Papers
Topics
Authors
Recent
2000 character limit reached

Dual-Domain Coarse-to-Fine Progressive Estimation Network for Simultaneous Denoising, Limited-View Reconstruction, and Attenuation Correction of Cardiac SPECT (2401.13140v1)

Published 23 Jan 2024 in eess.IV and cs.CV

Abstract: Single-Photon Emission Computed Tomography (SPECT) is widely applied for the diagnosis of coronary artery diseases. Low-dose (LD) SPECT aims to minimize radiation exposure but leads to increased image noise. Limited-view (LV) SPECT, such as the latest GE MyoSPECT ES system, enables accelerated scanning and reduces hardware expenses but degrades reconstruction accuracy. Additionally, Computed Tomography (CT) is commonly used to derive attenuation maps ($\mu$-maps) for attenuation correction (AC) of cardiac SPECT, but it will introduce additional radiation exposure and SPECT-CT misalignments. Although various methods have been developed to solely focus on LD denoising, LV reconstruction, or CT-free AC in SPECT, the solution for simultaneously addressing these tasks remains challenging and under-explored. Furthermore, it is essential to explore the potential of fusing cross-domain and cross-modality information across these interrelated tasks to further enhance the accuracy of each task. Thus, we propose a Dual-Domain Coarse-to-Fine Progressive Network (DuDoCFNet), a multi-task learning method for simultaneous LD denoising, LV reconstruction, and CT-free $\mu$-map generation of cardiac SPECT. Paired dual-domain networks in DuDoCFNet are cascaded using a multi-layer fusion mechanism for cross-domain and cross-modality feature fusion. Two-stage progressive learning strategies are applied in both projection and image domains to achieve coarse-to-fine estimations of SPECT projections and CT-derived $\mu$-maps. Our experiments demonstrate DuDoCFNet's superior accuracy in estimating projections, generating $\mu$-maps, and AC reconstructions compared to existing single- or multi-task learning methods, under various iterations and LD levels. The source code of this work is available at https://github.com/XiongchaoChen/DuDoCFNet-MultiTask.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. A. J. Einstein, “Effects of radiation exposure from cardiac imaging: how good are the data?” Journal of the American College of Cardiology, vol. 59, no. 6, pp. 553–565, 2012.
  2. Z. Zhu, K. Wahid, P. Babyn, D. Cooper, I. Pratt, and Y. Carter, “Improved compressed sensing-based algorithm for sparse-view ct image reconstruction,” Computational and mathematical methods in medicine, vol. 2013, 2013.
  3. S. Goetze, T. L. Brown, W. C. Lavely, Z. Zhang, and F. M. Bengel, “Attenuation correction in myocardial perfusion spect/ct: effects of misregistration and value of reregistration,” Journal of Nuclear Medicine, vol. 48, no. 7, pp. 1090–1095, 2007.
  4. L. Saleki, P. Ghafarian, A. Bitarafan-Rajabi, N. Yaghoobi, B. Fallahi, and M. R. Ay, “The influence of misregistration between ct and spect images on the accuracy of ct-based attenuation correction of cardiac spect/ct imaging: Phantom and clinical studies,” Iranian Journal of Nuclear Medicine, vol. 27, no. 2, pp. 63–72, 2019.
  5. I. Shiri, K. AmirMozafari Sabet, H. Arabi, M. Pourkeshavarz, B. Teimourian, M. R. Ay, and H. Zaidi, “Standard spect myocardial perfusion estimation from half-time acquisitions using deep convolutional residual neural networks,” Journal of Nuclear Cardiology, pp. 1–19, 2020.
  6. N. Aghakhan Olia, A. Kamali-Asl, S. Hariri Tabrizi, P. Geramifar, P. Sheikhzadeh, S. Farzanefar, H. Arabi, and H. Zaidi, “Deep learning–based denoising of low-dose spect myocardial perfusion images: quantitative assessment and clinical performance,” European journal of nuclear medicine and molecular imaging, pp. 1–15, 2022.
  7. J. Sun, H. Jiang, Y. Du, C.-Y. Li, T.-H. Wu, Y.-H. Liu, B.-H. Yang, and G. S. Mok, “Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion spect,” Journal of Nuclear Cardiology, pp. 1–16, 2022.
