Abstract
In 2020, breast cancer affected around two million people worldwide. Early cancer detection is, therefore, needed to save many lives and reduce treatment costs. Nowadays, mammography and self- palpation are the most popular monitoring methods. The high number of cases and the difficulty of correct self-diagnosis has prompted this research work to design a fully autonomous robot to perform breast palpation. Specifically, this study focuses on learning the path for a successful breast examination of a silicone model. Learning from demonstrations proved to be the most suitable approach to reproduce the desired path. We implemented a teleoperation control between two Franka Emika Panda robots with tactile and force feedback to perform palpation on both simple and complex shapes. Moreover, we created a dataset of simple palpation strategy. Finally, we developed and tested different sequential neural networks such as Recurrent Neural Network (RNN), Long short-term memory (LSTM), Gated recurrent unit (GRU) and Temporal Convolutional Network (TCN) to learn the stochastic behaviour of the acquired palpation trajectories. The results showed that TCN is capable of reproducing the desired behaviour with more accuracy and stability than the other models.
This work was partially supported by Cancer Research UK C24524/A30038 in ARTEMIS project.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Breast self-examination (it can save your life) (2017). https://www.youtube.com/watch?v=LrfE6JUwIms&t=142s&ab_channel=RafflesHospital
The breast exam - stanford medicine 25 (2018). https://www.youtube.com/watch?v=pJ55UtP0_nA&t=410s&ab_channel=StanfordMedicine25
Examination of female breasts (2018). https://www.youtube.com/watch?v=LrfE6JUwIms&t=142s&ab_channel=RafflesHospital
Cancer today (2021). https://gco.iarc.fr/today/home
Ahn, B., Kim, Y., Oh, C.K., Kim, J.: Robotic palpation and mechanical property characterization for abnormal tissue localization. Med. Biol. Eng. Comput. 50(9), 961–971 (2012)
Ayvali, E., Ansari, A., Wang, L., Simaan, N., Choset, H.: Utility-guided palpation for locating tissue abnormalities. IEEE Rob. Autom. Lett. 2(2), 864–871 (2017)
Cho, K., Van Merriënboer, B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: encoder-decoder approaches. arXiv preprint arXiv:1409.1259 (2014)
Elliott, S., Xu, Z., Cakmak, M.: Learning generalizable surface cleaning actions from demonstration. In: 2017 26th IEEE International Symposium on Robot and Human Interactive Communication (RO-MAN), pp. 993–999. IEEE (2017)
Fu, R., Zhang, Z., Li, L.: Using LSTM and GRU neural network methods for traffic flow prediction. In: 2016 31st Youth Academic Annual Conference of Chinese Association of Automation (YAC), pp. 324–328. IEEE (2016)
Gers, F.A., Schmidhuber, J., Cummins, F.: Learning to forget: continual prediction with LSTM. Neural Comput. 12(10), 2451–2471 (2000)
Ghalamzan, A., Nazari, K., Hashempour, H., Zhong, F.: Deep-LfD: deep robot learning from demonstrations. Softw. Impacts 9, 100087 (2021)
Ghalamzan Esfahani, A., Ragaglia, M.: Robot learning from demonstrations: emulation learning in environments with moving obstacles. Rob. Auton. Syst. 101, 45–56 (2018)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Lea, C., Flynn, M.D., Vidal, R., Reiter, A., Hager, G.D.: Temporal convolutional networks for action segmentation and detection. In: proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156–165 (2017)
McDonald, S., Saslow, D., Alciati, M.H.: Performance and reporting of clinical breast examination: a review of the literature. CA: Cancer J. Clin. 54(6), 345–361 (2004)
Nichols, K.A., Okamura, A.M.: Autonomous robotic palpation: machine learning techniques to identify hard inclusions in soft tissues. In: 2013 IEEE International Conference on Robotics and Automation, pp. 4384–4389. IEEE (2013)
Nichols, K.A., Okamura, A.M.: Methods to segment hard inclusions in soft tissue during autonomous robotic palpation. IEEE Trans. Rob. 31(2), 344–354 (2015)
Pardi, T., Ortenzi, V., Fairbairn, C., Pipe, T., Ghalamzan Esfahani, A., Stolkin, R.: Planning maximum-manipulability cutting paths. IEEE Rob. Autom. Lett. 5(2), 1999–2006 (2020)
Pastor, F., Gandarias, J.M., García-Cerezo, A.J., Gómez-de Gabriel, J.M.: Using 3D convolutional neural networks for tactile object recognition with robotic palpation. Sensors 19(24), 5356 (2019)
Pérez-Higueras, N., Caballero, F., Merino, L.: Learning human-aware path planning with fully convolutional networks. In: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5897–5902. IEEE (2018)
Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning internal representations by error propagation. Technical report, California Univ San Diego La Jolla Inst for Cognitive Science (1985)
Xiao, B., et al.: Depth estimation of hard inclusions in soft tissue by autonomous robotic palpation using deep recurrent neural network. IEEE Trans. Autom. Sci. Eng. 17(4), 1791–1799 (2020)
Xie, Z., Zhang, Q., Jiang, Z., Liu, H.: Robot learning from demonstration for path planning: a review. Sci. China Technol. Sci. 1–10 (2020)
Yan, Y., Pan, J.: Fast localization and segmentation of tissue abnormalities by autonomous robotic palpation. IEEE Rob. Autom. Lett. 6(2), 1707–1714 (2021)
Zhang, Y., Zou, Y., Tang, J., Liang, J.: A lane-changing prediction method based on temporal convolution network. arXiv preprint arXiv:2011.01224 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Crivellari, M., Sanni, O., Zanchettin, A., Esfahani, A.G. (2021). Deep Robot Path Planning from Demonstrations for Breast Cancer Examination. In: Fox, C., Gao, J., Ghalamzan Esfahani, A., Saaj, M., Hanheide, M., Parsons, S. (eds) Towards Autonomous Robotic Systems. TAROS 2021. Lecture Notes in Computer Science(), vol 13054. Springer, Cham. https://doi.org/10.1007/978-3-030-89177-0_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-89177-0_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89176-3
Online ISBN: 978-3-030-89177-0
eBook Packages: Computer ScienceComputer Science (R0)