“Deep-Onto” network for surgical workflow and context recognition
- 181 Downloads
Surgical workflow recognition and context-aware systems could allow better decision making and surgical planning by providing the focused information, which may eventually enhance surgical outcomes. While current developments in computer-assisted surgical systems are mostly focused on recognizing surgical phases, they lack recognition of surgical workflow sequence and other contextual element, e.g., “Instruments.” Our study proposes a hybrid approach, i.e., using deep learning and knowledge representation, to facilitate recognition of the surgical workflow.
We implemented “Deep-Onto” network, which is an ensemble of deep learning models and knowledge management tools, ontology and production rules. As a prototypical scenario, we chose robot-assisted partial nephrectomy (RAPN). We annotated RAPN videos with surgical entities, e.g., “Step” and so forth. We performed different experiments, including the inter-subject variability, to recognize surgical steps. The corresponding subsequent steps along with other surgical contexts, i.e., “Actions,” “Phase” and “Instruments,” were also recognized.
The system was able to recognize 10 RAPN steps with the prevalence-weighted macro-average (PWMA) recall of 0.83, PWMA precision of 0.74, PWMA F1 score of 0.76, and the accuracy of 74.29% on 9 videos of RAPN.
We found that the combined use of deep learning and knowledge representation techniques is a promising approach for the multi-level recognition of RAPN surgical workflow.
KeywordsDeep learning Knowledge representation Robot-assisted partial nephrectomy Surgical workflow
This project has received funding from the European Unions Horizon 2020 research and innovation programme under Grant Agreement No. H2020-ICT-2016-732515. The Titan Xp used for this research was donated by the NVIDIA Corporation.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
Informed consent was obtained from all individual participants included in the study.
- 1.Blum T, Feussner H, Navab N (2010) Modeling and segmentation of surgical workflow from laparoscopic video. In: MICCAI international conference on medical image computing and computer-assisted-intervention, 2010. MICCAI 2010, vol 13(3), pp 400–407. https://doi.org/10.1007/978-3-642-15711-0_50
- 7.Government of Alberta (2018) Robot-assisted partial nephrectomy for renal cell carcinoma: mini review. https://open.alberta.ca/dataset/0e172257-2820-4eba-9915-f0add1d14f0d/resource/0e537ff8-f84a-4f7f-a00b-ebfbdea0289e/download/ahtdp-partial-nephrectomy-2017.pdf. Accessed 02 May 2018
- 8.Lin HC, Shafran I, Murphy TE, Okamura AM, Yuh DD, Hager GD (2005) Automatic detection and segmentation of robot-assisted surgical motions. In: International conference on medical image computing and computer-assisted intervention, vol 8(Pt 1), pp 802–810. https://doi.org/10.1007/11566465_99
- 9.Katić D, Julliard C, Wekerle AL, Kenngott H, Möller-Stich BP, Dillmann R, Speidel S, Jannin P, Gibaud B (2015) LapOntoSPM: an ontology for laparoscopic surgeries and its application to surgical phase recognition. Int J Comput Assist Radiol Surg 10(9):1427–34. https://doi.org/10.1007/s11548-015-1222-1 CrossRefGoogle Scholar
- 13.Cadene R, Robert T, Thome N, Cord M (2016) M2CAI workflow challenge: convolutional neural network with time smoothing and hidden Markov model for video frames classification. arXiv preprint arXiv:1610.05541
- 15.Szegedy C, Vanhoucke V, loffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR). https://doi.org/10.1109/cvpr.2016.308
- 17.Kingma DP, Ba J (2017) Adam: a method for stochastic optimization. arXiv:1412.6980
- 18.Kaouk JH, Khalifeh A, Hillyer S, Haber G-P, Stein RJ, Autorino R (2012) Robot-assisted laparoscopic partial nephrectomy: step-by-step contemporary technique and surgical outcomes at a single high-volume institution. Eur Urol 62(3):553–561. https://doi.org/10.1016/j.eururo.2012.05.021 CrossRefGoogle Scholar
- 19.Neumuth T, Strau G, Meixensberger J, Lemke HU, Burgert O (2006) Acquisition of process descriptions from surgical interventions. In: Bressan S, Kung J, Wagner R (eds) DEXA 2006 LNCS, vol 4080. Springer, Heidelberg, pp 602–611Google Scholar
- 20.Gibaud B, Forestier G, Feldmann C, Ferrigno G, Gonçalves P, Haidegger T, Julliard C, Katić D, Kenngott H, Maier-Hein L, März K, de Momi E, Nagy DA, Nakawala H, Neumann J, Neumuth T, Balderrama JR, Speidel S, Wagner M, Jannin P (2018) Toward a standard ontology of surgical process models. Int J Comput Assist Radiol Surg 13(9):1397–1408. https://doi.org/10.1007/s11548-018-1824-5 CrossRefGoogle Scholar
- 22.Rosse C, Mejino JLV (2007) The foundational model of anatomy ontology. In: Burger A, Davidson D, Baldock R (eds) Anatomy ontologies for bioinformatics. Computational biology, vol 6. Springer, London, pp 59–117. https://doi.org/10.1007/978-1-84628-885-2_4
- 23.Information Artifact Ontology. https://code.google.com/p/information-artifact-ontology. Accessed 17 Aug 2016
- 24.W3C Time Ontology. https://www.w3.org/TR/owl-time/. Accessed 20 Aug 2016
- 26.Protégé, Stanford Center for Biomedical Informatics Research. http://protege.stanford.edu. Accessed 12 Jan 2016
- 27.Horrocks I, Patel-Scheider P, Boley H, Tabet S, Grosof B, Dean M (2017) SWRL: a semantic web rule language combining OWL and RuleML. W3C Member Submission 2004. https://www.w3.org/Submission/SWRL. Accessed 23 Feb 2017
- 28.Chollet F (2015) Keras. https://github.com/fchollet/keras. Accessed 05 May 2017
- 29.Horridge M, Bechhofer S (2011) The OWL API: a Java API for OWL ontologies. Semant Web J 2(1):11–21Google Scholar
- 31.Kipp M (2007) Anvil—a generic annotation tool for multimodal dialogue. In: 7th European conference on speech communication and technology (Eurospeech), pp 1367–1370Google Scholar
- 33.Maaten LV, Hinton G (2008) Visualize data using t-SNE. J Mach Learn Res 9:2579–2605Google Scholar
- 34.Nakawala N, De Momi E, Pescatori LE, Morelli A, Ferrigno G (2017) Inductive learning of the surgical workflow model through video annotations. In: IEEE 30th international symposium on computer-based medical systems, CBMS 2017, Thessaloniki, Greece. https://doi.org/10.1109/CBMS.2017.91