Skip to main content
SpringerLink
Log in

Toward a New Frontier in PET Image Reconstruction: A Paradigm Shift to the Learning-Based Methods

  • Chapter
  • First Online:
Gamma Ray Imaging

  • 387 Accesses

Abstract

Positron emission tomography (PET) is an important tomographic imaging modality and is widely used in cardiology, neurology, and oncology. PET reconstruction, which is a fundamental part of instrumentation, allows to generate 3D tomographic images of the tracer’s spatial-temporal distribution based on the position and timing of the detected annihilation gammas. Good knowledge on the performance characteristics of different reconstruction algorithms can be highly beneficial to obtain reliable quantitative images more efficiently. This chapter will describe the 3D image reconstruction algorithms used in PET and the most important evolutions in the last twenty years: from statistical iterative reconstruction (MLEM, OSEM, and MAP) to the state-of-the-art learning-based (Dictionary-learning, kernel-based, and Deep-learning) algorithms. Physical corrections (scatter, attenuation, etc.) and reconstruction acceleration will be covered as well. In addition, we will demonstrate how computational and physical modeling of the PET image acquisition process for a cutting-edge PET scanner. Specifically, recent progress in artificial intelligence (AI) or deep learning is rapidly becoming one of the most important technologies of our era. Numerous results showed that deep-learning based methods could recover faint signals from noisy PET raw data, which is caused by the limited scan time and injected dose. As a result, we are frequently called for a paradigm shift in PET reconstruction community. However, conventional deep learning model is purely data-driven and essentially based on massive amounts of data. Through end-to-end training, the network is learned to find and correlate patterns between inputs and outputs without necessarily capturing their cause-and-effect relationships. In some scenarios, the performance of deep networks may degrade significantly, and sometimes may even underperform traditional approaches. In contrast, physics, biology, and other natural sciences have long relied on solid scientific models and principles. The tried-and-true domain knowledge could be used to stabilize/regularize the deep-learning model. In this chapter, we will provide a glimpse of what to expect in the future with exciting insights into topics, such as how to construct the interpretable, generalizable, data-efficient, and physics-constrained models in PET reconstruction.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
eBook
USD 16.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 89.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Cormack, A. M. (1963). Representation of a function by its line integrals, with some radiological applications. Journal of Applied Physics, 34(9), 2722–2727.

    Article  ADS  MATH  Google Scholar 

  2. Bracewell, R. N. (1956). Strip integration in radio astronomy. Australian Journal of Physics, 9, 198.

    Article  ADS  MathSciNet  MATH  Google Scholar 

  3. National Electrical Manufacturers Association. (2018). NEMA Standards publication NU 2-2018: Performance measurements of positron emission tomographs (PET) (p. 41). National Electrical Manufacturers Association.

    Google Scholar 

  4. Razifar, P., et al. (2005). Noise correlation in PET, CT, SPECT and PET/CT data evaluated using autocorrelation function: A phantom study on data, reconstructed using FBP and OSEM. BMC Medical Imaging, 5(1), 5.

    Article  Google Scholar 

  5. Teymurazyan, A., Riauka, T., Jans, H.-S., & Robinson, D. (2013). Properties of noise in positron emission tomography images reconstructed with filtered-backprojection and row-action maximum likelihood algorithm. Journal of Digital Imaging, 26(3), 447–456.

    Article  Google Scholar 

  6. Santarelli, M. F., Positano, V., & Landini, L. (2017). Measured PET data characterization with the negative binomial distribution model. Journal of Medical and Biological Engineering, 37(3), 299–312.

    Article  Google Scholar 

  7. Van Slambrouck, K., et al. (2015). Bias reduction for low-statistics PET: Maximum likelihood reconstruction with a modified Poisson distribution. IEEE Transactions on Medical Imaging, 34(1), 126–136.

    Article  Google Scholar 

  8. Wilson, D. W., Tsui, B. M., & Barrett, H. H. (1994). Noise properties of the EM algorithm. II. Monte Carlo simulations. Physics in Medicine & Biology, 39(5), 847.

