Skip to main content
SpringerLink
Log in

Improvising limitations of DNN based ultrasound image reconstruction

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

Ultrasound modalities are cost-effective and radiation-free technology for real-time medical imaging. These modalities require image reconstruction to obtain the actual ultrasound images from ultrasound raw data. The ultrasound raw data is obtained in the form of echo after scanning an imaging plane through ultrasound waves. The most commonly used image reconstruction beamforming technique is Delay and Sum (DAS). Other sophisticated beamforming techniques are Delay Multiply and Sum (DMAS) and Minimum Variance Distortionless Response (MVDR). DAS has limited image quality, and the employment of sophisticated techniques increases the computational complexity and computational time with improvement in image quality. To overcome these problems, various DNN (Deep Neural Networks) based techniques have been proposed which can reconstruct ultrasound images directly from ultrasound raw data. But DNN implementation has two limitations: accuracy of reconstruction and generalizability of the model. To overcome these limitations, we are proposing methodologies with a DNN model which was able to reduce these limitations. Firstly, we generated the datasets which include multiple shapes such as line, circle, ellipse, and parabola. After that, we have implemented a CNN-DNN (Convolution Neural Network and Deep Neural Network) hybrid model which has significantly improved computational time as well as image quality. We have trained our model with different sets of data to validate the reconstruction of the image matrix. We achieved a significant improvement in computational time of around 100 times (from around 0.6 s to 0.0059 s) as compared to DAS beamforming technique. At the same time, we also achieved a significant improvement in image quality with 37.19 dB average and 41.37 dB maximum improved Peak Signal to Noise Ratio (PSNR), and 87.41% average and 95% maximum Structural Similarity Index Matrix (SSIM) value. We also achieved generalizability and precise image reconstruction by using the proposed model.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  1. Fouad M, Metwally Y, Schmitz G, Huebner M, Abd El Ghany MA (2020) “Deep learning utilization in beamforming enhancement for medical ultrasound.” Proc. - 2020 IEEE 44th Annu. Comput. Software, Appl. Conf. COMPSAC 2020, pp. 717–722. https://doi.org/10.1109/COMPSAC48688.2020.0-175.

  2. Chen H, Xu H, Shi P, Gong Y, Qiu Z, Shi L, Zhang Q (2021) 3-D Gabor-based anisotropic diffusion for speckle noise suppression in dynamic ultrasound images. Phys Eng Sci Med 44(1):207–219. https://doi.org/10.1007/s13246-020-00969-x

    Article  CAS  Google Scholar 

  3. Bierig SM, Jones A (2009) Accuracy and cost comparison of ultrasound versus alternative imaging modalities, including CT, MR, PET, and angiography. J Diagn Med Sonogr 25(3):138–144. https://doi.org/10.1177/8756479309336240

    Article  Google Scholar 

  4. Perrot V, Polichetti M, Varray F, Garcia D (2021) So you think you can DAS? A viewpoint on delay-and-sum beamforming. Ultrasonics 111:106309. https://doi.org/10.1016/j.ultras.2020.106309

    Article  Google Scholar 

  5. Beamforming P, Nguyen NQ, Prager RW (2017) Minimum variance approaches to ultrasound. IEEE Trans Med Imaging 36(2):374–384

    Article  Google Scholar 

  6. Synnevåg JF, Austeng A, Holm S (2009) Benefits of minimum-variance beamforming in medical ultrasound imaging. IEEE Trans Ultrason Ferroelectr Freq Control 56(9):1868–1879. https://doi.org/10.1109/TUFFC.2009.1263

    Article  Google Scholar 

  7. Matrone G, Savoia AS, Caliano G, Magenes G (2015) The delay multiply and sum beamforming algorithm in ultrasound B-mode medical imaging. IEEE Trans Med Imaging 34(4):940–949. https://doi.org/10.1109/TMI.2014.2371235

    Article  Google Scholar 

  8. Vayyeti A, Thittai AK (2020) A filtered delay weight multiply and sum (F-DwMAS) beamforming for ultrasound imaging: preliminary results. Proc—Int Symp Biomed Imaging 2020(1):312–315. https://doi.org/10.1109/ISBI45749.2020.9098528

    Article  Google Scholar 

  9. Zhang J, He Q, Xiao Y, Zheng H, Wang C, Luo J (2020) Self-supervised learning of a deep neural network for ultrafast ultrasound imaging as an inverse problem. IEEE Int Ultrason Symp. IUS 2020:2019–2022. https://doi.org/10.1109/IUS46767.2020.9251533

    Article  Google Scholar 

  10. Luijten B et al (2019) Deep learning for fast adaptive beamforming. ICASSP IEEE Int Conf Acoust Speech Signal Process—Proc 2019:1333–1337. https://doi.org/10.1109/ICASSP.2019.8683478

    Article  Google Scholar 

  11. Wang Y, Kempski K, Kang JU, Bell MAL (2020) A conditional adversarial network for single plane wave beamforming. IEEE Int Ultrason Symp IUS 2020:20–23. https://doi.org/10.1109/IUS46767.2020.9251729

