{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:32:01Z","timestamp":1774416721833,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2019,1,16]],"date-time":"2019-01-16T00:00:00Z","timestamp":1547596800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s11548-018-01910-0","type":"journal-article","created":{"date-parts":[[2019,1,16]],"date-time":"2019-01-16T00:47:56Z","timestamp":1547599676000},"page":"483-492","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":94,"title":["A dataset of laryngeal endoscopic images with comparative study on convolution neural network-based semantic segmentation"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0156-7247","authenticated-orcid":false,"given":"Max-Heinrich","family":"Laves","sequence":"first","affiliation":[]},{"given":"Jens","family":"Bicker","sequence":"additional","affiliation":[]},{"given":"L\u00fcder A.","family":"Kahrs","sequence":"additional","affiliation":[]},{"given":"Tobias","family":"Ortmaier","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,1,16]]},"reference":[{"key":"1910_CR1","doi-asserted-by":"publisher","unstructured":"Allin S, Galeotti J, Stetten G, Dailey SH (2004) Enhanced snake based segmentation of vocal folds. In: IEEE international symposium on biomedical imaging: nano to macro, vol 1, pp 812\u2013815. \n                    https:\/\/doi.org\/10.1109\/ISBI.2004.1398662","DOI":"10.1109\/ISBI.2004.1398662"},{"key":"1910_CR2","doi-asserted-by":"publisher","unstructured":"Aubreville M, Knipfer C, Oetter N, Jaremenko C, Rodner E, Denzler J, Bohr C, Neumann H, Stelzle F, Maier A (2017) Automatic classification of cancerous tissue in laserendomicroscopy images of the oral cavity using deep learning. Sci Rep. \n                    https:\/\/doi.org\/10.1038\/s41598-017-12320-8","DOI":"10.1038\/s41598-017-12320-8"},{"issue":"12","key":"1910_CR3","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder\u2013decoder architecture for image segmentation. IEEE Trans Pattern Anal Mach Intell 39(12):2481\u20132495. \n                    https:\/\/doi.org\/10.1109\/TPAMI.2016.2644615","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"1910_CR4","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1109\/JBHI.2014.2374975","volume":"20","author":"C Barbalata","year":"2016","unstructured":"Barbalata C, Mattos LS (2016) Laryngeal tumor detection and classification in endoscopic video. IEEE J Biomed Health Inf 20(1):322\u2013332. \n                    https:\/\/doi.org\/10.1109\/JBHI.2014.2374975","journal-title":"IEEE J Biomed Health Inf"},{"issue":"03","key":"1910_CR5","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1055\/s-0036-1583547","volume":"37","author":"JM Barkmeier-Kraemer","year":"2016","unstructured":"Barkmeier-Kraemer JM, Patel RR (2016) The next 10 years in voice evaluation and treatment. Semin Speech Lang 37(03):158\u2013165. \n                    https:\/\/doi.org\/10.1055\/s-0036-1583547","journal-title":"Semin Speech Lang"},{"issue":"3","key":"1910_CR6","doi-asserted-by":"publisher","first-page":"e158","DOI":"10.1016\/j.cmpb.2011.07.015","volume":"104","author":"M Cabezas","year":"2011","unstructured":"Cabezas M, Oliver A, Llad\u00f3 X, Freixenet J, Cuadra MB (2011) A review of atlas-based segmentation for magnetic resonance brain images. Comput Methods Programs Biomed 104(3):e158\u2013e177. \n                    https:\/\/doi.org\/10.1016\/j.cmpb.2011.07.015","journal-title":"Comput Methods Programs Biomed"},{"key":"1910_CR7","doi-asserted-by":"publisher","unstructured":"Cordts M, Omran M, Ramos S, Rehfeld T, Enzweiler M, Benenson R, Franke U, Roth S, Schiele B (2016) The cityscapes dataset for semantic urban scene understanding. In: IEEE conference on computer vision and pattern recognition, pp 3213\u20133223. \n                    https:\/\/doi.org\/10.1109\/CVPR.2016.350","DOI":"10.1109\/CVPR.2016.350"},{"issue":"8","key":"1910_CR8","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1049\/iet-cvi.2018.5243","volume":"12","author":"A Creswell","year":"2018","unstructured":"Creswell A, Pouplin A, Bharath AA (2018) Denoising adversarial autoencoders: classifying skin lesions using limited labelled training data. IET Comput Vis 12(8):1105\u20131111. \n                    