Knowledge transfer for surgical activity prediction

Abstract : Purpose - Lack of annotated training data hinders automatic recognition and prediction of surgical activities necessary for situation-aware operating rooms. We propose using knowledge transfer to compensate for data deficit and improve prediction. Methods - We used two approaches to extract and transfer surgical process knowledge. First, we encoded semantic information about surgical terms using word embedding. Secondly, we passed knowledge between different clinical datasets of neurosurgical procedures using transfer learning. Results - The combination of two methods provided 22% improvement of activity prediction. We also made several pertinent observations about surgical practices based on the results of the performed transfer. Conclusion - Word embedding boosts learning process. Transfer learning was shown to be more effective than a simple combination of data, especially for less similar procedures.
Document type :
Journal articles
Complete list of metadatas

https://hal-univ-rennes1.archives-ouvertes.fr/hal-01807370
Contributor : Laurent Jonchère <>
Submitted on : Monday, June 4, 2018 - 4:27:47 PM
Last modification on : Friday, November 30, 2018 - 2:29:14 PM

Links full text

Identifiers

Collections

Citation

Olga Dergachyova, Xavier Morandi, Pierre Jannin. Knowledge transfer for surgical activity prediction. International Journal of Computer Assisted Radiology and Surgery, Springer Verlag, 2018, 13 (9), pp.1409-1417. ⟨10.1007/s11548-018-1768-9⟩. ⟨hal-01807370⟩

Share

Metrics

Record views

648