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

• Published in: arXiv.org
• Main Authors: Garcia-Peraza-Herrera, Luis C, Li, Wenqi, Lucas Fidon, Gruijthuijsen, Caspar, Devreker, Alain, Attilakos, George, Deprest, Jan, Emmanuel Vander Poorten, Stoyanov, Danail, Vercauteren, Tom, Ourselin, Sebastien
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 04.07.2017
• Subjects: Artificial neural networks; Automation; Computer Science - Computer Vision and Pattern Recognition; Feature extraction; Labeling; Machine learning; Multiscale analysis; Optimization; Real time; Regularization; Robotics; Segmentation; Semantics; Surgical apparatus & instruments; Surgical instruments

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...