Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
175 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Deep Few-view High-resolution Photon-counting Extremity CT at Halved Dose for a Clinical Trial (2403.12331v1)

Published 19 Mar 2024 in physics.med-ph and cs.CV

Abstract: The latest X-ray photon-counting computed tomography (PCCT) for extremity allows multi-energy high-resolution (HR) imaging for tissue characterization and material decomposition. However, both radiation dose and imaging speed need improvement for contrast-enhanced and other studies. Despite the success of deep learning methods for 2D few-view reconstruction, applying them to HR volumetric reconstruction of extremity scans for clinical diagnosis has been limited due to GPU memory constraints, training data scarcity, and domain gap issues. In this paper, we propose a deep learning-based approach for PCCT image reconstruction at halved dose and doubled speed in a New Zealand clinical trial. Particularly, we present a patch-based volumetric refinement network to alleviate the GPU memory limitation, train network with synthetic data, and use model-based iterative refinement to bridge the gap between synthetic and real-world data. The simulation and phantom experiments demonstrate consistently improved results under different acquisition conditions on both in- and off-domain structures using a fixed network. The image quality of 8 patients from the clinical trial are evaluated by three radiologists in comparison with the standard image reconstruction with a full-view dataset. It is shown that our proposed approach is essentially identical to or better than the clinical benchmark in terms of diagnostic image quality scores. Our approach has a great potential to improve the safety and efficiency of PCCT without compromising image quality.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (56)
  1. S. Joyce, O. J. O’Connor, M. M. Maher, and M. F. McEntee, “Strategies for dose reduction with specific clinical indications during computed tomography,” Radiography, vol. 26, pp. S62–S68, 2020.
  2. M. Söderberg and M. Gunnarsson, “Automatic exposure control in computed tomography–an evaluation of systems from different manufacturers,” Acta Radiol., vol. 51, no. 6, pp. 625–634, 2010.
  3. N. Muhammad, M. Karim, H. Harun, M. Rahman, R. Azlan, and N. Sumardi, “The impact of tube current and iterative reconstruction algorithm on dose and image quality of infant ct head examination,” Radiat. Phys. Chem., p. 110272, 2022.
  4. M. J. Willemink, M. Persson, A. Pourmorteza, N. J. Pelc, and D. Fleischmann, “Photon-counting ct: technical principles and clinical prospects,” Radiology, vol. 289, no. 2, pp. 293–312, 2018.
  5. O. Benjaminov, E. Perlow, Z. Romman, R. Levinson, B. Bashara, M. Cohen et al., “Novel, energy-discriminating photon counting CT system (EDCT): first clinical evaluation—CT angiography: Carotid artery stenosis,” presented at the Radiol. Soc. North Amer. 2008 Sci. Assem. Annu. Meeting, Chicago, IL, USA, 2 2008.
  6. K. Rajendran, M. Petersilka, A. Henning, E. R. Shanblatt, B. Schmidt, T. G. Flohr et al., “First clinical photon-counting detector ct system: technical evaluation,” Radiology, vol. 303, no. 1, pp. 130–138, 2022.
  7. R. K. Panta, A. P. Butler, P. H. Butler, N. J. de Ruiter, S. T. Bell, M. F. Walsh et al., “First human imaging with mars photon-counting ct,” in IEEE Nucl. Sci. Symp. Medi. imag. Conf.   IEEE, 2018, pp. 1–7.
  8. F. Ostadhossein, I. Tripathi, L. Benig, D. LoBato, M. Moghiseh, C. Lowe et al., “Multi-“color” delineation of bone microdamages using ligand-directed sub-5 nm hafnia nanodots and photon counting ct imaging,” Adv. Funct. Mater., vol. 30, no. 4, p. 1904936, 2020.
  9. A. S. Wang and N. J. Pelc, “Spectral photon counting ct: Imaging algorithms and performance assessment,” IEEE Trans. Radiat. Plasma Med. Sci., vol. 5, no. 4, pp. 453–464, 2020.
  10. E. Y. Sidky, C.-M. Kao, and X. Pan, “Accurate image reconstruction from few-views and limited-angle data in divergent-beam ct,” J. X-ray Sci. Technol., vol. 14, no. 2, pp. 119–139, 2006.
  11. Q. Xu, H. Yu, X. Mou, L. Zhang, J. Hsieh, and G. Wang, “Low-dose x-ray ct reconstruction via dictionary learning,” IEEE Trans. Med. Imag., vol. 31, no. 9, pp. 1682–1697, 2012.
  12. Y. Mäkinen, L. Azzari, and A. Foi, “Collaborative filtering of correlated noise: Exact transform-domain variance for improved shrinkage and patch matching,” IEEE Trans. Imag. Proc., vol. 29, pp. 8339–8354, 2020.
  13. G. Wang, J. C. Ye, and B. De Man, “Deep learning for tomographic image reconstruciton,” Nat. Mach. Intell., vol. 2, no. 12, pp. 737–748, 2020.
