Orthogonal Region Selection Network for Laryngeal Closure Detection in Laryngoscopy Videos

Wang, Yang Yang; Hamad, Ali; Lever, Teresa E.; Bunyak, Filiz

doi:10.1109/embc44109.2020.9176149

Cited by 3 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Others use various techniques to analyze glottic dynamics, including VF tracking and glottic segmentation 22,24,27,31,33,37,38,41 . Automated segmentation is used in low‐speed videoendoscopy to analyze glottic movement in transnasal endoscopy videos and to detect laryngeal adductor reflex events 29,40,43,44 . Estimation of glottic midline can facilitate assessment of oscillatory symmetry.…”

Section: Discussionmentioning

confidence: 99%

Development and Application of Automated Vocal Fold Tracking Software in a Rat Surgical Model

Pennington‐FitzGerald,

Joshi,

Honzel

et al. 2023

The Laryngoscope

View full text Add to dashboard Cite

ObjectiveThe rat is a widely used model for studying vocal fold (VF) function after recurrent laryngeal nerve injury, but common techniques for evaluating rat VF motion remain subjective and imprecise. To address this, we developed a software package, called RatVocalTracker1.0 (RVT1.0), to quantify VF motion and tested it on rats with iatrogenic unilateral vocal fold paralysis (VFP).MethodsA deep neural network was trained to identify the positions of the VFs and arytenoid cartilages (ACs) in transoral laryngoscope videos of the rat glottis. Software was developed to estimate glottic midline, VF displacement, VF velocity, and AC angle. The software was applied to laryngoscope videos of adult rats before and after right recurrent and superior laryngeal nerve transection (N = 15; 6M, 9F). All software calculated metrics were compared before and after injury and validated against manually calculated metrics.ResultsRVT1.0 accurately tracked and quantified VF displacement, VF velocity, and AC angle. Significant differences were found before and after surgery for all RVT1.0 calculated metrics. There was strong agreement between programmatically and manually calculated measures. Automated analysis was also more efficient than nearly all manual methods.ConclusionThis approach provides fast, accurate assessment of VF motion in rats with minimal labor and allows for quantitative comparison of lateral differences in movement. Through this novel analysis method, we can differentiate healthy movement from unilateral VFP. RVT1.0 is open‐source and will be a valuable tool for researchers using the rat model for laryngology research.Level of EvidenceNA Laryngoscope, 2023

show abstract

Section: Discussionmentioning

confidence: 99%

Development and Application of Automated Vocal Fold Tracking Software in a Rat Surgical Model

Pennington‐FitzGerald,

Joshi,

Honzel

et al. 2023

The Laryngoscope

View full text Add to dashboard Cite

show abstract

“…Hamad et al employed an ensemble of deep cascades for the detection of LAR events 9 . Wang et al proposed a combination of convolutional neural networks to automatically detect the open or closed state of the glottis 10 . Please also see the review by Andrade‐Miranda et al for further methods for computational, image‐based glottal motion analysis 45 .…”

Section: Discussionmentioning

confidence: 99%

“…9 Wang et al proposed a combination of convolutional neural networks to automatically detect the open or closed state of the glottis. 10 Please also see the review by Andrade-Miranda et al for further methods for computational, image-based glottal motion analysis. 45 A combination of the algorithms presented in this work with a recurrent neural network, as proposed by G omez for subglottal pressure estimation 46 and by Fehling et al for glottis and VF segmentation, 47 could further increase reliability and accuracy.…”

Section: Discussionmentioning

confidence: 99%

“…However, their use was thus far restricted by the amount of experience required to apply the available methods for LAR evaluation and by a limited reproducibility of these methods. Recent developments in the field of LAR analysis focus on a more controlled reflex stimulation with a calibrated aesthesiometer 5,6 or standardized air bursts, 7 and on computer‐assisted approaches for optical LAR assessment 7–10 . The LAR can also be evoked by droplet impact; this is the principle of Microdroplet Impulse Testing of the LAR , or MIT‐LAR for short 11 .…”

Section: Introductionmentioning

confidence: 99%

“…Recent developments in the field of LAR analysis focus on a more controlled reflex stimulation with a calibrated aesthesiometer 5,6 or standardized air bursts, 7 and on computer-assisted approaches for optical LAR assessment. [7][8][9][10] The LAR can also be evoked by droplet impact; this is the principle of Microdroplet Impulse Testing of the LAR, or MIT-LAR for short. 11 A droplet is similar to the physiological triggers of the LAR, such as food particles or saliva, and avoids the invasiveness associated with electrical methods.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Computational Analysis of the Droplet‐Stimulated Laryngeal Adductor Reflex in High‐Speed Sequences

et al. 2022

View full text Add to dashboard Cite

Objectives/Hypothesis The laryngeal adductor reflex (LAR) is an important protective mechanism of the airways. Its physiology is still not completely understood. The available methods for LAR evaluation offer limited reproducibility and/or rely on subjective interpretation. A new approach, termed Microdroplet Impulse Testing of the LAR (MIT‐LAR), was recently introduced. Here, the LAR is elicited by a droplet and a laryngoscopic high‐speed recording is acquired simultaneously. In the present work, image‐processing algorithms for autonomous MIT‐LAR sequence analysis were developed. This allowed the automated approximation of kinematic LAR parameters in humans. Study Design Development and testing of computational methods. Methods Computational image processing enabled the autonomous estimation of the glottal area, the glottal angle, and the vocal fold edge distance in MIT‐LAR sequences. A suitable analytical representation of these glottal parameters allowed the extraction of seven relevant LAR parameters. The obtained values were compared to the literature. Results A generalized logistic function showed the highest average goodness of fit among four different analytical approaches for each of the glottal parameters. Autonomous sequence analysis yielded bilateral LAR response latencies of (229 ± 116) ms and (182 ± 60) ms for cases of complete and incomplete glottal closure, respectively. The initial/average/maximum angular vocal fold adduction velocity was estimated at (157 ± 115) °s−1/(891 ± 516) °s−1/(929 ± 583) °s−1 and (88 ± 53) °s−1/(421 ± 221) °s−1/(520 ± 238) °s−1 for complete and incomplete glottal closure, respectively. Conclusion The automated extraction of LAR parameters from laryngoscopic high‐speed sequences can potentially increase the objectiveness of optical LAR characterization and reduce the associated workload. The proposed methods may thus be helpful for future research on this vital reflex. Level of Evidence NA Laryngoscope, 132:2412–2419, 2022

show abstract

LARNet-STC: Spatio-temporal orthogonal region selection network for laryngeal closure detection in endoscopy videos

Wang

Hamad

Palaniappan

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

Orthogonal Region Selection Network for Laryngeal Closure Detection in Laryngoscopy Videos

Cited by 3 publications

References 26 publications

Development and Application of Automated Vocal Fold Tracking Software in a Rat Surgical Model

Development and Application of Automated Vocal Fold Tracking Software in a Rat Surgical Model

Computational Analysis of the Droplet‐Stimulated Laryngeal Adductor Reflex in High‐Speed Sequences

LARNet-STC: Spatio-temporal orthogonal region selection network for laryngeal closure detection in endoscopy videos

Contact Info

Product

Resources

About