    Article  Google Scholar 

  12. Stepanishen PR (1971) The time-dependent force and radiation impedance on a piston in a rigid infinite planar baffle. J Acoust Soc Am 49(3B):841–849. https://doi.org/10.1121/1.1912424

    Article  Google Scholar 

  13. Stepanishen PR (1981) Pulsed transmit/receive response of ultrasonic piezoelectric transducers. J Acoust Soc Am 69(6):1815–1827. https://doi.org/10.1121/1.385919

    Article  Google Scholar 

  14. Arendt Jensen J (1991) A model for the propagation and scattering of ultrasound in tissue. J Acoust Soc Am 89(1):182–190. https://doi.org/10.1121/1.400497

    Article  Google Scholar 

  15. Jensen A, Svendsen B (1992) Calculation of pressure fields from arbitrarily. Ultrason Ferroelectr Freq Control IEEE Trans 39(2):262–267

    Article  CAS  Google Scholar 

  16. Ul Sabha S (2018) A novel and efficient round robin algorithm with intelligent time slice and shortest remaining time first. Mater Today Proc 5(5):12009–12015. https://doi.org/10.1016/j.matpr.2018.02.175

    Article  Google Scholar 

  17. Saranya C, Manikandan G (2013) A study on normalization techniques for privacy preserving data mining. Int J Eng Technol 5(3):2701–2704

    Google Scholar 

  18. Lopez Pinaya WH, Vieira S, Garcia-Dias R, Mechelli A (2019) Autoencoders. Elsevier Inc., Amsterdam

    Google Scholar 

  19. Jang M, Seo S, Kang P (2019) Recurrent neural network-based semantic variational autoencoder for Sequence-to-sequence learning. Inf Sci (Ny) 490:59–73. https://doi.org/10.1016/j.ins.2019.03.066

    Article  Google Scholar 

  20. Chen M, Shi X, Zhang Y, Wu D, Guizani M (2017) Deep feature learning for medical image analysis with convolutional autoencoder neural network. IEEE Trans Big Data 7(4):750–758. https://doi.org/10.1109/tbdata.2017.2717439

    Article  Google Scholar 

  21. Zhao F, Feng J, Zhao J, Yang W, Yan S (2018) Robust LSTM-autoencoders for face de-occlusion in the wild. IEEE Trans Image Process 27(2):778–790. https://doi.org/10.1109/TIP.2017.2771408

    Article  Google Scholar 

  22. Li X et al (2017) An image reconstruction framework based on deep neural network for electrical impedance tomography. Proc—Int Conf Image Process ICIP 2017:3585–3589. https://doi.org/10.1109/ICIP.2017.8296950

    Article  Google Scholar 

  23. Partovi FY, Anandarajan M (2002) Classifying inventory using an artificial neural network approach. Comput Ind Eng 41(4):389–404

    Article  Google Scholar 

  24. Agarap AF (2018) “Deep learning using rectified linear units (ReLU),” no. 1, pp. 2–8, 2018, [Online]. http://arxiv.org/abs/1803.08375. Accessed Aug 2021

  25. Kingma DP, Ba JL (2015) Adam: A Method for Stochastic Optimization. Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). https://doi.org/10.48550/arXiv.1412.6980

  26. Ye J (2011) Cosine similarity measures for intuitionistic fuzzy sets and their applications. Math Comput Model 53(1–2):91–97. https://doi.org/10.1016/j.mcm.2010.07.022

    Article  Google Scholar 

  27. Poobathy D, Chezian RM (2014) Edge detection operators: peak signal to noise ratio based comparison. Int J Image, Graph Signal Process 6(10):55–61. https://doi.org/10.5815/ijigsp.2014.10.07

    Article  Google Scholar 

  28. Simoncelli EP, Sheikh HR, Bovik AC, Wang Z (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans image Process 13(4):600–612

    Article  Google Scholar 

  29. Chervyakov N, Lyakhov P, Nagornov N (2020) Analysis of the quantization noise in discrete wavelet transform filters for 3D medical imaging. Appl Sci. https://doi.org/10.3390/app10041223

    Article  Google Scholar 

Download references

Acknowledgements

We would like to thank IIT Ropar and Department of Biomedical Engineering for providing us with the necessary infrastructure and support for carrying out this research.

Funding

The authors declare that no funds, grants, or other support were received during the preparation of this manuscript.

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, Indian Institute of Technology, Ropar, Punjab, India

    Balendra, Rajat Suvra Halder & Ashish Sahani

Authors
  1. Balendra
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Rajat Suvra Halder
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ashish Sahani
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Ba and AS. The first draft of the manuscript was written by RSH and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Rajat Suvra Halder.

Ethics declarations

Conflict of interest

The authors have no relevant financial or non-financial interests to disclose.

Ethical approval

No human or animal subjects were involved in this study. Hence no ethical approval is required.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Balendra, Halder, R.S. & Sahani, A. Improvising limitations of DNN based ultrasound image reconstruction. Phys Eng Sci Med 45, 1139–1151 (2022). https://doi.org/10.1007/s13246-022-01181-9

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-022-01181-9

Keywords

Search

Navigation