  14. J. He, Y. Yang, Y. Wang, D. Zeng, Z. Bian, H. Zhang, J. Sun, Z. Xu, and J. Ma, “Optimizing a parameterized plug-and-play admm for iterative low-dose ct reconstruction,” IEEE Trans. Med. Imag., vol. 38, no. 2, pp. 371–382, 2018.
  15. H. Chen, Y. Zhang, Y. Chen, J. Zhang, W. Zhang, H. Sun et al., “Learn: Learned experts’ assessment-based reconstruction network for sparse-data ct,” IEEE Trans. Med. Imag., vol. 37, no. 6, pp. 1333–1347, 2018.
  16. L. Shen, W. Zhao, and L. Xing, “Patient-specific reconstruction of volumetric computed tomography images from a single projection view via deep learning,” Nat. Biomed. Eng., vol. 3, no. 11, pp. 880–888, 2019.
  17. W. Wu, D. Hu, C. Niu, H. Yu, V. Vardhanabhuti, and G. Wang, “Drone: Dual-domain residual-based optimization network for sparse-view ct reconstruction,” IEEE Trans. Med. Imag., vol. 40, no. 11, pp. 3002–3014, 2021.
  18. M. Thies, F. Wagner, M. Gu, L. Folle, L. Felsner, and A. Maier, “Learned cone-beam ct reconstruction using neural ordinary differential equations,” arXiv preprint arXiv:2201.07562, 2022.
  19. X. Li, K. Jing, Y. Yang, Y. Wang, J. Ma, H. Zheng, and Z. Xu, “Noise-generating and imaging mechanism inspired implicit regularization learning network for low dose ct reconstrution,” IEEE Trans. Med. Imag., 2023.
  20. M. Li, P. Lorraine, J. Pack, G. Wang, and B. De Man, “Realistic ct noise modeling for deep learning training data generation and application to super-resolution,” in 17th Int. Meeting Fully 3D Imag. Recon. Radiol. Nucl. Med., Stony Brook, NY, USA, 7 2023.
  21. M. Du, K. Liang, Y. Liu, and Y. Xing, “Investigation of domain gap problem in several deep-learning-based ct metal artefact reduction methods,” arXiv preprint arXiv:2111.12983, 2021.
  22. J. Xu, Y. Huang, M.-M. Cheng, L. Liu, F. Zhu, Z. Xu, and L. Shao, “Noisy-as-clean: Learning self-supervised denoising from corrupted image,” IEEE Trans. Imag. Proc., vol. 29, pp. 9316–9329, 2020.
  23. N. Moran, D. Schmidt, Y. Zhong, and P. Coady, “Noisier2noise: Learning to denoise from unpaired noisy data,” in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit., 2020, pp. 12 064–12 072.
  24. A. A. Hendriksen, D. M. Pelt, and K. J. Batenburg, “Noise2inverse: Self-supervised deep convolutional denoising for tomography,” IEEE Trans. Comput. Imag., vol. 6, pp. 1320–1335, 2020.
  25. N. Yuan, J. Zhou, and J. Qi, “Half2half: deep neural network based ct image denoising without independent reference data,” Phys. Med. Biol., vol. 65, no. 21, p. 215020, 2020.
  26. Z. Zhang, X. Liang, W. Zhao, and L. Xing, “Noise2context: Context-assisted learning 3d thin-layer for low-dose ct,” Med. Phys., vol. 48, no. 10, pp. 5794–5803, 2021.
  27. C. Niu, M. Li, F. Fan, W. Wu, X. Guo, Q. Lyu, and G. Wang, “Noise suppression with similarity-based self-supervised deep learning,” IEEE Trans. Med. Imag., 2022.
  28. M. R. Hestenes, “Multiplier and gradient methods,” Journal of optimization theory and applications, vol. 4, no. 5, pp. 303–320, 1969.
  29. S. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein et al., “Distributed optimization and statistical learning via the alternating direction method of multipliers,” Found. Trends Mach. Learn., vol. 3, no. 1, pp. 1–122, 2011.
  30. Y. Wang, W. Yin, and J. Zeng, “Global convergence of admm in nonconvex nonsmooth optimization,” J. Sci. Comput., vol. 78, no. 1, pp. 29–63, 2019.
  31. G. Alain and Y. Bengio, “What regularized auto-encoders learn from the data-generating distribution,” J. Mach. Learn. Res., vol. 15, no. 1, pp. 3563–3593, 2014.
  32. W. Dong, P. Wang, W. Yin, G. Shi, F. Wu, and X. Lu, “Denoising prior driven deep neural network for image restoration,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 41, no. 10, pp. 2305–2318, 2018.
  33. K. Zhang, Y. Li, W. Zuo, L. Zhang, L. Van Gool, and R. Timofte, “Plug-and-play image restoration with deep denoiser prior,” IEEE Trans. Pattern Anal. Mach. Intell., 2021.
  34. B. Zhu, J. Z. Liu, S. F. Cauley, B. R. Rosen, and M. S. Rosen, “Image reconstruction by domain-transform manifold learning,” Nature, vol. 555, no. 7697, pp. 487–492, 2018.