https:\/\/doi.org\/10.1049\/iet-cvi.2018.5243","journal-title":"IET Comput Vis"},{"issue":"5","key":"1910_CR9","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1016\/j.rti.2005.06.008","volume":"11","author":"C Doignon","year":"2005","unstructured":"Doignon C, Graebling P, de Mathelin M (2005) Real-time segmentation of surgical instruments inside the abdominal cavity using a joint hue saturation color feature. Real-Time Imaging 11(5):429\u2013442. \n                    https:\/\/doi.org\/10.1016\/j.rti.2005.06.008","journal-title":"Real-Time Imaging"},{"issue":"8","key":"1910_CR10","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1177\/0003489415575548","volume":"124","author":"DT Friedrich","year":"2015","unstructured":"Friedrich DT, Scheithauer MO, Greve J, Duvvuri U, Sommer F, Hoffmann TK, Schuler PJ (2015) Potential advantages of a single-port, operator-controlled flexible endoscope system for transoral surgery of the larynx. Ann Otol Rhinol Laryngol 124(8):655\u2013662. \n                    https:\/\/doi.org\/10.1177\/0003489415575548","journal-title":"Ann Otol Rhinol Laryngol"},{"key":"1910_CR11","unstructured":"Gal Y, Ghahramani Z (2016) Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33rd international conference on machine learning, vol 48, pp 1050\u20131059"},{"key":"1910_CR12","doi-asserted-by":"publisher","unstructured":"Garc\u00eda-Peraza-Herrera LC, Li W, Gruijthuijsen C, Devreker A, Attilakos G, Deprest J, Poorten EV, Stoyanov D, Vercauteren T, Ourselin S (2017) Real-time segmentation of non-rigid surgical tools based on deep learning and tracking. In: Lecture Notes on Computer Science LNCS, vol 10170, pp 84\u201395. \n                    https:\/\/doi.org\/10.1007\/978-3-319-54057-3_8","DOI":"10.1007\/978-3-319-54057-3_8"},{"issue":"4","key":"1910_CR13","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/S0893-6080(96)00098-6","volume":"10","author":"S Hashem","year":"1997","unstructured":"Hashem S (1997) Optimal linear combinations of neural networks. Neural Netw 10(4):599\u2013614. \n                    https:\/\/doi.org\/10.1016\/S0893-6080(96)00098-6","journal-title":"Neural Netw"},{"key":"1910_CR14","doi-asserted-by":"publisher","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: IEEE International conference on computer vision, pp 1026\u20131034. \n                    https:\/\/doi.org\/10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"1910_CR15","first-page":"5574","volume":"30","author":"A Kendall","year":"2017","unstructured":"Kendall A, Gal Y (2017) What uncertainties do we need in Bayesian deep learning for computer vision? Adv Neural Inf Process Syst 30:5574\u20135584","journal-title":"Adv Neural Inf Process Syst"},{"key":"1910_CR16","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. ArXiv e-prints \n                    https:\/\/arxiv.org\/abs\/1412.6980"},{"key":"1910_CR17","doi-asserted-by":"crossref","unstructured":"Lin TY, Goyal P, Girshick R, He K, Doll\u00e1r P (2017) Focal loss for dense object detection. ArXiv e-prints \n                    arXiv:1708.02002","DOI":"10.1109\/ICCV.2017.324"},{"key":"1910_CR18","doi-asserted-by":"publisher","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition, pp 3431\u20133440. \n                    https:\/\/doi.org\/10.1109\/CVPR.2015.7298965","DOI":"10.1109\/CVPR.2015.7298965"},{"issue":"8","key":"1910_CR19","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/TMI.2006.877092","volume":"25","author":"JA Noble","year":"2006","unstructured":"Noble JA, Boukerroui D (2006) Ultrasound image segmentation: a survey. IEEE Trans Med Imaging 25(8):987\u20131010. \n                    https:\/\/doi.org\/10.1109\/TMI.2006.877092","journal-title":"IEEE Trans Med Imaging"},{"key":"1910_CR20","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/S1361-8415(00)00041-4","volume":"5","author":"SD Olabarriaga","year":"2001","unstructured":"Olabarriaga SD, Smeulders AWM (2001) Interaction in the segmentation of medical images: a survey. Med Image Anal 5:127\u2013142. \n                    https:\/\/doi.org\/10.1016\/S1361-8415(00)00041-4","journal-title":"Med Image Anal"},{"issue":"3","key":"1910_CR21","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.compmedimag.2007.12.003","volume":"32","author":"V