    Article  ADS  Google Scholar 

  9. Barrett, H. H., Wilson, D. W., & Tsui, B. M. (1994). Noise properties of the EM algorithm. I. Theory. Physics in Medicine & Biology, 39(5), 833.

    Article  ADS  Google Scholar 

  10. Lange, K., & Carson, R. (1984). EM reconstruction algorithms for emission and transmission tomography. Journal of Computer Assisted Tomography, 8(2), 306–316.

    Google Scholar 

  11. Shepp, L. A., & Vardi, Y. (1982). Maximum likelihood reconstruction for emission tomography. IEEE Transactions on Medical Imaging, 1(2), 113–122.

    Article  Google Scholar 

  12. Boellaard, R., Lingen, A. V., & Lammertsma, A. A. (2001). Experimental and clinical evaluation of iterative reconstruction (OSEM) in dynamic PET: Quantitative characteristics and effects on kinetic modeling. Journal of Nuclear Medicine, 42(5), 808–817.

    Google Scholar 

  13. Reader, A. J., Visvikis, D., Erlandsson, K., Ott, R. J., & Flower, M. A. (1998). Intercomparison of four reconstruction techniques for positron volume imaging with rotating planar detectors. Physics in Medicine & Biology, 43(4), 823–834.

    Article  ADS  Google Scholar 

  14. Yavuz, M., & Fessler, J. A. (1998). Statistical image reconstruction methods for randoms-precorrected PET scans. Medical Image Analysis, 2(4), 369–378.

    Article  Google Scholar 

  15. Yavuz, M., & Fessler, J. A. (1997). New statistical models for randoms-precorrected PET scans. In J. Duncan & G. Gindi (Eds.), Information processing in medical imaging (Lecture Notes in Computer Science) (Vol. 1230, pp. 190–203). Springer.

    Chapter  Google Scholar 

  16. Brasse, D., Kinahan, P. E., Lartizien, C., Comtat, C., Casey, M., & Michel, C. (2005). Correction methods for random coincidences in fully 3D whole-body PET: Impact on data and image quality. Journal of Nuclear Medicine, 46(5), 859–867.

    Google Scholar 

  17. Badawi, R. D., Miller, M. P., Bailey, D. L., & Marsden, P. K. (1999). Randoms variance reduction in 3D PET. Physics in Medicine & Biology, 44(4), 941–954.

    Article  ADS  Google Scholar 

  18. Zhang, X., Zhou, J., Cherry, S. R., Badawi, R. D., & Qi, J. (2017). Quantitative image reconstruction for total-body PET imaging using the 2-meter long EXPLORER scanner. Physics in Medicine & Biology, 62(6), 2465–2485.

    Article  ADS  Google Scholar 

  19. Bailey, D. L., & Meikle, S. R. (1994). A convolution-subtraction scatter correction method for 3D PET. Physics in Medicine & Biology, 39(3), 411.

    Article  ADS  Google Scholar 

  20. Lercher, M. J., & Wienhard, K. (1994). Scatter correction in 3-D PET. IEEE Transactions on Medical Imaging, 13(4), 649–657.

    Article  Google Scholar 

  21. Grootoonk, S., Spinks, T., Sashin, D., Spyrou, N., & Jones, T. (1996). Correction for scatter in 3D brain PET using a dual energy window method. Physics in Medicine & Biology, 41(12), 2757.

    Article  ADS  Google Scholar 

  22. Hamill, J., Efthimiou, N., Karp, J., & Surti, S. (2022). Evaluation of energy-based scatter compensation methods in clinical whole-body PET. Journal of Nuclear Medicine, 63(supplement 2), 2395.

    Google Scholar 

  23. Watson, C. C. (2000). New, faster, image-based scatter correction for 3D PET. IEEE Transactions on Nuclear Science, 47(4), 1587–1594.

    Article  ADS  Google Scholar 

  24. Ollinger, J. M. (1996). Model-based scatter correction for fully 3D PET. Physics in Medicine & Biology, 41(1), 153.

    Article  ADS  Google Scholar 

  25. Scheins, J. J., Lenz, M., Pietrzyk, U., Shah, N. J., & Lerche, C. W. (2021). High-throughput, accurate Monte Carlo simulation on CPU hardware for PET applications. Physics in Medicine & Biology, 66, 185001.

