, B. et al. A deep learning-based ring artifact correction method for X-ray CT. Radiat Detect Technol Methods 5, 493–503 (2021). https://doi.org/10.1007/s41605-021-00286-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s41605-021-00286-1