{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T14:50:53Z","timestamp":1785768653494,"version":"3.56.0"},"reference-count":34,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2025,1,29]],"date-time":"2025-01-29T00:00:00Z","timestamp":1738108800000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12126610"],"award-info":[{"award-number":["12126610"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306254"],"award-info":[{"award-number":["62306254"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Three-dimensional (3D) reconstruction of ossicular chain and bony labyrinth based on temporal bone high-resolution CT (HRCT) is useful for diagnosis and treatment guidance of middle and inner ear diseases. However, these structures are small and irregular, making manual reconstruction time-consuming.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Purpose<\/jats:title>\n                  <jats:p>To develop and validate an artificial intelligence (AI) model based on semisupervised learning for automated 3D reconstruction of ossicular chain and bony labyrinth on HRCT images.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>HRCT images from 304 ears of 152 consecutive patients retrospectively collected from a single center were randomly divided into training (246 ears), validation (28 ears), and internal test (30 ears) cohorts for model development. A novel semisupervised ear bone segmentation framework was used to train the AI model, and its performance was evaluated by Dice similarity coefficients. The trained algorithm was applied to a temporally independent test dataset of 30 ears of 15 patients from the same center for comparison with manual 3D reconstruction for processing time, target volume, and visual assessment of segmentation.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The AI model demonstrated a Dice score of 0.948 (95% CI, 0.940-0.955) for the internal and 0.979 (95% CI, 0.973-0.986) for the temporally independent test sets. In the latter dataset, the AI model required 2% or less processing time of manual 3D reconstruction for each ear (17.7\u2009seconds \u00b1 10.1 vs 1080.5\u2009seconds \u00b1 149.8; P &amp;lt; .001) and had an accuracy comparable to human experts in the volume and visual assessment of segmentation targets (P = .237-1.000). In a subgroup analysis, the model achieved accurate segmentation (Dice scores of 0.98-0.99) across various diseases (eg, otitis media, mastoiditis, otosclerosis, middle and inner ear malformations, M\u00e9ni\u00e8re disease).<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>The AI model enables robust, efficient and accurate 3D reconstruction for the small structures such as ossicular chain and bony labyrinth on HRCT images.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/radadv\/umaf004","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T00:19:31Z","timestamp":1738196371000},"source":"Crossref","is-referenced-by-count":4,"title":["Artificial intelligence model for automatic 3-dimensional reconstruction of ossicular chain and bony labyrinth from high-resolution CT"],"prefix":"10.1093","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1590-1381","authenticated-orcid":false,"given":"Mingwei","family":"Xie","sequence":"first","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay , Kowloon, Hong Kong 999077,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zehong","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangzi","family":"Shi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingnan","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongqiang","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1105-8083","authenticated-orcid":false,"given":"Xiaomeng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Clear Water Bay , Kowloon, Hong Kong 999077,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7746-5285","authenticated-orcid":false,"given":"Jun","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Radiology, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University , Guangzhou 510120,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2025,1,28]]},"reference":[{"issue":"3","key":"2025021600021595000_umaf004-B1","doi-asserted-by":"publisher","first-page":"743","DOI":"10.1148\/radiology.147.3.6844610","article-title":"Temporal bone disease: a comparison between high resolution computed tomography and pluridirectional tomography","volume":"147","author":"Virapongse","year":"1983","journal-title":"Radiology"},{"issue":"3","key":"2025021600021595000_umaf004-B2","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.anl.2015.08.007","article-title":"Usefulness of multislice-CT using multiplanar reconstruction in the preoperative assessment of the ossicular lesions in the middle ear diseases","volume":"43","author":"Fujiwara","year":"2016","journal-title":"Auris Nasus Larynx"},{"issue":"10","key":"2025021600021595000_umaf004-B3","first-page":"1015","article-title":"CT virtual endoscopy of the auditory ossicular chain: clinical applications","volume":"114","author":"Wang","year":"2001","journal-title":"Chin Med J (Engl)"},{"issue":"8","key":"2025021600021595000_umaf004-B4","doi-asserted-by":"publisher","first-page":"e44333","DOI":"10.7759\/cureus.44333","article-title":"High-resolution computed tomography and intraoperative correlation in cholesteatoma: enhancing preoperative evaluation and surgical management","volume":"15","author":"Kapoor","year":"2023","journal-title":"Cureus"},{"issue":"10","key":"2025021600021595000_umaf004-B5","doi-asserted-by":"publisher","first-page":"e697","DOI":"10.1097\/MAO.0000000000004012","article-title":"Diagnostic efficacy of high-resolution computed tomography densitometry for diagnosing otosclerosis","volume":"44","author":"Puiggros","year":"2023","journal-title":"Otol Neurotol"},{"issue":"2","key":"2025021600021595000_umaf004-B6","doi-asserted-by":"publisher","first-page":"386","DOI":"10.1002\/lary.28640","article-title":"Evaluating common cavity cochlear deformities using CT images and 3D reconstruction","volume":"131","author":"Weiss","year":"2021","journal-title":"Laryngoscope"},{"issue":"Suppl 