{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T18:02:52Z","timestamp":1789668172495,"version":"4.0.1"},"reference-count":41,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T00:00:00Z","timestamp":1769040000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"Hainan Provincial Department of Science and Technology, Key R&D Project of Hainan Province","award":["ZDYF2024LCLH004"],"award-info":[{"award-number":["ZDYF2024LCLH004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61906121"],"award-info":[{"award-number":["61906121"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Shanghai Key Clinical Specialty, Shanghai Eye Disease Research Center","award":["2022ZZ01003"],"award-info":[{"award-number":["2022ZZ01003"]}]},{"name":"Science and Technology Commission of Shanghai","award":["20DZ2270800"],"award-info":[{"award-number":["20DZ2270800"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,1,28]]},"abstract":"Abstract<\/jats:title>\n \n Objective.<\/jats:italic>\n To develop an efficient deep learning framework for precise three-dimensional (3D) segmentation of complex orbital structures in multi-sequence magnetic resonance imaging (MRI) and robust assessment of thyroid eye disease (TED) activity, thereby addressing limitations in computational complexity, segmentation accuracy, and integration of multi-sequence features to support clinical decision-making.\n Approach.<\/jats:italic>\n We propose RQNet, a U-shaped 3D segmentation network that incorporates the novel Refined Query Transformer Block with refined attention query multi-head self-attention. This design reduces attention complexity from\n \n \n \n <\/jats:tex-math>\n \n \n O<\/mml:mi>\n (<\/mml:mo>\n \n N<\/mml:mi>\n 2<\/mml:mn>\n <\/mml:msup>\n )<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n to\n \n \n \n <\/jats:tex-math>\n \n \n O<\/mml:mi>\n (<\/mml:mo>\n N<\/mml:mi>\n \u22c5<\/mml:mo>\n M<\/mml:mi>\n )<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n (\n \n \n \n <\/jats:tex-math>\n \n \n M<\/mml:mi>\n \u226a<\/mml:mo>\n N<\/mml:mi>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ) through pooled refined queries. High-quality segmentations then feed into a radiomics pipeline that extracts features per region of interest\u2014including shape, first-order, and texture descriptors. The MRI features from the three sequences\u2014T1-weighted imaging (T1WI), contrast-enhanced T1WI (T1CE), and T2-weighted imaging (T2WI)\u2014are subsequently integrated, with support vector machine, random forest, and logistic regression models employed for assessment to distinguish between active and inactive TED phases.\n Main results.<\/jats:italic>\n RQNet achieved Dice similarity coefficients of 83.34%\u201387.15% on TED datasets (T1WI, T2WI, T1CE), outperforming state-of-the-art models such as nnFormer, UNETR, SwinUNETR, SegResNet, and nnUNet. The radiomics fusion pipeline yielded area under the curve values of 84.65%\u201385.89% for TED activity assessment, surpassing single-sequence baselines and confirming the benefits of multi-sequence MRI feature fusion enhancements.\n Significance.<\/jats:italic>\n The proposed RQNet establishes an efficient segmentation network for 3D orbital MRI, providing accurate depictions of TED structures, robust radiomics-based activity assessment, and enhanced TED assessment through multi-sequence MRI feature integration.\n <\/jats:p>","DOI":"10.1088\/1361-6560\/ae3101","type":"journal-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T22:49:25Z","timestamp":1766616565000},"page":"025009","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Refined query network (RQNet) for precise MRI segmentation and robust TED activity assessment"],"prefix":"10.1088","volume":"71","author":[{"given":"Le","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianfeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duojin","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuefei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8636-861X","authenticated-orcid":true,"given":"Huifang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,1,22]]},"reference":[{"key":"pmbae3101bib1","doi-asserted-by":"publisher","first-page":"516","DOI":"10.5114\/pjr.2022.119808","type":"journal-article","article-title":"Segmentation of orbital and periorbital lesions detected in orbital magnetic resonance imaging by deep learning method","volume":"87","author":"Ayd\u0131n","year":"2022","journal-title":"Pol. J. Radiol."},{"key":"pmbae3101bib2","first-page":"pp 251","type":"conference-proceedings","article-title":"Attention deeplabv3+: multi-level context attention mechanism for skin lesion segmentation","author":"Azad","year":"2020"},{"key":"pmbae3101bib3","first-page":"pp 1287","type":"conference-proceedings","article-title":"Beyond self-attention: deformable large kernel attention for medical image segmentation","author":"Azad","year":"2024"},{"key":"pmbae3101bib4","doi-asserted-by":"publisher","first-page":"726","DOI":"10.1056\/NEJMra0905750","type":"journal-article","article-title":"Graves\u2019 ophthalmopathy","volume":"362","author":"Bahn","year":"2010","journal-title":"New Engl. J. Med."},{"key":"pmbae3101bib5","doi-asserted-by":"publisher","first-page":"G43","DOI":"10.1530\/EJE-21-0479","type":"journal-article","article-title":"The 2021 European Group on Graves\u2019 orbitopathy (EUGOGO) clinical practice guidelines for the medical management of Graves\u2019 orbitopathy","volume":"185","author":"(EUGOGO)","year":"2021","journal-title":"Eur. J. Endocrinol."