{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:10:31Z","timestamp":1785507031922,"version":"3.56.0"},"reference-count":19,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T00:00:00Z","timestamp":1785456000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100007465","name":"UiT The Arctic University of Norway","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100007465","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Updates Surg"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Ultrasound (US) is the primary imaging modality for thyroid evaluation, yet its diagnostic accuracy remains highly operator dependent. Automated identification of thyroid anatomy and adjacent vascular structures may improve standardisation, support image-guided procedures, and enhance preoperative decision-making in endocrine surgery. In this study, 300 B-mode ultrasound videos from 280 patients (111,679 frames) were used to develop a deep learning\u2013based segmentation model for simultaneous delineation of the thyroid gland and carotid artery. Data were split at the patient level into training\/validation (n\u2009=\u2009240) and an independent test set (n\u2009=\u200960). An expert-in-the-loop annotation workflow combining manual annotation, model-assisted pseudo-labelling, and expert refinement was implemented to enable efficient dataset construction. Segmentation performance was evaluated using the Dice similarity coefficient (DSC) and intersection over union (IoU). On the independent test set, the model achieved a DSC of 0.96\u2009\u00b1\u20090.02 and 0.96\u2009\u00b1\u20090.03 for the two segmented structures, with corresponding IoU values of 0.93\u2009\u00b1\u20090.03 and 0.93\u2009\u00b1\u20090.05. The model maintained consistent performance across varying anatomical presentations, including pathological nodules. Separately, evaluation of the expert-in-the-loop annotation pipeline showed high agreement between model-generated pseudo-labels and final expert-corrected annotations, indicating that the semi-automatic approach provided a strong initial approximation requiring only limited refinement. This multi-structure, video-based segmentation approach provides a clinically relevant foundation for artificial intelligence-assisted thyroid imaging, with potential applications in anatomical localisation, thyroid volume estimation, procedural guidance, three-dimensional reconstruction, and image-guided or robotic ultrasound systems.<\/jats:p>","DOI":"10.1007\/s13304-026-02782-9","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:27:20Z","timestamp":1785504440000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated segmentation of thyroid tissue and carotid artery in ultrasound videos using expert-in-the-loop deep learning: a foundational step toward AI-assisted thyroid diagnostics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0401-1826","authenticated-orcid":false,"given":"Maria","family":"Bolomiti","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5072-3610","authenticated-orcid":false,"given":"Joel","family":"Burman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9573-6525","authenticated-orcid":false,"given":"Keyur","family":"Radiya","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5318-8463","authenticated-orcid":false,"given":"Olav Inge","family":"H\u00e5skjold","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4672-7865","authenticated-orcid":false,"given":"Karl \u00d8yvind","family":"Mikalsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4136-3073","authenticated-orcid":false,"given":"Vegard Heimly","family":"Brun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,31]]},"reference":[{"key":"2782_CR1","doi-asserted-by":"publisher","DOI":"10.1177\/10507256251363120","author":"MD Ringel","year":"2025","unstructured":"Ringel MD, Sosa JA et al (2025) 2025 American Thyroid Association management guidelines for adult patients with differentiated thyroid cancer. Thyroid. https:\/\/doi.org\/10.1177\/10507256251363120","journal-title":"Thyroid"},{"key":"2782_CR2","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1159\/000478927","volume":"6","author":"G Russ","year":"2017","unstructured":"Russ G, Bonnema SJ, Erdogan MF, Durante C, Ngu R, Leenhardt L (2017) European Thyroid Association guidelines for ultrasound malignancy risk stratification of thyroid nodules in adults: the EU-TIRADS. Eur Thyroid J 6:225\u2013237. https:\/\/doi.org\/10.1159\/000478927","journal-title":"Eur Thyroid J"},{"key":"2782_CR3","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1001\/jama.2018.0898","volume":"319","author":"C Durante","year":"2018","unstructured":"Durante C, Grani G, Lamartina L, Filetti S, Mandel