{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T12:06:12Z","timestamp":1788264372161,"version":"build-2803163510"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T00:00:00Z","timestamp":1750032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:sec><jats:title>Objective<\/jats:title><jats:p>This study aims to construct a semantic segmentation-based auxiliary diagnostic model for thyroid eye disease (TED) focusing on eyelid retraction, eye movement disorders, ocular inflammation related to Clinical Activity Score (CAS), facilitating rapid and non-invasive diagnosis for suspected TED patients and enhancing the efficiency of treatment and diagnosis.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Data were collected from 153 subjects exhibiting symptoms of eyelid retraction, eye movement disorders, and ocular inflammation related to CAS. After quality screening, datasets for the primary position (303 eyes), gaze positions (1,199 eyes), and a multi-label inflammatory classification dataset (272 eyes) were constructed. The constructed TBRM-Net adopts a dual-branch feature extraction and fusion strategy to extract inflammation features for multi-label classification and recognition; the constructed DSR-Net performs segmentation of ocular structures and has designed a quantitative diagnostic algorithm.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The semantic segmentation-based auxiliary diagnostic model for TED demonstrated a mean pixel accuracy (MPA) of 94.1% in the primary position dataset and 95.0% in the gaze positions dataset. The accuracy for diagnosing eye movement disorders, upper eyelid retraction, and lower eyelid retraction reached 85.4%, 95.1%, and 87.0%, respectively. The accuracy for Redness of Eyelids, Swelling of Eyelids, Redness of Conjunctiva, Swelling of Conjunctiva, and Swelling of Caruncle or Plica reaches 81.8%, 78.8%, 90.6%, 73.5%, and 83.9%, respectively, with an average accuracy of 81.7%. Segmenting and classifying images of structures affected by ocular inflammation can effectively exclude interfering features. The designed quantitative algorithm provides greater interpretability than existing studies, thereby validating the effectiveness of the diagnostic system.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The deep learning-based auxiliary diagnostic model for TED established in this study exhibits high accuracy and interpretability in the diagnosis of ocular inflammation related to CAS, eyelid retraction, and eye movement disorders. It holds significant medical value in assisting doctors in formulating treatment plans and evaluating therapeutic effects.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fcell.2025.1609231","type":"journal-article","created":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T06:16:23Z","timestamp":1750054583000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Deep learning system for the auxiliary diagnosis of thyroid eye disease: evaluation of ocular inflammation, eyelid retraction, and eye movement disorder"],"prefix":"10.3389","volume":"13","author":[{"given":"Yu","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinying","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunfang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,16]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: a deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"Badrinarayanan","year":"2017","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B2","doi-asserted-by":"publisher","first-page":"249125","DOI":"10.1155\/2015\/249125","article-title":"Graves\u2019 ophthalmopathy: VISA versus EUGOGO classification, assessment, and management","volume":"2015","author":"Barrio-Barrio","year":"2015","journal-title":"J. Ophthalmol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1530\/EJE-07-0666","article-title":"Consensus statement of the European Group on Graves' orbitopathy (EUGOGO) on management of GO","volume":"158","author":"Bartalena","year":"2008","journal-title":"Eur. J. Endocrinol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"G43","DOI":"10.1530\/EJE-21-0479","article-title":"The 2021 European Group on Graves' orbitopathy (EUGOGO) clinical practice guidelines for the medical management of Graves' orbitopathy","volume":"185","author":"Bartalena","year":"2021","journal-title":"Eur. J. Endocrinol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1159\/000443828","article-title":"The 2016 European thyroid association\/European group on Graves' orbitopathy guidelines for the management of Graves' orbitopathy","volume":"5","author":"Bartalena","year":"2016","journal-title":"Eur. Thyroid J."},{"key":"B6","doi-asserted-by":"publisher","first-page":"615993","DOI":"10.3389\/fendo.2020.615993","article-title":"Epidemiology, natural history, risk factors, and prevention of Graves' orbitopathy","volume":"11","author":"Bartalena","year":"2020","journal-title":"Front. Endocrinol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"915","DOI":"10.16337\/j.1004-9037.2023.04.014","article-title":"Lightweight segmentation algorithm for TAO diseased areas based on DSE-Net","volume":"38","author":"Chen","year":"2023","journal-title":"J. Data Acquis. Process."