{"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":1791913616994,"version":"4.3.4"},"reference-count":43,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T00:00:00Z","timestamp":1664323200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG)","doi-asserted-by":"publisher","award":["DO1247\/8-2"],"award-info":[{"award-number":["DO1247\/8-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG)","doi-asserted-by":"publisher","award":["SCHU 3441\/3-2"],"award-info":[{"award-number":["SCHU 3441\/3-2"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG)","doi-asserted-by":"publisher","award":["R01 DC015570"],"award-info":[{"award-number":["R01 DC015570"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG)","doi-asserted-by":"publisher","award":["R21 DC016356"],"award-info":[{"award-number":["R21 DC016356"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institutes of Health","award":["DO1247\/8-2"],"award-info":[{"award-number":["DO1247\/8-2"]}]},{"name":"National Institutes of Health","award":["SCHU 3441\/3-2"],"award-info":[{"award-number":["SCHU 3441\/3-2"]}]},{"name":"National Institutes of Health","award":["R01 DC015570"],"award-info":[{"award-number":["R01 DC015570"]}]},{"name":"National Institutes of Health","award":["R21 DC016356"],"award-info":[{"award-number":["R21 DC016356"]}]},{"name":"National Institute on Deafness and Other Communication Disorders","award":["DO1247\/8-2"],"award-info":[{"award-number":["DO1247\/8-2"]}]},{"name":"National Institute on Deafness and Other Communication Disorders","award":["SCHU 3441\/3-2"],"award-info":[{"award-number":["SCHU 3441\/3-2"]}]},{"name":"National Institute on Deafness and Other Communication Disorders","award":["R01 DC015570"],"award-info":[{"award-number":["R01 DC015570"]}]},{"name":"National Institute on Deafness and Other Communication Disorders","award":["R21 DC016356"],"award-info":[{"award-number":["R21 DC016356"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Applied Sciences"],"abstract":"<jats:p>Endoscopic high-speed video (HSV) systems for visualization and assessment of vocal fold dynamics in the larynx are diverse and technically advancing. To consider resulting \u201cconcepts shifts\u201d for neural network (NN)-based image processing, re-training of already trained and used NNs is necessary to allow for sufficiently accurate image processing for new recording modalities. We propose and discuss several re-training approaches for convolutional neural networks (CNN) being used for HSV image segmentation. Our baseline CNN was trained on the BAGLS data set (58,750 images). The new BAGLS-RT data set consists of additional 21,050 images from previously unused HSV systems, light sources, and different spatial resolutions. Results showed that increasing data diversity by means of preprocessing already improves the segmentation accuracy (mIoU + 6.35%). Subsequent re-training further increases segmentation performance (mIoU + 2.81%). For re-training, finetuning with dynamic knowledge distillation showed the most promising results. Data variety for training and additional re-training is a helpful tool to boost HSV image segmentation quality. However, when performing re-training, the phenomenon of catastrophic forgetting should be kept in mind, i.e., adaption to new data while forgetting already learned knowledge.<\/jats:p>","DOI":"10.3390\/app12199791","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T20:58:47Z","timestamp":1664398727000},"page":"9791","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Re-Training of Convolutional Neural Networks for Glottis Segmentation in Endoscopic High-Speed Videos"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2717-4820","authenticated-orcid":false,"given":"Michael","family":"D\u00f6llinger","sequence":"first","affiliation":[{"name":"Division of Phoniatrics and Pediatric Audiology, Department of Otorhino-laryngology Head & Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-N\u00fcrnberg, 91054 Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Schraut","sequence":"additional","affiliation":[{"name":"Division of Phoniatrics and Pediatric Audiology, Department of Otorhino-laryngology Head & Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-N\u00fcrnberg, 91054 Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lea A.","family":"Henrich","sequence":"additional","affiliation":[{"name":"Division of Phoniatrics and Pediatric Audiology, Department of Otorhino-laryngology Head & Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-N\u00fcrnberg, 91054 Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh","family":"Chhetri","sequence":"additional","affiliation":[{"name":"Department of Head and Neck Surgery, David Geffen School of Medicine at the University of California, Los Angeles, Los Angeles, CA 90095, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0095-5360","authenticated-orcid":false,"given":"Matthias","family":"Echternach","sequence":"additional","affiliation":[{"name":"Division of Phoniatrics and Pediatric Audiology, Department of Otorhinolaryngology, Munich University Hospital (LMU), 80331 Munich, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7577-0267","authenticated-orcid":false,"given":"Aaron M.","family":"Johnson","sequence":"additional","affiliation":[{"name":"NYU Voice Center, Department of Otolaryngology\u2013Head and Neck Surgery, New York University, Grossman School of Medicine, New York, NY 10001, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melda","family":"Kunduk","sequence":"additional","affiliation":[{"name":"Department of Communication Sciences and Disorders, Louisiana State University, Baton Rouge, LA 70801, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1491-4068","authenticated-orcid":false,"given":"Youri","family":"Maryn","sequence":"additional","affiliation":[{"name":"Department of Speech, Language and Hearing Sciences, University of Ghent, 9000 Ghent, Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita R.","family":"Patel","sequence":"additional","affiliation":[{"name":"Department of Speech, Language and Hearing Sciences, Indiana University, Bloomington, IA 47401, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin","family":"Samlan","sequence":"additional","affiliation":[{"name":"Department of Speech, Language, & Hearing Sciences, University of Arizona, Tucson, AZ 85641, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marion","family":"Semmler","sequence":"additional","affiliation":[{"name":"Division of Phoniatrics and Pediatric Audiology, Department of Otorhino-laryngology Head & Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-N\u00fcrnberg, 91054 Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anne","family":"Sch\u00fctzenberger","sequence":"additional","affiliation":[{"name":"Division of Phoniatrics and Pediatric Audiology, Department of Otorhino-laryngology Head & Neck Surgery, University Hospital Erlangen, Friedrich-Alexander-University Erlangen-N\u00fcrnberg, 91054 Erlangen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"EL82","DOI":"10.1121\/1.4773200","article-title":"Vocal fold vibrations at high soprano fundamental frequencies","volume":"133","author":"Echternach","year":"2013","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"616985","DOI":"10.3389\/fphys.2021.616985","article-title":"3D-FV-FE aeroacoustic larynx model for investigation of functional based voice disorders","volume":"12","author":"Falk","year":"2021","journal-title":"Front. Physiol."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Thornton, F.N., D\u00f6llinger, M., Kniesburges, S., Berry, D.A., Alexiou, C., and Sch\u00fctzenberger, A. (2019). Impact of subharmonic and aperiodic laryngeal dynamics on the phonatory process analyzed in ex vivo rabbit models. Appl. Sci., 9.","DOI":"10.3390\/app9091963"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1657","DOI":"10.1121\/10.0003602","article-title":"Fluid-structure-acoustic interactions in an ex vivo porcine phonation model","volume":"149","author":"Semmler","year":"2021","journal-title":"J. Acoust. Soc. Am."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"151","DOI":"10.3109\/00016488809125120","article-title":"High-speed digital imaging of vocal fold vibration","volume":"458","author":"Hirose","year":"1988","journal-title":"Acta Otolaryngol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"502","DOI":"10.1177\/000348949310200703","article-title":"High-speed, light-intensified digital imaging of vocal fold vibrations in high optical resolution via indirect microlaryngoscopy","volume":"102","author":"Hess","year":"1993","journal-title":"Ann. Otol. Rhinol. Laryngol."