    Article  ADS  Google Scholar 

  26. Levin, C. S., Dahlbom, M., & Hoffman, E. J. (1995). A Monte Carlo correction for the effect of Compton scattering in 3-D PET brain imaging. IEEE Transactions on Nuclear Science, 42(4), 1181–1185.

    Article  ADS  Google Scholar 

  27. Berker, Y., Maier, J., & Kachelrieß, M. (2018). Deep scatter estimation in PET: Fast scatter correction using a convolutional neural network. In 2018 IEEE nuclear science symposium and medical imaging conference proceedings (NSS/MIC) (pp. 1–5). IEEE.

    Google Scholar 

  28. Qian, H., Rui, X., & Ahn, S. (2017). Deep learning models for PET scatter estimations. In 2017 IEEE nuclear science symposium and medical imaging conference (NSS/MIC) (pp. 1–5). IEEE.

    Google Scholar 

  29. Zaidi, H., & Montandon, M.-L. (2007). Scatter compensation techniques in PET. PET Clinics, 2(2), 219–234.

    Article  Google Scholar 

  30. Mazoyer, B., Roos, M., & Huesman, R. (1985). Dead time correction and counting statistics for positron tomography. Physics in Medicine & Biology, 30(5), 385.

    Article  ADS  Google Scholar 

  31. Guérin, B., & El Fakhri, G. (2008). Realistic PET Monte Carlo simulation with pixelated block detectors, light sharing, random coincidences and dead-time modeling. IEEE Transactions on Nuclear Science, 55(3), 942–952.

    Article  ADS  Google Scholar 

  32. Bailey, D. L., Meikle, S. R., & Jones, T. (1997). Effective sensitivity in 3D PET: The impact of detector dead time on 3D system performance. IEEE Transactions on Nuclear Science, 44(3), 1180–1185.

    Article  ADS  Google Scholar 

  33. Issa, A. S. M., et al. (2022). A detector block-pairwise dead time correction method for improved quantitation with a dedicated BrainPET scanner. Physics in Medicine & Biology, 67, 235004.

    Article  ADS  Google Scholar 

  34. Guez, D., Bataille, F., Comtat, C., Honore, P. F., Jan, S., & Kerhoas, S. (2008). Counting rates modeling for PET scanners with GATE. IEEE Transactions on Nuclear Science, 55(1), 516–523.

    Article  ADS  Google Scholar 

  35. Knoll, G. F. (2000). Radiation detection and measurement. Wiley.

    Google Scholar 

  36. Carney, J. P. J., Townsend, D. W., Rappoport, V., & Bendriem, B. (2006). Method for transforming CT images for attenuation correction in PET/CT imaging. Medical Physics, 33(4), 976–983.

    Article  ADS  Google Scholar 

  37. Kinahan, P. E., Townsend, D. W., Beyer, T., & Sashin, D. (1998). Attenuation correction for a combined 3D PET/CT scanner. Medical Physics, 25(10), 2046–2053.

    Article  ADS  Google Scholar 

  38. Wagenknecht, G., Kaiser, H. J., Mottaghy, F. M., & Herzog, H. (2013). MRI for attenuation correction in PET: Methods and challenges. Magma, 26(1), 99–113.

    Article  Google Scholar 

  39. Hofmann, M., et al. (2011). MRI-based attenuation correction for whole-body PET/MRI: Quantitative evaluation of segmentation- and atlas-based methods. Journal of Nuclear Medicine, 52(9), 1392.

    Article  Google Scholar 

  40. Rezaei, A., et al. (2012). Simultaneous reconstruction of activity and attenuation in time-of-flight PET. IEEE Transactions on Medical Imaging, 31(12), 2224–2233.

    Article  Google Scholar 

  41. Omidvari, N., et al. (2022). Lutetium background radiation in total-body PET—A simulation study on opportunities and challenges in PET attenuation correction. Frontiers in Nuclear Medicine, 2, 963067.

