Quantification and Analysis of Laryngeal Closure from Endoscopic Videos

Jianyu Lin; Emil S. Walsted; Vibeke Backer; James H. Hull; Daniel S. Elson

doi:10.1109/TBME.2018.2867636

Quantification and Analysis of Laryngeal Closure from Endoscopic Videos

Jianyu Lin^*, Emil S. Walsted, Vibeke Backer, James H. Hull, Daniel S. Elson

^*Corresponding author af dette arbejde

Institut for Klinisk Medicin

11 Citationer (Scopus)

Abstract

Objective: At present, there are no objective techniques to quantify and describe laryngeal obstruction, and the reproducibility of subjective manual quantification methods is insufficient, resulting in diagnostic inaccuracy and a poor signal-to-noise ratio in medical research. In this work, a workflow is proposed to quantify laryngeal movements from laryngoscopic videos, to facilitate the diagnosis procedure. Methods: The proposed method analyses laryngoscopic videos, and delineates glottic opening, vocal folds, and supraglottic structures, using a convolutional neural networks (CNNs) based algorithm. The segmentation is divided into two steps: A bounding box which indicates the region of interest (RoI) is found, followed by segmentation using fully convolutional networks (FCNs). The segmentation results are statistically quantified along the temporal dimension and processed using singular spectrum analysis (SSA), to extract clear objective information that can be used by the clinicians in diagnosis. Results: The segmentation was validated on 400 images from 20 videos acquired using different endoscopic systems from different patients. The results indicated significant improvements over using FCN only in terms of both processing speed (16 FPS vs. 8 FPS) and segmentation result statistics. Five clinical cases on patients have also been provided to showcase the quantitative analysis results using the proposed method. Conclusion: The proposed method guarantees a robust and fast processing of laryngoscopic videos. Measurements of glottic angles and supraglottic index showed distinctive patterns in the provided clinical cases. Significance: The proposed automated and objective method extracts important temporal laryngeal movement information, which can be used to aid laryngeal closure diagnosis.

Originalsprog	Engelsk
Artikelnummer	8450618
Tidsskrift	IEEE Transactions on Biomedical Engineering
Vol/bind	66
Udgave nummer	4
Sider (fra-til)	1127-1136
Antal sider	10
ISSN	0018-9294
DOI	https://doi.org/10.1109/TBME.2018.2867636
Status	Udgivet - 2019

Adgang til dokumentet

10.1109/TBME.2018.2867636

Citationsformater

@article{37c43a254b0c464ba73ac248bbc7b3e7,

title = "Quantification and Analysis of Laryngeal Closure from Endoscopic Videos",

abstract = "Objective: At present, there are no objective techniques to quantify and describe laryngeal obstruction, and the reproducibility of subjective manual quantification methods is insufficient, resulting in diagnostic inaccuracy and a poor signal-to-noise ratio in medical research. In this work, a workflow is proposed to quantify laryngeal movements from laryngoscopic videos, to facilitate the diagnosis procedure. Methods: The proposed method analyses laryngoscopic videos, and delineates glottic opening, vocal folds, and supraglottic structures, using a convolutional neural networks (CNNs) based algorithm. The segmentation is divided into two steps: A bounding box which indicates the region of interest (RoI) is found, followed by segmentation using fully convolutional networks (FCNs). The segmentation results are statistically quantified along the temporal dimension and processed using singular spectrum analysis (SSA), to extract clear objective information that can be used by the clinicians in diagnosis. Results: The segmentation was validated on 400 images from 20 videos acquired using different endoscopic systems from different patients. The results indicated significant improvements over using FCN only in terms of both processing speed (16 FPS vs. 8 FPS) and segmentation result statistics. Five clinical cases on patients have also been provided to showcase the quantitative analysis results using the proposed method. Conclusion: The proposed method guarantees a robust and fast processing of laryngoscopic videos. Measurements of glottic angles and supraglottic index showed distinctive patterns in the provided clinical cases. Significance: The proposed automated and objective method extracts important temporal laryngeal movement information, which can be used to aid laryngeal closure diagnosis.",

keywords = "convolutional neural networks, detection, Laryngeal obstruction, segmentation, singular spectrum analysis",

author = "Jianyu Lin and Walsted, {Emil S.} and Vibeke Backer and Hull, {James H.} and Elson, {Daniel S.}",

year = "2019",

doi = "10.1109/TBME.2018.2867636",

language = "English",

volume = "66",

pages = "1127--1136",

journal = "IEEE Transactions on Biomedical Engineering",

issn = "0018-9294",

publisher = "Institute of Electrical and Electronics Engineers",

number = "4",

}

TY - JOUR

T1 - Quantification and Analysis of Laryngeal Closure from Endoscopic Videos

AU - Lin, Jianyu

AU - Walsted, Emil S.