},{"key":"ref_7","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","year":"2005","journal-title":"Curr. Opin. Otolaryngol. Head Neck Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"140.e1","DOI":"10.1016\/j.jvoice.2020.07.037","article-title":"Glottal Airflow and Glottal Area Waveform Characteristics of Flow Phonation in Untrained Vocally Healthy Adults","volume":"36","author":"Patel","year":"2022","journal-title":"J. Voice"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Yamauchi, A., Imagawa, H., Yokonishi, H., Sakakibara, K.I., and Tayama, N. (2021). Multivariate Analysis of Vocal Fold Vibrations on Various Voice Disorders Using High-Speed Digital Imaging. Appl. Sci., 11.","DOI":"10.3390\/app11146284"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Schlegel, P., Semmler, M., Kunduk, M., D\u00f6llinger, M., Bohr, C., and Sch\u00fctzenberger, A. (2018). Influence of analyzed sequence length on parameters in laryngeal high-speed videoendoscopy. Appl. Sci., 8.","DOI":"10.3390\/app8122666"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"13760","DOI":"10.1038\/s41598-021-93149-0","article-title":"OpenHSV: An open platform for laryngeal high-speed videoendoscopy","volume":"11","author":"Kist","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1044\/2014_JSLHR-S-12-0278","article-title":"Characterizing vibratory kinematics in children and adults with high-speed digital imaging","volume":"57","author":"Patel","year":"2014","journal-title":"J. Speech. Lang. Hear Res."},{"key":"ref_13","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":"Eysholdt","year":"1996","journal-title":"Folia. Phoniatr. Logop."},{"key":"ref_14","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":"Neubauer","year":"2001","journal-title":"J. Acoust Soc. Am."},{"key":"ref_15","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":"Larsson","year":"2000","journal-title":"Laryngoscope"},{"key":"ref_16","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":"Yan","year":"2005","journal-title":"J. Voice"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/j.jvoice.2008.03.003","article-title":"Efficient and effective extraction of vocal fold vibratory patterns from high-speed digital imaging","volume":"24","author":"Zhang","year":"2010","journal-title":"J. Voice"},{"key":"ref_18","first-page":"100","article-title":"An automatic method to detect and track the glottal gap from high speed videoendoscopic images","volume":"29","year":"2015","journal-title":"Biomed. Eng. Online"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"103854","DOI":"10.1016\/j.bspc.2022.103854","article-title":"Analysis of Laryngeal High-Speed Videoendoscopy recordings\u2013ROI detection","volume":"78","author":"Ettler","year":"2022","journal-title":"Biomed. Signal. Processing Control."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yousef, A.M., Deliyski, D.D., Zacharias, S.R.C., de Alarcon, A., Orlikoff, R.F., and Naghibolhosseini, M. (2021). A hybrid machine-learning-based method for analytic representation of the vocal fold edges during connected speech. Appl. Sci., 11.","DOI":"10.3390\/app11031179"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1993","DOI":"10.1002\/lary.29886","article-title":"Applications of Artificial Intelligence to Office Laryngoscopy: A Scoping Review","volume":"132","author":"Yao","year":"2021","journal-title":"Laryngoscope"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5\u20139). U-net Convolutional networks for biomedical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Munich, Germany.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_23","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":"Lin","year":"2019","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Fehling, M.K., Grosch, F., Schuster, M.E., Schick, B., and Lohscheller, J. (2020). Fully automatic segmentation of glottis and vocal folds in endoscopic laryngeal high-speed videos using a deep Convolutional LSTM Network. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0227791"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2098","DOI":"10.1044\/2022_JSLHR-21-00540","article-title":"A Deep Learning Approach for Quantifying Vocal Fold Dynamics During Connected Speech Using Laryngeal High-Speed Videoendoscopy","volume":"65","author":"Yousef","year":"2022","journal-title":"J. Speech Lang. Hear. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1889","DOI":"10.1044\/2021_JSLHR-20-00498","article-title":"A deep learning enhanced novel software tool for laryngeal dynamics analysis","volume":"64","author":"Kist","year":"2021","journal-title":"J. Speech Lang. Hear. Res."},{"key":"ref_27","unstructured":"Dubrovskiy, D. (2017). Bilderverarbeitung bei Endoskopischen Hochgeschwindigkeitsaufnahmen der Stimmlippenbewegungen. [Ph.D. Thesis, Universit\u00e4t Erlangen-N\u00fcrnberg]."