    Article  Google Scholar 

  42. Defrise, M., Townsend, D., Bailey, D., Geissbuhler, A., & Jones, T. (1991). A normalization technique for 3D PET data. Physics in Medicine & Biology, 36(7), 939.

    Article  ADS  Google Scholar 

  43. Badawi, R. D., & Marsden, P. (1999). Developments in component-based normalization for 3D PET. Physics in Medicine & Biology, 44(2), 571.

    Article  ADS  Google Scholar 

  44. Bai, B., et al. (2002). Model-based normalization for iterative 3D PET image reconstruction. Physics in Medicine & Biology, 47(15), 2773.

    Article  ADS  Google Scholar 

  45. Wu, X. (1991). An efficient antialiasing technique. ACM SIGGRAPH Computer Graphics, 25(4), 143–152. ACM.

    Article  Google Scholar 

  46. Zhou, J., & Qi, J. (2011). Fast and efficient fully 3D PET image reconstruction using sparse system matrix factorization with GPU acceleration. Physics in Medicine & Biology, 56(20), 6739–6757.

    Article  ADS  Google Scholar 

  47. Terstegge, A., Weber, S., Herzog, H., Muller-Gartner, H., & Halling, H. (1996). High resolution and better quantification by tube of response modelling in 3D PET reconstruction. In 1996 IEEE nuclear science symposium. Conference record (Vol. 3, pp. 1603–1607). IEEE.

    Chapter  Google Scholar 

  48. Moses, W. W. (2011). Fundamental limits of spatial resolution in PET. Nuclear Instruments and Methods in Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment, 648, S236–S240.

    Article  ADS  Google Scholar 

  49. Stickel, J. R., & Cherry, S. R. (2005). High-resolution PET detector design: Modelling components of intrinsic spatial resolution. Physics in Medicine & Biology, 50(2), 179.

    Article  ADS  Google Scholar 

  50. Rahmim, A., Qi, J., & Sossi, V. (2013). Resolution modeling in PET imaging: Theory, practice, benefits, and pitfalls. Medical Physics, 40(6), 064301.

    Article  ADS  Google Scholar 

  51. Chen, S., Hu, P., Gu, Y., Yu, H., & Shi, H. (2020). Performance characteristics of the digital uMI550 PET/CT system according to the NEMA NU2-2018 standard. EJNMMI Physics, 7(1), 1–14.

    Article  Google Scholar 

  52. Tong, S., Alessio, A. M., Thielemans, K., Stearns, C., Ross, S., & Kinahan, P. E. (2011). Properties and mitigation of edge artifacts in PSF-based PET reconstruction. IEEE Transactions on Nuclear Science, 58(5), 2264–2275.

    Article  ADS  Google Scholar 

  53. Lee, K., Kinahan, P. E., Fessler, J. A., Miyaoka, R. S., Janes, M., & Lewellen, T. K. (2004). Pragmatic fully 3D image reconstruction for the MiCES mouse imaging PET scanner. Physics in Medicine & Biology, 49(19), 4563.

    Article  ADS  Google Scholar 

  54. Zeng, T., et al. (2020). A GPU-accelerated fully 3D OSEM image reconstruction for a high-resolution small animal PET scanner using dual-ended readout detectors. Physics in Medicine & Biology, 65(24), 245007.

    Article  ADS  Google Scholar 

  55. Gong, K., Cherry, S. R., & Qi, J. (2016). On the assessment of spatial resolution of PET systems with iterative image reconstruction. Physics in Medicine & Biology, 61(5), N193–N202.

    Article  Google Scholar 

  56. Chun, S. Y., & Fessler, J. A. (2009). Joint image reconstruction and nonrigid motion estimation with a simple penalty that encourages local invertibility. In Medical imaging 2009: Physics of medical imaging (Vol. 7258, pp. 288–296). SPIE.

    Google Scholar 

  57. Blume, M., Martinez-Moller, A., Keil, A., Navab, N., & Rafecas, M. (2010). Joint reconstruction of image and motion in gated positron emission tomography. IEEE Transactions on Medical Imaging, 29(11), 1892–1906.

