Imperial College London
Alternate

Professor Daniel Elson

Faculty of Medicine, Department of Surgery & Cancer

Professor of Surgical Imaging
 
 
 
//

Contact

 

+44 (0)20 7594 1700daniel.elson Website CV

 
 
//

Location

 

415 Bessemer BuildingBessemer BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Huang:2022:10.1109/tmrb.2022.3170215,
author = {Huang, B and Nguyen, A and Wang, S and Wang, Z and Mayer, E and Tuch, D and Vyas, K and Giannarou, S and Elson, DS},
doi = {10.1109/tmrb.2022.3170215},
journal = {IEEE Transactions on Medical Robotics and Bionics},
pages = {335--338},
title = {Simultaneous depth estimation and surgical tool segmentation in laparoscopic images},
url = {http://dx.doi.org/10.1109/tmrb.2022.3170215},
volume = {4},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Surgical instrument segmentation and depth estimation are crucial steps to improve autonomy in robotic surgery. Most recent works treat these problems separately, making the deployment challenging. In this paper, we propose a unified framework for depth estimation and surgical tool segmentation in laparoscopic images. The network has an encoder-decoder architecture and comprises two branches for simultaneously performing depth estimation and segmentation. To train the network end to end, we propose a new multi-task loss function that effectively learns to estimate depth in an unsupervised manner, while requiring only semi-ground truth for surgical tool segmentation. We conducted extensive experiments on different datasets to validate these findings. The results showed that the end-to-end network successfully improved the state-of-the-art for both tasks while reducing the complexity during their deployment.
AU  - Huang,B
AU  - Nguyen,A
AU  - Wang,S
AU  - Wang,Z
AU  - Mayer,E
AU  - Tuch,D
AU  - Vyas,K
AU  - Giannarou,S
AU  - Elson,DS
DO  - 10.1109/tmrb.2022.3170215
EP  - 338
PY  - 2022///
SN  - 2576-3202
SP  - 335
TI  - Simultaneous depth estimation and surgical tool segmentation in laparoscopic images
T2  - IEEE Transactions on Medical Robotics and Bionics
UR  - http://dx.doi.org/10.1109/tmrb.2022.3170215
UR  - https://ieeexplore.ieee.org/document/9762754
UR  - http://hdl.handle.net/10044/1/97519
VL  - 4
ER  -
Download