King's College London

Research portal

ToolNet: Holistically-nested real-time segmentation of robotic surgical tools

Research output: Chapter in Book/Report/Conference proceedingConference paper

Luis C. Garcia-Peraza-Herrera, Wenqi Li, Lucas Fidon, Caspar Gruijthuijsen, Alain Devreker, George Attilakos, Jan Deprest, Emmanuel Vander Poorten, Danail Stoyanov, Tom Vercauteren, Sebastien Ourselin

Original languageEnglish
Title of host publicationIROS 2017 - IEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages5717-5722
Number of pages6
Volume2017-September
ISBN (Electronic)9781538626825
DOIs
Publication statusE-pub ahead of print - 14 Dec 2017
Event2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017 - Vancouver, Canada
Duration: 24 Sep 201728 Sep 2017

Conference

Conference2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2017
CountryCanada
CityVancouver
Period24/09/201728/09/2017

King's Authors

Abstract

Real-time tool segmentation from endoscopic videos is an essential part of many computer-assisted robotic surgical systems and of critical importance in robotic surgical data science. We propose two novel deep learning architectures for automatic segmentation of non-rigid surgical instruments. Both methods take advantage of automated deep-learning-based multi-scale feature extraction while trying to maintain an accurate segmentation quality at all resolutions. The two proposed methods encode the multi-scale constraint inside the network architecture. The first proposed architecture enforces it by cascaded aggregation of predictions and the second proposed network does it by means of a holistically-nested architecture where the loss at each scale is taken into account for the optimization process. As the proposed methods are for real-time semantic labeling, both present a reduced number of parameters. We propose the use of parametric rectified linear units for semantic labeling in these small architectures to increase the regularization of the network while maintaining the segmentation accuracy. We compare the proposed architectures against state-of-the-art fully convolutional networks. We validate our methods using existing benchmark datasets, including ex vivo cases with phantom tissue and different robotic surgical instruments present in the scene. Our results show a statistically significant improved Dice Similarity Coefficient over previous instrument segmentation methods. We analyze our design choices and discuss the key drivers for improving accuracy.

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454