1","key":"2025021600021595000_umaf004-B7","doi-asserted-by":"publisher","first-page":"S117","DOI":"10.1148\/rg.26si065502","article-title":"Role of 3D CT in the evaluation of the temporal bone","volume":"26","author":"Fatterpekar","year":"2006","journal-title":"Radiographics"},{"issue":"8","key":"2025021600021595000_umaf004-B8","doi-asserted-by":"publisher","first-page":"696","DOI":"10.1016\/j.compmedimag.2014.06.019","article-title":"Quality assessment of 3D-CTVR, MPR and section plane techniques in ossicular chain reconstruction in middle ear cholesteatoma","volume":"38","author":"Liu","year":"2014","journal-title":"Comput Med Imaging Graph"},{"issue":"4","key":"2025021600021595000_umaf004-B9","doi-asserted-by":"publisher","first-page":"988","DOI":"10.1002\/ohn.317","article-title":"A self-configuring deep learning network for segmentation of temporal bone anatomy in cone-beam CT imaging","volume":"169","author":"Ding","year":"2023","journal-title":"Otolaryngol Head Neck Surg"},{"issue":"1","key":"2025021600021595000_umaf004-B10","doi-asserted-by":"publisher","first-page":"166","DOI":"10.1186\/s12880-021-00698-x","article-title":"Fully automated segmentation in temporal bone CT with neural network: a preliminary assessment study","volume":"21","author":"Wang","year":"2021","journal-title":"BMC Med Imaging"},{"issue":"2","key":"2025021600021595000_umaf004-B11","doi-asserted-by":"publisher","first-page":"e2229","DOI":"10.1002\/rcs.2229","article-title":"Automatic segmentation of temporal bone structures from clinical conventional CT using a CNN approach","volume":"17","author":"Lv","year":"2021","journal-title":"Int J Med Robot"},{"key":"2025021600021595000_umaf004-B12","first-page":"596","article-title":"Fixmatch: simplifying semi-supervised learning with consistency and confidence","volume":"33","author":"Sohn","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"key":"2025021600021595000_umaf004-B13","first-page":"2613","author":"Chen","year":"2021"},{"key":"2025021600021595000_umaf004-B14","first-page":"4248","author":"Wang","year":"2022"},{"key":"2025021600021595000_umaf004-B15","first-page":"14647","author":"Wang","year":"2022"},{"key":"2025021600021595000_umaf004-B16","first-page":"32424","article-title":"Debiased self-training for semi-supervised learning","volume":"35","author":"Chen","year":"2022","journal-title":"Adv Neural Inform Process Syst"},{"issue":"11","key":"2025021600021595000_umaf004-B17","doi-asserted-by":"crossref","first-page":"16589","DOI":"10.1109\/TNNLS.2023.3296652","article-title":"Exploring feature representation learning for semi-supervised medical image segmentation","volume":"35","author":"Wu","year":"2024","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"2025021600021595000_umaf004-B18","author":"Dosovitskiy","year":"2020"},{"key":"2025021600021595000_umaf004-B19","first-page":"1833","article-title":"Towards generic semi-supervised framework for volumetric medical image segmentation","volume":"36","author":"Wang","year":"2024","journal-title":"Adv Neural Inform Process Syst"},{"key":"2025021600021595000_umaf004-B20","first-page":"3627","author":"Wang","year":"2024"},{"key":"2025021600021595000_umaf004-B21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"key":"2025021600021595000_umaf004-B22","author":"Song","year":"2020"},{"key":"2025021600021595000_umaf004-B23","first-page":"8162","author":"Nichol","year":"2021"},{"key":"2025021600021595000_umaf004-B24","first-page":"1623","article-title":"Medsegdiff: Medical image segmentation with diffusion probabilistic model","author":"Wu","year":"2024","journal-title":"Med Imaging Deep Learn PMLR"},{"key":"2025021600021595000_umaf004-B25","first-page":"11536","author":"Rahman","year":"2023"},{"key":"2025021600021595000_umaf004-B26","doi-asserted-by":"publisher","first-page":"3342","DOI":"10.1109\/embc.2016.7591443","article-title":"ITK-SNAP: an interactive tool for semi-automatic segmentation of multi-modality biomedical images","volume":"2016","author":"Yushkevich","year":"2016","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"issue":"2","key":"2025021600021595000_umaf004-B27","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"},{"key":"2025021600021595000_umaf004-B28","first-page":"565","author":"Milletari","year":"2016"},{"key":"2025021600021595000_umaf004-B29","first-page":"605","author":"Yu","year":"2019"},{"key":"2025021600021595000_umaf004-B30","first-page":"318","author":"Luo","year":"2021"},{"key":"2025021600021595000_umaf004-B31","first-page":"34","author":"Wu","year":"2022"},{"key":"2025021600021595000_umaf004-B32","first-page":"582","author":"Wang","year":"2023"},{"issue":"9","key":"2025021600021595000_umaf004-B33","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/tpami.2023.3261988","article-title":"Diffusion models in vision: a survey","volume":"45","author":"Croitoru","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"2025021600021595000_umaf004-B34","doi-asserted-by":"publisher","first-page":"7303","DOI":"10.1038\/s41598-023-34341-2","article-title":"Denoising diffusion probabilistic models for 3D medical image generation","volume":"13","author":"Khader","year":"2023","journal-title":"Sci Rep"}],"container-title":["Radiology Advances"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/radadv\/advance-article-pdf\/doi\/10.1093\/radadv\/umaf004\/61686039\/umaf004.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/1\/umaf004\/61686039\/umaf004.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/radadv\/article-pdf\/2\/1\/umaf004\/61686039\/umaf004.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,16]],"date-time":"2025-02-16T00:02:31Z","timestamp":1739664151000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/radadv\/article\/doi\/10.1093\/radadv\/umaf004\/7989450"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":34,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1,14]]}},"URL":"https:\/\/doi.org\/10.1093\/radadv\/umaf004","relation":{},"ISSN":["2976-9337"],"issn-type":[{"value":"2976-9337","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2025,1]]},"article-number":"umaf004"}}