Exploring Real-Time Tracking of Vocal Fold Polyps in Video-Stroboscopy Using Deep Learning.

Λεπτομέρειες βιβλιογραφικής εγγραφής
Τίτλος:	Exploring Real-Time Tracking of Vocal Fold Polyps in Video-Stroboscopy Using Deep Learning.
Συγγραφείς:	Kaza S; Cornell Tech, New York, New York, USA., Mohanty AS; Center for Computational and Integrative Biology, Rutgers University, Camden, New Jersey, USA., Serpedin A; Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA., Yau J; Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA., Kim YE; Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA., Kutler RB; Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA., Elemento O; Englander Institute for Precision Medicine, Weill Cornell Medicine, New York, New York, USA., Sulica L; Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA., Khosravi P; 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., Rameau A; Department of Otolaryngology-Head and Neck Surgery, Sean Parker Institute for the Voice, Weill Cornell Medicine, New York, New York, USA.
Πηγή:	The Laryngoscope [Laryngoscope] 2026 Jun; Vol. 136 (6), pp. 2511-2518. Date of Electronic Publication: 2026 Feb 02.
Τύπος έκδοσης:	Journal Article; Research Support, N.I.H., Extramural
Γλώσσα:	English
Στοιχεία περιοδικού:	Publisher: Wiley-Blackwell Country of Publication: United States NLM ID: 8607378 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1531-4995 (Electronic) Linking ISSN: 0023852X NLM ISO Abbreviation: Laryngoscope Subsets: MEDLINE
Imprint Name(s):	Publication: <2009- >: Philadelphia, PA : Wiley-Blackwell Original Publication: St. Louis, Mo. : [s.n., 1896-
Ιατρικοί όροι (MeSH):	Vocal Cords/diagnostic imaging , Vocal Cords/pathology , Stroboscopy/methods , Polyps/diagnosis , Polyps/diagnostic imaging , Video Recording/methods , Laryngeal Diseases/diagnosis , Deep Learning, Laryngoscopy/methods ; Humans ; Retrospective Studies ; Detection Algorithms ; Algorithms
Περίληψη:	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 F1 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 F1 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. (© 2026 The American Laryngological, Rhinological and Otological Society, Inc.)
References:	A. Esteva, K. Chou, S. Yeung, et al., “Deep Learning‐Enabled Medical Computer Vision,” npj Digital Medicine 4, no. 1 (2021): 5, https://doi.org/10.1038/s41746‐020‐00376‐2. E. Elyan, P. Vuttipittayamongkol, P. Johnston, et al., “Computer Vision and Machine Learning for Medical Image Analysis: Recent Advances, Challenges, and Way Forward,” Artificial Intelligence in Surgery 2, no. 1 (2022): 24–45. P. Yao, D. Witte, H. Gimonet, et al., “Automatic Classification of Informative Laryngoscopic Images Using Deep Learning,” Laryngoscope Investigative Otolaryngology 7, no. 2 (2022): 460–466, https://doi.org/10.1002/lio2.754. Y. E. Kim, A. Serpedin, P. Periyakoil, D. German, and A. Rameau, “Sociodemographic Reporting in Videomics Research: A Review of Practices in Otolaryngology—Head and Neck Surgery,” European Archives of Oto‐Rhino‐Laryngology 281, no. 11 (2024): 6047–6056, https://doi.org/10.1007/s00405‐024‐08659‐0. P. Yao, B. Geffen, H. McCrary, et al., “Measurements of the Pediatric Cartilaginous Eustachian Tube: Implications for Balloon Dilation,” Laryngoscope 133, no. 2 (2022): 396–402, https://doi.org/10.1002/lary.30113. H. Xiong, P. Lin, J. G. Yu, et al., “Computer‐Aided Diagnosis of Laryngeal Cancer via Deep Learning Based on Laryngoscopic Images,” eBioMedicine 48 (2019): 92–99, https://doi.org/10.1016/j.ebiom.2019.08.027. J. Ren, X. Jing, J. Wang, et al., “Automatic Recognition of Laryngoscopic Images Using a Deep‐Learning Technique,” Laryngoscope 130, no. 11 (2020): E686–E693, https://doi.org/10.1002/lary.28544. Y. Bensoussan, E. B. Vanstrum, M. M. Johns, 3rd, and A. Rameau, “Artificial Intelligence and Laryngeal Cancer: From Screening to Prognosis: A State of the Art Review,” Otolaryngology—Head and Neck Surgery 168, no. 3 (2023): 319–329, https://doi.org/10.1177/01945998221149713. P. Yao, M. Usman, Y. H. Chen, et al., “Applications