Advertisement

Towards Capturing Sonographic Experience: Cognition-Inspired Ultrasound Video Saliency Prediction

Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 1065)

Abstract

For visual tasks like ultrasound (US) scanning, experts direct their gaze towards regions of task-relevant information. Therefore, learning to predict the gaze of sonographers on US videos captures the spatio-temporal patterns that are important for US scanning. The spatial distribution of gaze points on video frames can be represented through heat maps termed saliency maps. Here, we propose a temporally bidirectional model for video saliency prediction (BDS-Net), drawing inspiration from modern theories of human cognition. The model consists of a convolutional neural network (CNN) encoder followed by a bidirectional gated-recurrent-unit recurrent convolutional network (GRU-RCN) decoder. The temporal bidirectionality mimics human cognition, which simultaneously reacts to past and predicts future sensory inputs. We train the BDS-Net alongside spatial and temporally one-directional comparative models on the task of predicting saliency in videos of US abdominal circumference plane detection. The BDS-Net outperforms the comparative models on four out of five saliency metrics. We present a qualitative analysis on representative examples to explain the model’s superior performance.

Keywords

Fetal ultrasound Video saliency prediction Gaze tracking Convolutional neural networks 

Notes

Acknowledgements

This work is supported by the ERC (ERC-ADG-2015 694581, project PULSE) and the EPSRC (EP/R013853/1 and EP/M013774/1). AP is funded by the NIHR Oxford Biomedical Research Centre.

References

  1. 1.
    Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. In: NIPS - Deep Learning Symposium (2016)Google Scholar
  2. 2.
    Bak, C., Kocak, A., Erdem, E., Erdem, A.: Spatio-temporal saliency networks for dynamic saliency prediction. IEEE Trans. Multimed. 20(7), 1688–1698 (2018)CrossRefGoogle Scholar
  3. 3.
    Ballas, N., Yao, L., Pal, C., Courville, A.: Delving deeper into convolutional networks for learning video representations. In: ICLR (2016)Google Scholar
  4. 4.
    Baumgartner, C.F., et al.: SonoNet: real-time detection and localisation of fetal standard scan planes in freehand ultrasound. IEEE Trans. Med. Imag. 36(11), 2204–2215 (2017)CrossRefGoogle Scholar
  5. 5.
    Bazzani, L., Larochelle, H., Torresani, L.: Recurrent mixture density network for spatiotemporal visual attention. In: ICLR (2017)Google Scholar
  6. 6.
    Bylinskii, Z., Judd, T., Oliva, A., Torralba, A., Durand, F.: What do different evaluation metrics tell us about saliency models? IEEE Trans. Pattern Anal. Mach. Intell. 41(3), 740–757 (2019)CrossRefGoogle Scholar
  7. 7.
    Bylinskii, Z., et al.: MIT Saliency Benchmark. http://saliency.mit.edu/
  8. 8.
    Cai, Y., Sharma, H., Chatelain, P., Noble, J.A.: SonoEyeNet: standardized fetal ultrasound plane detection informed by eye tracking. In: ISBI (2018)Google Scholar
  9. 9.
    Cai, Y., Sharma, H., Chatelain, P., Noble, J.A.: Multi-task sonoeyenet: detection of fetal standardized planes assisted by generated sonographer attention maps. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 871–879. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-00928-1_98CrossRefGoogle Scholar
  10. 10.
    Chaabouni, S., Benois-pineau, J., Hadar, O.: Deep Learning for Saliency Prediction in Natural Video. arXiv:1604.08010 (2016)
  11. 11.
    Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: EMNLP (2014)Google Scholar
  12. 12.
    Chung, J., Gulcehre, C., Cho, K., Bengio, Y.: Empirical evaluation of gated recurrent neural networks on sequence modeling. In: NIPS (2014)Google Scholar
  13. 13.
    Clark, A.: Whatever next? predictive brains, situated agents, and the future of cognitive science. Behav. Brain Sci. 36(03), 181–204 (2013)CrossRefGoogle Scholar
  14. 14.
    Droste, R., et al.: Ultrasound Image Representation Learning by Modeling Sonographer Visual Attention. Accepted at IPMI (2019)Google Scholar
  15. 15.
    Gal, Y., Ghahramani, Z.: A theoretically grounded application of dropout in recurrent neural networks. In: NIPS (2016)Google Scholar
  16. 16.
    Gao, Y., Alison Noble, J.: Detection and characterization of the fetal heartbeat in free-hand ultrasound sweeps with weakly-supervised two-streams convolutional networks. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 305–313. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66185-8_35CrossRefGoogle Scholar
  17. 17.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)CrossRefGoogle Scholar
  18. 18.
    Huang, W., Bridge, C.P., Noble, J.A., Zisserman, A.: Temporal heartnet: towards human-level automatic analysis of fetal cardiac screening video. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10434, pp. 341–349. Springer, Cham (2017).  https://doi.org/10.1007/978-3-319-66185-8_39CrossRefGoogle Scholar
  19. 19.
    Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)Google Scholar
  20. 20.
    Jetley, S., Murray, N., Vig, E.: End-to-end saliency mapping via probability distribution prediction. In: CVPR (2016)Google Scholar
  21. 21.
    Keskar, N.S., Socher, R.: Improving Generalization Performance by Switching from Adam to SGD. arXiv:1712.07628 (2017)
  22. 22.
    Sharma, H., Droste, R., Chatelain, P., Drukker, L., Papageorghiou, A., Noble, J.A.: Spatio-temporal partitioning and description of full-length routine fetal anomaly ultrasound scans. Accepted at IEEE ISBI 2019 (2019)Google Scholar
  23. 23.
    Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: NIPS (2014)Google Scholar
  24. 24.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ICLR (2015)Google Scholar
  25. 25.
    Song, H., Wang, W., Zhao, S., Shen, J., Lam, K.-M.: Pyramid dilated deeper ConvLSTM for video salient object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 744–760. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01252-6_44CrossRefGoogle Scholar
  26. 26.
    Ulyanov, D., Vedaldi, A., Lempitsky, V.: Instance Normalization: The Missing Ingredient for Fast Stylization. arxiv:1607.08022 (2016)
  27. 27.
    Wang, W., Shen, J., Guo, F., Cheng, M.M., Borji, A.: Revisiting video saliency: a large-scale benchmark and a new model. In: CVPR (2018)Google Scholar
  28. 28.
    Wu, Y., He, K.: Group normalization. In: ECCV (2018)Google Scholar
  29. 29.
    Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent Neural Network Regularization. arXiv:1409.2329 (2014)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Department of Engineering ScienceUniversity of OxfordOxfordUK
  2. 2.Nuffield Department of Women’s and Reproductive HealthUniversity of OxfordOxfordUK

Personalised recommendations