Nuclear Engineering and Technology

Korean Nuclear Society (한국원자력학회)
권호 표지
DOI QR코드

DOI QR Code

Application of a deep learning algorithm to Compton imaging of radioactive point sources with a single planar CdTe pixelated detector

  • Daniel, G. (Universite Paris-Saclay, CEA) ;
  • Gutierrez, Y. (AIM, CEA, CNRS, Universite Paris-Saclay) ;
  • Limousin, O. (AIM, CEA, CNRS, Universite Paris-Saclay)
  • Received : 2021.04.19
  • Accepted : 2021.10.19
  • Published : 2022.05.25
Download PDF
⟨ Previous Next ⟩

Abstract

Compton imaging is the main method for locating radioactive hot spots emitting high-energy gamma-ray photons. In particular, this imaging method is crucial when the photon energy is too high for coded-mask aperture imaging methods to be effective or when a large field of view is required. Reconstruction of the photon source requires advanced Compton event processing algorithms to determine the exact position of the source. In this study, we introduce a novel method based on a Deep Learning algorithm with a Convolutional Neural Network (CNN) to perform Compton imaging. This algorithm is trained on simulated data and tested on real data acquired with Caliste, a single planar CdTe pixelated detector. We show that performance in terms of source location accuracy is equivalent to state-of-the-art algorithms, while computation time is significantly reduced and sensitivity is improved by a factor of ~5 in the Caliste configuration.

Keywords

Acknowledgement

The authors wish to thank 3D PLUS and CEA for supporting this work within the framework of the joint laboratory ALB3DO (Advanced Lab for 3D Detection Device Developments).