AU - Backer, Vibeke

AU - Hull, James H.

AU - Elson, Daniel S.

PY - 2019

Y1 - 2019

N2 - Objective: At present, there are no objective techniques to quantify and describe laryngeal obstruction, and the reproducibility of subjective manual quantification methods is insufficient, resulting in diagnostic inaccuracy and a poor signal-to-noise ratio in medical research. In this work, a workflow is proposed to quantify laryngeal movements from laryngoscopic videos, to facilitate the diagnosis procedure. Methods: The proposed method analyses laryngoscopic videos, and delineates glottic opening, vocal folds, and supraglottic structures, using a convolutional neural networks (CNNs) based algorithm. The segmentation is divided into two steps: A bounding box which indicates the region of interest (RoI) is found, followed by segmentation using fully convolutional networks (FCNs). The segmentation results are statistically quantified along the temporal dimension and processed using singular spectrum analysis (SSA), to extract clear objective information that can be used by the clinicians in diagnosis. Results: The segmentation was validated on 400 images from 20 videos acquired using different endoscopic systems from different patients. The results indicated significant improvements over using FCN only in terms of both processing speed (16 FPS vs. 8 FPS) and segmentation result statistics. Five clinical cases on patients have also been provided to showcase the quantitative analysis results using the proposed method. Conclusion: The proposed method guarantees a robust and fast processing of laryngoscopic videos. Measurements of glottic angles and supraglottic index showed distinctive patterns in the provided clinical cases. Significance: The proposed automated and objective method extracts important temporal laryngeal movement information, which can be used to aid laryngeal closure diagnosis.

AB - Objective: At present, there are no objective techniques to quantify and describe laryngeal obstruction, and the reproducibility of subjective manual quantification methods is insufficient, resulting in diagnostic inaccuracy and a poor signal-to-noise ratio in medical research. In this work, a workflow is proposed to quantify laryngeal movements from laryngoscopic videos, to facilitate the diagnosis procedure. Methods: The proposed method analyses laryngoscopic videos, and delineates glottic opening, vocal folds, and supraglottic structures, using a convolutional neural networks (CNNs) based algorithm. The segmentation is divided into two steps: A bounding box which indicates the region of interest (RoI) is found, followed by segmentation using fully convolutional networks (FCNs). The segmentation results are statistically quantified along the temporal dimension and processed using singular spectrum analysis (SSA), to extract clear objective information that can be used by the clinicians in diagnosis. Results: The segmentation was validated on 400 images from 20 videos acquired using different endoscopic systems from different patients. The results indicated significant improvements over using FCN only in terms of both processing speed (16 FPS vs. 8 FPS) and segmentation result statistics. Five clinical cases on patients have also been provided to showcase the quantitative analysis results using the proposed method. Conclusion: The proposed method guarantees a robust and fast processing of laryngoscopic videos. Measurements of glottic angles and supraglottic index showed distinctive patterns in the provided clinical cases. Significance: The proposed automated and objective method extracts important temporal laryngeal movement information, which can be used to aid laryngeal closure diagnosis.

KW - convolutional neural networks

KW - detection

KW - Laryngeal obstruction

KW - segmentation

KW - singular spectrum analysis

U2 - 10.1109/TBME.2018.2867636

DO - 10.1109/TBME.2018.2867636

M3 - Journal article

C2 - 30176579

AN - SCOPUS:85052622569

SN - 0018-9294

VL - 66

SP - 1127

EP - 1136

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

IS - 4

M1 - 8450618

ER -

Quantification and Analysis of Laryngeal Closure from Endoscopic Videos

Abstract

Adgang til dokumentet

Fingeraftryk

Citationsformater