Abstract
3D ultrasound (US) is widely used due to its rich diagnostic information, portability and low cost. Automated standard plane (SP) localization in US volume not only improves efficiency and reduces user-dependence, but also boosts 3D US interpretation. In this study, we propose a novel Multi-Agent Reinforcement Learning (MARL) framework to localize multiple uterine SPs in 3D US simultaneously. Our contribution is two-fold. First, we equip the MARL with a one-shot neural architecture search (NAS) module to obtain the optimal agent for each plane. Specifically, Gradient-based search using Differentiable Architecture Sampler (GDAS) is employed to accelerate and stabilize the training process. Second, we propose a novel collaborative strategy to strengthen agents’ communication. Our strategy uses recurrent neural network (RNN) to learn the spatial relationship among SPs effectively. Extensively validated on a large dataset, our approach achieves the accuracy of 7.05\(^{\circ }\)/2.21 mm, 8.62\(^{\circ }\)/2.36 mm and 5.93\(^{\circ }\)/0.89 mm for the mid-sagittal, transverse and coronal plane localization, respectively. The proposed MARL framework can significantly increase the plane localization accuracy and reduce the computational cost and model size.
Y. Huang and X. Yang—Contribute equally to this wok.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Alansary, A., et al.: Automatic view planning with multi-scale deep reinforcement learning agents. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 277–285. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_32
Chykeyuk, K., Yaqub, M., Alison Noble, J.: Class-specific regression random forest for accurate extraction of standard planes from 3D echocardiography. In: Menze, B., Langs, G., Montillo, A., Kelm, M., Müller, H., Tu, Z. (eds.) MCV 2013. LNCS, vol. 8331, pp. 53–62. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-05530-5_6
Dong, X., Yang, Y.: Searching for a robust neural architecture in four GPU hours. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1761–1770 (2019)
Dou, H., et al.: Agent with warm start and active termination for plane localization in 3D ultrasound. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11768, pp. 290–298. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32254-0_33
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)
Li, Y.: Standard plane detection in 3D fetal ultrasound using an iterative transformation network. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11070, pp. 392–400. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00928-1_45
Li, Y.: Deep reinforcement learning: an overview. arXiv preprint (2017). arXiv:1701.07274
Liu, H., Simonyan, K., Yang, Y.: Darts: differentiable architecture search. arXiv preprint (2018). arXiv:1806.09055
Lorenz, C., et al.: Automated abdominal plane and circumference estimation in 3D us for fetal screening. In: Medical Imaging 2018: Image Processing, vol. 10574, p. 105740I. International Society for Optics and Photonics (2018)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Ni, D., et al.: Standard plane localization in ultrasound by radial component model and selective search. Ultrasound Med. Biol. 40(11), 2728–2742 (2014)
Ren, P., et al.: A comprehensive survey of neural architecture search: challenges and solutions. arXiv preprint (2020). arXiv:2006.02903
Ryou, H., Yaqub, M., Cavallaro, A., Roseman, F., Papageorghiou, A., Noble, J.A.: Automated 3D ultrasound biometry planes extraction for first trimester fetal assessment. In: Wang, L., Adeli, E., Wang, Q., Shi, Y., Suk, H-Il (eds.) MLMI 2016. LNCS, vol. 10019, pp. 196–204. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-47157-0_24
Schmidt-Richberg, A., et al.: Offset regression networks for view plane estimation in 3D fetal ultrasound. In: Medical Imaging 2019: Image Processing, vol. 10949, p. 109493K. International Society for Optics and Photonics (2019)
Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double Q-learning. In: Thirtieth AAAI conference on artificial intelligence (2016)
Vlontzos, A., Alansary, A., Kamnitsas, K., Rueckert, Dl, Kainz, B.: Multiple landmark detection using multi-agent reinforcement learning. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 262–270. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-32251-9_29
Wong, L., White, N., Ramkrishna, J., Júnior, E.A., Meagher, S., Costa, F.D.S.: Three-dimensional imaging of the uterus: the value of the coronal plane. World J. Radiol. 7(12), 484 (2015)
Acknowledgement
This work was supported by the grant from National Key R&D Program of China (No. 2019YFC0118300), Shenzhen Peacock Plan (No. KQTD2016053112051497, KQJSCX20180328095606003) and Medical Scientific Research Foundation of Guangdong Province, China (No. B2018031).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Huang, Y. et al. (2020). Searching Collaborative Agents for Multi-plane Localization in 3D Ultrasound. In: Martel, A.L., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2020. MICCAI 2020. Lecture Notes in Computer Science(), vol 12263. Springer, Cham. https://doi.org/10.1007/978-3-030-59716-0_53
Download citation
DOI: https://doi.org/10.1007/978-3-030-59716-0_53
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59715-3
Online ISBN: 978-3-030-59716-0
eBook Packages: Computer ScienceComputer Science (R0)