Exploring Real‐Time Tracking of Vocal Fold Polyps in Video‐Stroboscopy Using Deep Learning
The Laryngoscope · 2026
DOI: 10.1002/lary.70396 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Laryngoscope, 2026. Verfasst von Sanjana Kaza und 9 weiteren Autor:innen. Beteiligte Einrichtung: Cornell Tech, New York, New York, USA. Hauptthemen laut MEDLINE: Deep Learning, Vocal Cords, Stroboscopy, Polyps. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIA NIH HHS, NIH HHS, Common Fund.
Abstract (Originalsprache)
Objective
To develop and evaluate a deep learning object detection system for identifying vocal fold polyps in stroboscopic video frames using You Only Look Once ( YOLO ), and to assess the added benefit of temporal tracking on detection performance.
Methods
A retrospective dataset of 12,742 annotated frames from 55 laryngoscopy video recordings was annotated with bounding boxes identifying vocal fold polyps. Pretrained YOLO11 and YOLO12 models were fine‐tuned to detect the polyps in the frames. A temporal tracking algorithm was further developed to propagate missed detections across adjacent frames.
Results
YOLO12 outperformed YOLO11 across all metrics. On the hold‐out test set, YOLO12 reached a precision of 83.1% and an F 1 score of 67.6%, with a mean average precision at 0.5 (mAP@0.5) of 64.1%. By comparison, YOLO11 achieved a precision of 67.3% and an F 1 score of 56.2%, with a mAP@0.5 of 56.0%. Incorporating temporal tracking increased mAP@0.5 to 70.4% with YOLO 12, while maintaining a detection speed of 21.4 frames per second (fps), close to real time (30 fps).
Conclusions
Using YOLO 12 for vocal fold polyp detection in stroboscopy was enhanced with temporal tracking, achieving a mAP@0.5 of 70.4% with near real time performance. These results demonstrate the potential of real‐time AI‐assisted detection of vocal fold lesions. Level of Evidence 4.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cornell Tech, New York, New York, USA.
- Center for Computational and Integrative Biology, Rutgers University, Camden, New Jersey, USA.
- Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA.
- Englander Institute for Precision Medicine, Weill Cornell Medicine, New York, New York, USA.
- Department of Clinical Sciences, College of Medicine, University of Central Florida, Orlando, Florida, USA.
- Department of Computer Science, Institute for Artificial Intelligence, University of Central Florida, Orlando, Florida, USA.
ORCID-Profile: Sanjana Kaza, Jenny Yau, Yeo Eun Kim, Rachel B Kutler, Lucian Sulica, Anaïs Rameau
Förderung
- NIA NIH HHS
- NIH HHS
- Common Fund
- National Institute on Aging
Zitieren
APA
Kaza, S., Mohanty, A. S., Serpedin, A., Yau, J., Kim, Y. E., Kutler, R. B., Elemento, O., Sulica, L., Khosravi, P., & Rameau, A. (2026). Exploring Real‐Time Tracking of Vocal Fold Polyps in Video‐Stroboscopy Using Deep Learning. The Laryngoscope. https://doi.org/10.1002/lary.70396
Vancouver
Kaza S, Mohanty AS, Serpedin A, Yau J, Kim YE, Kutler RB, et al. Exploring Real‐Time Tracking of Vocal Fold Polyps in Video‐Stroboscopy Using Deep Learning. The Laryngoscope. 2026. doi:10.1002/lary.70396
BibTeX
@article{Kaza2026,
author = {Kaza, Sanjana and Mohanty, Abhinita S and Serpedin, Aisha and Yau, Jenny and Kim, Yeo Eun and Kutler, Rachel B and Elemento, Olivier and Sulica, Lucian and Khosravi, Pegah and Rameau, Anaïs},
title = {Exploring Real‐Time Tracking of Vocal Fold Polyps in Video‐Stroboscopy Using Deep Learning},
journal = {The Laryngoscope},
year = {2026},
doi = {10.1002/lary.70396}
}
EUVIMED