XClose

Wellcome / EPSRC Centre for Interventional and Surgical Sciences

Home
Menu

UCL Stereo-Endoscopic Reconstruction Validiation with CT

This dataset provides a ground truth validation for stereo reconstruction of ex vivo endoscopic video frames using computed tomography (CT).

Overview

This data set has been submitted for publication in Medical Image Analysis under thetitle “Validation of stereoendoscopic reconstruction algorithms using a ground truth depth derived from CT.” The dataset contains 16 frames with ground-truth vessel segmentation annotations taken from two different ex vivo porcine samples using thestraight and 30°endoscopes from the original classic da Vinci™ Surgical System from Intuitive, Inc.

Image from UCL SERV CT

The ground truth is provided by a CT scan from the O-arm™ system from Medtronic. The scan contains both the anatomy and the endoscope, enabling accurate location of the viewed anatomical surface relative to the endoscope.

Endoscope and anatomy localisation in CT

The ground truth is provided as stereo pairs with ground truth disparity and depth with labels for overlap region and occlusions.

Ground truth disparity and depth with original image showing occlusions and overlap

Downloading the Dataset

This dataset has been released. If you wish to have access to this dataset, please kindly fill the request form.

License

The UCL-SERV-CT Dataset is licensed under a Creative Commons Attribution 4.0 International (CC BY 4.0).

BY NC

Citing the Dataset

@inproceedings{edwards2020ucl-serv-ct,
title={ Validation of stereoendoscopic reconstruction algorithms using a ground truth depth derived from CT},
author={Edwards, PJ “Eddie” and Psychogyios, Dimitris and Stoyanov, Danail},
booktitle={Medical Image Analysis},
year={In Submission}
}

The following publication is also associated with this work.

@inproceedings{stoyanov2010real,
title={Real-time stereo reconstruction in robotically assisted minimally invasive surgery},
author={Stoyanov, Danail and Scarzanella, Marco Visentini and Pratt, Philip and Yang, Guang-Zhong},
booktitle={International Conference on Medical Image Computing and Computer-Assisted Intervention},
pages={275--282},
year={2010},
organization={Springer}
}

Contact

For comments, suggestions or feedback, or if you experience any problems with this website or the dataset, please contact Dimitris Psychogyios or Eddie Edwards.