Advertisement

Data-Driven Speed-of-Sound Reconstruction for Medical Ultrasound: Impacts of Training Data Format and Imperfections on Convergence

Conference paper
  • 169 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12722)

Abstract

B-mode imaging is a qualitative method and its interpretation depends on users’ experience. Quantitative tissue information can increase precision and decrease user ambiguity. For example, Speed-of-Sound (SoS) in tissue is known to carry diagnostic information. Studies showed the possibility of SoS reconstruction from ultrasound raw data (a.k.a., RF data) using deep neural networks (DNNs). However, many ultrasound systems are designed to process demodulated data (i.e., IQ data) and often decimate data in early stages of acquisition. In this study we investigated the impacts of input data format and decimation on convergence of the DNNs for SoS reconstruction. Our results show that fully data-driven SoS reconstruction is possible using demodulated ultrasound data presented in Cartesian or Polar format using an encoder-decoder network. We performed a study using only amplitude and only phase information of ultrasound data for SoS reconstruction. Our results showed that distortion of the phase information results in inconsistent SoS predictions, indicating sensitivity of the investigated approach to phase information. We demonstrated that without losing significant accuracy, decimated IQ data can be used for SoS reconstruction.

Keywords

Speed-of-Sound Deep Neural Network Ultrasound 

References

  1. 1.
    Benjamin, A., et al.: Surgery for obesity and related diseases: I. A novel approach to the quantification of the longitudinal speed of sound and its potential for tissue characterization. Ultrasound Med. Biol. 44(12), 2739–2748 (2018)CrossRefGoogle Scholar
  2. 2.
    Bernhardt, M., Vishnevskiy, V., Rau, R., Goksel, O.: Training variational networks with multidomain simulations: speed-of-sound image reconstruction. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 67(12), 2584–2594 (2020)CrossRefGoogle Scholar
  3. 3.
    Cho, J., Lee, K., Shin, E., Choy, G., Do, S.: How much data is needed to train a medical image deep learning system to achieve necessary high accuracy? arXiv preprint arXiv:1511.06348 (2015)
  4. 4.
    Feigin, M., Freedman, D., Anthony, B.W.: A deep learning framework for single-sided sound speed inversion in medical ultrasound. IEEE Trans. Biomed. Eng. 67(4), 1142–1151 (2019)CrossRefGoogle Scholar
  5. 5.
    Feigin, M., Zwecker, M., Freedman, D., Anthony, B.W.: Detecting muscle activation using ultrasound speed of sound inversion with deep learning. In: 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), pp. 2092–2095. IEEE (2020)Google Scholar
  6. 6.
    Hachiya, H., Ohtsuki, S., Tanaka, M.: Relationship between speed of sound in and density of normal and diseased rat livers. Jpn. J. Appl. Phys. 33(5S), 3130 (1994)CrossRefGoogle Scholar
  7. 7.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167 (2015)
  8. 8.
    Jeong, W.K., Lim, H.K., Lee, H.K., Jo, J.M., Kim, Y.: Principles and clinical application of ultrasound elastography for diffuse liver disease. Ultrasonography 33(3), 149 (2014)CrossRefGoogle Scholar
  9. 9.
    Khodr, Z.G., et al.: Determinants of the reliability of ultrasound tomography sound speed estimates as a surrogate for volumetric breast density. Med. Phys. 42(10), 5671–5678 (2015)CrossRefGoogle Scholar
  10. 10.
    Khun Jush, F., Biele, M., Dueppenbecker, P.M., Schmidt, O., Maier, A.: DNN-based speed-of-sound reconstruction for automated breast ultrasound. In: 2020 IEEE International Ultrasonics Symposium (IUS), pp. 1–7. IEEE (2020)Google Scholar
  11. 11.
    Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
  12. 12.
    Kirkhorn, J.: Introduction to IQ-demodulation of RF-data (1999)Google Scholar
  13. 13.
    Li, C., Duric, N., Littrup, P., Huang, L.: In vivo breast sound-speed imaging with ultrasound tomography. Ultrasound Med. Biol. 35(10), 1615–1628 (2009)CrossRefGoogle Scholar
  14. 14.
    Lucas, A., Iliadis, M., Molina, R., Katsaggelos, A.K.: Using deep neural networks for inverse problems in imaging: beyond analytical methods. IEEE Sig. Process. Mag. 35(1), 20–36 (2018)CrossRefGoogle Scholar
  15. 15.
    Matsuhashi, T., Yamada, N., Shinzawa, H., Takahashi, T.: An evaluation of hepatic ultrasound speed in injury models in rats: correlation with tissue constituents. J. Ultrasound Med. 15(8), 563–570 (1996)CrossRefGoogle Scholar
  16. 16.
    Ongie, G., Jalal, A., Baraniuk, C.A.M.R.G., Dimakis, A.G., Willett, R.: Deep learning techniques for inverse problems in imaging. IEEE J. Sel. Areas Inf. Theor. 1, 39–56 (2020)Google Scholar
  17. 17.
    Qu, X., Azuma, T., Liang, J.T., Nakajima, Y.: Average sound speed estimation using speckle analysis of medical ultrasound data. Int. J. Comput. Assist. Radiol. Surg. 7(6), 891–899 (2012)CrossRefGoogle Scholar
  18. 18.
    Sak, M., et al.: Using speed of sound imaging to characterize breast density. Ultrasound Med. Biol. 43(1), 91–103 (2017)CrossRefGoogle Scholar
  19. 19.
    Sanabria, S., et al.: Breast-density assessment with hand-held ultrasound: a novel biomarker to assess breast cancer risk and to tailor screening? Eur. Radiol. 28(8), 3165–3175 (2018).  https://doi.org/10.1007/s00330-017-5287-9CrossRefGoogle Scholar
  20. 20.
    Sanabria, S.J., Rominger, M.B., Goksel, O.: Speed-of-sound imaging based on reflector delineation. IEEE Trans. Biomed. Eng. 66(7), 1949–1962 (2018)CrossRefGoogle Scholar
  21. 21.
    Stähli, P., Kuriakose, M., Frenz, M., Jaeger, M.: Forward model for quantitative pulse-echo speed-of-sound imaging. arXiv preprint arXiv:1902.10639 (2019)
  22. 22.
    Szabo, T.L.: Diagnostic Ultrasound Imaging: Inside Out. Academic Press (2004)Google Scholar
  23. 23.
    Treeby, B.E., Cox, B.T.: k-wave: Matlab toolbox for the simulation and reconstruction of photoacoustic wave fields. J. Biomed. Opt. 15(2), 021314 (2010)CrossRefGoogle Scholar
  24. 24.
    Vishnevskiy, V., Sanabria, S.J., Goksel, O.: Image reconstruction via variational network for real-time hand-held sound-speed imaging. In: Knoll, F., Maier, A., Rueckert, D. (eds.) MLMIR 2018. LNCS, vol. 11074, pp. 120–128. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00129-2_14CrossRefGoogle Scholar
  25. 25.
    Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)

Copyright information

© Springer Nature Switzerland AG 2021

Authors and Affiliations

  1. 1.Technology ExcellenceSiemens Healthcare GmbHErlangenGermany
  2. 2.Pattern Recognition LabFriedrich-Alexander-UniversityErlangenGermany

Personalised recommendations