Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Hybrid model-based and deep learning-based metal artifact reduction method in dental cone-beam computed tomography

  • Jin Hur (Department of Computer Science and Engineering, Seoul National University) ;
  • Yeong-Gil Shin (Department of Computer Science and Engineering, Seoul National University) ;
  • Ho Lee (Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine)
  • Received : 2023.03.08
  • Accepted : 2023.05.12
  • Published : 2023.08.25
Download PDF
⟨ Previous Next ⟩

Abstract

Objective: To present a hybrid approach that incorporates a constrained beam-hardening estimator (CBHE) and deep learning (DL)-based post-refinement for metal artifact reduction in dental cone-beam computed tomography (CBCT). Methods: Constrained beam-hardening estimator (CBHE) is derived from a polychromatic X-ray attenuation model with respect to X-ray transmission length, which calculates associated parameters numerically. Deep-learning-based post-refinement with an artifact disentanglement network (ADN) is performed to mitigate the remaining dark shading regions around a metal. Artifact disentanglement network (ADN) supports an unsupervised learning approach, in which no paired CBCT images are required. The network consists of an encoder that separates artifacts and content and a decoder for the content. Additionally, ADN with data normalization replaces metal regions with values from bone or soft tissue regions. Finally, the metal regions obtained from the CBHE are blended into reconstructed images. The proposed approach is systematically assessed using a dental phantom with two types of metal objects for qualitative and quantitative comparisons. Results: The proposed hybrid scheme provides improved image quality in areas surrounding the metal while preserving native structures. Conclusion: This study may significantly improve the detection of areas of interest in many dentomaxillofacial applications.

Keywords

Acknowledgement

This study was presented at the International Conference on Nuclear Analytical Techniques in 2022 (NAT2022), which was held in Daejeon, Korea, from December 7 to 9, 2022. This study was supported by a faculty research grant from Yonsei University College of Medicine for 2022 (6-2022-0064) and the National Research Foundation of Korea (NRF) funded by the Korea government (MSIT) (2022R1A2C2011556).

