Abstract
Surgical action triplet recognition provides a better understanding of the surgical scene. This task is of high relevance as it provides the surgeon with context-aware support and safety. The current go-to strategy for improving performance is the development of new network mechanisms. However, the performance of current state-of-the-art techniques is substantially lower than other surgical tasks. Why is this happening? This is the question that we address in this work. We present the first study to understand the failure of existing deep learning models through the lens of robustness and explainability. Firstly, we study current existing models under weak and strong \(\delta -\)perturbations via an adversarial optimisation scheme. We then analyse the failure modes via feature based explanations. Our study reveals that the key to improving performance and increasing reliability is in the core and spurious attributes. Our work opens the door to more trustworthy and reliable deep learning models in surgical data science.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Allen-Zhu, Z., Li, Y.: Feature purification: how adversarial training performs robust deep learning. In: 2021 IEEE 62nd Annual Symposium on Foundations of Computer Science (FOCS), pp. 977–988. IEEE (2022)
Aviles, A.I., Alsaleh, S.M., Hahn, J.K., Casals, A.: Towards retrieving force feedback in robotic-assisted surgery: a supervised neuro-recurrent-vision approach. IEEE Trans. Haptics 10(3), 431–443 (2016)
Blum, T., Feußner, H., Navab, N.: Modeling and segmentation of surgical workflow from laparoscopic video. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6363, pp. 400–407. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15711-0_50
Dergachyova, O., Bouget, D., Huaulmé, A., Morandi, X., Jannin, P.: Automatic data-driven real-time segmentation and recognition of surgical workflow. Int. J. Comput. Assist. Radiol. Surg. 11(6), 1081–1089 (2016). https://doi.org/10.1007/s11548-016-1371-x
Engstrom, L., Ilyas, A., Santurkar, S., Tsipras, D., Tran, B., Madry, A.: Adversarial robustness as a prior for learned representations. arXiv preprint arXiv:1906.00945 (2019)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition (2015). https://doi.org/10.48550/ARXIV.1512.03385
Hsieh, C.Y., et al.: Evaluations and methods for explanation through robustness analysis. arXiv preprint arXiv:2006.00442 (2020)
Huang, G., Liu, Z., van der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks (2016). https://doi.org/10.48550/ARXIV.1608.06993
Katić, D., et al.: Knowledge-driven formalization of laparoscopic surgeries for rule-based intraoperative context-aware assistance. In: Stoyanov, D., Collins, D.L., Sakuma, I., Abolmaesumi, P., Jannin, P. (eds.) IPCAI 2014. LNCS, vol. 8498, pp. 158–167. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-07521-1_17
Koh, P.W., Liang, P.: Understanding black-box predictions via influence functions. In: International Conference on Machine Learning, pp. 1885–1894. PMLR (2017)
Liu, L., Dou, Q., Chen, H., Qin, J., Heng, P.A.: Multi-task deep model with margin ranking loss for lung nodule analysis. IEEE Trans. Med. Imaging 39(3), 718–728 (2019)
Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows (2021). https://doi.org/10.48550/ARXIV.2103.14030
Lo, B.P.L., Darzi, A., Yang, G.-Z.: Episode classification for the analysis of tissue/instrument interaction with multiple visual cues. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 230–237. Springer, Heidelberg (2003). https://doi.org/10.1007/978-3-540-39899-8_29
Maier-Hein, L., et al.: Surgical data science: enabling next-generation surgery. arXiv preprint arXiv:1701.06482 (2017)
Neumuth, T., Strauß, G., Meixensberger, J., Lemke, H.U., Burgert, O.: Acquisition of process descriptions from surgical interventions. In: Bressan, S., Küng, J., Wagner, R. (eds.) DEXA 2006. LNCS, vol. 4080, pp. 602–611. Springer, Heidelberg (2006). https://doi.org/10.1007/11827405_59
Nwoye, C.I., et al.: Recognition of instrument-tissue interactions in endoscopic videos via action triplets. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 364–374. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59716-0_35
