Journal
INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY
Volume 13, Issue 9, Pages 1409-1417Publisher
SPRINGER HEIDELBERG
DOI: 10.1007/s11548-018-1768-9
Keywords
Knowledge transfer; Word embedding; Transfer learning; Surgical activity prediction; Long Short-Term Memory
Funding
- French state funds - ANR within the Investissements d'Avenir programme (Labex CAMI) [ANR-11-LABX-0004]
Ask authors/readers for more resources
PurposeLack 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.MethodsWe 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.ResultsThe 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.ConclusionWord embedding boosts learning process. Transfer learning was shown to be more effective than a simple combination of data, especially for less similar procedures.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available