{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:38:18Z","timestamp":1777635498034,"version":"3.51.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T00:00:00Z","timestamp":1648425600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T00:00:00Z","timestamp":1648425600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100000055","name":"National Institute on Deafness and Other Communication Disorders","doi-asserted-by":"publisher","award":["R21 DC016972"],"award-info":[{"award-number":["R21 DC016972"]}],"id":[{"id":"10.13039\/100000055","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s00521-022-07107-6","type":"journal-article","created":{"date-parts":[[2022,3,28]],"date-time":"2022-03-28T10:03:42Z","timestamp":1648461822000},"page":"12197-12210","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["OtoXNet\u2014automated identification of eardrum diseases from otoscope videos: a deep learning study for video-representing images"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2537-8280","authenticated-orcid":false,"given":"Hamidullah","family":"Binol","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Khalid Khan","family":"Niazi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Charles","family":"Elmaraghy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aaron C.","family":"Moberly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Metin N.","family":"Gurcan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,28]]},"reference":[{"key":"7107_CR1","doi-asserted-by":"crossref","unstructured":"Alenezi, EMA, Kathryn J, Allison R, Alessandra L-S, McMahen CSE, Tao KFM, Julie M, Tess B, Richmond PC, Eikelboom RH (2021) Clinician-rated quality of video otoscopy recordings and still images for the asynchronous assessment of middle-ear disease. J Telemed Telec 1357633X20987783","DOI":"10.1177\/1357633X20987783"},{"key":"7107_CR2","doi-asserted-by":"crossref","unstructured":"Bay H, Tinne T, Luc VG (2006) Surf: speeded up robust features. In: European conference on computer vision. Springer, pp 404\u2013417","DOI":"10.1007\/11744023_32"},{"key":"7107_CR3","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1111\/srt.12817","volume":"26","author":"H Binol","year":"2020","unstructured":"Binol H, Plotner A, Sopkovich J, Kaffenberger B, Niazi MKK, Gurcan MN (2020) Ros-NET: a deep convolutional neural network for automatic identification of rosacea lesions. Skin Res Technol 26:413\u2013421","journal-title":"Skin Res Technol"},{"key":"7107_CR4","doi-asserted-by":"crossref","unstructured":"Binol, H, Moberly AC, Niazi MKK, Garth E, Jay S, Charles E, Theodoros T, Nazhat T-S, Lianbo Y, Gurcan MN (2020) Decision fusion on image analysis and tympanometry to detect eardrum abnormalities. In: Medical imaging 2020: computer-aided diagnosis, 113141M. International Society for Optics and Photonics","DOI":"10.1117\/12.2549394"},{"key":"7107_CR5","doi-asserted-by":"publisher","first-page":"5894","DOI":"10.3390\/app10175894","volume":"10","author":"H Binol","year":"2020","unstructured":"Binol H, Moberly AC, Niazi MKK, Essig G, Shah J, Elmaraghy C, Teknos T, Taj-Schaal N, Lianbo Yu, Gurcan MN (2020) SelectStitch: automated frame segmentation and stitching to create composite images from otoscope video clips. Appl Sci 10:5894","journal-title":"Appl Sci"},{"key":"7107_CR6","doi-asserted-by":"crossref","unstructured":"Binol, H, Niazi MKK, Plotner A, Jennifer S, Kaffenberger BH, Gurcan MN (2020) A multidimensional scaling and sample clustering to obtain a representative subset of training data for transfer learning-based rosacea lesion identification. In: Medical imaging 2020: computer-aided diagnosis. International Society for Optics and Photonics, p 1131415","DOI":"10.1117\/12.2549392"},{"key":"7107_CR7","doi-asserted-by":"crossref","unstructured":"Binol H, Niazi MKK, Garth E, Jay S, Mattingly JK, Harris MS, Charles E, Theodoros T, Nazhat T\u2010S, Lianbo Y (2020) Digital otoscopy videos versus composite images: a reader study to compare the accuracy of ENT physicians. The Laryngoscope","DOI":"10.1101\/2020.08.17.20176131"},{"key":"7107_CR8","doi-asserted-by":"crossref","unstructured":"Binol, H, Niazi MKK, Charles E, Moberly AC, Gurcan MN (2021) Automated video summarization and label assignment for otoscopy videos using deep learning and natural language processing. In: Medical imaging 2021: imaging informatics for healthcare, research, and applications, 116010S. International Society for Optics and