    Article  Google Scholar 

  58. Li, T., Zhang, M., Qi, W., Asma, E., & Qi, J. (2020). Motion correction of respiratory-gated PET images using deep learning based image registration framework. Physics in Medicine & Biology, 65(15), 155003.

    Article  ADS  Google Scholar 

  59. Mumcuoglu, E. U., Leahy, R., Cherry, S. R., & Zhou, Z. (1994). Fast gradient-based methods for Bayesian reconstruction of transmission and emission PET images. IEEE Transactions on Medical Imaging, 13(4), 687–701.

    Article  Google Scholar 

  60. Qi, J. Y., & Leahy, R. M. (1999). A theoretical study of the contrast recovery and variance of MAP reconstructions from PET data. IEEE Transactions on Medical Imaging, 18(4), 293–305.

    Article  Google Scholar 

  61. Leahy, R. M., & Qi, J. Y. (2000). Statistical approaches in quantitative positron emission tomography. Statistics and Computing, 10(2), 147–165.

    Article  Google Scholar 

  62. Fessler, J. A., & Hero, A. O. (1995). Penalized maximum-likelihood image-reconstruction using space-alternating generalized EM algorithms. IEEE Transactions on Image Processing, 4(10), 1417–1429.

    Article  ADS  Google Scholar 

  63. Ahn, S., & Leahy, R. M. (2008). Analysis of resolution and noise properties of nonquadratically regularized image reconstruction methods for PET. IEEE Transactions on Medical Imaging, 27(3), 413–424.

    Article  Google Scholar 

  64. Wang, C., Hu, Z., Shi, P., & Liu, H. (2014). Low dose PET reconstruction with total variation regularization. In 2014 36th annual international conference of the IEEE Engineering in Medicine and Biology Society (pp. 1917–1920). IEEE.

    Chapter  Google Scholar 

  65. Wang, G., & Qi, J. (2012). Penalized likelihood PET image reconstruction using patch-based edge-preserving regularization. IEEE Transactions on Medical Imaging, 31(12), 2194–2204.

    Article  Google Scholar 

  66. Mehranian, A., et al. (2017). PET image reconstruction using multi-parametric anato-functional priors. Physics in Medicine & Biology, 62(15), 5975.

    Article  ADS  Google Scholar 

  67. Vunckx, K., et al. (2012). Evaluation of three MRI-based anatomical priors for quantitative PET brain imaging. IEEE Transactions on Medical Imaging, 31(3), 599–612.

    Article  Google Scholar 

  68. Cheng-Liao, J., & Qi, J. (2011). PET image reconstruction with anatomical edge guided level set prior. Physics in Medicine & Biology, 56(21), 6899–6918.

    Article  ADS  Google Scholar 

  69. Schramm, G., et al. (2018). Evaluation of parallel level sets and Bowsher’s method as segmentation-free anatomical priors for time-of-flight PET reconstruction. IEEE Transactions on Medical Imaging, 37, 590–603.

    Article  Google Scholar 

  70. Tang, J., & Rahmim, A. (2009). Bayesian PET image reconstruction incorporating anato-functional joint entropy. Physics in Medicine & Biology, 54(23), 7063.

    Article  ADS  Google Scholar 

  71. Bowsher, J. E., et al. (2004). Utilizing MRI information to estimate F18-FDG distributions in rat flank tumors. In IEEE symposium conference record nuclear science 2004 (Vol. 4, pp. 2488–2492). IEEE.

    Chapter  Google Scholar 

  72. Zhang, M., Zhou, J., Niu, X., Asma, E., Wang, W., & Qi, J. (2017). Regularization parameter selection for penalized-likelihood list-mode image reconstruction in PET. Physics in Medicine & Biology, 62(12), 5114–5130.

    Article  ADS  Google Scholar 

  73. Reader, A. J., & Ellis, S. (2020). Bootstrap-optimised regularised image reconstruction for emission tomography. IEEE Transactions on Medical Imaging, 39(6), 2163–2175

    Google Scholar 

  74. Chen, S., Liu, H., Shi, P., & Chen, Y. (2015). Sparse representation and dictionary learning penalized image reconstruction for positron emission tomography. Physics in Medicine & Biology, 60(2), 807.

