{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,19]],"date-time":"2026-09-19T15:51:13Z","timestamp":1789833073778,"version":"4.0.1"},"reference-count":102,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T00:00:00Z","timestamp":1581292800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"DOI":"10.1371\/journal.pone.0227791","type":"journal-article","created":{"date-parts":[[2020,2,10]],"date-time":"2020-02-10T18:28:45Z","timestamp":1581359325000},"page":"e0227791","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":85,"title":["Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep Convolutional LSTM Network"],"prefix":"10.1371","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3592-5025","authenticated-orcid":true,"given":"Mona Kirstin","family":"Fehling","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4993-4085","authenticated-orcid":true,"given":"Fabian","family":"Grosch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Elke","family":"Schuster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Schick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00f6rg","family":"Lohscheller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2020,2,10]]},"reference":[{"issue":"11","key":"pone.0227791.ref001","doi-asserted-by":"crossref","first-page":"1988","DOI":"10.1097\/01.mlg.0000179174.32345.41","article-title":"Voice Disorders in the General Population: Prevalence, Risk Factors, and Occupational Impact","volume":"115","author":"N Roy","year":"2005","journal-title":"The Laryngoscope"},{"key":"pone.0227791.ref002","unstructured":"Titze IR. Principles of voice production. Behnke A, editor. National Center for Voice and Speech; 2000."},{"key":"pone.0227791.ref003","doi-asserted-by":"crossref","unstructured":"Takefuta Y, Jancosek EG, Brunt M. A statistical analysis of melody curves in the intonation of American English. In: Proceedings of the 7th International Congress of Phonetic Sciences. IPA Montreal, Canada; 1972. p. 1035\u20131039.","DOI":"10.1515\/9783110814750-142"},{"issue":"8","key":"pone.0227791.ref004","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1007\/s00405-003-0606-y","article-title":"Vocal fold vibration irregularities caused by different types of laryngeal asymmetry","volume":"260","author":"U Eysholdt","year":"2003","journal-title":"European Archives of Otorhinolaryngology"},{"issue":"2","key":"pone.0227791.ref005","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1121\/1.2159433","article-title":"A constitutive model of the human vocal fold cover for fundamental frequency regulation","volume":"119","author":"K Zhang","year":"2006","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"4","key":"pone.0227791.ref006","doi-asserted-by":"crossref","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":"J Lohscheller","year":"2007","journal-title":"Medical Image Analysis"},{"issue":"03","key":"pone.0227791.ref007","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1055\/s-0038-1634360","article-title":"Normal Voice Production: Computation of Driving Parameters from Endoscopic Digital High Speed Images","volume":"42","author":"M D\u00f6llinger","year":"2003","journal-title":"Methods of Information in Medicine"},{"issue":"1","key":"pone.0227791.ref008","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1177\/000348941112000104","article-title":"Differential Vibratory Characteristics of Adductor Spasmodic Dysphonia and Muscle Tension Dysphonia on High-Speed Digital Imaging","volume":"120","author":"RR Patel","year":"2011","journal-title":"Annals of Otology, Rhinology & Laryngology"},{"issue":"6","key":"pone.0227791.ref009","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1097\/MOO.0b013e3283585f04","article-title":"Current role of stroboscopy in laryngeal imaging","volume":"20","author":"DD Mehta","year":"2012","journal-title":"Current Opinion in Otolaryngology & Head and Neck Surgery"},{"issue":"3","key":"pone.0227791.ref010","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1097\/01.moo.0000163451.98079.ba","article-title":"What have we learned about laryngeal physiology from high-speed digital videoendoscopy?","volume":"13","author":"S Herteg\u00e5rd","year":"2005","journal-title":"Current Opinion in Otolaryngology & Head and Neck