Deploying computer vision detection method in medical simulation training using machine learning

Hang Ling Wu; Dailen Brown; Scarlett Miller; Jason Moore

doi:10.1115/DMD2023-3868

Deploying computer vision detection method in medical simulation training using machine learning

Hang Ling Wu, Dailen Brown, Scarlett Miller, Jason Moore

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A machine learning (ML) object detection algorithm was developed to replace the original color-based image detection algorithm for the Dynamic Haptic Robotic Trainer Plus (DHRT+). This image recognition system was used for medical training in Central Venous Catheterization (CVC). This image tracking allows for the training system to provide accurate performance feedback to the user during the training process. The ML object detection algorithm was developed and evaluated using training data. The results indicate that increasing the training data set improves the detection system's accuracy. The system was found to have an overall precision rate of 90.9% and a recall rate of 81.69%. This new ML model will be implemented into the DHRT+ system and used to train medical residents.

Original language	English (US)
Title of host publication	Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023
Publisher	American Society of Mechanical Engineers
ISBN (Electronic)	9780791886731
DOIs	https://doi.org/10.1115/DMD2023-3868
State	Published - 2023
Event	2023 Design of Medical Devices Conference, DMD 2023 - Minneapolis, United States Duration: Apr 17 2023 → Apr 21 2023

Publication series

Name	Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023

Conference

Conference	2023 Design of Medical Devices Conference, DMD 2023
Country/Territory	United States
City	Minneapolis
Period	4/17/23 → 4/21/23

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Medicine (miscellaneous)

Access to Document

10.1115/DMD2023-3868

Cite this

Wu, H. L., Brown, D., Miller, S., & Moore, J. (2023). Deploying computer vision detection method in medical simulation training using machine learning. In Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023 Article v001t06a001 (Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023). American Society of Mechanical Engineers. https://doi.org/10.1115/DMD2023-3868

@inproceedings{64b7c06671494e0f99125b49cca9b3a4,

title = "Deploying computer vision detection method in medical simulation training using machine learning",

abstract = "A machine learning (ML) object detection algorithm was developed to replace the original color-based image detection algorithm for the Dynamic Haptic Robotic Trainer Plus (DHRT+). This image recognition system was used for medical training in Central Venous Catheterization (CVC). This image tracking allows for the training system to provide accurate performance feedback to the user during the training process. The ML object detection algorithm was developed and evaluated using training data. The results indicate that increasing the training data set improves the detection system's accuracy. The system was found to have an overall precision rate of 90.9% and a recall rate of 81.69%. This new ML model will be implemented into the DHRT+ system and used to train medical residents.",

author = "Wu, {Hang Ling} and Dailen Brown and Scarlett Miller and Jason Moore",

note = "Publisher Copyright: {\textcopyright} 2023 by ASME.; 2023 Design of Medical Devices Conference, DMD 2023 ; Conference date: 17-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1115/DMD2023-3868",

language = "English (US)",

series = "Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023",

publisher = "American Society of Mechanical Engineers",

booktitle = "Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023",

}

Wu, HL, Brown, D, Miller, S & Moore, J 2023, Deploying computer vision detection method in medical simulation training using machine learning. in Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023., v001t06a001, Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023, American Society of Mechanical Engineers, 2023 Design of Medical Devices Conference, DMD 2023, Minneapolis, United States, 4/17/23. https://doi.org/10.1115/DMD2023-3868

Deploying computer vision detection method in medical simulation training using machine learning. / Wu, Hang Ling; Brown, Dailen; Miller, Scarlett et al.
Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023. American Society of Mechanical Engineers, 2023. v001t06a001 (Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Deploying computer vision detection method in medical simulation training using machine learning

AU - Wu, Hang Ling

AU - Brown, Dailen

AU - Miller, Scarlett

AU - Moore, Jason

PY - 2023

Y1 - 2023

N2 - A machine learning (ML) object detection algorithm was developed to replace the original color-based image detection algorithm for the Dynamic Haptic Robotic Trainer Plus (DHRT+). This image recognition system was used for medical training in Central Venous Catheterization (CVC). This image tracking allows for the training system to provide accurate performance feedback to the user during the training process. The ML object detection algorithm was developed and evaluated using training data. The results indicate that increasing the training data set improves the detection system's accuracy. The system was found to have an overall precision rate of 90.9% and a recall rate of 81.69%. This new ML model will be implemented into the DHRT+ system and used to train medical residents.

AB - A machine learning (ML) object detection algorithm was developed to replace the original color-based image detection algorithm for the Dynamic Haptic Robotic Trainer Plus (DHRT+). This image recognition system was used for medical training in Central Venous Catheterization (CVC). This image tracking allows for the training system to provide accurate performance feedback to the user during the training process. The ML object detection algorithm was developed and evaluated using training data. The results indicate that increasing the training data set improves the detection system's accuracy. The system was found to have an overall precision rate of 90.9% and a recall rate of 81.69%. This new ML model will be implemented into the DHRT+ system and used to train medical residents.

UR - http://www.scopus.com/inward/record.url?scp=85164990352&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85164990352&partnerID=8YFLogxK

U2 - 10.1115/DMD2023-3868

DO - 10.1115/DMD2023-3868

M3 - Conference contribution

AN - SCOPUS:85164990352

T3 - Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023

BT - Proceedings of the 2023 Design of Medical Devices Conference, DMD 2023

PB - American Society of Mechanical Engineers

T2 - 2023 Design of Medical Devices Conference, DMD 2023

Y2 - 17 April 2023 through 21 April 2023

ER -

Deploying computer vision detection method in medical simulation training using machine learning

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this