  8. A. J. Ramon, Y. Yang, P. H. Pretorius, K. L. Johnson, M. A. King, and M. N. Wernick, “Improving diagnostic accuracy in low-dose spect myocardial perfusion imaging with convolutional denoising networks,” IEEE transactions on medical imaging, vol. 39, no. 9, pp. 2893–2903, 2020.
  9. J. Liu, Y. Yang, M. N. Wernick, P. H. Pretorius, and M. A. King, “Deep learning with noise-to-noise training for denoising in spect myocardial perfusion imaging,” Medical physics, vol. 48, no. 1, pp. 156–168, 2021.
  10. Q. Liu, H. Liu, N. Mirian, S. Ren, V. Viswanath, J. Karp, S. Surti, and C. Liu, “A personalized deep learning denoising strategy for low-count pet images,” Physics in Medicine & Biology, vol. 67, no. 14, p. 145014, 2022.
  11. Z. Yu, M. A. Rahman, R. Laforest, T. H. Schindler, R. J. Gropler, R. L. Wahl, B. A. Siegel, and A. K. Jha, “Need for objective task-based evaluation of deep learning-based denoising methods: A study in the context of myocardial perfusion spect,” Medical physics, 2023.
  12. A. Sanaat, I. Shiri, H. Arabi, I. Mainta, R. Nkoulou, and H. Zaidi, “Deep learning-assisted ultra-fast/low-dose whole-body pet/ct imaging,” European journal of nuclear medicine and molecular imaging, vol. 48, pp. 2405–2415, 2021.
  13. W. Whiteley and J. Gregor, “Cnn-based pet sinogram repair to mitigate defective block detectors,” Physics in Medicine & Biology, vol. 64, no. 23, p. 235017, 2019.
  14. O. Ronneberger, P. Fischer, and T. Brox, “U-net: Convolutional networks for biomedical image segmentation,” in Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18.   Springer, 2015, pp. 234–241.
  15. M. Amirrashedi, S. Sarkar, H. Ghadiri, P. Ghafarian, H. Zaidi, and M. R. Ay, “A deep neural network to recover missing data in small animal pet imaging: Comparison between sinogram-and image-domain implementations,” in 2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).   IEEE, 2021, pp. 1365–1368.
  16. X. Chen, B. Zhou, H. Xie, T. Miao, H. Liu, W. Holler, M. Lin, E. J. Miller, R. E. Carson, A. J. Sinusas et al., “Dudoss: Deep-learning-based dual-domain sinogram synthesis from sparsely sampled projections of cardiac spect,” Medical Physics, vol. 50, no. 1, pp. 89–103, 2023.
  17. X. Chen and C. Liu, “Deep-learning-based methods of attenuation correction for spect and pet,” Journal of Nuclear Cardiology, pp. 1–20, 2022.
  18. L. Shi, J. A. Onofrey, H. Liu, Y.-H. Liu, and C. Liu, “Deep learning-based attenuation map generation for myocardial perfusion spect,” European Journal of Nuclear Medicine and Molecular Imaging, vol. 47, pp. 2383–2395, 2020.
  19. J. Yang, L. Shi, R. Wang, E. J. Miller, A. J. Sinusas, C. Liu, G. T. Gullberg, and Y. Seo, “Direct attenuation correction using deep learning for cardiac spect: A feasibility study,” Journal of Nuclear Medicine, vol. 62, no. 11, pp. 1645–1652, 2021.
  20. X. Chen, B. Zhou, L. Shi, H. Liu, Y. Pang, R. Wang, E. J. Miller, A. J. Sinusas, and C. Liu, “Ct-free attenuation correction for dedicated cardiac spect using a 3d dual squeeze-and-excitation residual dense network,” Journal of Nuclear Cardiology, vol. 29, no. 5, pp. 2235–2250, 2022.
  21. X. Chen, B. Zhou, H. Xie, L. Shi, H. Liu, W. Holler, M. Lin, Y.-H. Liu, E. J. Miller, A. J. Sinusas et al., “Direct and indirect strategies of deep-learning-based attenuation correction for general purpose and dedicated cardiac spect,” European Journal of Nuclear Medicine and Molecular Imaging, vol. 49, no. 9, pp. 3046–3060, 2022.
  22. Y. Du, J. Shang, J. Sun, L. Wang, Y.-H. Liu, H. Xu, and G. S. Mok, “Deep-learning-based estimation of attenuation map improves attenuation correction performance over direct attenuation estimation for myocardial perfusion spect,” Journal of Nuclear Cardiology, pp. 1–16, 2022.
  23. X. Chen, P. Hendrik Pretorius, B. Zhou, H. Liu, K. Johnson, Y.-H. Liu, M. A. King, and C. Liu, “Cross-vender, cross-tracer, and cross-protocol deep transfer learning for attenuation map generation of cardiac spect,” Journal of Nuclear Cardiology, vol. 29, no. 6, pp. 3379–3391, 2022.