},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1706.05587","article-title":"Rethinking atrous convolution for semantic image segmentation","volume":"2","author":"Chen","year":"2019","journal-title":"arxiv preprint arxiv:1706.05587"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1124775","DOI":"10.3389\/FCELL.2023.1124775","article-title":"Research progress and application of artificial intelligence in thyroid associated ophthalmopathy","volume":"11","author":"Diao","year":"2023","journal-title":"Front. Cell Dev. Biol."},{"key":"B10","doi-asserted-by":"publisher","first-page":"S75","DOI":"10.1097\/IOP.0000000000001148","article-title":"Surgical treatment of diplopia in Graves orbitopathy patients","volume":"34","author":"Eckstein","year":"2018","journal-title":"Ophthalmic Plastic Reconstr. Surg."},{"key":"B11","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"CE-net: context encoder network for 2D medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B12","doi-asserted-by":"publisher","first-page":"47","DOI":"10.22599\/bioj.8","article-title":"A comparative review of methods to record ocular rotations","volume":"6","author":"Hanif","year":"2009","journal-title":"Br. Ir. Orthopt. J."},{"key":"B13","first-page":"7132","article-title":"Squeeze-and-excitation networks","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Hu","year":"2018"},{"key":"B14","doi-asserted-by":"publisher","first-page":"3217","DOI":"10.16208\/j.issn1000-7024.2022.11.029","article-title":"Diagnosis of eyelid retraction based on improved Hough transform","volume":"43","author":"Hu","year":"2022","journal-title":"Comput. Eng. Des."},{"key":"B15","doi-asserted-by":"publisher","first-page":"22085","DOI":"10.1038\/S41598-022-25887-8","article-title":"Machine learning-assisted system using digital facial images to predict the clinical activity score in thyroid-associated orbitopathy","volume":"12","author":"Jae Hoon","year":"2022","journal-title":"Sci. Rep."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.00718","article-title":"Convolutional neural networks for text categorization: shallow word-level vs. deep character-level","author":"Johnson","year":"2016","journal-title":"arXiv preprint arXiv:1609.00718"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1722","DOI":"10.1136\/BJO-2022-321833","article-title":"Ensemble neural network model for detecting thyroid eye disease using external photographs","volume":"107","author":"Justin","year":"2022","journal-title":"Br. J. Ophthalmol."},{"key":"B18","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1034\/j.1600-0420.2002.800316.x","article-title":"High dose intravenous methylprednisolone pulse therapy versus oral prednisone for thyroid-associated ophthalmopathy","volume":"80","author":"Kauppinen-M\u00e4kelin","year":"2002","journal-title":"Acta Ophthalmol. Scand."},{"key":"B19","volume-title":"Research on iris location and disease classification method based on images of thyroid-related eye [Master\u2019s thesis, Chongqing University of Posts and Telecommunications]","author":"Liang","year":"2021"},{"key":"B20","first-page":"11976","article-title":"A convnet for the 2020s","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Liu","year":"2022"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1080\/02713683.2022.2053165","article-title":"Automated measurement of ocular movements using deep learning-based image analysis","volume":"47","author":"Lou","year":"2022","journal-title":"Curr. eye Res."},{"key":"B22","first-page":"116","article-title":"Shufflenet v2: practical guidelines for efficient cnn architecture design","volume-title":"Proceedings of the European conference on computer vision (ECCV)","author":"Ma","year":"2018"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2110.02178","article-title":"Mobilevit: light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arxiv preprint arxiv: 2110.02178"},{"key":"B24","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1109\/BigComp48618.2020.00-88","article-title":"Ocular-net: lite-residual encoder decoder network for accurate ocular regions segmentation in various sensor images","volume-title":"2020 IEEE international conference on big data and smart computing (BigComp)","author":"Naqvi","year":"2020"},{"key":"B25","doi-asserted-by":"publisher","first-page":"646","DOI":"10.3760\/CMA.J.CN112142-20220421-00201","article-title":"Chinese guideline on the diagnosis and treatment of thyroid-associated ophthalmopathy (2022)","volume":"58","year":"2022","journal-title":"Chin. J. Ophthalmol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.3760\/cma.j.cn115989-20190526-00233","article-title":"Research status and issues of severity grading and staging of thyroid-associated ophthalmopathy","volume":"40","author":"Ou","year":"2022","journal-title":"Chin. J. Exp. Ophthalmol."},{"key":"B27","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.beem.2011.11.007","article-title":"Evaluating Graves\u2019 orbitopathy","volume":"26","author":"Peter","year":"2012","journal-title":"Best Pract. Res. Clin. Endocrinol. Metabolism"},{"key":"B28","first-page":"234","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume-title":"Medical image computing and computer-assisted intervention \u2013 miccai 2015","author":"Ronneberger","year":"2015"},{"key":"B29","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1038\/icb.1945.51","article-title":"Development and course of exophthalmos and ophthalmoplegia in Graves' disease with special reference to the effect of thyroidectomy","volume":"5","author":"Rundle","year":"1945","journal-title":"Clin. Sci."