{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:46:56Z","timestamp":1791913616958,"version":"4.3.4"},"reference-count":44,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T00:00:00Z","timestamp":1752105600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Mol. Biosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Laryngeal high-speed video (HSV) is a widely used technique for diagnosing laryngeal diseases. Among various analytical approaches, segmentation of glottis regions has proven effective in evaluating vocal fold vibration patterns and detecting related disorders. However, the specific task of vocal fold segmentation remains underexplored in the literature.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we propose a novel automatic vocal fold segmentation system that relies solely on glottis information. The system leverages prompt engineering techniques tailored for the Segment Anything Model (SAM). Specifically, vocal fold-related features are extracted from U-Net-generated glottis masks, which are enhanced via brightness contrast adjustment and morphological closing. A coarse bounding box of the laryngeal region is also produced using the YOLO-v5 model. These components are integrated to form a bounding box prompt. Furthermore, a point prompt is derived by identifying local extrema in the first derivative of grayscale intensity along lines intersecting the glottis, offering additional guidance on vocal fold locations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental evaluation demonstrates that our method, which does not require labeled vocal fold training data, achieves competitive segmentation performance. The proposed approach reaches a Dice Coefficient of 0.91, which is comparable to fully supervised methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>\n                      Our results suggest that it is feasible to achieve accurate vocal fold segmentation using only glottis-based prompts and without supervised vocal fold annotations. Extracted features on the resulting masks further validate the effectiveness of the proposed system. To encourage further research, we release our code at:\n                      <jats:ext-link>https:\/\/github.com\/yucongzh\/Laryngoscopic-Image-Segmentation-Toolkit<\/jats:ext-link>\n                      .\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmolb.2025.1616271","type":"journal-article","created":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T04:12:11Z","timestamp":1752120731000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["An automatic laryngoscopic image segmentation system based on SAM prompt engineering: from glottis annotation to vocal fold segmentation"],"prefix":"10.3389","volume":"12","author":[{"given":"Yucong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,10]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"E219","DOI":"10.1002\/lary.28669","article-title":"An open-source computer vision tool for automated vocal fold tracking from videoendoscopy","volume":"131","author":"Adamian","year":"2021","journal-title":"Laryngoscope"},{"key":"B2","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1016\/j.ymssp.2013.06.036","article-title":"Uncertainty quantification of voice signal production mechanical model and experimental updating","volume":"40","author":"Cataldo","year":"2013","journal-title":"Mech. Syst. Signal Process."},{"key":"B3","doi-asserted-by":"publisher","first-page":"2793","DOI":"10.1002\/lary.31245","article-title":"Clinical and anatomical variation during assessment of maximum glottic angle","volume":"134","author":"DeChance","year":"2024","journal-title":"Laryngoscope"},{"key":"B4","doi-asserted-by":"publisher","first-page":"COIMG-132","DOI":"10.2352\/EI.2025.37.14.COIMG-132","article-title":"Segment anything model (sam) for digital pathology: assess zero-shot segmentation on whole slide imaging","volume":"37","author":"Deng","year":"2023","journal-title":"IS&T Int. Symp. Electron Imaging"},{"key":"B5","first-page":"1","article-title":"Deep learning model development with u-net architecture for glottis segmentation","author":"Derdiman","year":"2021"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2285","DOI":"10.1002\/lary.30473","article-title":"Predictive outcomes of deep learning measurement of the anterior glottic angle in bilateral vocal fold immobility","volume":"133","author":"DeVore","year":"2023","journal-title":"Laryngoscope"},{"key":"B7","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"B8","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1044\/jshd.2102.233","article-title":"Effect of voice quality on communication","volume":"21","author":"Diehl","year":"1956","journal-title":"J. Speech Hear. Disord."},{"key":"B9","doi-asserted-by":"publisher","first-page":"e0227791","DOI":"10.1371\/journal.pone.0227791","article-title":"Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep convolutional lstm network","volume":"15","author":"Fehling","year":"2020","journal-title":"PLoS One"},{"key":"B10","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1016\/j.jvoice.2020.08.029","article-title":"Non-linear image distortions in flexible fiberoptic endoscopes and their effects on calibrated horizontal measurements using high-speed videoendoscopy","volume":"36","author":"Ghasemzadeh","year":"2022","journal-title":"J. Voice"},{"key":"B11","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41597-020-0526-3","article-title":"Bagls, a multihospital benchmark for automatic glottis segmentation","volume":"7","author":"G\u00f3mez","year":"2020","journal-title":"Sci. data"},{"key":"B12","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1006\/jpho.2001.0147","article-title":"Phonation types: a cross-linguistic overview","volume":"29","author":"Gordon","year":"2001","journal-title":"J. Phonetics"},{"key":"B13","volume-title":"Computer-vision benchmark segment-anything model (sam) in medical images: accuracy in 12 datasets","author":"He","year":"2023"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1008","DOI":"10.1044\/jshr.3705.1008","article-title":"Analysis of vocal disorders with methods from nonlinear dynamics","volume":"37","author":"Herzel","year":"1994","journal-title":"J. Speech, Lang. Hear. Res."