  24. S. K. Zhou, H. Greenspan, C. Davatzikos, J. S. Duncan, B. Van Ginneken, A. Madabhushi, J. L. Prince, D. Rueckert, and R. M. Summers, “A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises,” Proceedings of the IEEE, vol. 109, no. 5, pp. 820–838, 2021.
  25. C. Qin, W. Bai, J. Schlemper, S. E. Petersen, S. K. Piechnik, S. Neubauer, and D. Rueckert, “Joint learning of motion estimation and segmentation for cardiac mr image sequences,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II 11.   Springer, 2018, pp. 472–480.
  26. T. Estienne, M. Lerousseau, M. Vakalopoulou, E. Alvarez Andres, E. Battistella, A. Carré, S. Chandra, S. Christodoulidis, M. Sahasrabudhe, R. Sun et al., “Deep learning-based concurrent brain registration and tumor segmentation,” Frontiers in computational neuroscience, p. 17, 2020.
  27. Z. Xu and M. Niethammer, “Deepatlas: Joint semi-supervised learning of image registration and segmentation,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13–17, 2019, Proceedings, Part II 22.   Springer, 2019, pp. 420–429.
  28. G. Balakrishnan, A. Zhao, M. R. Sabuncu, J. Guttag, and A. V. Dalca, “Voxelmorph: a learning framework for deformable medical image registration,” IEEE transactions on medical imaging, vol. 38, no. 8, pp. 1788–1800, 2019.
  29. K. Ta, S. S. Ahn, J. C. Stendahl, A. J. Sinusas, and J. S. Duncan, “A semi-supervised joint network for simultaneous left ventricular motion tracking and segmentation in 4d echocardiography,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2020: 23rd International Conference, Lima, Peru, October 4–8, 2020, Proceedings, Part VI 23.   Springer, 2020, pp. 468–477.
  30. L. Qiu and H. Ren, “Rsegnet: A joint learning framework for deformable registration and segmentation,” IEEE Transactions on Automation Science and Engineering, vol. 19, no. 3, pp. 2499–2513, 2021.
  31. B. Li, W. J. Niessen, S. Klein, M. de Groot, M. A. Ikram, M. W. Vernooij, and E. E. Bron, “Longitudinal diffusion mri analysis using segis-net: a single-step deep-learning framework for simultaneous segmentation and registration,” NeuroImage, vol. 235, p. 118004, 2021.
  32. B. Wu, Z. Zhou, J. Wang, and Y. Wang, “Joint learning for pulmonary nodule segmentation, attributes and malignancy prediction,” in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).   IEEE, 2018, pp. 1109–1113.
  33. C.-F. Li, Y.-D. Xu, X.-H. Ding, J.-J. Zhao, R.-Q. Du, L.-Z. Wu, and W.-P. Sun, “Multir-net: a novel joint learning network for covid-19 segmentation and classification,” Computers in Biology and Medicine, vol. 144, p. 105340, 2022.
  34. Y. Hong, B. Wei, Z. Han, X. Li, Y. Zheng, and S. Li, “Mmcl-net: spinal disease diagnosis in global mode using progressive multi-task joint learning,” Neurocomputing, vol. 399, pp. 307–316, 2020.
  35. Q. Xu, Y. Zeng, W. Tang, W. Peng, T. Xia, Z. Li, F. Teng, W. Li, and J. Guo, “Multi-task joint learning model for segmenting and classifying tongue images using a deep neural network,” IEEE journal of biomedical and health informatics, vol. 24, no. 9, pp. 2481–2489, 2020.
  36. T. Li, M. Zhang, W. Qi, E. Asma, and J. Qi, “Deep learning based joint pet image reconstruction and motion estimation,” IEEE transactions on medical imaging, vol. 41, no. 5, pp. 1230–1241, 2021.
  37. B. Zhou, Y.-J. Tsai, X. Chen, J. S. Duncan, and C. Liu, “Mdpet: a unified motion correction and denoising adversarial network for low-dose gated pet,” IEEE transactions on medical imaging, vol. 40, no. 11, pp. 3154–3164, 2021.
  38. X. Chen, Z. Peng, and G. H. Valadez, “Dd-cisenet: Dual-domain cross-iteration squeeze and excitation network for accelerated mri reconstruction,” arXiv preprint arXiv:2305.00088, 2023.
  39. X. Chen, Y. Shinagawa, Z. Peng, and G. H. Valadez, “Dual-domain cross-iteration squeeze-excitation network for sparse reconstruction of brain mri,” arXiv preprint arXiv:2210.02523, 2022.
  40. X. Chen, B. Zhou, H. Xie, X. Guo, Q. Liu, A. J. Sinusas, and C. Liu, “Dual-domain iterative network with adaptive data consistency for joint denoising and few-angle reconstruction of low-dose cardiac spect,” in Workshop on Medical Image Learning with Limited and Noisy Data.   Springer, 2023, pp. 49–59.
