Skip to main content

CLSTM-KF reconstruction method for a low-activity moving radiation source localization and tracking with a coded-aperture gamma camera

Abstract

Background

Accurate localization of a low-activity moving radiation source plays an important role in nuclear security and safety. The coded-aperture gamma camera is generally applied to detect a radiation source, but its reconstruction methods may have some limitations when the radiation source is motional and weak.

Purpose

The purpose of this paper is to improve the quality of the reconstruction images and the localization accuracy when detecting a low-activity moving radiation source with a gamma camera.

Method

The CLSTM-KF method consists of the CLSTM network and the Kalman filter. The CLSTM network is applied to improve the CNR of reconstruction images by making an adaptive superposition for sequential reconstruction images decoded by the correlation analysis method. After the CLSTM network, a series of sequential positions would be filtered by the Kalman filter.

Results

By comparing with the traditional methods of the gamma camera, the CLSTM-KF method performs well in improving both the CNR of reconstruction images and the localization accuracy. Moreover, the computation time of the CLSTM-KF method can also meet the application requirements.

Conclusion

In summary, the CLSTM-KF method provides a better choice than the traditional methods in locating and tracking a low-activity moving radiation source.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

References

  1. M.J. Cielak, K.A.A. Gamage, R. Glover, Coded-aperture imaging systems: past, present and future development: a review. Radiat. Meas. 92, 59–71 (2016). https://doi.org/10.1016/j.radmeas.2016.08.002

    Article  Google Scholar 

  2. P. Fracas, G. Krishnamachari, J.P. Gayral, et al. Methodologies and systems to meet the challenges of locating and recovering orphan sources: source search operation conducted by French and Indian teams in the Republic of Georgia. na. 2003

  3. Durrant PT, Dallimore M, Jupp ID, et al. The application of pinhole and coded aperture imaging in the nuclear environment. Nucl. Instrum. Methods Phys. Res. Sect. A Accel. Spectrom. Dect. Assoc. Equip. 422(1-3), 667-671(1999). https://doi.org/10.1016/s0168-9002(98)01014-6

  4. R. Accorsi, F. Gasparini, R.C. Lanza, A coded aperture for high-resolution nuclear medicine planar imaging with a conventional Anger camera: experimental results. IEEE Trans. Nucl. Sci. 48(6), 2411–2417 (2001). https://doi.org/10.1109/nssmic.2001.1008643

    ADS  Article  Google Scholar 

  5. E.E. Fenimore, T.M. Cannon, Uniformly redundant arrays: digital reconstruction methods. Appl. Optics. 20(10), 1858–1864 (1981). https://doi.org/10.1117/12.956690

    ADS  Article  Google Scholar 

  6. A.P. Dempster, N.M. Laird, D.B. Rubin, Maximum likelihood from incomplete data via the EM algorithm. J. Roy. Stat. Soc.: Ser. B (Methodol.) 39(1), 1–22 (1977). https://doi.org/10.1142/9789812388759_0028

    MathSciNet  Article  MATH  Google Scholar 

  7. C.A. Johnson, A. Sofer. Interior-point methodology for large-scale regularized maximum likelihood reconstruction in emission tomography. 1997

  8. E.T. Jaynes, On the rationale of maximum-entropy methods. Proc. IEEE 70(9), 939–952 (1982). https://doi.org/10.1109/proc.1982.12425

    ADS  Article  Google Scholar 

  9. R. Zhang, P. Gong, X. Tang et al., Reconstruction method for gamma-ray coded-aperture imaging based on convolutional neural network. Nucl Instrum Methods Phys Res Sect A Accel Spectrom Dect Assoc Equip 934, 41–51 (2019). https://doi.org/10.1016/j.nima.2019.04.055

    ADS  Article  Google Scholar 

  10. T. Yamane, A. Kondo, M. Takahashi et al., Ultrafast bone scintigraphy scan for detecting bone metastasis using a CZT whole-body gamma camera. Eur. J. Nucl. Med. Mol. Imaging 46(8), 1672–1677 (2019). https://doi.org/10.1007/s00259-019-04329-0

    Article  Google Scholar 

  11. M. Chandy, C. Pilotto, R. McLean. Networked sensing systems for detecting people carrying radioactive material. 2008 5th International Conference on Networked Sensing Systems. IEEE, pp 148–155 (2008). https://doi.org/10.1109/inss.2008.4610916

  12. R.B. Vilim, R.T. Klann, S.C.D.L. Barrera, et al. Tracking of weak radiation sources in crowded venues. IEEE Nuclear Science Symposium conference record. Nuclear Science Symposium. 995–1001 (2009). https://doi.org/10.1109/nssmic.2009.5402449