Surgery"},{"issue":"3","key":"pone.0227791.ref011","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1097\/01.moo.0000162262.26868.df","article-title":"Introduction to high-speed imaging of the larynx","volume":"13","author":"KA Kendall","year":"2005","journal-title":"Current Opinion in Otolaryngology & Head and Neck Surgery"},{"issue":"4","key":"pone.0227791.ref012","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1097\/MLG.0b013e318161f9e1","article-title":"Phonovibrogram Visualization of Entire Vocal Fold Dynamics","volume":"118","author":"J Lohscheller","year":"2008","journal-title":"The Laryngoscope"},{"issue":"3","key":"pone.0227791.ref013","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1097\/MOO.0b013e3283395dd4","article-title":"State of the Art Laryngeal Imaging: Research and Clinical Implications","volume":"18","author":"DD Deliyski","year":"2010","journal-title":"Current Opinion in Otolaryngology & Head and Neck Surgery"},{"issue":"4","key":"pone.0227791.ref014","doi-asserted-by":"crossref","first-page":"182","DOI":"10.3109\/14015439.2012.731083","article-title":"Vocal fold vibration amplitude, open quotient, speed quotient and their variability along glottal length: Kymographic data from normal subjects","volume":"38","author":"J Lohscheller","year":"2012","journal-title":"Logopedics Phoniatrics Vocology"},{"key":"pone.0227791.ref015","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.artmed.2015.10.002","article-title":"A generalized procedure for analyzing sustained and dynamic vocal fold vibrations from laryngeal high-speed videos using phonovibrograms","volume":"66","author":"J Unger","year":"2016","journal-title":"Artificial Intelligence in Medicine"},{"issue":"Suppl. 458","key":"pone.0227791.ref016","doi-asserted-by":"crossref","first-page":"151","DOI":"10.3109\/00016488809125120","article-title":"High-speed digital imaging of vocal fold vibration","volume":"105","author":"H Hirose","year":"1988","journal-title":"Acta Oto-Laryngologica"},{"issue":"9","key":"pone.0227791.ref017","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1177\/000348949110000907","article-title":"Strobovideolaryngoscopy: results and clinical value","volume":"100","author":"RT Sataloff","year":"1991","journal-title":"Annals of Otology, Rhinology & Laryngology"},{"issue":"2","key":"pone.0227791.ref018","doi-asserted-by":"crossref","first-page":"1249","DOI":"10.1121\/1.412234","article-title":"Voice simulation with a body-cover model of the vocal folds","volume":"97","author":"BH Story","year":"1995","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"6","key":"pone.0227791.ref019","doi-asserted-by":"crossref","first-page":"3003","DOI":"10.1121\/1.1324678","article-title":"A finite-element model of vocal-fold vibration","volume":"108","author":"F Alipour","year":"2000","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"6","key":"pone.0227791.ref020","doi-asserted-by":"crossref","first-page":"e101128","DOI":"10.1371\/journal.pone.0101128","article-title":"Quantitative Measurement of Vocal Fold Vibration in Male Radio Performers and Healthy Controls Using High-Speed Videoendoscopy","volume":"9","author":"S Warhurst","year":"2014","journal-title":"PLoS ONE"},{"issue":"11","key":"pone.0227791.ref021","doi-asserted-by":"crossref","first-page":"e0187486","DOI":"10.1371\/journal.pone.0187486","article-title":"Biomechanical simulation of vocal fold dynamics in adults based on laryngeal high-speed videoendoscopy","volume":"12","author":"M D\u00f6llinger","year":"2017","journal-title":"PLoS ONE"},{"issue":"5","key":"pone.0227791.ref022","doi-asserted-by":"crossref","first-page":"e0175865","DOI":"10.1371\/journal.pone.0175865","article-title":"Laryngeal evidence for the first and second passaggio in professionally trained sopranos","volume":"12","author":"M Echternach","year":"2017","journal-title":"PLoS ONE"},{"issue":"10","key":"pone.0227791.ref023","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1007\/s00405-009-1050-4","article-title":"Advances in laryngeal imaging","volume":"266","author":"A Verikas","year":"2009","journal-title":"European Archives of Oto-Rhino-Laryngology"},{"issue":"1","key":"pone.0227791.ref024","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1159\/000111802","article-title":"Clinical Implementation of Laryngeal High-Speed Videoendoscopy: Challenges and Evolution","volume":"60","author":"DD Deliyski","year":"2007","journal-title":"Folia Phoniatrica et Logopaedica"},{"issue":"3","key":"pone.0227791.ref025","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1109\/TMI.2007.903690","article-title":"Phonovibrography: Mapping High-Speed Movies of Vocal Fold Vibrations Into 2-D Diagrams for Visualizing and Analyzing the Underlying Laryngeal Dynamics","volume":"27","author":"J Lohscheller","year":"2008","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"2","key":"pone.0227791.ref026","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.jvoice.2004.04.006","article-title":"Analysis of Vocal-fold Vibrations from High-Speed Laryngeal Images Using a Hilbert Transform-Based Methodology","volume":"19","author":"Y Yan","year":"2005","journal-title":"Journal of Voice"},{"issue":"3","key":"pone.0227791.ref027","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1121\/1.1646401","article-title":"On the use of the derivative of electroglottographic signals for characterization of nonpathological phonation","volume":"115","author":"N Henrich","year":"2004","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"3","key":"pone.0227791.ref028","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.jvoice.2016.09.026","article-title":"High-speed Videolaryngoscopy: Quantitative Parameters of Glottal Area Waveforms and High-speed Kymography in Healthy Individuals","volume":"31","author":"M Tsutsumi","year":"2017","journal-title":"Journal of Voice"},{"key":"pone.0227791.ref029","article-title":"Dependencies and Ill-designed Parameters Within High-speed Videoendoscopy and Acoustic Signal Analysis","author":"P Schlegel","year":"2018","journal-title":"Journal of Voice"},{"issue":"4","key":"pone.0227791.ref030","doi-asserted-by":"crossref","first-page":"e0154586","DOI":"10.1371\/journal.pone.0154586","article-title":"Effects of Vocal Fold Nodules on Glottal Cycle Measurements Derived from High-Speed Videoendoscopy in Children","volume":"11","author":"RR Patel","year":"2016","journal-title":"PLoS ONE"},{"issue":"4","key":"pone.0227791.ref031","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1159\/000266404","article-title":"Direct Evaluation of High-Speed Recordings of Vocal Fold Vibrations","volume":"48","author":"U Eysholdt","year":"1996","journal-title":"Folia Phoniatrica et Logopaedica"},{"issue":"3","key":"pone.0227791.ref032","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1016\/S0892-1997(00)80087-9","article-title":"Functional Imaging of Vocal Fold Vibration: Digital Multislice High-Speed Kymography","volume":"14","author":"T Wittenberg","year":"2000","journal-title":"Journal of Voice"},{"key":"pone.0227791.ref033","doi-asserted-by":"crossref","unstructured":"Novoz\u00e1msk\u1ef3 A, Sedl\u00e1\u0159 J, Zita A, \u0160roubek F, Flussef J, \u0160vec JG, et al. Image analysis of videokymographic data. In: 2015 IEEE International Conference on Image Processing (ICIP). IEEE; 2015. p. 78\u201382.","DOI":"10.1109\/ICIP.2015.7350763"},{"issue":"6","key":"pone.0227791.ref034","doi-asserted-by":"crossref","first-page":"3179","DOI":"10.1121\/1.1406498","article-title":"Spatio-temporal analysis of irregular vocal fold oscillations: Biphonation due to desynchronization of spatial modes","volume":"110","author":"J Neubauer","year":"2001","journal-title":"The Journal of the Acoustical Society of America"},{"issue":"4","key":"pone.0227791.ref035","doi-asserted-by":"crossref","first-page":"043114","DOI":"10.1063\/1.2784384","article-title":"Quantifying the complexity of excised larynx vibrations from high-speed imaging using spatiotemporal and nonlinear dynamic analyses","volume":"17","author":"Y Zhang","year":"2007","journal-title":"Chaos: An Interdisciplinary Journal of Nonlinear Science"},{"issue":"9","key":"pone.0227791.ref036","doi-asserted-by":"crossref","first-page":"2422","DOI":"10.1109\/TBME.2014.2318774","article-title":"Quantifying Spatiotemporal Properties of Vocal Fold Dynamics Based on a Multiscale Analysis of Phonovibrograms","volume":"61","author":"J Unger","year":"2014","journal-title":"IEEE Trans Biomed Eng"},{"key":"pone.0227791.ref037","unstructured":"Yan Y, Bless D, Chen X. Biomedical Image Analysis in High-speed Laryngeal Imaging of Voice Production. In: 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference. IEEE; 2005."