Abstract
Purpose
Automatic recognition and removal of smoke in surgical procedures can reduce risks to the patient by supporting the surgeon. Surgical smoke changes its visibility over time, impacting the vision depending on its amount and the volume of the body cavity. While modern deep learning algorithms for computer vision require large amounts of data, annotations for training are scarce. This paper investigates the use of unlabeled training data with a modern time-based deep learning algorithm.
Methods
We propose to improve the state of the art in smoke recognition by enhancing a image classifier based on convolutional neural networks with a recurrent architecture thereby providing temporal context to the algorithm. We enrich the training with unlabeled recordings from similar procedures. The influence of surgical tools on the smoke recognition task is studied to reduce a possible bias.
Results
The evaluations show that smoke recognition benefits from the additional temporal information during training. The use of unlabeled data from the same domain in a semi-supervised training procedure shows additional improvements reaching an accuracy of 86.8%. The proposed balancing policy is shown to have a positive impact on learning the discrimination of co-occurring surgical tools.
Conclusions
This study presents, to the best of our knowledge, the first use of a time series algorithm for the recognition of surgical smoke and the first use of this algorithm in the described semi-supervised setting. We show that the performance improvements with unlabeled data can be enhanced by integrating temporal context. We also show that adaption of the data distribution is beneficial to avoid learning biases.
Similar content being viewed by others
References
Bar O, Neimark D, Zohar M, Hager GD, Girshick R, Fried GM, Wolf T, Asselmann D (2020) Impact of data on generalization of ai for surgical intelligence applications. Sci Rep 10(1):1–12
Chen L, Tang W, John NW, Wan TR, Zhang JJ (2020) De-smokegcn: Generative cooperative networks for joint surgical smoke detection and removal. IEEE Trans Med Imag 39(5):1615–1625. https://doi.org/10.1109/TMI.2019.2953717
Czempiel T, Paschali M, Keicher M, Simson W, Feussner H, Kim ST, Navab N (2020) Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In: Martel AL, Abolmaesumi P, Stoyanov D, Mateus D, Zuluaga MA, Zhou SK, Racoceanu D, Joskowicz L (eds) Medical image computing and computer assisted intervention—MICCAI 2020. Springer International Publishing, Cambridge, pp 343–352
Funke I, Jenke A, Mees ST, Weitz J, Speidel S, Bodenstedt S (2018) Temporal Coherence-based Self-supervised Learning for Laparoscopic Workflow Analysis. In: OR 2.0 Context-Aware Operating Theaters, Computer Assisted Robotic Endoscopy, Clinical Image-Based Procedures, and Skin Image Analysis, vol. 11041, pp 85–93, Springer International Publishing, Cambridge
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Huang G, Liu Z, van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition
Jin Y, Dou Q, Chen H, Yu L, Qin J, Fu C, Heng P (2018) Sv-rcnet: Workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans Med Imag 37(5):1114–1126. https://doi.org/10.1109/TMI.2017.2787657
Johnson JM, Khoshgoftaar TM (2019) Survey on deep learning with class imbalance. J Big Data 6(1):27
Laine S, Aila T (2017) Temporal ensembling for semi-supervised learning. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24–26, 2017, Conference Track Proceedings. OpenReview.net. https://openreview.net/forum?id=BJ6oOfqge
Leibetseder A, Primus MJ, Petscharnig S, Schoeffmann K (2017) Image-based smoke detection in laparoscopic videos. In: Computer assisted and robotic endoscopy and clinical image-based procedures. Springer, Berlin, pp 70–87
Leibetseder A, Primus MJ, Petscharnig S, Schoeffmann K (2017) Real-time image-based smoke detection in endoscopic videos. Proceedings of the on Thematic Workshops of ACM Multimedia 2017:296–304
Maier-Hein L, Eisenmann M, Sarikaya D, März K, Collins T, Malpani A, Fallert J, Feussner H, Giannarou S, Mascagni P, Nakawala H, Park A, Pugh C, Stoyanov D, Vedula SS, Müller BP, Cleary K, Fichtinger G, Forestier G, Gibaud B, Grantcharov T, Hashizume M, Kenngott H, Kikinis R, Mündermann L, Navab N, Onogur S, Sznitman R, Taylor R, Dietlinde Tizabi M, Wagner M, Hager GD, Neumuth T, Padoy N, Jannin P, Speidel S (2020) Surgical Data Science—from Concepts to Clinical Translation. arXiv e-prints arXiv:2011.02284
Reiter W (2020) Improving endoscopic smoke detection with semi-supervised noisy student models. Curr Direct Biomed Eng 6(1):26
Ross T, Zimmerer D, Vemuri A, Isensee F, Wiesenfarth M, Bodenstedt S, Both F, Kessler P, Wagner M, Müller B, Kenngott H, Speidel S, Kopp-Schneider A, Maier-Hein K, Maier-Hein L (2018) Exploiting the potential of unlabeled endoscopic video data with self-supervised learning. Int J CARS 13(6):925–933. https://doi.org/10.1007/s11548-018-1772-0
Takahashi H, Yamasaki M, Hirota M, Miyazaki Y, Moon JH, Souma Y, Mori M, Doki Y, Nakajima K (2013) Automatic smoke evacuation in laparoscopic surgery: a simplified method for objective evaluation. Surg Endosc 27(8):2980–2987
Tarvainen A, Valpola H (2017) Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. In: I. Guyon, U. von Luxburg, S. Bengio, H.M. Wallach, R. Fergus, S.V.N. Vishwanathan, R. Garnett (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4–9, 2017, Long Beach, CA, USA, pp. 1195–1204. https://proceedings.neurips.cc/paper/2017/hash/68053af2923e00204c3ca7c6a3150cf7-Abstract.html
Twinanda A, Mutter D, Marescaux J, Mathelin M, Padoy N (2016) Single and multi-task architectures for surgical workflow challenge. In: Proceedings of workshop and challenges on modeling and monitoring of computer assisted interventions (M2CAI) at Medical Image Computing and Computer-Assisted Intervention (MICCAI)
Twinanda AP, Shehata S, Mutter D, Marescaux J, de Mathelin M, Padoy N (2017) EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imag 36(1):86–97
Wu Z, Guo Y, Lin W, Yu S, Ji Y (2018) A weighted deep representation learning model for imbalanced fault diagnosis in cyber-physical systems. Sensors 18(4):1096
Xie Q, Luong MT, Hovy E, Le QV (2020) Self-training with noisy student improves imagenet classification. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10687–10698
Yengera G, Mutter D, Marescaux J, Padoy N (2018) Less is more: Surgical phase recognition with less annotations through self-supervised pre-training of cnn-lstm networks. arXiv preprint arXiv:1805.08569
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest
Ethical approval
For this type of study, formal consent is not required
Informed consent
This article contains patient data from publically available datasets. Informed consent was obtained from patients for non-public recordings.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Reiter, W. Co-occurrence balanced time series classification for the semi-supervised recognition of surgical smoke. Int J CARS 16, 2021–2027 (2021). https://doi.org/10.1007/s11548-021-02411-3
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-021-02411-3