  41. B. Zhou, X. Chen, H. Xie, S. K. Zhou, J. S. Duncan, and C. Liu, “Dudoufnet: dual-domain under-to-fully-complete progressive restoration network for simultaneous metal artifact reduction and low-dose ct reconstruction,” IEEE Transactions on Medical Imaging, vol. 41, no. 12, pp. 3587–3599, 2022.
  42. B. Zhou, X. Chen, S. K. Zhou, J. S. Duncan, and C. Liu, “Dudodr-net: Dual-domain data consistent recurrent network for simultaneous sparse view and metal artifact reduction in computed tomography,” Medical Image Analysis, vol. 75, p. 102289, 2022.
  43. T. Wang, Y. Lei, Y. Fu, J. F. Wynne, W. J. Curran, T. Liu, and X. Yang, “A review on medical imaging synthesis using deep learning and its clinical applications,” Journal of applied clinical medical physics, vol. 22, no. 1, pp. 11–36, 2021.
  44. Y. Liu, X. Chen, J. Cheng, and H. Peng, “A medical image fusion method based on convolutional neural networks,” in 2017 20th international conference on information fusion (Fusion).   IEEE, 2017, pp. 1–7.
  45. R. Hou, D. Zhou, R. Nie, D. Liu, and X. Ruan, “Brain ct and mri medical image fusion using convolutional neural networks and a dual-channel spiking cortical model,” Medical & biological engineering & computing, vol. 57, pp. 887–900, 2019.
  46. Y. Liu, X. Chen, R. K. Ward, and Z. J. Wang, “Medical image fusion via convolutional sparsity based morphological component analysis,” IEEE Signal Processing Letters, vol. 26, no. 3, pp. 485–489, 2019.
  47. K.-j. Xia, H.-s. Yin, and J.-q. Wang, “A novel improved deep convolutional neural network model for medical image fusion,” Cluster Computing, vol. 22, pp. 1515–1527, 2019.
  48. X. Song, H. Chao, X. Xu, H. Guo, S. Xu, B. Turkbey, B. J. Wood, T. Sanford, G. Wang, and P. Yan, “Cross-modal attention for multi-modal image registration,” Medical Image Analysis, vol. 82, p. 102612, 2022.
  49. X. Chen, B. Zhou, H. Xie, X. Guo, J. Zhang, J. S. Duncan, E. J. Miller, A. J. Sinusas, J. A. Onofrey, and C. Liu, “Dusfe: Dual-channel squeeze-fusion-excitation co-attention for cross-modality registration of cardiac spect and ct,” Medical Image Analysis, p. 102840, 2023.
  50. X. Chen, B. Zhou, H. Xie, X. Guo, Q. Liu, A. J. Sinusas, and C. Liu, “Cross-domain iterative network for simultaneous denoising, limited-angle reconstruction, and attenuation correction of cardiac spect,” in International Workshop on Machine Learning in Medical Imaging.   Springer, 2023, pp. 12–22.
  51. C. Chan, J. Dey, Y. Grobshtein, J. Wu, Y.-H. Liu, R. Lampert, A. J. Sinusas, and C. Liu, “The impact of system matrix dimension on small fov spect reconstruction with truncated projections,” Medical physics, vol. 43, no. 1, pp. 213–224, 2016.
  52. GE-HealthCare, “Ge myospect es: A perfect fit for today’s practice of cardiology,” Available at https://www.gehealthcare.com/products/molecular-imaging/myospect (2023).
  53. S. W. Zamir, A. Arora, S. Khan, M. Hayat, F. S. Khan, M.-H. Yang, and L. Shao, “Multi-stage progressive image restoration,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2021, pp. 14 821–14 831.
  54. G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4700–4708.
  55. O. Oktay, J. Schlemper, L. L. Folgoc, M. Lee, M. Heinrich, K. Misawa, K. Mori, S. McDonagh, N. Y. Hammerla, B. Kainz et al., “Attention u-net: Learning where to look for the pancreas,” arXiv preprint arXiv:1804.03999, 2018.
  56. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.
  57. X. Chen, B. Zhou, H. Xie, X. Guo, J. Zhang, A. J. Sinusas, J. A. Onofrey, and C. Liu, “Dual-branch squeeze-fusion-excitation module for cross-modality registration of cardiac spect and ct,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2022, pp. 46–55.

Summary

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

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

Whiteboard

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up