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"E654","DOI":"10.1002\/lary.28475","article-title":"Intersegmenter variability in high-speed laryngoscopy-based glottal area waveform measures","volume":"130","author":"Maryn","year":"2020","journal-title":"Laryngoscope"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"20723","DOI":"10.1038\/s41598-020-77216-6","article-title":"Rethinking glottal midline detection","volume":"10","author":"Kist","year":"2020","journal-title":"Sci Rep."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-020-0526-3","article-title":"BAGLS, a multihospital benchmark for automatic glottis segmentation","volume":"7","author":"Gomez","year":"2020","journal-title":"Sci. Data"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","article-title":"Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning?","volume":"35","author":"Tajbakhsh","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Sun, C., Shrivastava, A., Singh, S., and Gupta, A. (2017, January 22\u201329). Revisiting unreasonable effectiveness of data in deep learning era. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.","DOI":"10.1109\/ICCV.2017.97"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Lomonaco, V., and Maltoni, D. (2016). Comparing incremental learning strategies for convolutional neural networks. IAPR Workshop on Artificial Neural Networks in Pattern Recognition, Springer.","DOI":"10.1007\/978-3-319-46182-3_15"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Du, G., Cao, X., Liang, J., Chen, X., and Zhan, Y. (2020). Medical Image Segmentation based on U-Net: A Review. J. Imaging Sci. Technol., 64.","DOI":"10.2352\/J.ImagingSci.Technol.2020.64.2.020508"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Sudre, C.H., Li, W., Vercauteren, T., Ourselin, S., and Jorge Cardoso, M. (2017). Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Buslaev, A., Iglovikov, V.I., Khvedchenya, E., Parinov, A., Druzhinin, M., and Kalinin, A.A. (2020). Albumentations: Fast and Flexible Image Augmentations. Information, 11.","DOI":"10.3390\/info11020125"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","article-title":"A survey on Image Data Augmentation for Deep Learning","volume":"6","author":"Shorten","year":"2019","journal-title":"J. Big Data"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Oliveira, A., Pereira, S., and Silva, C.A. (2017, January 16\u201318). Augmenting data when training a CNN for retinal vessel segmentation: How to warp?. Proceedings of the IEEE 5th Portuguese Meeting on Bioengineering (ENBENG), Coimbra, Portugal.","DOI":"10.1109\/ENBENG.2017.7889443"},{"key":"ref_39","unstructured":"Hinton, G., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv, Available online: https:\/\/arxiv.org\/abs\/1503.02531."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Kemker, R., McClure, M., Abitino, A., Hayes, T., and Kanan, C. (2018, January 2\u20137). Measuring Catastrophic Forgetting in Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LO, USA.","DOI":"10.1609\/aaai.v32i1.11651"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.neunet.2019.03.010","article-title":"Continuous learning in single-incremental-task scenarios","volume":"116","author":"Maltoni","year":"2019","journal-title":"Neural Netw."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1109\/5326.983933","article-title":"Learn++: An incremental learning algorithm for supervised neural networks","volume":"31","author":"Polikar","year":"2001","journal-title":"IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.)"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1615","DOI":"10.1109\/TMI.2016.2521419","article-title":"3D reconstruction of human laryngeal dynamics based on endoscopic high-speed recordings","volume":"35","author":"Semmler","year":"2016","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Applied Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3417\/12\/19\/9791\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:41:34Z","timestamp":1760143294000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3417\/12\/19\/9791"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,28]]},"references-count":43,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["app12199791"],"URL":"https:\/\/doi.org\/10.3390\/app12199791","relation":{},"ISSN":["2076-3417"],"issn-type":[{"value":"2076-3417","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,28]]}}}