    Article  ADS  Google Scholar 

  75. Tahaei, M. S., & Reader, A. J. (2016). Patch-based image reconstruction for PET using prior-image derived dictionaries. Physics in Medicine & Biology, 61(18), 6833.

    Article  ADS  Google Scholar 

  76. Tang, J., Yang, B., Wang, Y., & Ying, L. (2016). Sparsity-constrained PET image reconstruction with learned dictionaries. Physics in Medicine & Biology, 61(17), 6347.

    Article  ADS  Google Scholar 

  77. Rubinstein, R., Bruckstein, A. M., & Elad, M. (2010). Dictionaries for sparse representation modeling. Proceedings of the IEEE, 98(6), 1045–1057.

    Article  Google Scholar 

  78. Gribonval, R., & Schnass, K. (2010). Dictionary identification—Sparse matrix-factorization via ℓ1-minimization. IEEE Transactions on Information Theory, 56(7), 3523–3539.

    Article  MathSciNet  MATH  Google Scholar 

  79. Aharon, M., Elad, M., & Bruckstein, A. (2006). K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation. IEEE Transactions on Signal Processing, 54, 4311–4322.

    Article  ADS  MATH  Google Scholar 

  80. Wang, G., & Qi, J. (2015). PET image reconstruction using kernel method. IEEE Transactions on Medical Imaging, 34(1), 61–71.

    Article  Google Scholar 

  81. Hutchcroft, W., Wang, G., Chen, K. T., Catana, C., & Qi, J. (2016). Anatomically-aided PET reconstruction using the kernel method. Physics in Medicine & Biology, 61(18), 6668–6683.

    Article  ADS  Google Scholar 

  82. Gong, K., Cheng-Liao, J., Wang, G., Chen, K. T., Catana, C., & Qi, J. (2018). Direct Patlak reconstruction from dynamic PET data using the kernel method with MRI information based on structural similarity. IEEE Transactions on Medical Imaging, 37(4), 955–965.

    Article  Google Scholar 

  83. Wei, D., Charikar, M., & Kai, L. (2011). Efficient k-nearest neighbor graph construction for generic similarity measures. In International conference on World Wide Web. ACM.

    Google Scholar 

  84. Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.

    Article  ADS  Google Scholar 

  85. Haggstrom, I., Schmidtlein, C. R., Campanella, G., & Fuchs, T. J. (2019). DeepPET: A deep encoder-decoder network for directly solving the PET image reconstruction inverse problem. Medical Image Analysis, 54, 253–262.

    Article  Google Scholar 

  86. Liu, Z. Y., Chen, H., & Liu, H. F. (2019). Deep learning based framework for direct reconstruction of PET images. In Medical image computing and computer assisted intervention – MICCAI 2019, Pt III (Vol. 11766, pp. 48–56).

    Chapter  Google Scholar 

  87. Hu, Z. L., et al. (2021). DPIR-Net: Direct PET image reconstruction based on the Wasserstein generative adversarial network. IEEE Transactions on Radiation and Plasma Medical Sciences, 5(1), 35–43.

    Article  Google Scholar 

  88. Li, Y., et al. (2023). A deep neural network for parametric image reconstruction on a large axial field-of-view PET. European Journal of Nuclear Medicine and Molecular Imaging, 50(3), 701–714.

    Article  Google Scholar 

  89. Whiteley, W., Luk, W. K., & Gregor, J. (2020). DirectPET: full-size neural network PET reconstruction from sinogram data. Journal of Medical Imaging, 7(3), 032503.

    Article  Google Scholar 

  90. Whiteley, W., Panin, V., Zhou, C. Y., Cabello, J., Bharkhada, D., & Gregor, J. (2021). FastPET: Near real-time reconstruction of PET histo-image data using a neural network. IEEE Transactions on Radiation and Plasma Medical Sciences, 5(1), 65–77.

    Article  Google Scholar 

  91. Feng, T., et al. (2021). Deep learning-based image reconstruction for TOF PET with DIRECT data partitioning format. Physics in Medicine & Biology, 66(16), 165007.

