{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T09:16:51Z","timestamp":1778923011559,"version":"3.51.4"},"reference-count":45,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T00:00:00Z","timestamp":1769990400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100015326","name":"Common Fund","doi-asserted-by":"publisher","award":["OT2 OD032720"],"award-info":[{"award-number":["OT2 OD032720"]}],"id":[{"id":"10.13039\/100015326","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["K76 AG079040"],"award-info":[{"award-number":["K76 AG079040"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["The Laryngoscope"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>\n                      To develop and evaluate a deep learning object detection system for identifying vocal fold polyps in stroboscopic video frames using You Only Look Once (\n                      <jats:styled-content style=\"fixed-case\">YOLO<\/jats:styled-content>\n                      ), and to assess the added benefit of temporal tracking on detection performance.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>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\u2010tuned to detect the polyps in the frames. A temporal tracking algorithm was further developed to propagate missed detections across adjacent frames.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      YOLO12 outperformed YOLO11 across all metrics. On the hold\u2010out test set, YOLO12 reached a precision of 83.1% and an\n                      <jats:italic>F<\/jats:italic>\n                      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\n                      <jats:italic>F<\/jats:italic>\n                      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\u2009frames per second (fps), close to real time (30\u2009fps).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>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\u2010time AI\u2010assisted detection of vocal fold lesions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Level of Evidence<\/jats:title>\n                    <jats:p>4.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/lary.70396","type":"journal-article","created":{"date-parts":[[2026,2,2]],"date-time":"2026-02-02T10:52:59Z","timestamp":1770029579000},"page":"2511-2518","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Real\u2010Time Tracking of Vocal Fold Polyps in Video\u2010Stroboscopy Using Deep Learning"],"prefix":"10.1002","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3401-9645","authenticated-orcid":false,"given":"Sanjana","family":"Kaza","sequence":"first","affiliation":[{"name":"Cornell Tech  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinita S.","family":"Mohanty","sequence":"additional","affiliation":[{"name":"Center for Computational and Integrative Biology Rutgers University  Camden New Jersey USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aisha","family":"Serpedin","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Sean Parker Institute for the Voice, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2953-835X","authenticated-orcid":false,"given":"Jenny","family":"Yau","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Sean Parker Institute for the Voice, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7201-7545","authenticated-orcid":false,"given":"Yeo Eun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Sean Parker Institute for the Voice, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5202-6888","authenticated-orcid":false,"given":"Rachel B.","family":"Kutler","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Sean Parker Institute for the Voice, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Elemento","sequence":"additional","affiliation":[{"name":"Englander Institute for Precision Medicine, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8989-2073","authenticated-orcid":false,"given":"Lucian","family":"Sulica","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Sean Parker Institute for the Voice, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pegah","family":"Khosravi","sequence":"additional","affiliation":[{"name":"Department of Clinical Sciences, College of Medicine University of Central Florida  Orlando Florida USA"},{"name":"Department of Computer Science Institute for Artificial Intelligence, University of Central Florida  Orlando Florida USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1543-2634","authenticated-orcid":false,"given":"Ana\u00efs","family":"Rameau","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery Sean Parker Institute for the Voice, Weill Cornell Medicine  New York New York USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,2,2]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746\u2010020\u201000376\u20102"},{"issue":"1","key":"e_1_2_9_3_1","first-page":"24","article-title":"Computer Vision and Machine Learning for Medical Image Analysis: Recent Advances, Challenges, and Way Forward","volume":"2","author":"Elyan E.","year":"2022","journal-title":"Artificial Intelligence in Surgery"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/lio2.754"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00405\u2010024\u201008659\u20100"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.30113"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2019.08.027"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.28544"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1177\/01945998221149713"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.29886"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.638182"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e41137"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3381234"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107326"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.105031"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2025.05.045"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104519"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73376-5_12"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201081842\u20109"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.7326\/ANNALS\u201024\u201000981"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.7326\/M22\u20103678"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers17050797"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"L.Wu Z.Hu Y.Ji P.Luo andS.Zhang \u201cMulti\u2010Frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial\u2010Temporal Feature Transformation \u201dpreprint arXiv July 2021 https:\/\/doi.org\/10.48550\/arXiv.2107.03609.","DOI":"10.1007\/978-3-030-87240-3_29"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2015.04.002"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108539"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1002\/hed.27441"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-023-01139-2"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00405\u2010023\u201008190\u20108"},{"key":"e_1_2_9_33_1","unstructured":"Ultralytics \u201cCoco \u201daccessed April 14 2025 https:\/\/docs.ultralytics.com\/datasets\/detect\/coco."},{"key":"e_1_2_9_34_1","unstructured":"Ultralytics \u201cYolo11 \u201daccessed April 21 2025 https:\/\/docs.ultralytics.com\/models\/yolo11."},{"key":"e_1_2_9_35_1","unstructured":"Ultralytics \u201cYolo12 \u201daccessed April 14 2025 https:\/\/docs.ultralytics.com\/models\/yolo12."},{"key":"e_1_2_9_36_1","unstructured":"Ultralytics \u201cTrain \u201daccessed April 14 2025 https:\/\/docs.ultralytics.com\/modes\/train."},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"R. R.Selvaraju M.Cogswell A.Das R.Vedantam D.Parikh andD.Batra \u201cGrad\u2010CAM: Visual Explanations From Deep Networks via Gradient\u2010Based Localization \u201dpreprint arXiv December 2019 https:\/\/doi.org\/10.48550\/arXiv.1610.02391.","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_2_9_38_1","unstructured":"Medium \u201cYOLO12: Redefining Object Detection With an Attention\u2010Centric Architecture (Watt FSN Tech. #) \u201dFebruary 2025 https:\/\/medium.com\/@felixsam922\/yolo12\u2010redefining\u2010object\u2010detection\u2010with\u2010an\u2010attention\u2010centric\u2010architecture\u2010a0029fac00a3."},{"key":"e_1_2_9_39_1","unstructured":"H.Ye H.Miao J.Liu D.Wang andH.Li \u201cTemporal Context Framework for Endoscopy Artefact Segmentation and Detection \u201d2022 https:\/\/openreview.net\/forum?id=dBQOJVkc1D."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201065060\u2010x"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1111\/anae.16194"},{"key":"e_1_2_9_42_1","unstructured":"R. L.DraelosandL.Carin \u201cUse HiResCAM Instead of Grad\u2010CAM for Faithful Explanations of Convolutional Neural Networks \u201dpreprint arXiV November 2021 https:\/\/doi.org\/10.48550\/arXiv.2011.08891."},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2018.06.037"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760\u2010023\u201002835\u20101"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1053\/j.gastro.2018.04.003"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1093\/gastro\/goac081"}],"container-title":["The Laryngoscope"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lary.70396","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/lary.70396","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/lary.70396","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T08:47:43Z","timestamp":1778921263000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/lary.70396"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,2]]},"references-count":45,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1002\/lary.70396"],"URL":"https:\/\/doi.org\/10.1002\/lary.70396","archive":["Portico"],"relation":{},"ISSN":["0023-852X","1531-4995"],"issn-type":[{"value":"0023-852X","type":"print"},{"value":"1531-4995","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,2]]},"assertion":[{"value":"2025-07-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}