Osma-Ruiz","year":"2008","unstructured":"Osma-Ruiz V, Godino-Llorente JI, S\u00e1enz-Lech\u00f3n N, Fraile R (2008) Segmentation of the glottal space from laryngeal images using the watershed transform. Comput Med Imaging Graph 32(3):193\u2013201","journal-title":"Comput Med Imaging Graph"},{"issue":"9","key":"1910_CR22","doi-asserted-by":"publisher","first-page":"1277","DOI":"10.1016\/0031-3203(93)90135-J","volume":"26","author":"NR Pal","year":"1993","unstructured":"Pal NR, Pal SK (1993) A review on image segmentation techniques. Pattern Recognit 26(9):1277\u20131294. \n                    https:\/\/doi.org\/10.1016\/0031-3203(93)90135-J","journal-title":"Pattern Recognit"},{"key":"1910_CR23","doi-asserted-by":"publisher","unstructured":"Panek D, Skalski A, Zielinski T, Deliyski DD (2015) Voice pathology classification based on high-speed videoendoscopy. In: Annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp 735\u2013738. \n                    https:\/\/doi.org\/10.1109\/EMBC.2015.7318467","DOI":"10.1109\/EMBC.2015.7318467"},{"key":"1910_CR24","unstructured":"Paszke A, Chaurasia A, Kim S, Culurciello E (2016) ENet: a deep neural network architecture for real-time semantic segmentation. ArXiv e-prints \n                    http:\/\/arxiv.org\/abs\/1606.02147"},{"key":"1910_CR25","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in PyTorch. In: 31st Conference on neural information processing systems (NIPS). \n                    https:\/\/openreview.net\/forum?id=BJJsrmfCZ\n                    \n                  . Accessed 1 Oct 2018"},{"issue":"1","key":"1910_CR26","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1109\/TPAMI.2005.17","volume":"27","author":"SL Phung","year":"2005","unstructured":"Phung SL, Bouzerdoum A, Chai D (2005) Skin segmentation using color pixel classification: analysis and comparison. IEEE Trans Pattern Anal Mach Intell 27(1):148\u2013154. \n                    https:\/\/doi.org\/10.1109\/TPAMI.2005.17","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"1910_CR27","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/S0895-6111(03)00054-5","volume":"28","author":"M Rajab","year":"2004","unstructured":"Rajab M, Woolfson M, Morgan S (2004) Application of region-based segmentation and neural network edge detection to skin lesions. Comput Med Imaging Graph 28(1):61\u201368. \n                    https:\/\/doi.org\/10.1016\/S0895-6111(03)00054-5","journal-title":"Comput Med Imaging Graph"},{"issue":"1","key":"1910_CR28","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1109\/TITS.2017.2750080","volume":"19","author":"E Romera","year":"2018","unstructured":"Romera E, \u00c1lvarez JM, Bergasa LM, Arroyo R (2018) ERFNet: efficient residual factorized convnet for real-time semantic segmentation. IEEE Trans Intell Transp Syst 19(1):263\u2013272. \n                    https:\/\/doi.org\/10.1109\/TITS.2017.2750080","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"1910_CR29","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: Medical image computing and computer-assisted intervention\u2014MICCAI 2015, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1910_CR30","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.media.2017.06.004","volume":"40","author":"A Schoob","year":"2017","unstructured":"Schoob A, Kundrat D, Kahrs LA, Ortmaier T (2017) Stereo vision-based tracking of soft tissue motion with application to online ablation control in laser microsurgery. Med Image Anal 40:80\u201395. \n                    https:\/\/doi.org\/10.1016\/j.media.2017.06.004","journal-title":"Med Image Anal"},{"key":"1910_CR31","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.optlaseng.2016.03.002","volume":"83","author":"A Schoob","year":"2016","unstructured":"Schoob A, Kundrat D, Lekon S, Kahrs LA, Ortmaier T (2016) Color-encoded distance for interactive focus positioning in laser microsurgery. Opt Lasers Eng 83:71\u201379. \n                    https:\/\/doi.org\/10.1016\/j.optlaseng.2016.03.002","journal-title":"Opt Lasers Eng"},{"issue":"12","key":"1910_CR32","doi-asserted-by":"publisher","first-page":"2325","DOI":"10.1007\/s11548-016-1420-5","volume":"11","author":"A