},{"issue":"5","key":"pone.0227791.ref038","doi-asserted-by":"crossref","first-page":"794","DOI":"10.1109\/TBME.2006.889182","article-title":"Extracting Physiologically Relevant Parameters of Vocal Folds From High-Speed Video Image Series","volume":"54","author":"C Tao","year":"2007","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"pone.0227791.ref039","article-title":"Automated Measurement of Vocal Fold Vibratory Asymmetry From High-Speed Videoendoscopy Recordings","author":"DD Mehta","year":"2011","journal-title":"Journal of Speech, Language, and Hearing Research"},{"issue":"6","key":"pone.0227791.ref040","first-page":"306","article-title":"Analysis of Vocal Fold Vibrations from High-Speed Digital Images Based On Dynamic Time Warping","volume":"8","author":"AIA Rahman","year":"2014","journal-title":"International Journal of Medical, Health, Biomedical, Bioengineering and Pharmaceutical Engineering"},{"issue":"3","key":"pone.0227791.ref041","doi-asserted-by":"crossref","first-page":"795","DOI":"10.1109\/TBME.2014.2364862","article-title":"Fully Automated Glottis Segmentation in Endoscopic Videos Using Local Color and Shape Features of Glottal Regions","volume":"62","author":"O Gloger","year":"2015","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"12","key":"pone.0227791.ref042","doi-asserted-by":"crossref","first-page":"2117","DOI":"10.1097\/00005537-200012000-00028","article-title":"Vocal Fold Vibrations: High-Speed Imaging, Kymography, and Acoustic Analysis: A Preliminary Report","volume":"110","author":"H Larsson","year":"2000","journal-title":"The Laryngoscope"},{"issue":"6","key":"pone.0227791.ref043","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/BF01213501","article-title":"Recording, processing, and analysis of digital high-speed sequences in glottography","volume":"8","author":"T Wittenberg","year":"1995","journal-title":"Machine Vision and Applications"},{"issue":"7","key":"pone.0227791.ref044","doi-asserted-by":"crossref","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":"Y Yan","year":"2006","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"pone.0227791.ref045","unstructured":"Marendic B, Galatsanos N, Bless D. New active contour algorithm for tracking vibrating vocal folds. In: Proceedings 2001 International Conference on Image Processing. IEEE; 2001."},{"key":"pone.0227791.ref046","unstructured":"Allin S, Galeotti J, Stetten G, Dailey SH. Enhanced snake-based segmentation of vocal folds. In: 2004 2nd IEEE International Symposium on Biomedical Imaging: Macro to Nano. IEEE; 2004."},{"issue":"1","key":"pone.0227791.ref047","first-page":"1","article-title":"Automatic high-speed video glottis segmentation using salient regions and 3D geodesic active contours","volume":"2015","author":"F Schenk","year":"2015","journal-title":"Annals of the British Machine Vision Association"},{"issue":"3","key":"pone.0227791.ref048","doi-asserted-by":"crossref","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":"V Osma-Ruiz","year":"2008","journal-title":"Computerized Medical Imaging and Graphics"},{"key":"pone.0227791.ref049","unstructured":"Schulz H, Behnke S. Object-Class Segmentation using DeepConvolutional Neural Networks. In: Proceedings of the DAGM Workshop on New Challenges in Neural Computation. Citeseer; 2011. p. 58\u201361."},{"key":"pone.0227791.ref050","unstructured":"Szegedy C, Toshev A, Erhan D. Deep Neural Networks for Object Detection. In: Advances in Neural Information Processing Systems; 2013. p. 2553\u20132561."},{"key":"pone.0227791.ref051","unstructured":"Krizhevsky A, Sutskever I, Hinton GE. ImageNet Classification with Deep Convolutional Neural Networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editors. Advances in Neural Information Processing Systems 25. Curran Associates, Inc.; 2012. p. 1097\u20131105."