  13. N.S.V. Rao, M. Shankar, J.C. Chin, et al. Identification of low-level point radiation sources using a sensor network. 2008 International conference on information processing in sensor networks (IPSN 2008). IEEE, pp 493–504 (2008). https://doi.org/10.1109/ipsn.2008.19

  14. B. Deb, Iterative estimation of location and trajectory of radioactive sources with a networked system of detectors. IEEE Trans. Nucl. Sci. 60(2), 1315–1326 (2013). https://doi.org/10.1109/tns.2013.2247060

    ADS  Article  Google Scholar 

  15. J. Zhao, C.J. Sullivan, Detection and parameter estimation of radioactive sources with mobile sensor networks. Radiat. Phys. Chem. 155, 265–270 (2019). https://doi.org/10.1016/j.radphyschem.2018.06.018

    ADS  Article  Google Scholar 

  16. T. Mikolov, S. Kombrink, L. Burget, et al. Extensions of recurrent neural network language model. 2011 IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE. 5528-5531(2011). https://doi.org/10.1109/icassp.2011.5947611

  17. S. Hochreiter, J. Schmidhuber, Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997). https://doi.org/10.7717/peerjcs.216/fig-4

    Article  Google Scholar 

  18. Sundermeyer M, Schluter R, Ney H, et al. LSTM Neural Networks for Language Modeling. conference of the international speech communication association.194-197(2012)

  19. Tao X, Gao H, Shen X, et al. Scale-recurrent network for deep image deblurring. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8174-8182(2018). https://doi.org/10.1109/cvpr.2018.00853

  20. Srivastava N, Mansimov E, Salakhudinov R. Unsupervised learning of video representations using lstms. International conference on machine learning. 843-852(2015)

  21. S.H.I. Xingjian, Z. Chen, H. Wang H, et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv Neural Inf Process Syst, pp 802–810(2015)

  22. Z. Liu, C.J. Sullivan, Prediction of weather induced background radiation fluctuation with recurrent neural networks. Radiat. Phys. Chem. 155, 275–280 (2019). https://doi.org/10.1016/j.radphyschem.2018.03.005

    ADS  Article  Google Scholar 

  23. R. Zhang, Q. Zou. Time series prediction and anomaly detection of light curve using lstm neural network. J. Phys: Conference Series. 1061(1), 012012(2018). https://doi.org/10.1016/j.radphyschem.2018.03.005

  24. J. Chen, L. Yang, Y. Zhang, et al. Combining fully convolutional and recurrent neural networks for 3d biomedical image segmentation. Advances in neural information processing systems, pp 3036–3044 (2016)

  25. V. Badrinarayanan, A. Kendall, R. Cipolla, Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481–2495 (2017). https://doi.org/10.1109/tpami.2016.2644615

    Article  Google Scholar 

  26. Chen L C, Zhu Y, Papandreou G, et al. Encoder-decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European conference on computer vision (ECCV). 801-818(2018). https://doi.org/10.1007/978-3-030-01234-2_49

  27. K. Cho, B. Van Merriënboer, C. Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078(2014). https://doi.org/10.3115/v1/d14-1179

  28. I. Sutskever, O. Vinyals, Q.V. Le Q V. Sequence to sequence learning with neural networks. Advances in neural information processing systems, pp 3104–3112 (2014)

  29. R.J. Williams, J. Peng, An efficient gradient-based algorithm for on-line training of recurrent network trajectories. Neural Comput. 2(4), 490–501 (1990). https://doi.org/10.1162/neco.1990.2.4.490

    Article  Google Scholar 

  30. D.P. Kingma, J. Ba. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980(2014)

  31. Welch G, Bishop G. An introduction to the Kalman filter. 1995

  32. P.O. Gutman, M. Velger, Tracking targets using adaptive Kalman filtering. IEEE Trans. Aerosp. Electron. Syst. 26(5), 691–699 (1990). https://doi.org/10.1109/7.102704

    ADS  Article  Google Scholar 

  33. S.K. Weng, C.M. Kuo, S.K. Tu, Video object tracking using adaptive Kalman filter. J. Vis. Commun. Image Represent. 17(6), 1190–1208 (2006). https://doi.org/10.1016/j.jvcir.2006.03.004

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding authors

Correspondence to Shuang-Quan Liu or Long Wei.

Additional information

This work is supported by the National Natural Science Foundation of China (No. 11905229).

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Zou, Y., Liu, SQ., Sun, XL. et al. CLSTM-KF reconstruction method for a low-activity moving radiation source localization and tracking with a coded-aperture gamma camera. Radiat Detect Technol Methods 5, 228–237 (2021). https://doi.org/10.1007/s41605-020-00232-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s41605-020-00232-7

Keywords

  • Low activity
  • Coded-aperture gamma camera
  • Convolutional long short-term memory network
  • Kalman filter