},{"key":"B30","doi-asserted-by":"publisher","first-page":"4510","DOI":"10.1109\/CVPR.2018.00474","article-title":"Mobilenetv2: inverted residuals and linear bottlenecks","volume":"2018","author":"Sandler","year":"2018","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"B31","doi-asserted-by":"publisher","first-page":"NP15","DOI":"10.1177\/1120672120946929","article-title":"Vertical restrictive strabismus associated with proptosis: similar clinical signs, different etiopathogenetic causes. A report of three patients","volume":"32","author":"Savino","year":"2020","journal-title":"Eur. J. Ophthalmol."},{"key":"B32","doi-asserted-by":"publisher","first-page":"15808","DOI":"10.1038\/s41598-021-94178-5","article-title":"Real-world artificial intelligence-based opportunistic screening for diabetic retinopathy in endocrinology and indigenous healthcare settings in Australia","volume":"11","author":"Scheetz","year":"2021","journal-title":"Sci. Rep."},{"key":"B33","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.21037\/QIMS-22-551","article-title":"Deep learning-based image analysis of eyelid morphology in thyroid-associated ophthalmopathy","volume":"13","author":"Shao","year":"","journal-title":"Quantitative Imaging Med. Surg."},{"key":"B34","doi-asserted-by":"publisher","first-page":"841","DOI":"10.13389\/j.cnki.rao.2023.0169","article-title":"Guidelines for the application of artificial intelligence in thyroid-related ophthalmopathy","volume":"43","author":"Shao","year":"","journal-title":"Rec. Adv. Ophthalmol."},{"key":"B35","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1136\/bjophthalmol-2017-311452","article-title":"Review of economic evaluations of teleophthalmology as a screening strategy for chronic eye disease in adults","volume":"102","author":"Sharafeldin","year":"2018","journal-title":"Br. J. Ophthalmol."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1283374","DOI":"10.3389\/fendo.2023.1283374","article-title":"How patients experience thyroid eye disease","volume":"14","author":"Smith","year":"2023","journal-title":"Front. Endocrinol."},{"key":"B37","volume-title":"Shi Yong Lei Qi Bing Xue [Practical Lei Qi Bing Xue]","author":"Tao","year":"2019"},{"key":"B38","first-page":"23","article-title":"Unext: mlp-based rapid medical image segmentation network","volume-title":"International conference on medical image computing and computer-assisted intervention","author":"Valanarasu","year":"2022"},{"key":"B39","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1016\/j.ajo.2021.05.007","article-title":"PeriorbitAI: artificial intelligence automation of eyelid and periorbital measurements","volume":"230","author":"Van Brummen","year":"2021","journal-title":"Am. J. Ophthalmol."},{"key":"B40","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1089\/tmj.2023.0041","article-title":"Smartphone eye examination: artificial intelligence and telemedicine","volume":"30","author":"Vilela","year":"2024","journal-title":"Telemedicine J. E-health Official J. Am. Telemedicine Assoc."},{"key":"B41","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1038\/eye.1993.123","article-title":"Diagrammatic representation of strabismus","volume":"7","author":"Vivian","year":"1993","journal-title":"Eye Lond. Engl."},{"key":"B42","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1089\/105072502761016476","article-title":"Epidemiology and prevention of Graves' ophthalmopathy","volume":"12","author":"Wiersinga","year":"2002","journal-title":"J. Am. Thyroid Assoc."},{"key":"B43","doi-asserted-by":"publisher","first-page":"920716","DOI":"10.3389\/FMED.2022.920716","article-title":"An intelligent diagnostic system for thyroid-associated ophthalmopathy based on facial images","volume":"9","author":"Xiao","year":"2022","journal-title":"Front. Med."},{"key":"B44","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1109\/CVPR.2017.634","article-title":"Aggregated residual transformations for deep neural networks","volume":"2017","author":"Xie","year":"2016","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"B45","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1080\/10408360091174303","article-title":"Thyroid-associated ophthalmopathy: clinical features, pathogenesis, and management","volume":"37","author":"Yamada","year":"2000","journal-title":"Crit. Rev. Clin. laboratory Sci."},{"key":"B46","volume-title":"Ophthalmology","author":"Yang","year":"2018"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.27288\/d.cnki.gsxyu.2023.001544","article-title":"Analysis of 99mTc-DTPA SPECT\/CT orbital imaging in 794 patients with thyroid-related ophthalmopathy of different genders and ages [Master\u2019s thesis, Shanxi Medical University]. Master\u2019s","author":"Zhang","year":"2023"}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1609231\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T06:16:31Z","timestamp":1750054591000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1609231\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,16]]},"references-count":47,"alternative-id":["10.3389\/fcell.2025.1609231"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2025.1609231","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,16]]},"article-number":"1609231"}}