In-vivo markerless motion detection from volumetric optical coherence tomography data using CNNs

First published in
Progress in Biomedical Optics and Imaging - Proceedings of SPIE  
Number in series
11598
Article Number
115981H
Citation
Image-Guided Procedures, Robotic Interventions, and Modeling: SPIE Medical Imaging (2021)
Contribution to Conference
SPIE Medical Imaging, 2021  
Publisher DOI
10.1117/12.2581023
Scopus ID
2-s2.0-85105600209
Publisher
SPIE
ISBN
978-1-5106-4026-9
978-1-5106-4025-2
Precise navigation is an important task in robot-assisted and minimally invasive surgery. The need for optical markers and a lack of distinct anatomical features on skin or organs complicate tissue tracking with commercial tracking systems. Previous work has shown the feasibility of a 3D optical coherence tomography based system for this purpose. Furthermore, convolutional neural networks have been proven to precisely detect shifts between volumes. However, most experiments have been performed with phantoms or ex-vivo tissue. We introduce an experimental setup and perform measurements on perfused and non-perfused (dead) tissue of in-vivo xenograft tumors. We train 3D siamese deep learning models and evaluate the precision of the motion prediction. The network\'s ability to predict shifts for different motion magnitudes and also the performance for the different volume axes are compared. The root-mean-square errors are 0:12mm and 0:08mm on perfused and non-perfused tumor tissue, respectively
DDC Class
004: Informatik
600: Technik
610: Medizin
620: Ingenieurwissenschaften
Funding(s)
Robotisierte Ultraschall-gestützte Bildgebung zur Echtzeit-Bewegungskompensation in der Strahlentherapie (RobUST), Phase II  
Funding Organisations
Deutsche Forschungsgemeinschaft (DFG)  
More Funding Information
This work was partially funded by the i3 initiative of the Hamburg University of Technology and by the German
Research Foundation (DFG, grant number SCHL 1844/2-2).