Olga Dergachyova1,2, Xavier Morandi3,4,5, Pierre Jannin3,4. 1. INSERM, U1099, 35000, Rennes, France. olga.dergachyova@univ-rennes1.fr. 2. Université de Rennes 1, LTSI, 35000, Rennes, France. olga.dergachyova@univ-rennes1.fr. 3. INSERM, U1099, 35000, Rennes, France. 4. Université de Rennes 1, LTSI, 35000, Rennes, France. 5. Département de Neurochirurgie, CHU Rennes, 35000, Rennes, France.
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.
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.
Entities:
Keywords:
Knowledge transfer; Long Short-Term Memory; Surgical activity prediction; Transfer learning; Word embedding
Authors: Fabien Despinoy; David Bouget; Germain Forestier; Cedric Penet; Nabil Zemiti; Philippe Poignet; Pierre Jannin Journal: IEEE Trans Biomed Eng Date: 2015-10-26 Impact factor: 4.538
Authors: Christian Meißner; Jürgen Meixensberger; Andreas Pretschner; Thomas Neumuth Journal: Minim Invasive Ther Allied Technol Date: 2014-01-21 Impact factor: 2.442
Authors: Andru P Twinanda; Sherif Shehata; Didier Mutter; Jacques Marescaux; Michel de Mathelin; Nicolas Padoy Journal: IEEE Trans Med Imaging Date: 2016-07-22 Impact factor: 10.048
Authors: Hoo-Chang Shin; Holger R Roth; Mingchen Gao; Le Lu; Ziyue Xu; Isabella Nogues; Jianhua Yao; Daniel Mollura; Ronald M Summers Journal: IEEE Trans Med Imaging Date: 2016-02-11 Impact factor: 10.048