UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

Gesture Classification in Robotic Surgery using Recurrent Neural Networks with Kinematic Information

Mazomenos, E; Watson, D; Kotorov, R; Stoyanov, D; (2018) Gesture Classification in Robotic Surgery using Recurrent Neural Networks with Kinematic Information. In: Althoefer, Kaspar and Vander Poorten, Emmanuel, (eds.) Proceedings of the 8th Joint Workshop on New Technology for Computer/Robot Assisted Surgery (CRAS 2018). CRAS: London, UK. Green open access

[thumbnail of CRAS018Extended_Abs_ebm.pdf]
Preview
Text
CRAS018Extended_Abs_ebm.pdf - Accepted Version

Download (365kB) | Preview

Abstract

In this work we introduce the application of Recurrent Neural Networks (RNNs) on surgical kinematic data, for the classification of gestures in three fundamental surgical tasks (suturing, needle passing knot tying). The developed RNN-based classifier achieves close to 60% average classification accuracy for all three tasks when trained and tested with dVSS kinematic data from the same operator. Our preliminary work indicates that this type of artificial neural networks can be the building blocks in gesture classification systems which can form the basis for further developing automated skill assessment methods in robotic surgery.

Type: Proceedings paper
Title: Gesture Classification in Robotic Surgery using Recurrent Neural Networks with Kinematic Information
Event: 8th Joint Workshop on New Technologies for Computer/Robotic Assisted Surgery (CRAS 2018, 10-11 September 2018, Queen Mary University of London
Location: London, U.K.
Dates: 10 September 2018 - 11 September 2018
Open access status: An open access version is available from UCL Discovery
Publisher version: https://www.cras-eu.org/past%20events/cras-2018-pa...
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Med Phys and Biomedical Eng
URI: https://discovery.ucl.ac.uk/id/eprint/10056615
Downloads since deposit
95Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item