Nwoye, C.I., Padoy, N.: Data splits and metrics for method benchmarking on surgical action triplet datasets. arXiv preprint arXiv:2204.05235 (2022)
Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med. Image Anal. 78, 102433 (2022)
Olah, C., et al.: The building blocks of interpretability. Distill 3(3), e10 (2018)
Plumb, G., Molitor, D., Talwalkar, A.S.: Model agnostic supervised local explanations. In: Advances in Neural Information Processing Systems, vol. 31 (2018)
Ribeiro, M.T., Singh, S., Guestrin, C.: “Why should I trust you?” explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144 (2016)
Shrikumar, A., Greenside, P., Kundaje, A.: Learning important features through propagating activation differences. In: International Conference on Machine Learning, pp. 3145–3153. PMLR (2017)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep inside convolutional networks: visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034 (2013)
Singla, S., Feizi, S.: Salient imagenet: how to discover spurious features in deep learning? In: International Conference on Learning Representations (2021)
Singla, S., Nushi, B., Shah, S., Kamar, E., Horvitz, E.: Understanding failures of deep networks via robust feature extraction. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 12853–12862 (2021)
Sundararajan, M., Taly, A., Yan, Q.: Axiomatic attribution for deep networks. In: International Conference on Machine Learning, pp. 3319–3328. PMLR (2017)
Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86–97 (2016)
Velanovich, V.: Laparoscopic vs open surgery. Surg. Endosc. 14(1), 16–21 (2000)
Vercauteren, T., Unberath, M., Padoy, N., Navab, N.: CAI4CAI: the rise of contextual artificial intelligence in computer-assisted interventions. Proc. IEEE 108(1), 198–214 (2019)
Wilson, E.B., Bagshahi, H., Woodruff, V.D.: Overview of general advantages, limitations, and strategies. In: Kim, K.C. (ed.) Robotics in General Surgery, pp. 17–22. Springer, New York (2014). https://doi.org/10.1007/978-1-4614-8739-5_3
Wong, E., Santurkar, S., Madry, A.: Leveraging sparse linear layers for debuggable deep networks. In: International Conference on Machine Learning, pp. 11205–11216. PMLR (2021)
Xu, K., et al.: Structured adversarial attack: towards general implementation and better interpretability. arXiv preprint arXiv:1808.01664 (2018)
Yeh, C.K., Hsieh, C.Y., Suggala, A., Inouye, D.I., Ravikumar, P.K.: On the (in) fidelity and sensitivity of explanations. In: Advances in Neural Information Processing Systems, vol. 32 (2019)
Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2921–2929 (2016)
Zisimopoulos, O., et al.: DeepPhase: surgical phase recognition in CATARACTS videos. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-López, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 265–272. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-00937-3_31
Acknowledgements
YC and AIAR greatly acknowledge support from a C2D3 Early Career Research Seed Fund and CMIH EP/T017961/1, University of Cambridge.
CBS acknowledges support from the Philip Leverhulme Prize, the Royal Society Wolfson Fellowship, the EPSRC advanced career fellowship EP/V029428/1, EPSRC grants EP/S026045/1 and EP/T003553/1, EP/N014588/1, EP/T017961/1, the Wellcome Innovator Awards 215733/Z/19/Z and 221633/Z/20/Z, the European Union Horizon 2020 research and innovation programme under the Marie Skodowska-Curie grant agreement No. 777826 NoMADS, the Cantab Capital Institute for the Mathematics of Information and the Alan Turing Institute.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cheng, Y., Liu, L., Wang, S., Jin, Y., Schönlieb, CB., Aviles-Rivero, A.I. (2023). Why Deep Surgical Models Fail?: Revisiting Surgical Action Triplet Recognition Through the Lens of Robustness. In: Chen, H., Luo, L. (eds) Trustworthy Machine Learning for Healthcare. TML4H 2023. Lecture Notes in Computer Science, vol 13932. Springer, Cham. https://doi.org/10.1007/978-3-031-39539-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-39539-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39538-3
Online ISBN: 978-3-031-39539-0
eBook Packages: Computer ScienceComputer Science (R0)