    Article  ADS  Google Scholar 

  92. Kandarpa, V. S. S., Bousse, A., Benoit, D., & Visvikis, D. (2021). DUG-RECON: A framework for direct image reconstruction using convolutional generative networks. IEEE Transactions on Radiation and Plasma Medical Sciences, 5(1), 44–53.

    Article  Google Scholar 

  93. Ote, K., & Hashimoto, F. (2022). Deep-learning-based fast TOF-PET image reconstruction using direction information. Radiological Physics and Technology, 15(1), 72–82.

    Article  Google Scholar 

  94. Ma, R. Y., et al. (2022). An encoder-decoder network for direct image reconstruction on sinograms of a long axial field of view PET. European Journal of Nuclear Medicine and Molecular Imaging, 49(13), 4464–4477.

    Article  Google Scholar 

  95. Liu, Z. Y., Ye, H. H., & Liu, H. F. (2022). Deep-learning-based framework for PET image reconstruction from sinogram domain. Applied Sciences-Basel, 12(16), 8118.

    Article  Google Scholar 

  96. Lv, L., et al. (Apr 2022). A back-projection-and-filtering-like (BPF-like) reconstruction method with the deep learning filtration from listmode data in TOF-PET. Medical Physics, 49(4), 2531–2544.

    Article  ADS  Google Scholar 

  97. Kim, K., et al. (Jun 2018). Penalized PET reconstruction using deep learning prior and local linear fitting. IEEE Transactions on Medical Imaging, 37(6), 1478–1487.

    Article  Google Scholar 

  98. Xie, N. B., et al. (2022). Penalized-likelihood PET image reconstruction using 3D structural convolutional sparse coding. IEEE Transactions on Biomedical Engineering, 69(1), 4–14.

    Article  MathSciNet  Google Scholar 

  99. Li, T. T., Zhang, M. X., Qi, W. Y., Asma, E., & Qi, J. Y. (2022). Deep learning based joint PET image reconstruction and motion estimation. IEEE Transactions on Medical Imaging, 41(5), 1230–1241.

    Article  Google Scholar 

  100. Gong, K., et al. (2019). Iterative PET image reconstruction using convolutional neural network representation. IEEE Transactions on Medical Imaging, 38(3), 675–685.

    Article  Google Scholar 

  101. Xie, Z. H., et al. (2020). Generative adversarial network based regularized image reconstruction for PET. Physics in Medicine & Biology, 65(12), 125016.

    Article  ADS  Google Scholar 

  102. Li, S. Q., & Wang, G. B. (2022). Deep kernel representation for image reconstruction in PET. IEEE Transactions on Medical Imaging, 41(11), 3029–3038.

    Article  Google Scholar 

  103. Gong, K., Catana, C., Qi, J. Y., & Li, Q. Z. (2019). PET image reconstruction using deep image prior. IEEE Transactions on Medical Imaging, 38(7), 1655–1665.

    Article  Google Scholar 

  104. Cui, J. N., et al. (2019). PET image denoising using unsupervised deep learning. European Journal of Nuclear Medicine and Molecular Imaging, 46(13), 2780–2789.

    Article  Google Scholar 

  105. Sudarshan, V. P., Reddy, K. P. K., Singh, M., Gubbi, J., & Pal, A. (2022). Uncertainty-informed Bayesian PET image reconstruction using a deep image prior. In N. Haq, P. Johnson, A. Maier, C. Qin, T. Würfl, & J. Yoo (Eds.), Machine learning for medical image reconstruction. MLMIR 2022 (Lecture Notes in Computer Science) (Vol. 13587, pp. 145–155).

    Chapter  Google Scholar 

  106. Gong, K., et al. (2022). Direct reconstruction of linear parametric images from dynamic PET using nonlocal deep image prior. IEEE Transactions on Medical Imaging, 41(3), 680–689.

    Google Scholar 

  107. Cui, J. N., Gong, K., Guo, N., Kim, K., Liu, H. F., & Li, Q. Z. (2022). Unsupervised PET logan parametric image estimation using conditional deep image prior. Medical Image Analysis, 80, 102519.