Photonics","DOI":"10.1117\/12.2582009"},{"key":"7107_CR9","first-page":"4","volume":"5","author":"J-Y Bouguet","year":"2001","unstructured":"Bouguet J-Y (2001) Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel corporation 5:4","journal-title":"Intel corporation"},{"key":"7107_CR10","doi-asserted-by":"publisher","first-page":"1831","DOI":"10.3390\/app11041831","volume":"11","author":"S Camalan","year":"2021","unstructured":"Camalan S, Moberly AC, Teknos T, Essig G, Elmaraghy C, Taj-Schaal N, Gurcan MN (2021) OtoPair: combining right and left eardrum otoscopy images to improve the accuracy of automated image analysis. Appl Sci 11:1831","journal-title":"Appl Sci"},{"key":"7107_CR11","doi-asserted-by":"crossref","unstructured":"Camalan S, Niazi MKK, Moberly AC, Theodoros T, Garth E, Charles E, Nazhat T-S, Gurcan MN (2020) OtoMatch: Content-based eardrum image retrieval using deep learning. PloS one 15:e0232776","DOI":"10.1371\/journal.pone.0232776"},{"key":"7107_CR12","doi-asserted-by":"publisher","first-page":"514","DOI":"10.1109\/ACCESS.2014.2325029","volume":"2","author":"X-W Chen","year":"2014","unstructured":"Chen X-W, Lin X (2014) Big data deep learning: challenges and perspectives. IEEE access 2:514\u2013525","journal-title":"IEEE access"},{"key":"7107_CR13","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1109\/TIP.2010.2092441","volume":"20","author":"G Deng","year":"2010","unstructured":"Deng G (2010) A generalized unsharp masking algorithm. IEEE Trans Image Process 20:1249\u20131261","journal-title":"IEEE Trans Image Process"},{"key":"7107_CR14","doi-asserted-by":"crossref","unstructured":"Deng J, Wei D, Richard S, Li-Jia L, Kai L, Li F-F (2009) Imagenet: a large-scale hierarchical image database. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"7107_CR15","doi-asserted-by":"publisher","first-page":"551","DOI":"10.1109\/TIT.1983.1056714","volume":"29","author":"H Edelsbrunner","year":"1983","unstructured":"Edelsbrunner H, Kirkpatrick D, Seidel R (1983) On the shape of a set of points in the plane. IEEE Trans Inf Theory 29:551\u2013559","journal-title":"IEEE Trans Inf Theory"},{"key":"7107_CR16","doi-asserted-by":"crossref","unstructured":"Gygli M, Helmut G, Hayko R, Luc VG (2014) Creating summaries from user videos. In: European conference on computer vision. Springer, pp 505\u2013520","DOI":"10.1007\/978-3-319-10584-0_33"},{"key":"7107_CR17","doi-asserted-by":"crossref","unstructured":"Han B, Jihun H, Jack S (2011) Personalized video summarization with human in the loop. In: 2011 IEEE workshop on applications of computer vision (WACV). IEEE, pp 51\u201357","DOI":"10.1109\/WACV.2011.5711483"},{"key":"7107_CR18","doi-asserted-by":"crossref","unstructured":"He K, Xiangyu Z, Shaoqing R, Jian S (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"7107_CR19","unstructured":"Jeffay K, Hong JZ (2001) Readings in multimedia computing and networking (Elsevier)"},{"key":"7107_CR20","doi-asserted-by":"crossref","unstructured":"Jiang X, Shan L, Scott PJ (2011) Morphological method for surface metrology and dimensional metrology based on the alpha shape. Measur Sci Technol 23:015003","DOI":"10.1088\/0957-0233\/23\/1\/015003"},{"key":"7107_CR21","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1001\/archpedi.1992.02160160053013","volume":"146","author":"PH Kaleida","year":"1992","unstructured":"Kaleida PH, Stool SE (1992) Assessment of otoscopists\u2019 accuracy regarding middle-ear effusion: otoscopic validation. Am J Dis Child 146:433\u2013435","journal-title":"Am J Dis Child"},{"key":"7107_CR22","unstructured":"Kasher MS (2018) Otitis media analysis-an automated feature extraction and image classification system"},{"key":"7107_CR23","doi-asserted-by":"crossref","unstructured":"Khorbotly S, Firas H (2011) A modified approximation of 2D Gaussian smoothing filters for fixed-point platforms. In: 2011 IEEE 43rd southeastern symposium on system theory, pp 151\u201359. IEEE","DOI":"10.1109\/SSST.2011.5753797"},{"key":"7107_CR24","unstructured":"Kingma DP, Jimmy B (2014) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"7107_CR25","first-page":"27","volume":"2013","author":"A Kuruvilla","year":"2013","unstructured":"Kuruvilla A, Shaikh N, Hoberman A, Kova\u010devi\u0107 J (2013) Automated diagnosis of otitis media: vocabulary and grammar. J Biomed Imag 2013:27","journal-title":"J Biomed Imag"},{"key":"7107_CR26","doi-asserted-by":"publisher","first-page":"1827","DOI":"10.3390\/app9091827","volume":"9","author":"JY