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

ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools

Garcia-Peraza-Herrera, LC; Li, W; Fidon, L; Gruijthuijsen, C; Devreker, A; Attilakos, G; Deprest, J; ... Ourselin, S; + view all (2017) ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools. In: Bicchi, A and Okamura, A, (eds.) Proceedings of 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). (pp. pp. 5717-5722). IEEE: USA: New York. Green open access

[thumbnail of Ourselin_1706.08126v2.pdf]
Preview
Text
Ourselin_1706.08126v2.pdf - Accepted Version

Download (5MB) | Preview

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-learningbased 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 realtime 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.

Type: Proceedings paper
Title: ToolNet: Holistically-Nested Real-Time Segmentation of Robotic Surgical Tools
Event: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 24-28 September 2017, Vancouver, British Columbia, Canada
Location: Vancouver, CANADA
Dates: 24 September 2017 - 28 September 2017
Open access status: An open access version is available from UCL Discovery
DOI: 10.1109/IROS.2017.8206462
Publisher version: https://doi.org/10.1109/IROS.2017.8206462
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.
Keywords: Instruments, Robots, Image segmentation, Tools, Surgery, Real-time systems, Computer architecture
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/1560882
Downloads since deposit
101Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item