Unsupervised binocular depth prediction network for laparoscopic surgery
Minimally invasive laparoscopic surgery is associated with small wounds and short recovery time, reducing postoperative infections. Traditional two-dimensional (2D) laparoscopic imaging lacks depth perception and does not provide quantitative depth information, thereby limiting the field of vision a...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Taylor & Francis Group
2019-10-01
|
Series: | Computer Assisted Surgery |
Subjects: | |
Online Access: | http://dx.doi.org/10.1080/24699322.2018.1557889 |
id |
doaj-9bc84048096b4234bff5bbd58923bbb4 |
---|---|
record_format |
Article |
spelling |
doaj-9bc84048096b4234bff5bbd58923bbb42020-11-25T02:05:33ZengTaylor & Francis GroupComputer Assisted Surgery2469-93222019-10-01240303510.1080/24699322.2018.15578891557889Unsupervised binocular depth prediction network for laparoscopic surgeryKe Xu0Zhiyong Chen1Fucang Jia2Guilin University of Electronic TechnologyGuilin University of Electronic TechnologyShenzhen Institutes of Advanced Technology, Chinese Academy of SciencesMinimally invasive laparoscopic surgery is associated with small wounds and short recovery time, reducing postoperative infections. Traditional two-dimensional (2D) laparoscopic imaging lacks depth perception and does not provide quantitative depth information, thereby limiting the field of vision and operation during surgery. However, three-dimensional (3D) laparoscopic imaging from 2 D images lets surgeons have a depth perception. However, the depth information is not quantitative and cannot be used for robotic surgery. Therefore, this study aimed to reconstruct the accurate depth map for binocular 3 D laparoscopy. In this study, an unsupervised learning method was proposed to calculate the accurate depth while the ground-truth depth was not available. Experimental results proved that the method not only generated accurate depth maps but also provided real-time computation, and it could be used in minimally invasive robotic surgery.http://dx.doi.org/10.1080/24699322.2018.1557889Depth estimation3D reconstructionlaparoscopic surgeryunsupervised learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ke Xu Zhiyong Chen Fucang Jia |
spellingShingle |
Ke Xu Zhiyong Chen Fucang Jia Unsupervised binocular depth prediction network for laparoscopic surgery Computer Assisted Surgery Depth estimation 3D reconstruction laparoscopic surgery unsupervised learning |
author_facet |
Ke Xu Zhiyong Chen Fucang Jia |
author_sort |
Ke Xu |
title |
Unsupervised binocular depth prediction network for laparoscopic surgery |
title_short |
Unsupervised binocular depth prediction network for laparoscopic surgery |
title_full |
Unsupervised binocular depth prediction network for laparoscopic surgery |
title_fullStr |
Unsupervised binocular depth prediction network for laparoscopic surgery |
title_full_unstemmed |
Unsupervised binocular depth prediction network for laparoscopic surgery |
title_sort |
unsupervised binocular depth prediction network for laparoscopic surgery |
publisher |
Taylor & Francis Group |
series |
Computer Assisted Surgery |
issn |
2469-9322 |
publishDate |
2019-10-01 |
description |
Minimally invasive laparoscopic surgery is associated with small wounds and short recovery time, reducing postoperative infections. Traditional two-dimensional (2D) laparoscopic imaging lacks depth perception and does not provide quantitative depth information, thereby limiting the field of vision and operation during surgery. However, three-dimensional (3D) laparoscopic imaging from 2 D images lets surgeons have a depth perception. However, the depth information is not quantitative and cannot be used for robotic surgery. Therefore, this study aimed to reconstruct the accurate depth map for binocular 3 D laparoscopy. In this study, an unsupervised learning method was proposed to calculate the accurate depth while the ground-truth depth was not available. Experimental results proved that the method not only generated accurate depth maps but also provided real-time computation, and it could be used in minimally invasive robotic surgery. |
topic |
Depth estimation 3D reconstruction laparoscopic surgery unsupervised learning |
url |
http://dx.doi.org/10.1080/24699322.2018.1557889 |
work_keys_str_mv |
AT kexu unsupervisedbinoculardepthpredictionnetworkforlaparoscopicsurgery AT zhiyongchen unsupervisedbinoculardepthpredictionnetworkforlaparoscopicsurgery AT fucangjia unsupervisedbinoculardepthpredictionnetworkforlaparoscopicsurgery |
_version_ |
1724937528668061696 |