An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters

Alper Denasi, F. Khan, K.J. Boskma, M. Kaya, Christoph Hennersperger, Rüdiger Göbl, Maria Tirindelli, Nassir Navab, S. Misra

Research output: Contribution to conferencePaperAcademicpeer-review

1 Downloads (Pure)

Abstract

Minimally invasive surgery involves using flexible medical instruments such as endoscopes and catheters. Magnetically actuated catheters can provide improved steering precision over conventional catheters. However, besides the actuation
method, an accurate tip position is required for precise control of the medical instruments. In this study, the tip position obtained from transverse 2D ultrasound images and multicore optical shape sensors are combined using a robust sensor fusion algorithm. The tip position is tracked in the ultrasound images using a template-based tracker and a convolutional neural network based tracker, respectively. Experimental results for a rhombus path are presented, where data obtained from both tracking sources are fused using Luenberger and Kalman state estimators. The mean and standard deviation of the Euclidean
error for the Luenberger observer is 0.2+-0.11 [mm] whereas for the Kalman filter it is 0.18+-0.13 [mm], respectively.
Original languageEnglish
Number of pages8
Publication statusPublished - May 2018
Event2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - The Brisbane Convention & Exhibition Venue, Brisbane, Australia
Duration: 21 May 201825 May 2018
https://icra2018.org/

Conference

Conference2018 IEEE International Conference on Robotics and Automation, ICRA 2018
Abbreviated titleICRA
CountryAustralia
CityBrisbane
Period21/05/1825/05/18
Internet address

Fingerprint

Catheters
Fusion reactions
Ultrasonics
Sensors
Endoscopy
Kalman filters
Surgery
Neural networks

Cite this

Denasi, A., Khan, F., Boskma, K. J., Kaya, M., Hennersperger, C., Göbl, R., ... Misra, S. (2018). An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters. Paper presented at 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia.
Denasi, Alper ; Khan, F. ; Boskma, K.J. ; Kaya, M. ; Hennersperger, Christoph ; Göbl, Rüdiger ; Tirindelli, Maria ; Navab, Nassir ; Misra, S. / An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters. Paper presented at 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia.8 p.
@conference{f04928c0f0d0411cb119305b15beb31d,
title = "An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters",
abstract = "Minimally invasive surgery involves using flexible medical instruments such as endoscopes and catheters. Magnetically actuated catheters can provide improved steering precision over conventional catheters. However, besides the actuationmethod, an accurate tip position is required for precise control of the medical instruments. In this study, the tip position obtained from transverse 2D ultrasound images and multicore optical shape sensors are combined using a robust sensor fusion algorithm. The tip position is tracked in the ultrasound images using a template-based tracker and a convolutional neural network based tracker, respectively. Experimental results for a rhombus path are presented, where data obtained from both tracking sources are fused using Luenberger and Kalman state estimators. The mean and standard deviation of the Euclideanerror for the Luenberger observer is 0.2+-0.11 [mm] whereas for the Kalman filter it is 0.18+-0.13 [mm], respectively.",
author = "Alper Denasi and F. Khan and K.J. Boskma and M. Kaya and Christoph Hennersperger and R{\"u}diger G{\"o}bl and Maria Tirindelli and Nassir Navab and S. Misra",
year = "2018",
month = "5",
language = "English",
note = "2018 IEEE International Conference on Robotics and Automation, ICRA 2018, ICRA ; Conference date: 21-05-2018 Through 25-05-2018",
url = "https://icra2018.org/",

}

Denasi, A, Khan, F, Boskma, KJ, Kaya, M, Hennersperger, C, Göbl, R, Tirindelli, M, Navab, N & Misra, S 2018, 'An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters' Paper presented at 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia, 21/05/18 - 25/05/18, .

An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters. / Denasi, Alper ; Khan, F.; Boskma, K.J.; Kaya, M.; Hennersperger, Christoph; Göbl, Rüdiger; Tirindelli, Maria; Navab, Nassir; Misra, S.

2018. Paper presented at 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia.

Research output: Contribution to conferencePaperAcademicpeer-review

TY - CONF

T1 - An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters

AU - Denasi, Alper

AU - Khan, F.

AU - Boskma, K.J.

AU - Kaya, M.

AU - Hennersperger, Christoph

AU - Göbl, Rüdiger

AU - Tirindelli, Maria

AU - Navab, Nassir

AU - Misra, S.

PY - 2018/5

Y1 - 2018/5

N2 - Minimally invasive surgery involves using flexible medical instruments such as endoscopes and catheters. Magnetically actuated catheters can provide improved steering precision over conventional catheters. However, besides the actuationmethod, an accurate tip position is required for precise control of the medical instruments. In this study, the tip position obtained from transverse 2D ultrasound images and multicore optical shape sensors are combined using a robust sensor fusion algorithm. The tip position is tracked in the ultrasound images using a template-based tracker and a convolutional neural network based tracker, respectively. Experimental results for a rhombus path are presented, where data obtained from both tracking sources are fused using Luenberger and Kalman state estimators. The mean and standard deviation of the Euclideanerror for the Luenberger observer is 0.2+-0.11 [mm] whereas for the Kalman filter it is 0.18+-0.13 [mm], respectively.

AB - Minimally invasive surgery involves using flexible medical instruments such as endoscopes and catheters. Magnetically actuated catheters can provide improved steering precision over conventional catheters. However, besides the actuationmethod, an accurate tip position is required for precise control of the medical instruments. In this study, the tip position obtained from transverse 2D ultrasound images and multicore optical shape sensors are combined using a robust sensor fusion algorithm. The tip position is tracked in the ultrasound images using a template-based tracker and a convolutional neural network based tracker, respectively. Experimental results for a rhombus path are presented, where data obtained from both tracking sources are fused using Luenberger and Kalman state estimators. The mean and standard deviation of the Euclideanerror for the Luenberger observer is 0.2+-0.11 [mm] whereas for the Kalman filter it is 0.18+-0.13 [mm], respectively.

M3 - Paper

ER -

Denasi A, Khan F, Boskma KJ, Kaya M, Hennersperger C, Göbl R et al. An Observer-Based Fusion Method using Multicore Optical Shape Sensors and Ultrasound Images for Magnetically-Actuated Catheters. 2018. Paper presented at 2018 IEEE International Conference on Robotics and Automation, ICRA 2018, Brisbane, Australia.