of Artificial Intelligence to Office Laryngoscopy: A Scoping Review,” Laryngoscope 132, no. 10 (2022): 1993–2016, https://doi.org/10.1002/lary.29886. R. Yang and Y. Yu, “Artificial Convolutional Neural Network in Object Detection and Semantic Segmentation for Medical Imaging Analysis,” Frontiers in Oncology 11 (2021): 638182, https://doi.org/10.3389/fonc.2021.638182. C. Albuquerque, R. Henriques, and M. Castelli, “Deep Learning‐Based Object Detection Algorithms in Medical Imaging: Systematic Review,” Heliyon 11, no. 1 (2025): e00000. M. G. Ragab, S. J. Abdulkadir, A. Muneer, et al., “A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023),” IEEE Access 12 (2024): 57815–57836, https://doi.org/10.1109/ACCESS.2024.3381234. K. He, G. Gkioxari, P. Dollár, and R. Girshick, “Mask R‐CNN,” in Proceedings of the IEEE International Conference on Computer Vision (IEEE, 2017), 2961–2969, https://doi.org/10.1109/ICCV.2017.322. R. Girshick, “Fast R‐CNN,” in Proceedings of the IEEE International Conference on Computer Vision (IEEE, 2015), 1440–1448, https://doi.org/10.1109/ICCV.2015.169. S. Ren, K. He, R. Girshick, and J. Sun, “Faster R‐CNN: Towards Real‐Time Object Detection With Region Proposal Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence 39, no. 6 (2017): 1137–1149, https://doi.org/10.1109/TPAMI.2016.2577031. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, “You Only Look Once: Unified, Real‐Time Object Detection,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE, 2016), 779–788, https://doi.org/10.1109/CVPR.2016.91. X. Yang, E. Song, G. Ma, et al., “Yolo‐Ob: An Improved Anchor‐Free Real‐Time Multiscale Colon Polyp Detector in Colonoscopy,” Biomedical Signal Processing and Control 103 (2025): 107326, https://doi.org/10.1016/j.bspc.2024.107326. I. Pacal, A. Karaman, D. Karaboga, et al., “An Efficient Real‐Time Colonic Polyp Detection With YOLO Algorithms Trained by Using Negative Samples and Large Datasets,” Computers in Biology and Medicine 141 (2022): 105031, https://doi.org/10.1016/j.compbiomed.2021.105031. Y. Liu, “Real‐Time Multi‐Class Detection of Colorectal Polyps Based on the Colon‐YOLO Network,” Alexandria Engineering Journal 127 (2025): 595–605, https://doi.org/10.1016/j.aej.2025.05.045. I. Pacal and D. Karaboga, “A Robust Real‐Time Deep Learning Based Automatic Polyp Detection System,” Computers in Biology and Medicine 134 (2021): 104519, https://doi.org/10.1016/j.compbiomed.2021.104519. A. Amer, A. Hussein, N. Ahmadvand, et al., “Generalized Polyp Detection From Colonoscopy Frames Using Proposed Edf‐yolo8 Network,” in Cancer Prevention, Detection, and Intervention, ed. S. Ali , F. van der Sommen , B. W. Papież , N. Ghatwary , Y. Jin , and I. Kolenbrander (Springer Nature Switzerland, 2025), 124–132, https://doi.org/10.1007/978‐3‐031‐73376‐5_12. J. Wan, W. Zhu, B. Chen, L. Wang, K. Chang, and X. Meng, “CRH‐YOLO for Precise and Efficient Detection of Gastrointestinal Polyps,” Scientific Reports 14, no. 1 (2024): 30033, https://doi.org/10.1038/s41598‐024‐81842‐9. S. Soleymanjahi, J. Huebner, L. Elmansy, et al., “Artificial Intelligence‐Assisted Colonoscopy for Polyp Detection: A Systematic Review and Meta‐Analysis,” Annals of Internal Medicine 177, no. 12 (2024): 1652–1663, https://doi.org/10.7326/ANNALS‐24‐00981. C. Hassan, M. Spadaccini, Y. Mori, et al., “Real‐Time Computer‐Aided Detection of Colorectal Neoplasia During Colonoscopy: A Systematic Review and Meta‐Analysis,” Annals of Internal Medicine 176, no. 9 (2023): 1209–1220, https://doi.org/10.7326/M22‐3678. M. Spadaccini, M. Menini, D. Massimi, et al., “Ai and Polyp Detection During Colonoscopy,” Cancers 17, no. 5 (2025): 797, https://doi.org/10.3390/cancers17050797. L. Wu, Z. Hu, Y. Ji, P. Luo, and S. Zhang, “Multi‐Frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial‐Temporal Feature Transformation,” preprint, arXiv, July 2021, https://doi.org/10.48550/arXiv.2107.03609. Y. Wang, W. Tavanapong, J. Wong, J. H. Oh, and P. C. de Groen, “Polyp‐Alert: Near Real‐Time Feedback During Colonoscopy,” Computer Methods