},{"key":"pone.0227791.ref052","doi-asserted-by":"crossref","unstructured":"Le QV, Ranzato M, Monga R, Devin M, Chen K, Corrado GS, et al. Building High-level FeaturesUsing Large Scale Unsupervised Learning. In: Proceedings of the 29th International Conference on Machine Learning, Edinburgh, Scotland, UK, 2012.; 2012.","DOI":"10.1109\/ICASSP.2013.6639343"},{"key":"pone.0227791.ref053","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification. In: Proceedings of the IEEE international conference on computer vision; 2015. p. 1026\u20131034.","DOI":"10.1109\/ICCV.2015.123"},{"issue":"7639","key":"pone.0227791.ref054","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"A Esteva","year":"2017","journal-title":"Nature"},{"key":"pone.0227791.ref055","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T. Fully Convolutional Networks for Semantic Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2015. p. 3431\u20133440.","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"9","key":"pone.0227791.ref056","doi-asserted-by":"crossref","first-page":"1342","DOI":"10.1038\/s41591-018-0107-6","article-title":"Clinically applicable deep learning for diagnosis and referral in retinal disease","volume":"24","author":"J De Fauw","year":"2018","journal-title":"Nature Medicine"},{"key":"pone.0227791.ref057","unstructured":"Shelhamer E, Long J, Darrell T. Fully Convolutional Networks for Semantic Segmentation. arXiv preprint arXiv: 160506211. 2016;."},{"issue":"4","key":"pone.0227791.ref058","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"Y LeCun","year":"1989","journal-title":"Neural Computation"},{"key":"pone.0227791.ref059","unstructured":"Simonyan K, Zisserman A. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv preprint arXiv: 14091556. 2015;."},{"key":"pone.0227791.ref060","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al. Going Deeper with Convolutions. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2015.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"pone.0227791.ref061","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J. Deep Residual Learning for Image Recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2016. p. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"12","key":"pone.0227791.ref062","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation","volume":"39","author":"V Badrinarayanan","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"pone.0227791.ref063","unstructured":"Kayalibay B, Jensen G, van der Smagt P. CNN-based Segmentation of Medical Imaging Data. arXiv preprint arXiv:170103056. 2017;."},{"key":"pone.0227791.ref064","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.cmpb.2018.01.025","article-title":"NiftyNet: a deep-learning platform for medical imaging","volume":"158","author":"E Gibson","year":"2018","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"7","key":"pone.0227791.ref065","doi-asserted-by":"crossref","first-page":"1562","DOI":"10.1109\/TMI.2018.2791721","article-title":"Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning","volume":"37","author":"G Wang","year":"2018","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0227791.ref066","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","article-title":"A survey on deep learning in medical image analysis","volume":"42","author":"G Litjens","year":"2017","journal-title":"Medical Image Analysis"},{"issue":"5","key":"pone.0227791.ref067","doi-asserted-by":"crossref","first-page":"1207","DOI":"10.1109\/TMI.2016.2535865","article-title":"Lung Pattern Classification for Interstitial Lung Diseases Using a Deep Convolutional Neural Network","volume":"35","author":"M Anthimopoulos","year":"2016","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"pone.0227791.ref068","first-page":"234","volume-title":"Lecture Notes in Computer Science","author":"O Ronneberger","year":"2015"},{"key":"pone.0227791.ref069","doi-asserted-by":"crossref","unstructured":"Xu X, Wang R, Tan T, Xu F. An improved UNet architecture for simultaneous arteriole and venule segmentation in fundus image. In: 22nd Conference on Medical Image Understanding and Analysis 2018; 2018.","DOI":"10.1007\/978-3-319-95921-4_31"},{"key":"pone.0227791.ref070","unstructured":"Oktay O, Schlemper J, Folgoc LL, Lee MCH, Heinrich MP, Misawa K, et al. Attention U-Net: Learning Where to Look for the Pancreas. arXiv preprint arXiv: 180403999. 2018;."