{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T18:31:57Z","timestamp":1786386717975,"version":"build-2736575974"},"reference-count":46,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aao-hnsfjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Otolaryngol.--head neck surg."],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To evaluate a deep learning (DL)\u2010based approach for predicting air\u2010bone gap (ABG) from tympanic membrane (TM) perforation images using automated segmentation and feature extraction, addressing the limitations of audiometry availability in certain populations or settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Study Design<\/jats:title>\n                    <jats:p>Prospective, cross\u2010sectional diagnostic study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Setting<\/jats:title>\n                    <jats:p>Tertiary academic medical center.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 1239 otoscopic images were collected between January 2019 and May 2023. Of these, 1014 intact TM images and 150 perforated TM images were used for model development and validation, and 75 intraoperative perforated images were reserved for independent testing. A Mask region\u2010based convolutional neural network (Mask R\u2010CNN) model was trained to segment TM and perforation areas. Segmentation performance was evaluated using class pixel accuracy (CPA), intersection over union (IoU), and Dice coefficient. Quantitative features\u2014including perforation ratio and spatial metrics\u2014were extracted to predict ABG using theoretical and quadratic regression models. Model performance was assessed using\n                      <jats:italic>R<\/jats:italic>\n                      \u00b2, root mean square error (RMSE), and the proportion of predictions within 10\u2009dB of measured ABG.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      TM segmentation achieved CPA, IoU, and Dice scores of 0.794, 0.702, and 0.875; perforation segmentation yielded scores of 0.824, 0.729, and 0.894. ABG prediction showed\n                      <jats:italic>R<\/jats:italic>\n                      \u00b2 values of 0.433 (theoretical) and 0.516 (quadratic), with RMSEs of 6.15 and 5.68\u2009dB. Deep learning (DL)\u2010assisted models achieved accuracy of 83% and 86%, comparable to manual annotation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>DL\u2010based analysis of TM images enables accurate ABG prediction and may provide a scalable tool to support assessment of conductive hearing loss in environments without access to audiometry.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/ohn.70074","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T20:26:49Z","timestamp":1763497609000},"page":"403-412","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning\u2010Assisted Prediction of Air\u2010Bone Gap Using Tympanic Membrane Perforation Image Features"],"prefix":"10.1002","volume":"174","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7015-4771","authenticated-orcid":false,"given":"Te\u2010Yi","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Otolaryngology Hsinchu Cathay General Hospital Hsinchu Taiwan"},{"name":"Department of Biomedical Sciences and Engineering National Central University Taoyuan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsiang\u2010Chih","family":"Chang","sequence":"additional","affiliation":[{"name":"Institute of Population Health Sciences National Health Research Institutes Miaoli County Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pa\u2010Chun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology Cathay General Hospital Taipei Taiwan"},{"name":"School of Medicine Fu\u2010Jen Catholic University New Taipei City Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Su\u2010Yi","family":"Hsu","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology Cathay General Hospital Taipei Taiwan"},{"name":"School of Medicine Fu\u2010Jen Catholic University New Taipei City Taiwan"},{"name":"School of Medicine National Tsing Hua University Hsinchu Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Te\u2010Yung","family":"Fang","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology Cathay General Hospital Taipei Taiwan"},{"name":"School of Medicine Fu\u2010Jen Catholic University New Taipei City Taiwan"},{"name":"Department of Otolaryngology Sijhih Cathay General Hospital New Taipei City Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Van\u2010Truong","family":"Pham","sequence":"additional","affiliation":[{"name":"Department of Automation Engineering Hanoi University of Science and Technology  Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thi\u2010Thao","family":"Tran","sequence":"additional","affiliation":[{"name":"Department of Automation Engineering Hanoi University of Science and Technology  Vietnam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6261-8509","authenticated-orcid":false,"given":"Chen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences and Engineering National Central University Taoyuan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Men\u2010Tzung","family":"Lo","sequence":"additional","affiliation":[{"name":"Department of Biomedical Sciences and Engineering National Central University Taoyuan Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"e_1_2_8_2_1","unstructured":"World Health Organization. Deafness and hearing loss. Geneva: World Health Organization; 2024. Accessed August 16 2025.https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/deafness-and-hearing-loss"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1177\/0194599815623467"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/00129492-200303000-00023"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1001\/archotol.124.3.249"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/geront\/43.5.661"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2013.1868"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1542\/peds.106.3.e43"},{"issue":"2","key":"e_1_2_8_9_1","first-page":"2","article-title":"The