Automation of surgical skill assessment using a three-stage machine learning algorithm
Abstract Surgical skills are associated with clinical outcomes. To improve surgical skills and thereby reduce adverse outcomes, continuous surgical training and feedback is required. Currently, assessment of surgical skills is a manual and time-consuming process which is prone to subjective interpre...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-03-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-021-84295-6 |
id |
doaj-dc51263bc4504396ad577f84e95bb043 |
---|---|
record_format |
Article |
spelling |
doaj-dc51263bc4504396ad577f84e95bb0432021-03-11T12:18:25ZengNature Publishing GroupScientific Reports2045-23222021-03-011111910.1038/s41598-021-84295-6Automation of surgical skill assessment using a three-stage machine learning algorithmJoël L. Lavanchy0Joel Zindel1Kadir Kirtac2Isabell Twick3Enes Hosgor4Daniel Candinas5Guido Beldi6Department of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of BernDepartment of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of BernCaresyntaxCaresyntaxCaresyntaxDepartment of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of BernDepartment of Visceral Surgery and Medicine, Inselspital, Bern University Hospital, University of BernAbstract Surgical skills are associated with clinical outcomes. To improve surgical skills and thereby reduce adverse outcomes, continuous surgical training and feedback is required. Currently, assessment of surgical skills is a manual and time-consuming process which is prone to subjective interpretation. This study aims to automate surgical skill assessment in laparoscopic cholecystectomy videos using machine learning algorithms. To address this, a three-stage machine learning method is proposed: first, a Convolutional Neural Network was trained to identify and localize surgical instruments. Second, motion features were extracted from the detected instrument localizations throughout time. Third, a linear regression model was trained based on the extracted motion features to predict surgical skills. This three-stage modeling approach achieved an accuracy of 87 ± 0.2% in distinguishing good versus poor surgical skill. While the technique cannot reliably quantify the degree of surgical skill yet it represents an important advance towards automation of surgical skill assessment.https://doi.org/10.1038/s41598-021-84295-6 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Joël L. Lavanchy Joel Zindel Kadir Kirtac Isabell Twick Enes Hosgor Daniel Candinas Guido Beldi |
spellingShingle |
Joël L. Lavanchy Joel Zindel Kadir Kirtac Isabell Twick Enes Hosgor Daniel Candinas Guido Beldi Automation of surgical skill assessment using a three-stage machine learning algorithm Scientific Reports |
author_facet |
Joël L. Lavanchy Joel Zindel Kadir Kirtac Isabell Twick Enes Hosgor Daniel Candinas Guido Beldi |
author_sort |
Joël L. Lavanchy |
title |
Automation of surgical skill assessment using a three-stage machine learning algorithm |
title_short |
Automation of surgical skill assessment using a three-stage machine learning algorithm |
title_full |
Automation of surgical skill assessment using a three-stage machine learning algorithm |
title_fullStr |
Automation of surgical skill assessment using a three-stage machine learning algorithm |
title_full_unstemmed |
Automation of surgical skill assessment using a three-stage machine learning algorithm |
title_sort |
automation of surgical skill assessment using a three-stage machine learning algorithm |
publisher |
Nature Publishing Group |
series |
Scientific Reports |
issn |
2045-2322 |
publishDate |
2021-03-01 |
description |
Abstract Surgical skills are associated with clinical outcomes. To improve surgical skills and thereby reduce adverse outcomes, continuous surgical training and feedback is required. Currently, assessment of surgical skills is a manual and time-consuming process which is prone to subjective interpretation. This study aims to automate surgical skill assessment in laparoscopic cholecystectomy videos using machine learning algorithms. To address this, a three-stage machine learning method is proposed: first, a Convolutional Neural Network was trained to identify and localize surgical instruments. Second, motion features were extracted from the detected instrument localizations throughout time. Third, a linear regression model was trained based on the extracted motion features to predict surgical skills. This three-stage modeling approach achieved an accuracy of 87 ± 0.2% in distinguishing good versus poor surgical skill. While the technique cannot reliably quantify the degree of surgical skill yet it represents an important advance towards automation of surgical skill assessment. |
url |
https://doi.org/10.1038/s41598-021-84295-6 |
work_keys_str_mv |
AT joelllavanchy automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm AT joelzindel automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm AT kadirkirtac automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm AT isabelltwick automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm AT eneshosgor automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm AT danielcandinas automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm AT guidobeldi automationofsurgicalskillassessmentusingathreestagemachinelearningalgorithm |
_version_ |
1724224521241624576 |