17 February 2012 Real-time motion compensation for EM bronchoscope tracking with smooth output - ex-vivo validation
Author Affiliations +
Proceedings Volume 8316, Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling; 83163A (2012); doi: 10.1117/12.911192
Event: SPIE Medical Imaging, 2012, San Diego, California, United States
Abstract
Navigated bronchoscopy provides benefits for endoscopists and patients, but accurate tracking information is needed. We present a novel real-time approach for bronchoscope tracking combining electromagnetic (EM) tracking, airway segmentation, and a continuous model of output. We augment a previously published approach by including segmentation information in the tracking optimization instead of image similarity. Thus, the new approach is feasible in real-time. Since the true bronchoscope trajectory is continuous, the output is modeled using splines and the control points are optimized with respect to displacement from EM tracking measurements and spatial relation to segmented airways. Accuracy of the proposed method and its components is evaluated on a ventilated porcine ex-vivo lung with respect to ground truth data acquired from a human expert. We demonstrate the robustness of the output of the proposed method against added artificial noise in the input data. Smoothness in terms of inter-frame distance is shown to remain below 2 mm, even when up to 5 mm of Gaussian noise are added to the input. The approach is shown to be easily extensible to include other measures like image similarity.
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Tobias Reichl, Ingmar Gergel, Manuela Menzel, Hubert Hautmann, Ingmar Wegner, Hans-Peter Meinzer, Nassir Navab, "Real-time motion compensation for EM bronchoscope tracking with smooth output - ex-vivo validation", Proc. SPIE 8316, Medical Imaging 2012: Image-Guided Procedures, Robotic Interventions, and Modeling, 83163A (17 February 2012); doi: 10.1117/12.911192; https://doi.org/10.1117/12.911192
PROCEEDINGS
6 PAGES


SHARE
KEYWORDS
Image segmentation

Sensors

Lung

Image registration

Bronchoscopy

Data acquisition

Electromagnetism

Back to Top