    Article  Google Scholar 

  108. Yokota, T., Kawai, K., Sakata, M., Kimura, Y., & Hontani, H. (2019). Dynamic PET image reconstruction using nonnegative matrix factorization incorporated with deep image prior. In 2019 IEEE/CVF international conference on computer vision (ICCV 2019) (pp. 3126–3135). IEEE.

    Google Scholar 

  109. Hashimoto, F., Ote, K., & Onishi, Y. (2022). PET image reconstruction incorporating deep image prior and a forward projection model. IEEE Transactions on Radiation and Plasma Medical Sciences, 6(8), 841–846.

    Article  Google Scholar 

  110. Gong, K., et al. (2019). MAPEM-Net: An unrolled neural network for fully 3D PET image reconstruction. In 15th international meeting on fully three-dimensional image reconstruction in radiology and nuclear medicine (Vol. 11072, p. 110720O). SPIE.

    Google Scholar 

  111. Gong, K., et al. (2019). EMnet: An unrolled deep neural network for PET image reconstruction. In Medical imaging 2019: Physics of medical imaging (Vol. 10948, p. 1094853). SPIE.

    Google Scholar 

  112. Mehranian, A., & Reader, A. J. (2021). Model-based deep learning PET image reconstruction using forward-backward splitting expectation-maximization. IEEE Transactions on Radiation and Plasma Medical Sciences, 5(1), 54–64.

    Article  Google Scholar 

  113. Lim, H. K., Chun, I. Y., Dewaraja, Y. K., & Fessler, J. A. (2020). Improved low-count quantitative PET reconstruction with an iterative neural network. IEEE Transactions on Medical Imaging, 39(11), 3512–3522.

    Article  Google Scholar 

  114. Chun, I. Y., & Fessler, J. A. (2018). Deep BCD-Net using identical encoding-decoding CNN structures for iterative image recovery. In Proceedings 2018 IEEE 13th image, video, and multidimensional signal processing workshop (IVMSP). IEEE.

    Google Scholar 

  115. Thielemans, K., et al. (2012). STIR: Software for tomographic image reconstruction release 2. Physics in Medicine & Biology, 57(4), 867.

    Article  ADS  Google Scholar 

  116. Ovtchinnikov, E., et al. (2020). SIRF: Synergistic image reconstruction framework. Computer Physics Communications, 249, 107087.

    Article  MathSciNet  Google Scholar 

  117. Paszke, A., et al. (2019). Pytorch: An imperative style, high-performance deep learning library. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d’Alché Buc, E. Fox, & R. Garnett (Eds.), Advances in neural information processing systems (Vol. 32, pp. 8024–8035). Curran Associates, Inc.

    Google Scholar 

Download references

Acknowledgments

The authors would like to thank Prof. Huafeng Liu of Zhejiang University for the valuable discussions and proof-reading. This work was supported by National Natural Science Foundation of China (82061Y0031), Foundation of Beijing Municipal Education Commission (73202Y1022), Shenzhen Science and Technology Program (KQTD20180412181221912, JCYJ20200109140603831), and Start-up Research Fund from the Institute of Medical Technology, Peking University Health Science Center.

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, Peking University, Beijing, China

    Zifeng Tian

  2. Institute of Medical Technology and National Biomedical Imaging Center, Peking University, Beijing, China

    Zhaoheng Xie

  3. Department of Biomedical Engineering, University of California, Davis, CA, USA

    Zhaoheng Xie

Authors
  1. Zifeng Tian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhaoheng Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhaoheng Xie .

Editor information

Editors and Affiliations

  1. University of California at Davis, Davis, CA, USA

    Junwei Du

  2. Emerging Technologies CMOS Inc., Port Moody, BC, Canada

    Krzysztof (Kris) Iniewski

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this chapter

Check for updates. Verify currency and authenticity via CrossMark

Cite this chapter

Tian, Z., Xie, Z. (2023). Toward a New Frontier in PET Image Reconstruction: A Paradigm Shift to the Learning-Based Methods. In: Du, J., Iniewski, K.(. (eds) Gamma Ray Imaging. Springer, Cham. https://doi.org/10.1007/978-3-031-30666-2_2

Download citation

Publish with us

Policies and ethics

Search

Navigation