A Deep Learning Approach for Pose Estimation from Volumetric OCT Data

03/10/2018
by   Nils Gessert, et al.
0

Tracking the pose of instruments is a central problem in image-guided surgery. For microscopic scenarios, optical coherence tomography (OCT) is increasingly used as an imaging modality. OCT is suitable for accurate pose estimation due to its micrometer range resolution and volumetric field of view. However, OCT image processing is challenging due to speckle noise and reflection artifacts in addition to the images' 3D nature. We address pose estimation from OCT volume data with a new deep learning-based tracking framework. For this purpose, we design a new 3D convolutional neural network (CNN) architecture to directly predict the 6D pose of a small marker geometry from OCT volumes. We use a hexapod robot to automatically acquire labeled data points which we use to train 3D CNN architectures for multi-output regression. We use this setup to provide an in-depth analysis on deep learning-based pose estimation from volumes. Specifically, we demonstrate that exploiting volume information for pose estimation yields higher accuracy than relying on 2D representations with depth information. Supporting this observation, we provide quantitative and qualitative results that 3D CNNs effectively exploit the depth structure of marker objects. Regarding the deep learning aspect, we present efficient design principles for 3D CNNs, making use of insights from the 2D deep learning community. In particular, we present Inception3D as a new architecture which performs best for our application. We show that our deep learning approach reaches errors at our ground-truth label's resolution. We achieve a mean average error of 14.89 ± 9.3 and 0.096 ± 0.072 for position and orientation learning, respectively.

READ FULL TEXT

page 3

page 5

page 7

page 8

page 11

page 14

page 16

research
10/22/2018

Two-path 3D CNNs for calibration of system parameters for OCT-based motion compensation

Automatic motion compensation and adjustment of an intraoperative imagin...
research
10/26/2018

Deep learning based 2.5D flow field estimation for maximum intensity projections of 4D optical coherence tomography

In laser microsurgery, image-based control of the ablation laser can lea...
research
07/02/2020

4D Spatio-Temporal Convolutional Networks for Object Position Estimation in OCT Volumes

Tracking and localizing objects is a central problem in computer-assiste...
research
12/20/2019

DeepSFM: Structure From Motion Via Deep Bundle Adjustment

Structure from motion (SfM) is an essential computer vision problem whic...
research
04/26/2018

Force Estimation from OCT Volumes using 3D CNNs

Purpose Estimating the interaction forces of instruments and tissue is o...
research
12/02/2019

Efficient Convolutional Neural Networks for Depth-Based Multi-Person Pose Estimation

Achieving robust multi-person 2D body landmark localization and pose est...
research
01/19/2019

Endoscopic vs. volumetric OCT imaging of mastoid bone structure for pose estimation in minimally invasive cochlear implant surgery

Purpose: The facial recess is a delicate structure that must be protecte...

Please sign up or login with your details

Forgot password? Click here to reset