Head CT Scan Motion Artifact Correction via Diffusion-Based Generative Models (original) (raw)

Abstract

Head motion is a major source of image artifacts in head computed tomography (CT), degrading the image quality and impacting diagnosis. Image-domain-based motion correction is practical for routine use since it doesn’t rely on hard-to-obtain CT projection data. However, existing convolutional neural network (CNN)-based methods tend to over-smooth images, particularly in cases of moderate to severe 3D motion artifacts. Motivated by the improved image quality and more stable training of diffusion-based generative models, we propose a novel 3D head CT motion correction approach based on conditional diffusion, named HeadMotion-EDM (HM-EDM). This approach has three features. Firstly, we utilize motion-corrupted images as the conditional input. Secondly, we leverage the advanced Elucidated Diffusion Model (EDM) framework, which integrates several pivotal engineering improvements in the diffusion model and significantly expedites the sampling process. Thirdly, we design an efficient 3D-patch-wise training method for 3D CT data. Comparative studies demonstrate that our approach surpasses CNN-based techniques as well as the denoising diffusion probabilistic model (DDPM) in both simulation and phantom studies. Furthermore, radiologists reviewed the results of applying HM-EDM to real-world portable head CT scans, showing its effectiveness in eliminating motion artifacts and improving diagnostic value.

Similar content being viewed by others

References

  1. Kyme, A.Z., Fulton, R.R.: Motion estimation and correction in SPECT, PET and CT. Phys. Med. Biol. 66(18) (2021). https://doi.org/10.1088/1361-6560/ac093b
  2. Kim, J.-H., Sun, T., Alcheikh, A.R., Kuncic, Z., Nuyts, J., Fulton, R.: Correction for human head motion in helical x-ray CT. Phys. Med. Biol. 61(4), 1416–1438 (2016). https://doi.org/10.1088/0031-9155/61/4/1416
    Article Google Scholar
  3. Sun, T., Kim, J.-H., Fulton, R., Nuyts, J.: An iterative projection-based motion estimation and compensation scheme for head X-ray CT. Med. Phys. 43(10), 5705 (2016). https://doi.org/10.1118/1.4963218
    Article MATH Google Scholar
  4. Ouadah, S., Jacobson, M., Stayman, J.W., Ehtiati, T., Weiss, C., Siewerdsen, J.H.: Correction of patient motion in cone-beam CT using 3D–2D registration. Phys. Med. Biol. 62(23), 8813–8831 (2017). https://doi.org/10.1088/1361-6560/aa9254
    Article Google Scholar
  5. Bruder, H., Rohkohl, C., Stierstorfer, K., Flohr, T.: Compensation of skull motion and breathing motion in CT using data-based and image-based metrics, respectively. Med. Imaging 2016 Phys. Med. Imaging SPIE, 348–359 (2016). https://doi.org/10.1117/12.2217395
  6. Jang, S., Kim, S., Kim, M., Ra, J.B.: Head motion correction based on filtered backprojection for X-ray CT imaging. Med. Phys. 45(2), 589–604 (2018). https://doi.org/10.1002/mp.12705
    Article MATH Google Scholar
  7. Kim, S., Chang, Y., Ra, J.B.: Cardiac motion correction based on partial angle reconstructed images in x-ray CT. Med. Phys. 42(5), 2560–2571 (2015). https://doi.org/10.1118/1.4918580
    Article MATH Google Scholar
  8. Hahn, J., et al.: Motion compensation in the region of the coronary arteries based on partial angle reconstructions from short-scan CT data. Med. Phys. 44(11), 5795–5813 (2017). https://doi.org/10.1002/mp.12514
    Article MATH Google Scholar
  9. Chen, Z., Li, Q., Wu, D.: Estimate and compensate head motion in non-contrast head CT scans using partial angle reconstruction and deep learning. Med. Phys. 51(5), 3309–3321 (2024). https://doi.org/10.1002/mp.17047
    Article MATH Google Scholar
  10. Ko, Y., Moon, S., Baek, J., Shim, H.: Rigid and non-rigid motion artifact reduction in X-ray CT using attention module. Med. Image Anal. 67, 101883 (2021). https://doi.org/10.1016/j.media.2020.101883
    Article MATH Google Scholar
  11. Su, B., et al.: A deep learning method for eliminating head motion artifacts in computed tomography. Med. Phys. 49(1), 411–419 (2022). https://doi.org/10.1002/mp.15354
    Article MATH Google Scholar
  12. Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. arXiv, 16 December 2020. http://arxiv.org/abs/2006.11239. Accessed 11 Dec 2023
  13. Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv, 10 February 2021. https://doi.org/10.48550/arXiv.2011.13456
  14. Song, Y., Shen, L., Xing, L., Ermon, S.: Solving inverse problems in medical imaging with score-based generative models. arXiv.org. https://arxiv.org/abs/2111.08005v2. Accessed 11 Dec 2023
  15. Chung, H., Ryu, D., McCann, M.T., Klasky, M.L., Ye, J.C.: Solving 3D inverse problems using pre-trained 2D diffusion models. arXiv, 19 November 2022. https://doi.org/10.48550/arXiv.2211.10655
  16. Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. arXiv, 11 October 2022. https://doi.org/10.48550/arXiv.2206.00364
  17. Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv, 05 October 2022. https://doi.org/10.48550/arXiv.2010.02502
  18. Anderson, B.D.O.: Reverse-time diffusion equation models. Stoch. Process. Their Appl. 12(3), 313–326 (1982). https://doi.org/10.1016/0304-4149(82)90051-5
    Article MathSciNet MATH Google Scholar
  19. Dockhorn, T., Vahdat, A., Kreis, K.: Score-based generative modeling with critically-damped Langevin diffusion. arXiv, 25 March 2022. https://doi.org/10.48550/arXiv.2112.07068
  20. Vahdat, A., Kreis, K., Kautz, J.: Score-based generative modeling in latent space. arXiv, 02 December 2021. https://doi.org/10.48550/arXiv.2106.05931
  21. Huang, L., Qin, J., Zhou, Y., Zhu, F., Liu, L., Shao, L.: Normalization techniques in training DNNs: methodology, analysis and application. IEEE Trans. Pattern Anal. Mach. Intell. 45(08), 10173–10196 (2023). https://doi.org/10.1109/TPAMI.2023.3250241
    Article MATH Google Scholar

