EUVIMEDEUVIMED entdecken
Crossref

Computer Vision Model to Detect and Classify Laryngomalacia From Pediatric Video Nasolaryngoscopy

Yasmine Madan iD, Zeyna Nida Copty, Zejia Chen, Karan S Chahal, Paul Esemu-Ezewu, Nikolaus E Wolter iD, Evan J Propst, Clyde Matava, Jennifer M Siu iD

The Laryngoscope · 2026

DOI: 10.1002/lary.70439 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Laryngoscope, 2026. Verfasst von Yasmine Madan und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Otolaryngology-Head and Neck Surgery, Hospital for Sick Children, University of Toronto, Toronto, Ontario, Canada. Hauptthemen laut MEDLINE: Laryngomalacia, Laryngoscopy. Die Arbeit nennt 24 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

Laryngomalacia diagnosis and subtype classification is typically based on flexible nasolaryngoscopy, but this can be challenging, particularly for clinicians who see it infrequently. Infant movement may also prolong the procedure. Automated computer vision (CV) assessment of video nasolaryngoscopy may improve diagnostic accuracy, shorten procedure time, and reduce infant discomfort. The aim was to develop a CV model to segment laryngeal anatomy, differentiate between normal and laryngomalacia cases, and classify laryngomalacia type (1, 2, or 3).

Methods

A total of 241 pediatric nasolaryngoscopy videos were obtained from The Hospital for Sick Children between August 2023 and March 2025 from participants < 1 year old. Videos were annotated and randomly assigned to a training set [192 (80%)] and testing set [49 (20%)]. Three binary classification models (fine‐tuned for feature extraction) were developed to predict laryngomalacia and classify its type. CV predictions were compared with diagnoses made by three staff otolaryngologists.

Results

The CV model's Dice similarity coefficient for laryngeal anatomy segmentation was 0.86 (95% CI: 0.85–0.88). The model differentiated normal from laryngomalacia cases with an accuracy of 0.90 and predicted type 1 and type 2 laryngomalacia with accuracies of 0.86 and 0.90, respectively. A type 3 model was not developed due to insufficient cases.

Conclusion

The CV model successfully segmented laryngeal anatomy, differentiated normal from laryngomalacia cases, and classified type 1 and 2 laryngomalacia from pediatric video nasolaryngoscopy. With dataset expansion, further algorithm refinement, and external validation, this model may serve as a clinical decision support tool in the future. Level of Evidence 3.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

LaryngomalaciaLaryngoscopyHumansInfantVideo RecordingFemaleMaleLarynx

Stichwörter der Autor:innen

computer visionlaryngomalacialaryngoscopypediatric

Autor:innen und Institutionen

  • Department of Otolaryngology-Head and Neck Surgery, Hospital for Sick Children, University of Toronto, Toronto, Ontario, Canada.
  • Department of Anesthesia and Pain Medicine, Hospital for Sick Children, University of Toronto, Toronto, Ontario, Canada.

ORCID-Profile: Yasmine Madan, Nikolaus E Wolter, Jennifer M Siu

Zitieren

APA

Madan, Y., Copty, Z. N., Chen, Z., Chahal, K. S., Esemu-Ezewu, P., Wolter, N. E., Propst, E. J., Matava, C., & Siu, J. M. (2026). Computer Vision Model to Detect and Classify Laryngomalacia From Pediatric Video Nasolaryngoscopy. The Laryngoscope. https://doi.org/10.1002/lary.70439

Vancouver

Madan Y, Copty ZN, Chen Z, Chahal KS, Esemu-Ezewu P, Wolter NE, et al. Computer Vision Model to Detect and Classify Laryngomalacia From Pediatric Video Nasolaryngoscopy. The Laryngoscope. 2026. doi:10.1002/lary.70439

BibTeX
@article{Madan2026,
  author = {Madan, Yasmine and Copty, Zeyna Nida and Chen, Zejia and Chahal, Karan S and Esemu-Ezewu, Paul and Wolter, Nikolaus E and Propst, Evan J and Matava, Clyde and Siu, Jennifer M},
  title = {Computer Vision Model to Detect and Classify Laryngomalacia From Pediatric Video Nasolaryngoscopy},
  journal = {The Laryngoscope},
  year = {2026},
  doi = {10.1002/lary.70439}
}
Kostenlos starten →