  35. J. Xu and F. Noo, “Convex optimization algorithms in medical image reconstruction—in the age of ai,” Phys. Med. Biol., vol. 67, no. 7, p. 07TR01, 2022.
  36. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Int. Conf. Med. Imag. Comput. Comput. Assist. Interv.   Springer, 2015, pp. 234–241.
  37. S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He, “Aggregated residual transformations for deep neural networks,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 1492–1500.
  38. G. Huang, S. Liu, L. Van der Maaten, and K. Q. Weinberger, “Condensenet: An efficient densenet using learned group convolutions,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2018, pp. 2752–2761.
  39. B. Lim, S. Son, H. Kim, S. Nah, and K. Mu Lee, “Enhanced deep residual networks for single image super-resolution,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., 2017, pp. 136–144.
  40. C. H. McCollough, A. C. Bartley, R. E. Carter, B. Chen, T. A. Drees, P. Edwards et al., “Low-dose ct for the detection and classification of metastatic liver lesions: results of the 2016 low dose ct grand challenge,” Med. Phys., vol. 44, no. 10, pp. e339–e352, 2017.
  41. M. Li, D. S. Rundle, and G. Wang, “X-ray photon-counting data correction through deep learning,” arXiv preprint arXiv:2007.03119, 2020.
  42. Y. Zhang, K. Li, K. Li, L. Wang, B. Zhong, and Y. Fu, “Image super-resolution using very deep residual channel attention networks,” in Proc. Eur. Conf. Comput. Vis., 2018, pp. 286–301.
  43. C. Qiao, D. Li, Y. Guo, C. Liu, T. Jiang, Q. Dai, and D. Li, “Evaluation and development of deep neural networks for image super-resolution in optical microscopy,” Nat. Methods, vol. 18, no. 2, pp. 194–202, 2021.
  44. W. Van Aarle, W. J. Palenstijn, J. Cant, E. Janssens, F. Bleichrodt, A. Dabravolski et al., “Fast and flexible x-ray tomography using the astra toolbox,” Opt. Exp., vol. 24, no. 22, pp. 25 129–25 147, 2016.
  45. M. Shamouilian, “Fast speckle noise reduction for oct imaging,” Ph.D. dissertation, New York Univ.,New York, Jan. 2021.
  46. Z. Chen, X. Jin, L. Li, and G. Wang, “A limited-angle ct reconstruction method based on anisotropic tv minimization,” Phys. Med. Biol., vol. 58, no. 7, p. 2119, 2013.
  47. N. J. De Ruiter, P. H. Butler, A. P. Butler, S. T. Bell, A. I. Chernoglazov, and M. F. Walsh, “Mars imaging and reconstruction challenges,” in 14th Int. Meeting Fully 3D Imag. Recon. Radiol. Nucl. Med., Xi’an, China, 2017, pp. 18–23.
  48. M. Bath and L. Mansson, “Visual grading characteristics (vgc) analysis: a non-parametric rank-invariant statistical method for image quality evaluation,” Brit. J. Radiol., vol. 80, no. 951, pp. 169–176, 2007.
  49. M. Li, X. Guo, A. Verma, A. Rudkouskaya, A. M. McKenna, X. Intes, G. Wang, and M. Barroso, “Contrast-enhanced photon-counting micro-ct of tumor xenograft models,” bioRxiv, pp. 2024–01, 2024.
  50. J. A. Hanley and B. J. McNeil, “The meaning and use of the area under a receiver operating characteristic (roc) curve.” Radiology, vol. 143, no. 1, pp. 29–36, 1982.
  51. F. Noo, M. Defrise, and R. Clackdoyle, “Single-slice rebinning method for helical cone-beam ct,” Phys. Med. Biol., vol. 44, no. 2, p. 561, 1999.
  52. M. Li, Z. Fang, W. Cong, C. Niu, W. Wu, J. Uher, J. Bennett, J. T. Rubinstein, and G. Wang, “Clinical micro-CT empowered by interior tomography, robotic scanning, and deep learning,” IEEE Access, vol. 8, pp. 229 018–229 032, 12 2020.
  53. M. Li, J. Bohacova, J. Uher, W. Cong, J. Rubinstein, and G. Wang, “Motion correction for robot-based x-ray photon-counting CT at ultrahigh resolution,” in Proc. SPIE Dev. X-Ray Tomo. XIV, vol. 12242.   SPIE, 8 2022.
  54. Q. Gao, Z. Li, J. Zhang, Y. Zhang, and H. Shan, “Corediff: Contextual error-modulated generalized diffusion model for low-dose ct denoising and generalization,” IEEE Trans. Med. Imag., vol. 43, no. 2, pp. 745–759, 2024.
  55. W. Xia, Q. Lyu, and G. Wang, “Low-dose ct using denoising diffusion probabilistic model for 20×\times× speedup,” arXiv:2209.15136, 2022.
  56. M. Li, C. Lowe, A. Butler, P. Butler, and G. Wang, “Motion correction via locally linear embedding for helical photon-counting CT,” in Proc. SPIE 7th Int. Conf. Imag. Form. X-Ray Comput. Tomo., vol. 12304, 6 2022.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now