Download references

Author information

Authors and Affiliations

  1. Center for Advanced Medical Computing and Analysis, Massachusetts General Hospital and Harvard Medical School, Boston, MA, 02114, USA
    Zhennong Chen, Siyeop Yoon, Matthew Tivnan, Quanzheng Li & Dufan Wu
  2. Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA, 02114, USA
    Quirin Strotzer, Rehab Naeem Khalid & Rajiv Gupta

Authors

  1. Zhennong Chen
  2. Siyeop Yoon
  3. Quirin Strotzer
  4. Rehab Naeem Khalid
  5. Matthew Tivnan
  6. Quanzheng Li
  7. Rajiv Gupta
  8. Dufan Wu

Corresponding author

Correspondence toDufan Wu .

Editor information

Editors and Affiliations

  1. University of Pittsburgh, Pittsburgh, PA, USA
    Shandong Wu
  2. National Institute of Biomedical Imaging and Bioengineering, Bethesda, MD, USA
    Behrouz Shabestari
  3. Stanford University, Stanford, CA, USA
    Lei Xing

Rights and permissions

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Cite this paper

Chen, Z. et al. (2025). Head CT Scan Motion Artifact Correction via Diffusion-Based Generative Models. In: Wu, S., Shabestari, B., Xing, L. (eds) Applications of Medical Artificial Intelligence. AMAI 2024. Lecture Notes in Computer Science, vol 15384. Springer, Cham. https://doi.org/10.1007/978-3-031-82007-6\_3

Download citation

Keywords

Publish with us