Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 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

CT Material Decomposition using Spectral Diffusion Posterior Sampling (2402.03476v1)

Published 5 Feb 2024 in eess.IV, cs.LG, and physics.med-ph

Abstract: In this work, we introduce a new deep learning approach based on diffusion posterior sampling (DPS) to perform material decomposition from spectral CT measurements. This approach combines sophisticated prior knowledge from unsupervised training with a rigorous physical model of the measurements. A faster and more stable variant is proposed that uses a jumpstarted process to reduce the number of time steps required in the reverse process and a gradient approximation to reduce the computational cost. Performance is investigated for two spectral CT systems: dual-kVp and dual-layer detector CT. On both systems, DPS achieves high Structure Similarity Index Metric Measure(SSIM) with only 10% of iterations as used in the model-based material decomposition(MBMD). Jumpstarted DPS (JSDPS) further reduces computational time by over 85% and achieves the highest accuracy, the lowest uncertainty, and the lowest computational costs compared to classic DPS and MBMD. The results demonstrate the potential of JSDPS for providing relatively fast and accurate material decomposition based on spectral CT data.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (19)
  1. Y. Long and J. A. Fessler, “Multi-material decomposition using statistical image reconstruction for spectral ct,” IEEE transactions on medical imaging, vol. 33, no. 8, pp. 1614–1626, 2014.
  2. X. Jiang, C. Fang, P. Hu, H. Cui, L. Zhu, and Y. Yang, “Fast and effective single-scan dual-energy cone-beam ct reconstruction and decomposition denoising based on dual-energy vectorization,” Medical physics, vol. 48, no. 9, pp. 4843–4856, 2021.
  3. S. Tilley, W. Zbijewski, and J. W. Stayman, “Model-based material decomposition with a penalized nonlinear least-squares ct reconstruction algorithm,” Physics in Medicine & Biology, vol. 64, no. 3, p. 035005, 2019.
  4. H. Gong, S. Tao, K. Rajendran, W. Zhou, C. H. McCollough, and S. Leng, “Deep-learning-based direct inversion for material decomposition,” Medical physics, vol. 47, no. 12, pp. 6294–6309, 2020.
  5. W. Wu, D. Hu, C. Niu, L. V. Broeke, A. P. Butler, P. Cao, J. Atlas, A. Chernoglazov, V. Vardhanabhuti, and G. Wang, “Deep learning based spectral ct imaging,” Neural Networks, vol. 144, pp. 342–358, 2021.
  6. J. F. Abascal, N. Ducros, V. Pronina, S. Rit, P.-A. Rodesch, T. Broussaud, S. Bussod, P. C. Douek, A. Hauptmann, S. Arridge et al., “Material decomposition in spectral ct using deep learning: a sim2real transfer approach,” IEEE Access, vol. 9, pp. 25 632–25 647, 2021.
  7. J. Zhu, T. Su, X. Zhang, J. Yang, D. Mi, Y. Zhang, X. Gao, H. Zheng, D. Liang, and Y. Ge, “Feasibility study of three-material decomposition in dual-energy cone-beam ct imaging with deep learning,” Physics in Medicine & Biology, vol. 67, no. 14, p. 145012, 2022.
  8. W. Fang, D. Wu, K. Kim, M. K. Kalra, R. Singh, L. Li, and Q. Li, “Iterative material decomposition for spectral ct using self-supervised noise2noise prior,” Physics in Medicine & Biology, vol. 66, no. 15, p. 155013, 2021.
  9. A. Eguizabal, O. Öktem, and M. U. Persson, “Deep learning for material decomposition in photon-counting ct,” arXiv preprint arXiv:2208.03360, 2022.
  10. H. Chung, J. Kim, M. T. Mccann, M. L. Klasky, and J. C. Ye, “Diffusion posterior sampling for general noisy inverse problems,” arXiv preprint arXiv:2209.14687, 2022.
  11. S. Li, M. Tivnan, Y. Shen, and J. W. Stayman, “Diffusion posterior sampling for nonlinear ct reconstruction,” arXiv preprint arXiv:2312.01464, 2023.
  12. R. Cassetta, M. Lehmann, M. Haytmyradov, R. Patel, A. Wang, L. Cortesi, D. Morf, D. Seghers, M. Surucu, H. Mostafavi et al., “Fast-switching dual energy cone beam computed tomography using the on-board imager of a commercial linear accelerator,” Physics in Medicine & Biology, vol. 65, no. 1, p. 015013, 2020.
  13. W. Wang, Y. Ma, M. Tivnan, J. Li, G. J. Gang, W. Zbijewski, M. Lu, J. Zhang, J. Star-Lack, R. E. Colbeth et al., “High-resolution model-based material decomposition in dual-layer flat-panel cbct,” Medical physics, vol. 48, no. 10, pp. 6375–6387, 2021.
  14. Y. Song, J. Sohl-Dickstein, D. P. Kingma, A. Kumar, S. Ermon, and B. Poole, “Score-based generative modeling through stochastic differential equations,” arXiv preprint arXiv:2011.13456, 2020.
  15. J. Ho, A. Jain, and P. Abbeel, “Denoising diffusion probabilistic models,” Advances in neural information processing systems, vol. 33, pp. 6840–6851, 2020.
  16. J. Song, C. Meng, and S. Ermon, “Denoising diffusion implicit models,” arXiv preprint arXiv:2010.02502, 2020.
  17. P. Stenner, T. Berkus, and M. Kachelriess, “Empirical dual energy calibration (edec) for cone-beam computed tomography,” Medical physics, vol. 34, no. 9, pp. 3630–3641, 2007.
  18. P. R. Mendonça, P. Lamb, and D. V. Sahani, “A flexible method for multi-material decomposition of dual-energy ct images,” IEEE transactions on medical imaging, vol. 33, no. 1, pp. 99–116, 2013.
  19. H. R. Roth, L. Lu, A. Seff, K. M. Cherry, J. Hoffman, S. Wang, J. Liu, E. Turkbey, and R. M. Summers, “A new 2.5 d representation for lymph node detection using random sets of deep convolutional neural network observations,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2014: 17th International Conference, Boston, MA, USA, September 14-18, 2014, Proceedings, Part I 17.   Springer, 2014, pp. 520–527.
Citations (3)
View on Semantic Scholar

Summary

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

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