},{"key":"pone.0227791.ref071","first-page":"1140","article-title":"A Multi-scale U-Net for Semantic Segmentation of Histological Images from Radical Prostatectomies","volume":"2017","author":"J Li","year":"2018","journal-title":"AMIA Annual Symposium Proceedings"},{"key":"pone.0227791.ref072","doi-asserted-by":"crossref","unstructured":"Rao MVA, Krishnamurthy R, Gopikishore P, Priyadharshini V, Ghosh PK. Automatic glottis localization and segmentation in stroboscopic videos usingdeep neural network. In: Interspeech; 2018. p. 3007\u20133011.","DOI":"10.21437\/Interspeech.2018-2572"},{"issue":"3","key":"pone.0227791.ref073","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1007\/s11548-018-01910-0","article-title":"A Dataset of Laryngeal Endoscopic Images with Comparative Study on Convolution Neural Network Based Semantic Segmentation","volume":"14","author":"MH Laves","year":"2019","journal-title":"International journal of computer assisted radiology and surgery"},{"issue":"4","key":"pone.0227791.ref074","doi-asserted-by":"crossref","first-page":"1127","DOI":"10.1109\/TBME.2018.2867636","article-title":"Quantification and Analysis of Laryngeal Closure from Endoscopic Videos","volume":"66","author":"J Lin","year":"2019","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"pone.0227791.ref075","unstructured":"Lipton ZC, Berkowitz J, Elkan C. A Critical Review of Recurrent Neural Networks for Sequence Learning. arXiv preprint arXiv:150600019. 2015;."},{"issue":"8","key":"pone.0227791.ref076","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"S Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"pone.0227791.ref077","unstructured":"Stollenga MF, Byeon W, Liwicki M, Schmidhuber J. Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation. In: Advances in neural information processing systems; 2015. p. 2998\u20133006."},{"key":"pone.0227791.ref078","unstructured":"Chen J, Yang L, Zhang Y, Alber M, Chen DZ. Combining Fully Convolutional and Recurrent Neural Networks for 3D Biomedical Image Segmentation. In: 29th Conference on Neural Information Processing Systems (NIPS 2016); 2016. p. 3036\u20133044."},{"key":"pone.0227791.ref079","doi-asserted-by":"crossref","unstructured":"Gao Y, Phillips JM, Zheng Y, Min R, Fletcher PT, Gerig G. Fully Convolutional Structured LSTM Networks for joint 4D Medical Image Segmentation. In: 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018). IEEE; 2018. p. 1104\u20131108.","DOI":"10.1109\/ISBI.2018.8363764"},{"key":"pone.0227791.ref080","doi-asserted-by":"crossref","unstructured":"Arbelle A, Raviv TR. Microscopy Cell Segmentation via Convolutional LSTM Networks. In: 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019). IEEE; 2019. p. 1008\u20131012.","DOI":"10.1109\/ISBI.2019.8759447"},{"key":"pone.0227791.ref081","doi-asserted-by":"crossref","unstructured":"Cho K, van Merrienboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, et al. Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. arXiv preprint arXiv: 14061078. 2014;.","DOI":"10.3115\/v1\/D14-1179"},{"key":"pone.0227791.ref082","unstructured":"Clevert DA, Unterthiner T, Hochreiter S. Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). In: International Conference on Learning Representations 2016; 2015."},{"key":"pone.0227791.ref083","unstructured":"Ioffe S, Szegedy C. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. In: Bach F, Blei D, editors. Proceedings of the 32nd International Conference on Machine Learning. vol. 37 of Proceedings of Machine Learning Research. Lille, France: PMLR; 2015. p. 448\u2013456."},{"key":"pone.0227791.ref084","unstructured":"Shi X, Zhourong C, Wang H, Yeung DY, Wong WK, Woo Wc. Convolutional LSTM network: A Machine Learning Approach for Precipitation Nowcasting. In: Advances in Neural Information Processing Systems; 2015. p. 802\u2013810."},{"key":"pone.0227791.ref085","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014;."},{"key":"pone.0227791.ref086","unstructured":"Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics; 2010. p. 249\u2013256."},{"key":"pone.0227791.ref087","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems; 2015. Available from: https:\/\/www.tensorflow.org\/."