Schoob","year":"2016","unstructured":"Schoob A, Laves MH, Kahrs LA, Ortmaier T (2016) Soft tissue motion tracking with application to tablet-based incision planning in laser surgery. Int J Comput Assist Radiol Surg 11(12):2325\u20132337. \n                    https:\/\/doi.org\/10.1007\/s11548-016-1420-5","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"5","key":"1910_CR33","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1109\/TMI.2016.2535302","volume":"35","author":"N Tajbakhsh","year":"2016","unstructured":"Tajbakhsh N, Shin JY, Gurudu SR, Hurst RT, Kendall CB, Gotway MB, Liang J (2016) Convolutional neural networks for medical image analysis: full training or fine tuning? IEEE Trans Med Imaging 35(5):1299\u20131312. \n                    https:\/\/doi.org\/10.1109\/TMI.2016.2535302","journal-title":"IEEE Trans Med Imaging"},{"key":"1910_CR34","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1016\/j.compbiomed.2015.02.001","volume":"62","author":"HI Turkmen","year":"2015","unstructured":"Turkmen HI, Karsligil ME, Kocak I (2015) Classification of laryngeal disorders based on shape and vascular defects of vocal folds. Comput Biol Med 62:76\u201385. \n                    https:\/\/doi.org\/10.1016\/j.compbiomed.2015.02.001","journal-title":"Comput Biol Med"},{"issue":"1","key":"1910_CR35","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1158\/0008-5472.CAN-14-1458","volume":"75","author":"J Unger","year":"2015","unstructured":"Unger J, Lohscheller J, Reiter M, Eder K, Betz CS, Schuster M (2015) A noninvasive procedure for early-stage discrimination of malignant and precancerous vocal fold lesions based on laryngeal dynamics analysis. Cancer Res 75(1):31\u201339. \n                    https:\/\/doi.org\/10.1158\/0008-5472.CAN-14-1458","journal-title":"Cancer Res"},{"issue":"7","key":"1910_CR36","doi-asserted-by":"publisher","first-page":"1562","DOI":"10.1109\/TMI.2018.2791721","volume":"37","author":"G Wang","year":"2018","unstructured":"Wang G, Li W, Zuluaga MA, Pratt R, Patel PA, Aertsen M, Doel T, David AL, Deprest J, Ourselin S, Vercauteren T (2018) Interactive medical image segmentation using deep learning with image-specific fine tuning. IEEE Trans Med Imaging 37(7):1562\u20131573. \n                    https:\/\/doi.org\/10.1109\/TMI.2018.2791721","journal-title":"IEEE Trans Med Imaging"},{"issue":"1","key":"1910_CR37","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1016\/S0004-3702(02)00190-X","volume":"137","author":"ZH Zhou","year":"2002","unstructured":"Zhou ZH, Wu J, Tang W (2002) Ensembling neural networks: many could be better than all. Artif Intell 137(1):239\u2013263. \n                    https:\/\/doi.org\/10.1016\/S0004-3702(02)00190-X","journal-title":"Artif Intell"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11548-018-01910-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-018-01910-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-018-01910-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,1,15]],"date-time":"2020-01-15T19:06:03Z","timestamp":1579115163000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11548-018-01910-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,16]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["1910"],"URL":"https:\/\/doi.org\/10.1007\/s11548-018-01910-0","relation":{},"ISSN":["1861-6410","1861-6429"],"issn-type":[{"value":"1861-6410","type":"print"},{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,16]]},"assertion":[{"value":"9 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 December 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The endoscopic video images were acquired by Prof. Giorgio Peretti (Director of Otorhinolaryngology at Ospedale Policlinico San Martino, University of Genova). Patients gave their written consent for the procedure and the use of the data. No further approval is necessary for such endoscopic recordings. The videos were anonymized and made available inside the RALP consortium for further usage.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Formal consent"}},{"value":"All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and\/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical standards"}}]}}