},{"key":"pmbae3101bib6","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","type":"preprint"},{"key":"pmbae3101bib7","author":"Grant","year":"2024","type":"book"},{"key":"pmbae3101bib8","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-93227-3","type":"journal-article","article-title":"A deep learning method for automatic segmentation of the bony orbit in MRI and CT images","volume":"11","author":"Hamwood","year":"2021","journal-title":"Sci. Rep."},{"key":"pmbae3101bib9","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","type":"journal-article","article-title":"A survey on vision transformer","volume":"45","author":"Han","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"pmbae3101bib10","first-page":"pp 272","type":"conference-proceedings","article-title":"Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images","author":"Hatamizadeh","year":"2021"},{"key":"pmbae3101bib11","first-page":"pp 574","type":"conference-proceedings","article-title":"UNETR: transformers for 3D medical image segmentation","author":"Hatamizadeh","year":"2022"},{"key":"pmbae3101bib12","doi-asserted-by":"publisher","first-page":"430","DOI":"10.1007\/s10384-015-0410-4","type":"journal-article","article-title":"Changes of orbital tissue volumes and proptosis in patients with thyroid extraocular muscle swelling after methylprednisolone pulse therapy","volume":"59","author":"Higashiyama","year":"2015","journal-title":"Jpn. J. Ophthalmol."},{"key":"pmbae3101bib13","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1148\/radiology.172.3.2772184","type":"journal-article","article-title":"Graves ophthalmopathy: MR imaging of the orbits","volume":"172","author":"Hosten","year":"1989","journal-title":"Radiology"},{"key":"pmbae3101bib14","first-page":"pp 334","type":"conference-proceedings","article-title":"Brain tumor segmentation (BraTS) challenge short paper: improving three-dimensional brain tumor segmentation using segresnet and hybrid boundary-dice loss","author":"Hsu","year":"2021"},{"key":"pmbae3101bib15","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1002\/jmri.28088","type":"journal-article","article-title":"T2-weighted MR imaging-derived radiomics for pretreatment determination of therapeutic response to glucocorticoid in patients with thyroid-associated ophthalmopathy: comparison with semiquantitative evaluation","volume":"56","author":"Hu","year":"2022","journal-title":"J. Magn. Reson. Imaging"},{"key":"pmbae3101bib16","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","type":"journal-article","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":"pmbae3101bib17","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1007\/s12020-022-03167-9","type":"journal-article","article-title":"The combination of T2-mapping value of lacrimal gland and clinical indicators can improve the stage prediction of Graves\u2019 ophthalmopathy compared to clinical activity scores","volume":"78","author":"Jiang","year":"2022","journal-title":"Endocrine"},{"key":"pmbae3101bib18","doi-asserted-by":"publisher","first-page":"307","DOI":"10.5507\/bp.2014.001","type":"journal-article","article-title":"Correlation between magnetic resonance imaging and ultrasound measurements of eye muscle thickness in thyroid-associated orbitopathy","volume":"159","author":"Karhanova","year":"2015","journal-title":"Biomed. Pap."},{"key":"pmbae3101bib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12886-020-01783-5","type":"journal-article","article-title":"Detection of active and inactive phases of thyroid-associated ophthalmopathy using deep convolutional neural network","volume":"21","author":"Lin","year":"2021","journal-title":"BMC Ophthalmol."},{"key":"pmbae3101bib20","first-page":"pp 10012","type":"conference-proceedings","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"pmbae3101bib21","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1007\/s11604-019-00846-y","type":"journal-article","article-title":"Improvement of the MRI and clinical features of Asian Graves\u2019 ophthalmopathy by radiation therapy with steroids","volume":"37","author":"Ma","year":"2019","journal-title":"Jpn. J. Radiol."},{"key":"pmbae3101bib22","doi-asserted-by":"publisher","first-page":"488","DOI":"10.2967\/jnumed.118.222893","type":"journal-article","article-title":"Introduction to radiomics","volume":"61","author":"Mayerhoefer","year":"2020","journal-title":"J. Nucl. Med."},{"key":"pmbae3101bib23","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1136\/bjo.73.8.639","type":"journal-article","article-title":"Clinical criteria for the assessment of disease activity in Graves\u2019 ophthalmopathy: a novel approach","volume":"73","author":"Mourits","year":"1989","journal-title":"Br. J. Ophthalmol."},{"key":"pmbae3101bib24","doi-asserted-by":"publisher","first-page":"699","DOI":"10.3390\/bioengineering10060699","type":"journal-article","article-title":"Deep-learning-based segmentation of extraocular muscles from magnetic resonance images","volume":"10","author":"Qureshi","year":"2023","journal-title":"Bioengineering"},{"key":"pmbae3101bib25","first-page":"pp 11769","type":"conference-proceedings","article-title":"EMCAD: efficient multi-scale convolutional attention decoding for medical image segmentation","author":"Rahman","year":"2024"},{"key":"pmbae3101bib26","first-page":"pp 234","type":"conference-proceedings","article-title":"U-Net: convolutional networks for biomedical image segmentation","volume":"vol 18","author":"Ronneberger","year":"2015"},{"key":"pmbae3101bib27","doi-asserted-by":"publisher","first-page":"3377","DOI":"10.1109\/TMI.2024.3398728","type":"journal-article","article-title":"UNETR++: delving into efficient and accurate 3D medical image segmentation","volume":"43","author":"Shaker","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae3101bib28","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1111\/cen.13564","type":"journal-article","article-title":"Establishment of magnetic resonance imaging 3D reconstruction technology of orbital soft tissue and its preliminary application in patients with thyroid-associated ophthalmopathy","volume":"88","author":"Shen","year":"2018","journal-title":"Clin. Endocrinol."