aging auditory system: anatomic and physiologic changes and implications for rehabilitation","volume":"42","author":"Chisolm TH","year":"2003","journal-title":"Int J Audiol"},{"issue":"01","key":"e_1_2_8_10_1","first-page":"2","article-title":"Degree of hearing loss in association with site of tympanic membrane perforation: a systematic review","volume":"17","author":"Basheer HMU","year":"2023","journal-title":"Pak J Med Health Sci"},{"issue":"7","key":"e_1_2_8_11_1","first-page":"1","article-title":"The impact of tympanic membrane perforations on middle ear transfer function","volume":"279","author":"Bevis N","year":"2021","journal-title":"Eur Arch Otrhinolaryngol"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/MAO.0000000000002840"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00405-019-05710-3"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1017\/S0022215100088162"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.18203\/issn.2454-5929.ijohns20175606"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.18203\/issn.2454-5929.ijohns20180717"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1044\/2020_JSLHR-20-00068"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.5008741"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12070-011-0129-6"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.3342\/ceo.2015.8.2.92"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.mao.0000176177.17636.53"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2019.06.050"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01159-9"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.03.023"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/app9091827"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2017.07.015"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2016.02.017"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1002\/lary.29302"},{"issue":"3","key":"e_1_2_8_29_1","first-page":"1","article-title":"OtoVision: bridging machine learning and edge computing for effective and affordable ear disease diagnosis","volume":"37","author":"Yokananth R","year":"2024","journal-title":"Neural Comput Appl"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoto.2022.0900"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.37018\/MYWB9397"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.18203\/issn.2454-5929.ijohns20182699"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.18203\/issn.2454-5929.ijohns20183693"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.4103\/0971-7749.129796"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.otot.2021.05.009"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.18203\/issn.2454-5929.ijohns20180016"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102065"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-020-01772-7"},{"key":"e_1_2_8_39_1","article-title":"The semantic segmentation approach for normal and pathologic tympanic membrane using deep learning","author":"Seok J","year":"2019","journal-title":"BioRxiv"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.21053\/ceo.2022.00675"},{"key":"e_1_2_8_41_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0107-6"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_8_43_1","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: convolutional networks for biomedical image segmentation. Paper presented at: Medical image computing and computer\u2010assisted intervention\u2013MICCAI 2015: 18th international conference Munich Germany October 5\u20109 2015 proceedings part III 182015."},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0942-0"},{"key":"e_1_2_8_45_1","doi-asserted-by":"crossref","unstructured":"GuptaA SteadTS GantiL.Determining a meaningful R\u2010squared value in clinical medicine.Academic Medicine & Surgery.2024.","DOI":"10.62186\/001c.125154"},{"key":"e_1_2_8_46_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation. Paper presented at: Proceedings of the IEEE conference on computer vision and pattern recognition;2015.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_8_47_1","doi-asserted-by":"crossref","unstructured":"WangX PengY LuL LuZ BagheriM SummersRM.Chestx\u2010ray8: Hospital\u2010scale chest x\u2010ray database and benchmarks on weakly\u2010supervised classification and localization of common thorax diseases. Paper presented at: Proceedings of the IEEE conference on computer vision and pattern recognition;2017.","DOI":"10.1109\/CVPR.2017.369"}],"container-title":["Otolaryngology\u2013Head and Neck Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aao-hnsfjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ohn.70074","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aao-hnsfjournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/ohn.70074","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aao-hnsfjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/ohn.70074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T18:26:54Z","timestamp":1786386414000},"score":1,"resource":{"primary":{"URL":"https:\/\/aao-hnsfjournals.onlinelibrary.wiley.com\/doi\/10.1002\/ohn.70074"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":46,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/ohn.70074"],"URL":"https:\/\/doi.org\/10.1002\/ohn.70074","archive":["Portico"],"relation":{},"ISSN":["0194-5998","1097-6817"],"issn-type":[{"value":"0194-5998","type":"print"},{"value":"1097-6817","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"2025-05-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}