},{"issue":"3","key":"pone.0227791.ref088","doi-asserted-by":"crossref","first-page":"297","DOI":"10.2307\/1932409","article-title":"Measures of the Amount of Ecologic Association Between Species","volume":"26","author":"LR Dice","year":"1945","journal-title":"Ecology"},{"key":"pone.0227791.ref089","doi-asserted-by":"crossref","unstructured":"Ng CB, Tay YH, Goi BM. Comparing Image Representations for Training a Convolutional Neural Network to Classify Gender. In: 2013 1st International Conference on Artificial Intelligence, Modelling & Simulation; 2013. p. 29\u201333.","DOI":"10.1109\/AIMS.2013.13"},{"key":"pone.0227791.ref090","doi-asserted-by":"crossref","unstructured":"Reddy KS, Singh U, Uttam PK. Effect Of Image Colourspace On Performance Of Convolution Neural Networks. In: 2017 2nd IEEE International Conference on Recent Trends in Electronics, Information Communication Technology (RTEICT); 2017. p. 2001\u20132005.","DOI":"10.1109\/RTEICT.2017.8256949"},{"issue":"12","key":"pone.0227791.ref091","doi-asserted-by":"crossref","first-page":"2259","DOI":"10.1016\/S0031-3203(00)00149-7","article-title":"Color image segmentation: advances and prospects","volume":"34","author":"HD Cheng","year":"2001","journal-title":"Pattern Recognition"},{"key":"pone.0227791.ref092","doi-asserted-by":"crossref","unstructured":"Wu Y, He K. Group Normalization. In: European Conference on Computer Vision. Springer; 2018. p. 3\u201319.","DOI":"10.1007\/978-3-030-01261-8_1"},{"issue":"2","key":"pone.0227791.ref093","doi-asserted-by":"crossref","first-page":"1792","DOI":"10.1109\/LRA.2019.2896518","article-title":"Normalization in training U-Net for 2-D biomedical semantic segmentation","volume":"4","author":"XY Zhou","year":"2019","journal-title":"IEEE Robotics and Automation Letters"},{"key":"pone.0227791.ref094","unstructured":"Ulyanov D, Vedaldi A, Lempitsky V. Instance Normalization: The Missing Ingredient for Fast Stylization. arXiv preprint arXiv:160708022. 2016;."},{"key":"pone.0227791.ref095","first-page":"21","article-title":"Layer Normalization","volume":"1050","author":"JL Ba","year":"2016","journal-title":"arXiv preprint arXiv:160706450"},{"issue":"4","key":"pone.0227791.ref096","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1109\/42.363096","article-title":"Morphometric analysis of white matter lesions in MR images: method and validation","volume":"13","author":"AP Zijdenbos","year":"1994","journal-title":"IEEE Transactions on Medical Imaging"},{"issue":"3","key":"pone.0227791.ref097","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1093\/schbul\/17.3.483","article-title":"Measurement and Reliability: Statistical Thinking Considerations","volume":"17","author":"JJ Bartko","year":"1991","journal-title":"Schizophrenia Bulletin"},{"key":"pone.0227791.ref098","doi-asserted-by":"crossref","unstructured":"Caelles S, Maninis KK, Pont-Tuset J, Leal-Taix\u00e9 L, Cremers D, Van Gool L. One-Shot Video Object Segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 221\u2013230.","DOI":"10.1109\/CVPR.2017.565"},{"key":"pone.0227791.ref099","doi-asserted-by":"crossref","unstructured":"Yu F, Koltun V, Funkhouser T. Dilated Residual Networks. In: Conference on Computer Vision and Pattern Recognition (CVPR 2017); 2017.","DOI":"10.1109\/CVPR.2017.75"},{"key":"pone.0227791.ref100","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1016\/j.neuroimage.2018.07.005","article-title":"Fully Convolutional Network Ensembles for White Matter Hyperintensities Segmentation in MR Images","volume":"183","author":"H Li","year":"2018","journal-title":"NeuroImage"},{"issue":"01","key":"pone.0227791.ref101","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1117\/1.JMI.6.1.014006","article-title":"Recurrent residual U-Net for medical image segmentation","volume":"6","author":"MZ Alom","year":"2019","journal-title":"Journal of Medical Imaging"},{"key":"pone.0227791.ref102","doi-asserted-by":"crossref","unstructured":"Kamnitsas K, Bai W, Ferrante E, McDonagh S, Sinclair M, Pawlowski N, et al. Ensembles of Multiple Models and Architectures for Robust Brain Tumour Segmentation. In: International MICCAI Brainlesion Workshop. Springer; 2017. p. 450\u2013462.","DOI":"10.1007\/978-3-319-75238-9_38"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0227791","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T05:40:53Z","timestamp":1665812453000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0227791"}},"subtitle":[],"editor":[{"given":"Yuanquan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,2,10]]},"references-count":102,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2020,2,10]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0227791","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,10]]}}}