Toward a Neural-Symbolic Framework for Automated Workflow Analysis in Surgery
- 11 Downloads
Learning production rules from continuous data streams, e.g. surgical videos, is a challenging problem. To learn production rules, we present a novel framework consisting of deep learning models and inductive logic programming (ILP) system for learning surgical workflow entities that are needed in subsequent surgical tasks, e.g. “what kind of instruments will be needed in the next step?” As a prototypical scenario, we analyzed the Robot-Assisted Partial Nephrectomy (RAPN) workflow. To verify our framework, first consistent and complete rules were learnt from the video annotations which can classify RAPN surgical workflow and temporal sequence at high-granularity e.g. steps. After we found that RAPN workflow is hierarchical, we used combination of learned predicates, presenting workflow hierarchy, to predict the information on the next step followed by a classification of step sequences with deep learning models. The predicted rules on the RAPN workflow was verified by an expert urologist and conforms with the standard workflow of RAPN.
KeywordsProduction rules Robot-Assisted Partial Nephrectomy Surgical workflow Deep learning Inductive logic programming
This research is funded by the European Research Council (ERC) under the European Union’s H2020 research and innovation programme (grant agreement No. 742671 “ARS”). This work was supported by European Union’s Horizon 2020 research and innovation programme (grant agreement No. 732515 “SMARTsurg”).
Conflict of Interest
The authors confirm that there are no known conflicts of interest associated with this publication.
- 3.Garcez, A., Besold, T.R., de Raedt, L., Földiak, P., Hitzler, P., Icard, T., Kühnberger, K.-U., Lamb, L.C., Miikkulainen, R., Silver, D.L.: Neural-symbolic learning and reasoning: contributions and challenges. In: 2015 AAAI Spring Symposium, Palo Alto, California (2015)Google Scholar
- 4.Bock, H.-H.: Data Mining Tasks and Methods: Classification: the Goal of Classification. Handbook of Data Mining and Knowledge Discovery. Oxford University Press, New York (2002)Google Scholar
- 5.Dutra, I., Nassif, H., Page, D., Shavik, J., Strigel, R.M., Wu, Y., Elezaby, M.E., Burnside, E.: Integrating machine learning and physician knowledge to improve the accuracy of breast biopsy. In: AMIA Annual Symposium Proceedings, pp. 349–355 (2011)Google Scholar
- 6.Burnside, E.S., Davis, J., Costa, V.S., de Castro Dutra, I., Kahn Jr., C.E., Fine, J., Page, D.: Knowledge discovery from structured mammography reports using inductive logic programming. In: AMIA Annual Symposium Proceedings, pp. 96–100 (2005)Google Scholar
- 9.Srinivasan, A.: The Aleph Manual (1999). https://www.cs.ox.ac.uk/activities/programinduction/Aleph/aleph.html
- 10.Kipp, M.: Anvil–a generic annotation tool for multimodal dialogue. In: Proceedings of the 7th European Conference on Speech Communication and Technology (Eurospeech), pp. 1367–1370 (2001)Google Scholar
- 11.Agrawal, R., Imieliński, T., Swami, A.: Mining association rules between sets of items in large databases. In: Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data - SIGMOD 1993, p. 207 (1993)Google Scholar