References

  1. W.A. Kalender, R. Hebel, J. Ebersberger, Reduction of CT artifacts caused by metallic implants, Radiology 164 (2) (1987) 576-577. https://doi.org/10.1148/radiology.164.2.3602406
  2. S. Zhao, K.T. Bae, B. Whiting, G. Wang, A wavelet method for metal artifact reduction with multiple metallic objects in the field of view, J. X Ray Sci. Technol. 10 (1) (2002) 67-76, 2.
  3. M. Bal, L. Spies, Metal artifact reduction in CT using tissue-class modeling and adaptive prefiltering, Med. Phys. 33 (8) (2006) 2852-2859. https://doi.org/10.1118/1.2218062
  4. X. Duan, L. Zhang, Y. Xiao, J. Cheng, Z. Chen, Y. Xing, Metal Artifact Reduction in CT Images by Sinogram TV Inpainting, 2008 IEEE Nuclear Science Symposium Conference Record, IEEE, 2008, pp. 4175-4177.
  5. D. Prell, Y. Kyriakou, M. Beister, W.A. Kalender, A novel forward projection-based metal artifact reduction method for flat-detector computed tomography, Phys. Med. Biol. 54 (21) (2009) 6575.
  6. E. Meyer, R. Raupach, M. Lell, B. Schmidt, M. Kachelriess, Normalized metal artifact reduction (NMAR) in computed tomography, Med. Phys. 37 (10) (2010) 5482-5493. https://doi.org/10.1118/1.3484090
  7. Y. Li, X. Bao, X. Yin, Y. Chen, L. Luo, W. Chen, Metal Artifact Reduction in CT Based on Adaptive Steering Filter and Nonlocal Sinogram Inpainting, 2010 3rd International Conference on Biomedical Engineering and Informatics, IEEE, 2010, pp. 380-383.
  8. H.S. Park, J.K. Choi, K.-R. Park, K.S. Kim, S.-H. Lee, J.C. Ye, J.K. Seo, Metal artifact reduction in CT by identifying missing data hidden in metals, J. X Ray Sci. Technol. 21 (3) (2013) 357-372. https://doi.org/10.3233/XST-130384
  9. A. Mehranian, M.R. Ay, A. Rahmim, H. Zaidi, X-Ray CT metal artifact reduction using wavelet domain L0 sparse regularization, IEEE Trans. Med. Imag. 32 (9) (2013) 1707-1722. https://doi.org/10.1109/TMI.2013.2265136
  10. G. Wang, D.L. Snyder, J.A. O'Sullivan, M.W. Vannier, Iterative deblurring for CT metal artifact reduction, IEEE Trans. Med. Imag. 15 (5) (1996) 657-664. https://doi.org/10.1109/42.538943
  11. B. De Man, J. Nuyts, P. Dupont, G. Marchal, P. Suetens, Reduction of metal streak artifacts in x-ray computed tomography using a transmission maximum a posteriori algorithm, IEEE Trans. Nucl. Sci. 47 (3) (2000) 977-981. https://doi.org/10.1109/23.856534
  12. B. De Man, J. Nuyts, P. Dupont, G. Marchal, P. Suetens, An iterative maximum-likelihood polychromatic algorithm for CT, IEEE Trans. Med. Imag. 20 (10) (2001) 999-1008. https://doi.org/10.1109/42.959297
  13. I.A. Elbakri, J.A. Fessler, Segmentation-free statistical image reconstruction for polyenergetic X-ray computed tomography, in: Proceedings IEEE International Symposium on Biomedical Imaging, IEEE, 2002, pp. 828-831.
  14. C. Lemmens, D. Faul, J. Nuyts, Suppression of metal artifacts in CT using a reconstruction procedure that combines MAP and projection completion, IEEE Trans. Med. Imag. 28 (2) (2009) 250-260. https://doi.org/10.1109/TMI.2008.929103
  15. J. Wang, L. Xing, A binary image reconstruction technique for accurate determination of the shape and location of metal objects in x-ray computed tomography, J. X Ray Sci. Technol. 18 (4) (2010) 403-414. https://doi.org/10.3233/XST-2010-0271
  16. J. Hsieh, R.C. Molthen, C.A. Dawson, R.H. Johnson, An iterative approach to the beam hardening correction in cone beam CT, Med. Phys. 27 (1) (2000) 23-29. https://doi.org/10.1118/1.598853
  17. H.S. Park, D. Hwang, J.K. Seo, Metal artifact reduction for polychromatic X-ray CT based on a beam-hardening corrector, IEEE Trans. Med. Imag. 35 (2) (2016) 480-487. https://doi.org/10.1109/TMI.2015.2478905
  18. H. Shi, Z. Yang, S. Luo, Reduce beam hardening artifacts of polychromatic X-ray computed tomography by an iterative approximation approach, J. X Ray Sci. Technol. 25 (3) (2017) 417-428. https://doi.org/10.3233/XST-16187
  19. J. Hur, D. Kim, Y.-G. Shin, H. Lee, Metal artifact reduction method based on a constrained beam-hardening estimator for polychromatic x-ray CT, Phys. Med. Biol. 66 (6) (2021), 065025.
  20. H.S. Park, S.M. Lee, H.P. Kim, J.K. Seo, Y.E. Chung, CT sinogram-consistency learning for metal-induced beam hardening correction, Med. Phys. 45 (12) (2018) 5376-5384. https://doi.org/10.1002/mp.13199
  21. L. Gjesteby, Q. Yang, Y. Xi, Y. Zhou, J. Zhang, G. Wang, Deep learning methods to guide CT image reconstruction and reduce metal artifacts, in: Medical Imaging 2017: Physics of Medical Imaging, International Society for Optics and Photonics, 2017, 101322W.
  22. I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, A. Courville, Y. Bengio, Generative Adversarial Nets, Adv. Neural Inf. Process. Syst., 2014, pp. 2672-2680.
  23. P. Isola, J.-Y. Zhu, T. Zhou, A.A. Efros, Image-to-image translation with conditional adversarial networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1125-1134.
  24. M.U. Ghani, W.C. Karl, Fast enhanced CT metal artifact reduction using data domain deep learning, IEEE Trans. Comput. Imaging 6 (2019) 181-193. https://doi.org/10.1109/TCI.2019.2937221
  25. H. Zhao, O. Gallo, I. Frosio, J. Kautz, Loss functions for image restoration with neural networks, IEEE Trans. Comput. Imaging 3 (1) (2016) 47-57. https://doi.org/10.1109/TCI.2016.2644865
  26. H. Liao, W.-A. Lin, S.K. Zhou, J. Luo, ADN: artifact disentanglement network for unsupervised metal artifact reduction, IEEE Trans. Med. Imag. 39 (3) (2020) 634-643. https://doi.org/10.1109/TMI.2019.2933425
  27. W.-A. Lin, H. Liao, C. Peng, X. Sun, J. Zhang, J. Luo, R. Chellappa, S.K. Zhou, Dudonet: dual domain network for ct metal artifact reduction, Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (2019) 10512-10521.
  28. B. Zhou, X. Chen, S.K. Zhou, J.S. Duncan, C. Liu, DuDoDR-Net: dual-domain data consistent recurrent network for simultaneous sparse view and metal artifact reduction in computed tomography, Med. Image Anal. 75 (2022), 102289.
  29. H. Wang, Y. Li, H. Zhang, D. Meng, Y. Zheng, InDuDoNet+: a deep unfolding dual domain network for metal artifact reduction in CT images, Med. Image Anal. 85 (2023), 102729.
  30. L.A. Feldkamp, L. Davis, J.W. Kress, Practical cone-beam algorithm, J. Opt. Soc. Am. A 1 (6) (1984) 612-619. https://doi.org/10.1364/JOSAA.1.000612
  31. J. Hubbell, S. Seltzer, X-ray mass attenuation coefficients. https://www.nist.gov/pml/x-ray-mass-attenuation-coefficients, 2004.
  32. M. Nakao, K. Imanishi, N. Ueda, Y. Imai, T. Kirita, T. Matsuda, Regularized three-dimensional generative adversarial nets for unsupervised metal artifact reduction in head and neck CT images, IEEE Access 8 (2020) 109453-109465. https://doi.org/10.1109/ACCESS.2020.3002090
  33. K. Yan, X. Wang, L. Lu, R.M. Summers, DeepLesion: automated mining of largescale lesion annotations and universal lesion detection with deep learning, J. Med. Imag. 5 (3) (2018), 036501-036501. https://doi.org/10.1117/1.JMI.5.3.036501
  34. B. Glocker, D. Zikic, E. Konukoglu, D.R. Haynor, A. Criminisi, Vertebrae localization in pathological spine CT via dense classification from sparse annotations, in: Medical Image Computing and Computer-Assisted Intervention-MICCAI 2013: 16th International Conference, Nagoya, Japan, 2013, pp. 262-270. September 22-26, 2013, Proceedings, Part II 16, Springer.
  35. H. Lee, B.P. Fahimian, L. Xing, Binary moving-blocker-based scatter correction in cone-beam computed tomography with width-truncated projections: proof of concept, Phys. Med. Biol. 62 (6) (2017) 2176.