and Programs in Biomedicine 120, no. 3 (2015): 164–179, https://doi.org/10.1016/j.cmpb.2015.04.002. C. Baldini, L. Migliorelli, D. Berardini, et al., “Improving Real‐Time Detection of Laryngeal Lesions in Endoscopic Images Using a Decoupled Super‐Resolution Enhanced YOLO,” Computer Methods and Programs in Biomedicine 260 (2025): 108539. D. J. Wellenstein, J. Woodburn, H. A. Marres, and G. B. van den Broek, “Detection of Laryngeal Carcinoma During Endoscopy Using Artificial Intelligence,” Head & Neck 45, no. 9 (2023): 2217–2226. G. H. Kim, Y. J. Hwang, H. Lee, E. S. Sung, and K. W. Nam, “Convolutional Neural Network‐Based Vocal Cord Tumor Classification Technique for Home‐Based Self‐Prescreening Purpose,” BioMedical Engineering OnLine 22, no. 1 (2023): 81. P. Yao, D. Witte, A. German, et al., “A Deep Learning Pipeline for Automated Classification of Vocal Fold Polyps in Flexible Laryngoscopy,” European Archives of Oto‐Rhino‐Laryngology 281, no. 4 (2024): 2055–2062, https://doi.org/10.1007/s00405‐023‐08190‐8. Ultralytics, “Coco,” accessed April 14, 2025, https://docs.ultralytics.com/datasets/detect/coco. Ultralytics, “Yolo11,” accessed April 21, 2025, https://docs.ultralytics.com/models/yolo11. Ultralytics, “Yolo12,” accessed April 14, 2025, https://docs.ultralytics.com/models/yolo12. Ultralytics, “Train,” accessed April 14, 2025, https://docs.ultralytics.com/modes/train. R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad‐CAM: Visual Explanations From Deep Networks via Gradient‐Based Localization,” preprint, arXiv, December 2019, https://doi.org/10.48550/arXiv.1610.02391. Medium, “YOLO12: Redefining Object Detection With an Attention‐Centric Architecture (Watt FSN Tech. #),” February 2025, https://medium.com/@felixsam922/yolo12‐redefining‐object‐detection‐with‐an‐attention‐centric‐architecture‐a0029fac00a3. H. Ye, H. Miao, J. Liu, D. Wang, and H. Li, “Temporal Context Framework for Endoscopy Artefact Segmentation and Detection,” 2022, https://openreview.net/forum?id=dBQOJVkc1D. J. H. Kim, H. S. Jung, S. E. Lee, J. U. Hou, and Y. S. Kwon, “Improving Difficult Direct Laryngoscopy Prediction Using Deep Learning and Minimal Image Analysis: A Single‐Center Prospective Study,” Scientific Reports 14, no. 1 (2024): 14209, https://doi.org/10.1038/s41598‐024‐65060‐x. M. Xia, C. Jin, Y. Zheng, et al., “Deep Learning‐Based Facial Analysis for Predicting Difficult Videolaryngoscopy: A Feasibility Study,” Anaesthesia 79, no. 4 (2024): 399–409, https://doi.org/10.1111/anae.16194. R. L. Draelos and L. Carin, “Use HiResCAM Instead of Grad‐CAM for Faithful Explanations of Convolutional Neural Networks,” preprint, arXiV, November 2021, https://doi.org/10.48550/arXiv.2011.08891. G. Urban, P. Tripathi, T. Alkayali, et al., “Deep Learning Localizes and Identifies Polyps in Real Time With 96% Accuracy in Screening Colonoscopy,” Gastroenterology 155, no. 4 (2018): 1069–1078, https://doi.org/10.1053/j.gastro.2018.06.037. M. Lalinia and A. Sahafi, “Colorectal Polyp Detection in Colonoscopy Images Using YOLO‐V8 Network,” Signal, Image and Video Processing 18, no. 3 (2024): 2047–2058, https://doi.org/10.1007/s11760‐023‐02835‐1. M. Misawa, S. E. Kudo, Y. Mori, et al., “Artificial Intelligence‐Assisted Polyp Detection for Colonoscopy: Initial Experience,” Gastroenterology 154, no. 8 (2018): 2027–2029, https://doi.org/10.1053/j.gastro.2018.04.003. P. Wang, X. G. Liu, M. Kang, et al., “Artificial Intelligence Empowers the Second‐Observer Strategy for Colonoscopy: A Randomized Clinical Trial,” Gastroenterology Report 11 (2023): goac081, https://doi.org/10.1093/gastro/goac081.
Grant Information:	K76 AG079040 United States AG NIA NIH HHS; OT2 OD032720 United States OD NIH HHS
Contributed Indexing:	Keywords: artificial intelligence; object detection; stroboscopy; vocal fold polyp
Entry Date(s):	Date Created: 20260202 Date Completed: 20260706 Latest Revision: 20260729
Update Code:	20260729
PubMed Central ID:	PMC13186207
DOI:	10.1002/lary.70396
PMID:	41623203
Βάση Δεδομένων:	MEDLINE

Περιγραφή
ISSN:	1531-4995
DOI:	10.1002/lary.70396