References

  1. Y.-s. Kim, J.H. Kim, H.S. Lee, H.R. Lee, J.H. Park, J.H. Park, H. Seo, C. Lee, S.H. Park, C.H. Kim, Development of Compton imaging system for nuclear material monitoring at pyroprocessing test-bed facility, J. Nucl. Sci. Technol. 53 (12) (2016) 2040-2048. https://doi.org/10.1080/00223131.2016.1199333
  2. A. Koide, J. Kataoka, T. Masuda, S. Mochizuki, T. Taya, K. Sueoka, L. Tagawa, K. Fujieda, T. Maruhashi, T. Kurihara, T. Inaniwa, Precision imaging of 4.4 MeV gamma rays using a 3-D position sensitive Compton camera, Sci. Rep. 8 (2018). Article number: 8116.
  3. T. Tanaka, R. Blandford, K. Doutsu, T. Endo, T. Enoto, Y. Fukazawa, K. Fukami, T. Fukuyama, Y. Hanabata, J. Harayama, K. Hayashi, K. Hiragi, S. Ishikawa, J. Kataoka, J. Katsuta, T. Kitaguchi, M. Kokubun, M. Koseki, T. Kozu, G. Madejski, K. Makishima, M. Matsuoka, T. Miura, T. Mizuno, S. Nakahira, K. Nakajima, K. Nakazawa, S. Nishino, H. Nishioka, H. Noda, H. Odaka, S. Saito, S. Sasaki, R. Sato, S. Sugimoto, H. Tajima, T. Takahashi, M. Tashiro, Y. Terada, S. Torii, Y. Uchiyama, Y. Umeki, S. Watanabe, Y. Yaji, S. Yamada, K. Yamaoka, M. Yoshino, T. Yuasa, The Soft Gamma-Ray Detector for the ASTRO-H Mission, IEEE Nuclear Science Symposium Conference Record (NSS/MIC), 2009, pp. 2140-2144.
  4. W. Leo, Techniques for Nuclear and Particle Physics Experiments: A How-To Approach, Springer-Verlag, 1993.
  5. E. Ordonez, A. Bolozdynya, W. Chang, Doppler Broadening of Energy Spectra in Compton Cameras, 1997, 2, IEEE Nuclear Science Symposium Conference Record, Albuquerque, NM, USA, 1997, pp. 1361-1365.
  6. S. Takeda, Y. Ichinohe, K. Hagino, H. Odaka, T. Yuasa, S.-n. Ishikawa, T. Fukuyama, S. Saito, T. Sato, G. Sato, S. Watanabe, M. Kokubun, T. Takahashi, Applications and imaging techniques of a Si/CdTe Compton gamma-ray camera, TIPP 2011 - technology and instrumentation in particle physics 2011, Phys. Procedia 37 (2012) 859-866, 2012. https://doi.org/10.1016/j.phpro.2012.04.096
  7. G. Llosa, M. Trovato, J. Barrio, A. Etxebeste, E. Munoz, C. Lacasta, J.F. Oliver, M. Rafecas, C. Solaz, P. Solevi, First images of a three-layer Compton telescope prototype for treatment monitoring in hadron therapy, Front. Oncol. 6 (14) (2016).
  8. C. Lehner, Z. He, F. Zhang, 4Pi Compton imaging using a 3-D position-sensitive CdZnTe detector via weighted list-mode maximum likelihood, IEEE Trans. Nucl. Sci. 51 (4) (2004).
  9. L. Parra, H. Barrett, List-mode likelihood: EM algorithm and image quality estimation demonstrated on 2-D PET, IEEE Trans. Med. Imag. 17 (2) (1998).
  10. A. Andreyev, A. Sitek, A. Celler, Fast image reconstruction for Compton camera using stochastic origin ensemble approach, Nucl. Med. Phys. 38 (1) (2010) 429-438.
  11. A. Andreyev, A. Celler, I. Ozsahin, A. Sitek, Resolution recovery for Compton camera using origin ensemble algorithm, Med. Phys. 43 (8) (2016) 4866. https://doi.org/10.1118/1.4959551
  12. R. Zhang, P. Gong, X. Tang, P. Wang, C. Zhou, X. Zhu, L. Gao, D. Liang, Z. Wang, Reconstruction method for gamma-ray coded-aperture imaging based on convolutional neural network, Nucl. Instrum. Methods Phys. Res. A 934 (2019) 41-51. https://doi.org/10.1016/j.nima.2019.04.055
  13. R. Zhang, X. Tang, P. Gong, P. Wang, C. Zhou, X. Zhu, D. Liang, Z. Wang, Low-noise Reconstruction Method for Coded-Aperture Gamma Camera Based on Multi-Layer Perceptron, Nuclear Engineering and Technology, 2020.
  14. G. Daniel, O. Limousin, Extended Sources Reconstructions by Means of Coded Mask Aperture Systems and Deep Learning Algorithm, Submitted to NIM-A, 2021.
  15. S. Dubos, O. Limousin, C. Blondel, R. Chipaux, Y. Dolgorouky, O. Gevin, Y. Menesguen, A. Meuris, T. Orduna, T. Tourette, A. Sauvageon, Low energy characterization of Caliste HD, a fine pitch CdTe-based imaging spectrometer, IEEE Trans. Nucl. Sci. 60 (No. 5) (2013).
  16. A. Michalowska, O. Gevin, O. Lemaire, F. Lugiez, P. Baron, H. Grabas, F. Pinsard, O. Limousin, E. Delagnes, IDeF-X HD : a low power multi-gain CMOS ASIC for the readout of Cd(Zn)Te detectors, in: IEEE Nuclear Science Symposuim and Medical Imaging Conference, 2010. NSS/MIC p. 1556-1559 5874037.
  17. O. Gevin, F. Lugiez, A. Michalowska, A. Meuris, O. Limousin, E. Delagnes, O. Lemaire, F. Pinsard, IDeF-X HD: a CMOS ASIC for the Readout of Cd(Zn)Te Detectors for Space-Borne Applications, 2020 arXiv:2102.01992.
  18. G. Daniel, O. Limousin, D. Maier, A. Meuris, F. Carrel, Compton imaging reconstruction methods: a comparative performance study of direct back-projection, SOE, a new Bayesian algorithm and a new Compton inversion method applied to real data with Caliste, in: EPJ Web Conf, 225, ANIMMA, 2019, p. 2020.
  19. G. Daniel, F. Ceraudo, O. Limousin, D. Maier, A. Meuris, Automatic and real-time identification of radionuclides in gamma-ray spectra: a new method based on convolutional neural network trained with synthetic data set, IEEE Trans. Nucl. Sci. Proc.Animma. 67 (4) (2019) 644-653, 2020.
  20. A. Krizhevsky, I. Sutskever, G. Hinton, ImageNet classification with deep convolutional neural networks, Commun. ACM 60 (Issue 6) (2017).
  21. D. Kingma, J. Ba, Adam: a method for stochastic optimization, in: Conference Paper at the 3rd International Conference for Learning Representations, 2015. San Diego.
  22. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, PyTorch: an imperative style, high-performance deep learning library, Adv. Neural Inf. Process. Syst. 32 (2019) 8024-8035. NEURIPS2019.