Deep Learning Based Minimum Variance Beamforming for Ultrasound Imaging

  • Renxin Zhuang
  • Junying ChenEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11798)


Deep learning has been applied to ultrasound imaging recently, and it needs to be further studied to improve ultrasound beamforming methods. According to the latest research, deep neural network was able to suppress off-axis scattering signals in ultrasound channel data, which enhanced the performance of beamforming and improved the contrast of the output ultrasound images. Minimum variance beamforming was capable to present high lateral resolution, but lacked of high image contrast of ultrasound images. In order to effectively improve the contrast of minimum variance beamforming, this work investigated the combination of deep neural network and minimum variance beamforming. In the experiments, the simulated point target and cyst scenarios were adopted to evaluate the performance of the proposed methods. The results demonstrated that combining deep neural network and minimum variance beamforming can effectively reduce the side lobe level and thus can improve the contrast of the ultrasound images while maintaining the lateral resolution performance.


Minimum variance beamforming Deep learning High image contrast Ultrasound imaging 



This work is supported by “National Natural Science Foundation of China” (No. 61802130), “Guangdong Natural Science Foundation” (No. 2018A030310355), and “Guangzhou Science and Technology Program” (No. 201707010223).


  1. 1.
    Asl, B.M., Mahloojifar, A.: Eigenspace-based minimum variance beamforming applied to medical ultrasound imaging. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 57(11), 2381–2390 (2010)CrossRefGoogle Scholar
  2. 2.
    Asl, B.M., Mahloojifar, A.: Contrast enhancement and robustness improvement of adaptive ultrasound imaging using forward-backward minimum variance beamforming. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 58(4), 858–867 (2011)CrossRefGoogle Scholar
  3. 3.
    Goodfellow, I., Bengio, Y., Courville, A., Bengio, Y.: Deep Learning. MIT Press, Cambridge (2016)zbMATHGoogle Scholar
  4. 4.
    Havlice, J.F., Taenzer, J.C.: Medical ultrasonic imaging: an overview of principles and instrumentation. Proc. IEEE 67(4), 620–641 (1979)CrossRefGoogle Scholar
  5. 5.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  6. 6.
    Jensen, J.A.: Field: a program for simulating ultrasound systems. In: Proceedings of Nordic-Balttc Conference on Biomedical Imaging, pp. 351–353 (1996)Google Scholar
  7. 7.
    Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of International Conference for Learning Representations, pp. 1–15 (2015)Google Scholar
  8. 8.
    Liu, T., Zhao, H., Zheng, Y.: Eigenspace-based minimum variance beamforming combined with sign coherence factor for ultrasound beamforming. Acta Acustica 40(6), 855–862 (2015). (in Chinese)Google Scholar
  9. 9.
    Luchies, A.C., Byram, B.C.: Deep neural networks for ultrasound beamforming. IEEE Trans. Med. Imaging 37(9), 2010–2021 (2018)CrossRefGoogle Scholar
  10. 10.
    Simson, W., Paschali, M., Navab, N., Zahnd, G.: Deep learning beamforming for sub-sampled ultrasound data. In: Proceedings of IEEE International Ultrasonics Symposium, pp. 1–4 (2018)Google Scholar
  11. 11.
    Synnevåg, J.F., Austeng, A., Holm, S.: Adaptive beamforming applied to medical ultrasound imaging. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 54(8), 1606–1613 (2007)CrossRefGoogle Scholar
  12. 12.
    Zaharis, Z.D., Gotsisa, K.A., Sahalos, J.N.: Adaptive beamforming with low side lobe level using neural networks trained by mutated boolean PSO. Prog. Electromagnet. Res. 127, 139–154 (2012)CrossRefGoogle Scholar
  13. 13.
    Zaharis, Z.D., et al.: Implementation of antenna array beamforming by using a novel neural network structure. In: Proceedings of International Conference on Telecommunications and Multimedia, pp. 25–27 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.School of Software EngineeringSouth China University of TechnologyGuangzhouChina

Personalised recommendations