Lee","year":"2019","unstructured":"Lee JY, Choi S-H, Chung JW (2019) Automated classification of the tympanic membrane using a convolutional neural network. Appl Sci 9:1827","journal-title":"Appl Sci"},{"key":"7107_CR27","doi-asserted-by":"publisher","first-page":"e964","DOI":"10.1542\/peds.2012-3488","volume":"131","author":"AS Lieberthal","year":"2013","unstructured":"Lieberthal AS, Carroll AE, Chonmaitree T, Ganiats TG, Hoberman A, Jackson MA, Joffe MD, Miller DT, Rosenfeld RM, Sevilla XD (2013) The diagnosis and management of acute otitis media. Pediatrics 131:e964\u2013e999","journal-title":"Pediatrics"},{"key":"7107_CR28","doi-asserted-by":"crossref","unstructured":"Lin T-Y, Michael M, Serge B, James H, Pietro P, Deva R, Piotr D, Zitnick CL (2014) Microsoft coco: common objects in context. In: European conference on computer vision, pp 740\u2013755. Springer","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"7107_CR29","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.knosys.2015.01.010","volume":"80","author":"J Lu","year":"2015","unstructured":"Lu J, Behbood V, Hao P, Zuo H, Xue S, Zhang G (2015) Transfer learning using computational intelligence: a survey. Knowl Based Syst 80:14\u201323","journal-title":"Knowl Based Syst"},{"key":"7107_CR30","unstructured":"Microsoft. Image composite editor (ICE). Accessed 20 Dec 2018. https:\/\/www.microsoft.com\/en-us\/research\/product\/computational-photography-applications\/image-composite-editor\/"},{"key":"7107_CR31","unstructured":"Mironic\u0103 I, Constantin V, Dan CG (2011) Automatic pediatric otitis detection by classification of global image features. In: 2011 E-health and bioengineering conference (EHB), pp 1\u20134. IEEE"},{"key":"7107_CR32","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1177\/1357633X17708531","volume":"24","author":"AC Moberly","year":"2018","unstructured":"Moberly AC, Zhang M, Lianbo Yu, Gurcan M, Senaras C, Teknos TN, Elmaraghy CA, Taj-Schaal N, Essig GF (2018) Digital otoscopy versus microscopy: How correct and confident are ear experts in their diagnoses? J Telemed Telecare 24:453\u2013459","journal-title":"J Telemed Telecare"},{"key":"7107_CR33","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1016\/j.ebiom.2016.02.017","volume":"5","author":"HC Myburgh","year":"2016","unstructured":"Myburgh HC, Van Zijl WH, Swanepoel DeWet, Hellstr\u00f6m S, Laurent C (2016) Otitis media diagnosis for developing countries using tympanic membrane image-analysis. EBioMedicine 5:156\u2013160","journal-title":"EBioMedicine"},{"key":"7107_CR34","doi-asserted-by":"crossref","unstructured":"Niazi MKK, Thomas ET, Vidya A, Hartman DJ, Liron P, Gurcan MN (2018) Identifying tumor in pancreatic neuroendocrine neoplasms from Ki67 images using transfer learning. PloS One 13:e0195621","DOI":"10.1371\/journal.pone.0195621"},{"key":"7107_CR35","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan SJ, Yang Q (2009) A survey on transfer learning. IEEE Trans Knowl Data Eng 22:1345\u20131359","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"7107_CR36","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1097\/00006454-199806000-00032","volume":"17","author":"SI Pelton","year":"1998","unstructured":"Pelton SI (1998) Otoscopy for the diagnosis of otitis media. Pediatr Infect Dis J 17:540\u2013543","journal-title":"Pediatr Infect Dis J"},{"key":"7107_CR37","doi-asserted-by":"crossref","unstructured":"Physicians, American Academy of Family (2004) Otitis media with effusion. Pediatrics 113:1412","DOI":"10.1542\/peds.113.5.1412"},{"key":"7107_CR38","doi-asserted-by":"crossref","unstructured":"Prest A, Christian L, Javier C, Cordelia S, Vittorio F (2012) Learning object class detectors from weakly annotated video. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 3282\u20133289","DOI":"10.1109\/CVPR.2012.6248065"},{"key":"7107_CR39","unstructured":"Raghu M, Chiyuan Z, Jon K, Samy B (2019) Transfusion: understanding transfer learning for medical imaging. In: Advances in neural information processing systems, pp 3347\u20133357"},{"key":"7107_CR40","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1097\/MAO.0000000000000952","volume":"37","author":"LS Rosito","year":"2016","unstructured":"Rosito LS, Netto LS, Teixeira AR, Selaimen da Costa S (2016) Sensorineural hearing loss in cholesteatoma. Otol Neurotol 37:214\u2013217","journal-title":"Otol Neurotol"},{"key":"7107_CR41","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1007\/s10278-012-9483-5","volume":"26","author":"S