Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network
Image-based surgical instrument tracking in robot-assisted surgery is an active and challenging research area. Having a real-time knowledge of surgical instrument location is an essential part of a computer-assisted intervention system. Tracking can be used as visual feedback for servo control of a...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-10-01
|
Series: | Healthcare Technology Letters |
Subjects: | |
Online Access: | https://digital-library.theiet.org/content/journals/10.1049/htl.2019.0068 |
id |
doaj-698811b04a8b4486823e146def0603e6 |
---|---|
record_format |
Article |
spelling |
doaj-698811b04a8b4486823e146def0603e62021-04-02T12:55:34ZengWileyHealthcare Technology Letters2053-37132019-10-0110.1049/htl.2019.0068HTL.2019.0068Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural networkLiang Qiu0Changsheng Li1Changsheng Li2Hongliang Ren3Department of Biomedical Engineering, National University of SingaporeDepartment of Biomedical Engineering, National University of SingaporeDepartment of Biomedical Engineering, National University of SingaporeDepartment of Biomedical Engineering, National University of SingaporeImage-based surgical instrument tracking in robot-assisted surgery is an active and challenging research area. Having a real-time knowledge of surgical instrument location is an essential part of a computer-assisted intervention system. Tracking can be used as visual feedback for servo control of a surgical robot or transformed as haptic feedback for surgeon–robot interaction. In this Letter, the authors apply a multi-domain convolutional neural network for fast 2D surgical instrument tracking considering the application for multiple surgical tools and use a focal loss to decrease the effect of easy negative examples. They further introduce a new dataset based on m2cai16-tool and their cadaver experiments due to the lack of established public surgical tool tracking dataset despite significant progress in this field. Their method is evaluated on the introduced dataset and outperforms the state-of-the-art real-time trackers.https://digital-library.theiet.org/content/journals/10.1049/htl.2019.0068neural netsmedical roboticssurgerytime surgical instrument trackingrobot-assisted surgerymultidomain convolutional neural networkactive research areachallenging research areareal-time knowledgesurgical instrument locationcomputer-assisted intervention systemsurgical robotsurgeon–robot interactionmultiple surgical toolsestablished public surgical tool tracking dataset |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Liang Qiu Changsheng Li Changsheng Li Hongliang Ren |
spellingShingle |
Liang Qiu Changsheng Li Changsheng Li Hongliang Ren Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network Healthcare Technology Letters neural nets medical robotics surgery time surgical instrument tracking robot-assisted surgery multidomain convolutional neural network active research area challenging research area real-time knowledge surgical instrument location computer-assisted intervention system surgical robot surgeon–robot interaction multiple surgical tools established public surgical tool tracking dataset |
author_facet |
Liang Qiu Changsheng Li Changsheng Li Hongliang Ren |
author_sort |
Liang Qiu |
title |
Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network |
title_short |
Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network |
title_full |
Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network |
title_fullStr |
Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network |
title_full_unstemmed |
Real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network |
title_sort |
real-time surgical instrument tracking in robot-assisted surgery using multi-domain convolutional neural network |
publisher |
Wiley |
series |
Healthcare Technology Letters |
issn |
2053-3713 |
publishDate |
2019-10-01 |
description |
Image-based surgical instrument tracking in robot-assisted surgery is an active and challenging research area. Having a real-time knowledge of surgical instrument location is an essential part of a computer-assisted intervention system. Tracking can be used as visual feedback for servo control of a surgical robot or transformed as haptic feedback for surgeon–robot interaction. In this Letter, the authors apply a multi-domain convolutional neural network for fast 2D surgical instrument tracking considering the application for multiple surgical tools and use a focal loss to decrease the effect of easy negative examples. They further introduce a new dataset based on m2cai16-tool and their cadaver experiments due to the lack of established public surgical tool tracking dataset despite significant progress in this field. Their method is evaluated on the introduced dataset and outperforms the state-of-the-art real-time trackers. |
topic |
neural nets medical robotics surgery time surgical instrument tracking robot-assisted surgery multidomain convolutional neural network active research area challenging research area real-time knowledge surgical instrument location computer-assisted intervention system surgical robot surgeon–robot interaction multiple surgical tools established public surgical tool tracking dataset |
url |
https://digital-library.theiet.org/content/journals/10.1049/htl.2019.0068 |
work_keys_str_mv |
AT liangqiu realtimesurgicalinstrumenttrackinginrobotassistedsurgeryusingmultidomainconvolutionalneuralnetwork AT changshengli realtimesurgicalinstrumenttrackinginrobotassistedsurgeryusingmultidomainconvolutionalneuralnetwork AT changshengli realtimesurgicalinstrumenttrackinginrobotassistedsurgeryusingmultidomainconvolutionalneuralnetwork AT hongliangren realtimesurgicalinstrumenttrackinginrobotassistedsurgeryusingmultidomainconvolutionalneuralnetwork |
_version_ |
1721567197544841216 |