},{"key":"B15","doi-asserted-by":"publisher","first-page":"151","DOI":"10.3109\/00016488809125120","article-title":"High-speed digital imaging of vocal fold vibration","volume":"105","author":"Hirose","year":"1988","journal-title":"Acta Oto-Laryngologica"},{"key":"B16","volume-title":"When sam meets medical images: an investigation of segment anything model (sam) on multi-phase liver tumor segmentation","author":"Hu","year":"2023"},{"key":"B17","first-page":"1055","article-title":"Unet 3+: a full-scale connected unet for medical image segmentation","author":"Huang","year":"2020"},{"key":"B18","volume-title":"Learning to prompt segment anything models","author":"Huang","year":""},{"key":"B19","first-page":"483","article-title":"Segmenting medical images: from unet to res-unet and nnunet","author":"Huang","year":""},{"key":"B20","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1097\/00005537-199706000-00012","article-title":"Correlation between vocal functions and glottal measurements in patients with unilateral vocal fold paralysis","volume":"107","author":"Inagi","year":"1997","journal-title":"Laryngoscope"},{"key":"B21","volume-title":"Ultralytics\/yolov5: v7.0 - YOLOv5 SOTA realtime instance segmentation","author":"Jocher","year":"2022"},{"key":"B22","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1016\/j.specom.2011.07.010","article-title":"Automatic glottal segmentation using local-based active contours and application to glottovibrography","volume":"54","author":"Karakozoglou","year":"2012","journal-title":"Speech Commun."},{"key":"B23","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"B24","first-page":"234","article-title":"Improved u-net based on dual attention mechanism for glottis segmentation and dysphagia auxiliary diagnosis","author":"Lee","year":"2023"},{"key":"B25","doi-asserted-by":"publisher","first-page":"2083","DOI":"10.1109\/TCSVT.2023.3300846","article-title":"Erdunet: an efficient residual double-coding unet for medical image segmentation","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1016\/j.media.2007.04.005","article-title":"Clinically evaluated procedure for the reconstruction of vocal fold vibrations from endoscopic digital high-speed videos","volume":"11","author":"Lohscheller","year":"2007","journal-title":"Med. Image Anal."},{"key":"B27","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"B28","volume-title":"Sam vs bet: a comparative study for brain extraction and segmentation of magnetic resonance images using deep learning","author":"Mohapatra","year":"2023"},{"key":"B29","doi-asserted-by":"publisher","first-page":"441","DOI":"10.1177\/000348940010900501","article-title":"Glottal area waveform analysis of benign vocal fold lesions before and after surgery","volume":"109","author":"Noordzij","year":"2000","journal-title":"Ann. Otology, Rhinology Laryngology"},{"key":"B30","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.compmedimag.2007.12.003","article-title":"Segmentation of the glottal space from laryngeal images using the watershed transform","volume":"32","author":"Osma-Ruiz","year":"2008","journal-title":"Comput. Med. Imaging Graph."},{"key":"B31","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/s0734-189x(87)80186-x","article-title":"Adaptive histogram equalization and its variations","volume":"39","author":"Pizer","year":"1987","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"B32","volume-title":"Sam 2: segment anything in images and videos","author":"Ravi","year":"2024"},{"key":"B33","first-page":"74","article-title":"The growing importance of the voice and sound in communication in the digital age. The leading role of orality","volume-title":"AC\/E digital culture annual report. Digital trends in culture. Focus: reader in the digital age","author":"Rodero","year":"2018"},{"key":"B34","first-page":"234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B35","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1109\/83.663500","article-title":"Antiextensive connected operators for image and sequence processing","volume":"7","author":"Salembier","year":"1998","journal-title":"IEEE Trans. Image Process."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1859","DOI":"10.1097\/00005537-199911000-00027","article-title":"Videostrobokymography: a new method for the quantitative analysis of vocal fold vibration","volume":"109","author":"Sung","year":"1999","journal-title":"Laryngoscope"},{"key":"B37","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/0734-189x(85)90016-7","article-title":"Topological structural analysis of digitized binary images by border following","volume":"30","author":"Suzuki","year":"1985","journal-title":"Comput. Vis. Graph. Image Process."},{"key":"B38","doi-asserted-by":"publisher","first-page":"1509","DOI":"10.1007\/s00405-009-1050-4","article-title":"Advances in laryngeal imaging","volume":"266","author":"Verikas","year":"2009","journal-title":"Eur. Archives Oto-rhino-laryngology"},{"key":"B39","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1049\/iet-spr.2019.0383","article-title":"Hilbert\u2013huang\u2013hurst-based non-linear acoustic feature vector for emotion classification with stochastic models and learning systems","volume":"14","author":"Vieira","year":"2020","journal-title":"IET Signal Process."},{"key":"B40","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1177\/0194599821989608","article-title":"Application of a computer vision tool for automated glottic tracking to vocal fold paralysis patients","volume":"165","author":"Wang","year":"2021","journal-title":"Otolaryngology\u2013Head Neck Surg."},{"key":"B41","first-page":"42","article-title":"Levit-unet: make faster encoders with transformer for medical image segmentation","author":"Xu","year":"2023"},{"key":"B42","doi-asserted-by":"publisher","first-page":"1394","DOI":"10.1109\/TBME.2006.873751","article-title":"Automatic tracing of vocal-fold motion from high-speed digital images","volume":"53","author":"Yan","year":"2006","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B43","volume-title":"Interactive data synthesis for systematic vision adaptation via llms-aigcs collaboration","author":"Yu","year":"2023"},{"key":"B44","volume-title":"Multimodal laryngoscopic video analysis for assisted diagnosis of vocal cord paralysis","author":"Zhang","year":"2024"}],"container-title":["Frontiers in Molecular Biosciences"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2025.1616271\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T04:12:13Z","timestamp":1752120733000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmolb.2025.1616271\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,10]]},"references-count":44,"alternative-id":["10.3389\/fmolb.2025.1616271"],"URL":"https:\/\/doi.org\/10.3389\/fmolb.2025.1616271","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.172651962.24168480\/v1","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.172651962.24168480\/v2","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.172651962.24168480\/v3","asserted-by":"object"}]},"ISSN":["2296-889X"],"issn-type":[{"value":"2296-889X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,10]]},"article-number":"1616271"}}