Samsudin","year":"2013","unstructured":"Samsudin S, Adwan S, Arof H, Mokhtar N, Ibrahim F (2013) Development of automated image stitching system for radiographic images. J Digit Imaging 26:361\u2013370","journal-title":"J Digit Imaging"},{"key":"7107_CR42","doi-asserted-by":"crossref","unstructured":"Senaras C, Moberly AC, Theodoros T, Garth E, Charles E, Nazhat T-S, Lianbo Y, Metin G (2017) Autoscope: automated otoscopy image analysis to diagnose ear pathology and use of clinically motivated eardrum features. In: Medical imaging 2017: computer-aided diagnosis. International Society for Optics and Photonics, p 101341X","DOI":"10.1117\/12.2250592"},{"key":"7107_CR43","doi-asserted-by":"crossref","unstructured":"Senaras C, Moberly AC, Theodoros T, Garth E, Charles E, Nazhat T-S, Lianbo Y, Gurcan MN (2018) Detection of eardrum abnormalities using ensemble deep learning approaches. In: Medical imaging 2018: computer-aided diagnosis. International Society for Optics and Photonics, p 105751A","DOI":"10.1117\/12.2293297"},{"key":"7107_CR44","unstructured":"Shie C-K, Hao-Ting C, Fu-Cheng F, Chung-Jung C, Te-Yung F, Pa-Chun W (2014) A hybrid feature-based segmentation and classification system for the computer aided self-diagnosis of otitis media. In: 2014 36th annual international conference of the IEEE engineering in medicine and biology society. IEEE, pp 4655\u20134658"},{"key":"7107_CR45","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1111\/j.1745-7599.2001.tb00019.x","volume":"13","author":"A Sorrento","year":"2001","unstructured":"Sorrento A, Pichichero ME (2001) Assessing diagnostic accuracy and tympanocentesis skills by nurse practitioners in management of otitis media. J Am Acad Nurse Pract 13:524\u2013529","journal-title":"J Am Acad Nurse Pract"},{"key":"7107_CR46","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vincent V, Sergey I, Jon S, Zbigniew W (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"7107_CR47","doi-asserted-by":"publisher","first-page":"1060","DOI":"10.1097\/MAO.0000000000001897","volume":"39","author":"T-T Tran","year":"2018","unstructured":"Tran T-T, Fang T-Y, Pham V-T, Lin C, Wang P-C, Lo M-T (2018) Development of an Automatic Diagnostic Algorithm For Pediatric Otitis media. Otol Neurotol 39:1060\u20131065","journal-title":"Otol Neurotol"},{"key":"7107_CR48","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3724\/SP.J.2096-5796.2018.0008","volume":"1","author":"L Wei","year":"2019","unstructured":"Wei L, Zhong Z, Lang C, Yi Z (2019) A survey on image and video stitching. Virtual Reality Intell Hardw 1:55\u201383","journal-title":"Virtual Reality Intell Hardw"},{"key":"7107_CR49","doi-asserted-by":"crossref","unstructured":"Yap BW, Khatijahhusna AR, Hezlin AAR, Simon F, Zuraida K, Nik NA (2014) An application of oversampling, undersampling, bagging and boosting in handling imbalanced datasets. In: Proceedings of the first international conference on advanced data and information engineering (DaEng-2013). Springer, pp 13\u201322","DOI":"10.1007\/978-981-4585-18-7_2"},{"key":"7107_CR50","unstructured":"Yosinski J, Jeff C, Yoshua B, Hod L (2014) How transferable are features in deep neural networks? In: Advances in neural information processing systems, pp 3320\u20133328"},{"key":"7107_CR51","unstructured":"Zhang Y, Hang J, Yasuhide M, Manning CD, Langlotz CP (2020) Contrastive learning of medical visual representations from paired images and text. arXiv preprint arXiv:2010.00747"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07107-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07107-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07107-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T05:40:09Z","timestamp":1657863609000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07107-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,28]]},"references-count":51,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["7107"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07107-6","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2021.08.05.21261672","asserted-by":"object"}]},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,28]]},"assertion":[{"value":"7 June 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Authors ACM and CE are shareholders in Otologic Technologies. Authors ACM and MNG are paid consultants and serve on the Board of Directors for Otologic Technologies.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}]}}