Download PDFOpen PDF in browser

SimPS-Net: Simultaneous Pose & Segmentation Network of Surgical Tools

4 pagesPublished: March 8, 2024

Abstract

The ability to detect and localise surgical tools using RGB cameras during robotic assisted surgery can allow for the development of various implementations, such as vision- based active constraints and refinements in robot path planning, which can ultimately lead in improved patient safety during operation. For this purpose, the proposed network, SimPS-Net capable of both detection and 3D pose estimation of standard surgical tools using a single RGB camera, is introduced. In addition to the network, a novel dataset generated for training and testing is presented. The proposed network achieved a mean DICE coefficient of 85.0%, while also exhibiting a low average error of 5.5mm and 3.3◦ for 3D position and orientation respectively, thus outperforming the competing networks.

Keyphrases: 3d pose estimation, image segmentation, monocular, surgical tool detection, surgical tool localisation

In: Joshua W Giles (editor). Proceedings of The 22nd Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery, vol 6, pages 90-93.

BibTeX entry
@inproceedings{CAOS2023:SimPS_Net_Simultaneous_Pose,
  author    = {Spyridon Souipas and Anh Nguyen and Stephen Laws and Brian Davies and Ferdinando Rodriguez Y Baena},
  title     = {SimPS-Net: Simultaneous Pose & Segmentation Network of Surgical Tools},
  booktitle = {Proceedings of The 22nd Annual Meeting of the International Society for Computer Assisted Orthopaedic Surgery},
  editor    = {Joshua W Giles},
  series    = {EPiC Series in Health Sciences},
  volume    = {6},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-5305},
  url       = {/publications/paper/Hznz},
  doi       = {10.29007/plzv},
  pages     = {90-93},
  year      = {2024}}
Download PDFOpen PDF in browser