Concurrent Segmentation and Localization for Tracking of Surgical\n Instruments

2017/03/30 by Iro Laina, Laina, Iro, Nicola Rieke +11 · 2 citations
Engineering · Medicine · #Anatomy and Medical Technology #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Robotics and Sensor-Based Localization #Soft Robotics and Applications #Surgical Simulation and Training

paper · pdf · doi:10.48550/arxiv.1703.10701

openalex publication_date 2017/03/30 · openalex created_date 2022/10/05 · openalex updated_date 2026/07/28

Abstract

Real-time instrument tracking is a crucial requirement for various\ncomputer-assisted interventions. In order to overcome problems such as specular\nreflections and motion blur, we propose a novel method that takes advantage of\nthe interdependency between localization and segmentation of the surgical tool.\nIn particular, we reformulate the 2D instrument pose estimation as heatmap\nregression and thereby enable a concurrent, robust and near real-time\nregression of both tasks via deep learning. As demonstrated by our experimental\nresults, this modeling leads to a significantly improved performance than\ndirectly regressing the tool position and allows our method to outperform the\nstate of the art on a Retinal Microsurgery benchmark and the MICCAI EndoVis\nChallenge 2015.\n

Citations

• Flowing ConvNets for Human Pose Estimation in Videos

Cited by

• Real-Time Surgical Instrument Defect Detection via Non-Destructive Testing
• Identifying Surgical Instruments in Laparoscopy Using Deep Learning Instance Segmentation

Related

• Real-time Instance Segmentation of Surgical Instruments using Attention and Multi-scale Feature Fusion
• Deep Residual Learning for Instrument Segmentation in Robotic Surgery
• A comprehensive survey on recent deep learning-based methods applied to surgical data
• Plug-in for visualizing 3D tool tracking from videos of Minimally Invasive Surgeries
• Fast and Robust Localization of Surgical Array using Kalman Filter