Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology
In dysphagia, food materials frequently invade the laryngeal airway, potentially resulting in serious consequences, such as asphyxia or pneumonia. The VFSS (videofluoroscopic swallowing study) procedure can be used to visualize the occurrence of airway invasion, but its reliability is limited by hum...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-09-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/18/6179 |
id |
doaj-2edae209eabf4cee886166953240ac53 |
---|---|
record_format |
Article |
spelling |
doaj-2edae209eabf4cee886166953240ac532020-11-25T02:55:14ZengMDPI AGApplied Sciences2076-34172020-09-01106179617910.3390/app10186179Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning TechnologySeong Jae Lee0Joo Young Ko1Hyun Il Kim2Sang-Il Choi3Department of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaDepartment of Rehabilitation Medicine, College of Medicine, Dankook University, Cheonan 31116, KoreaDepartment of Computer Science and Engineering, Dankook University, Gyeonggi-do 16890, KoreaDepartment of Computer Science and Engineering, Dankook University, Gyeonggi-do 16890, KoreaIn dysphagia, food materials frequently invade the laryngeal airway, potentially resulting in serious consequences, such as asphyxia or pneumonia. The VFSS (videofluoroscopic swallowing study) procedure can be used to visualize the occurrence of airway invasion, but its reliability is limited by human errors and fatigue. Deep learning technology may improve the efficiency and reliability of VFSS analysis by reducing the human effort required. A deep learning model has been developed that can detect airway invasion from VFSS images in a fully automated manner. The model consists of three phases: (1) image normalization, (2) dynamic ROI (region of interest) determination, and (3) airway invasion detection. Noise induced by movement and learning from unintended areas is minimized by defining a “dynamic” ROI with respect to the center of the cervical spinal column as segmented using U-Net. An Xception module, trained on a dataset consisting of 267,748 image frames obtained from 319 VFSS video files, is used for the detection of airway invasion. The present model shows an overall accuracy of 97.2% in classifying image frames and 93.2% in classifying video files. It is anticipated that the present model will enable more accurate analysis of VFSS data.https://www.mdpi.com/2076-3417/10/18/6179deglutition disordersaspirationvideofluoroscopydeep learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Seong Jae Lee Joo Young Ko Hyun Il Kim Sang-Il Choi |
spellingShingle |
Seong Jae Lee Joo Young Ko Hyun Il Kim Sang-Il Choi Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology Applied Sciences deglutition disorders aspiration videofluoroscopy deep learning |
author_facet |
Seong Jae Lee Joo Young Ko Hyun Il Kim Sang-Il Choi |
author_sort |
Seong Jae Lee |
title |
Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology |
title_short |
Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology |
title_full |
Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology |
title_fullStr |
Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology |
title_full_unstemmed |
Automatic Detection of Airway Invasion from Videofluoroscopy via Deep Learning Technology |
title_sort |
automatic detection of airway invasion from videofluoroscopy via deep learning technology |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-09-01 |
description |
In dysphagia, food materials frequently invade the laryngeal airway, potentially resulting in serious consequences, such as asphyxia or pneumonia. The VFSS (videofluoroscopic swallowing study) procedure can be used to visualize the occurrence of airway invasion, but its reliability is limited by human errors and fatigue. Deep learning technology may improve the efficiency and reliability of VFSS analysis by reducing the human effort required. A deep learning model has been developed that can detect airway invasion from VFSS images in a fully automated manner. The model consists of three phases: (1) image normalization, (2) dynamic ROI (region of interest) determination, and (3) airway invasion detection. Noise induced by movement and learning from unintended areas is minimized by defining a “dynamic” ROI with respect to the center of the cervical spinal column as segmented using U-Net. An Xception module, trained on a dataset consisting of 267,748 image frames obtained from 319 VFSS video files, is used for the detection of airway invasion. The present model shows an overall accuracy of 97.2% in classifying image frames and 93.2% in classifying video files. It is anticipated that the present model will enable more accurate analysis of VFSS data. |
topic |
deglutition disorders aspiration videofluoroscopy deep learning |
url |
https://www.mdpi.com/2076-3417/10/18/6179 |
work_keys_str_mv |
AT seongjaelee automaticdetectionofairwayinvasionfromvideofluoroscopyviadeeplearningtechnology AT jooyoungko automaticdetectionofairwayinvasionfromvideofluoroscopyviadeeplearningtechnology AT hyunilkim automaticdetectionofairwayinvasionfromvideofluoroscopyviadeeplearningtechnology AT sangilchoi automaticdetectionofairwayinvasionfromvideofluoroscopyviadeeplearningtechnology |
_version_ |
1724717414431588352 |