},{"key":"pmbae3101bib29","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1177\/197140091302600509","type":"journal-article","article-title":"Disease activity in Graves\u2019 ophthalmopathy: diagnosis with orbital MR imaging and correlation with clinical score","volume":"26","author":"Tortora","year":"2013","journal-title":"Neuroradiol. J."},{"key":"pmbae3101bib30","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.3174\/ajnr.A6538","type":"journal-article","article-title":"Fully automated segmentation of globes for volume quantification in CT images of orbits using deep learning","volume":"41","author":"Umapathy","year":"2020","journal-title":"Am. J. Neuroradiol."},{"key":"pmbae3101bib31","first-page":"pp 23","type":"conference-proceedings","article-title":"UNeXt: MLP-based rapid medical image segmentation network","author":"Valanarasu","year":"2022"},{"key":"pmbae3101bib32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12902-018-0240-8","type":"journal-article","article-title":"A single-center retrospective study of factors related to the effects of intravenous glucocorticoid therapy in moderate-to-severe and active thyroid-associated ophthalmopathy","volume":"18","author":"Wang","year":"2018","journal-title":"BMC Endocr. Disord."},{"key":"pmbae3101bib33","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1530\/EC-21-0162","type":"journal-article","article-title":"Texture analysis of orbital magnetic resonance imaging for monitoring and predicting treatment response to glucocorticoids in patients with thyroid-associated ophthalmopathy","volume":"10","author":"Wang","year":"2021","journal-title":"Endocr. Connect."},{"key":"pmbae3101bib34","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1186\/s13244-022-01292-7","type":"journal-article","article-title":"Radiomics analysis of the optic nerve for detecting dysthyroid optic neuropathy, based on water-fat imaging","volume":"13","author":"Wu","year":"2022","journal-title":"Insights Imaging"},{"key":"pmbae3101bib35","doi-asserted-by":"publisher","first-page":"1116","DOI":"10.1016\/j.neuroimage.2006.01.015","type":"journal-article","article-title":"User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability","volume":"31","author":"Yushkevich","year":"2006","journal-title":"Neuroimage"},{"key":"pmbae3101bib36","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s12967-023-04792-2","type":"journal-article","article-title":"Whole-orbit radiomics: machine learning-based multi-and fused-region radiomics signatures for intravenous glucocorticoid response prediction in thyroid eye disease","volume":"22","author":"Zhang","year":"2024","journal-title":"J. Transl. Med."},{"key":"pmbae3101bib37","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41597-025-04427-9","type":"journal-article","article-title":"TOM500: a multi-organ annotated orbital MRI dataset for thyroid eye disease","volume":"12","author":"Zhang","year":"2025","journal-title":"Sci. Data"},{"key":"pmbae3101bib38","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1002\/jmri.29114","type":"journal-article","article-title":"Application of quantitative MRI in thyroid eye disease: imaging techniques and clinical practices","volume":"60","author":"Zhang","year":"2024","journal-title":"J. Magn. Reson. Imaging"},{"key":"pmbae3101bib39","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1109\/TMI.2020.3034995","type":"journal-article","article-title":"Inter-slice context residual learning for 3D medical image segmentation","volume":"40","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae3101bib40","doi-asserted-by":"publisher","DOI":"10.3389\/fcell.2023.1135959","type":"journal-article","article-title":"Automatic measurement of exophthalmos based orbital CT images using deep learning","volume":"11","author":"Zhang","year":"2023","journal-title":"Front. Cell Dev. Biol."},{"key":"pmbae3101bib41","article-title":"nnFormer: interleaved transformer for volumetric segmentation","author":"Zhou","year":"2021","type":"preprint"}],"container-title":["Physics in Medicine & Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T09:05:44Z","timestamp":1769072744000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae3101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,22]]},"references-count":41,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1,22]]},"published-print":{"date-parts":[[2026,1,28]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae3101","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,22]]},"assertion":[{"value":"Refined query network (RQNet) for precise MRI segmentation and robust TED activity assessment","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-09-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-24","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-01-22","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}