SJ, Cooper DS (2018) The diagnosis and management of thyroid nodules: a review. JAMA 319:914\u2013924. https:\/\/doi.org\/10.1001\/jama.2018.0898","journal-title":"JAMA"},{"key":"2782_CR4","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1186\/s40842-016-0025-9","volume":"2","author":"S Tamhane","year":"2016","unstructured":"Tamhane S, Gharib H (2016) Thyroid nodules: updates in diagnosis and management. Clin Diabetes Endocrinol 2:17. https:\/\/doi.org\/10.1186\/s40842-016-0025-9","journal-title":"Clin Diabetes Endocrinol"},{"key":"2782_CR5","doi-asserted-by":"publisher","first-page":"361","DOI":"10.32604\/cmes.2023.031229","volume":"139","author":"L Chen","year":"2023","unstructured":"Chen L, Chen H, Pan Z et al (2023) ThyroidNet: a deep learning network for localization and classification of thyroid nodules. Comput Model Eng Sci 139:361\u2013382. https:\/\/doi.org\/10.32604\/cmes.2023.031229","journal-title":"Comput Model Eng Sci"},{"key":"2782_CR6","doi-asserted-by":"publisher","first-page":"216","DOI":"10.3803\/EnM.2024.2058","volume":"40","author":"J Kim","year":"2025","unstructured":"Kim J, Kim MH, Lim DJ et al (2025) Deep learning technology for classification of thyroid nodules using multi-view ultrasound images: potential benefits and challenges in clinical application. Endocrinol Metab (Seoul) 40:216\u2013224. https:\/\/doi.org\/10.3803\/EnM.2024.2058","journal-title":"Endocrinol Metab (Seoul)"},{"key":"2782_CR7","doi-asserted-by":"publisher","first-page":"1614603","DOI":"10.3389\/fonc.2025.1614603","volume":"15","author":"Y Zhang","year":"2025","unstructured":"Zhang Y, Liu X, Chen J, Wang H, Li Q, Zhao L, Sun Y, Zhang H, Liu Y (2025) Diagnostic performance of ultrasound characteristics-based artificial intelligence models for thyroid nodules: a systematic review and meta-analysis. Front Oncol 15:1614603. https:\/\/doi.org\/10.3389\/fonc.2025.1614603","journal-title":"Front Oncol"},{"key":"2782_CR8","doi-asserted-by":"publisher","first-page":"817","DOI":"10.1007\/s12020-025-04287-8","volume":"89","author":"P Fern\u00e1ndez Velasco","year":"2025","unstructured":"Fern\u00e1ndez Velasco P, Est\u00e9vez Asensio L, Torres B et al (2025) Preliminary analysis of AI-based thyroid nodule evaluation in a non-subspecialist endocrinology setting. Endocr 89:817\u2013825. https:\/\/doi.org\/10.1007\/s12020-025-04287-8","journal-title":"Endocr"},{"key":"2782_CR9","doi-asserted-by":"publisher","first-page":"967","DOI":"10.3233\/XST-221206","volume":"30","author":"S Zhou","year":"2022","unstructured":"Zhou S, Qiu Y, Han L et al (2022) A lightweight network for automatic thyroid nodule location and recognition with high speed and accuracy in ultrasound images. J Xray Sci Technol 30:967\u2013981. https:\/\/doi.org\/10.3233\/XST-221206","journal-title":"J Xray Sci Technol"},{"key":"2782_CR10","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, S\u00e1nchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60\u201388. https:\/\/doi.org\/10.1016\/j.media.2017.07.005","journal-title":"Med Image Anal"},{"key":"2782_CR11","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","volume":"18","author":"F Isensee","year":"2021","unstructured":"Isensee F, Jaeger PF, Kohl SAA, Petersen J, Maier-Hein KH (2021) NnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods 18:203\u2013211. https:\/\/doi.org\/10.1038\/s41592-020-01008-z","journal-title":"Nat Methods"},{"key":"2782_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102515","volume":"80","author":"F Gao","year":"2022","unstructured":"Gao F, Hu M, Zhong ME, Feng S, Tian X, Meng X, Ni-jia-ti M, Huang Z, Lv M, Song T, Zhang X, Zou X, Wu X (2022) Segmentation only uses sparse annotations: unified weakly and semi-supervised learning in medical images. Med Image Anal 80:102515. https:\/\/doi.org\/10.1016\/j.media.2022.102515","journal-title":"Med Image Anal"},{"key":"2782_CR13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-12602-6","volume":"15","author":"T Banerjee","year":"2025","unstructured":"Banerjee T, Singh DP, Swain D, Mahajan S, Kadry S, Kim J (2025) A novel hybrid deep learning approach combining deep feature attention and statistical validation for enhanced thyroid ultrasound segmentation. Sci Rep 15:27207. https:\/\/doi.org\/10.1038\/s41598-025-12602-6","journal-title":"Sci Rep"},{"key":"2782_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. MICCAI. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","journal-title":"MICCAI"},{"key":"2782_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.wfumbo.2024.100055","volume":"2","author":"R Munsterman","year":"2024","unstructured":"Munsterman R, Boers T, Braak SJ, Wolterink JM, Versluis M, Manohar S (2024) Deep learning-based segmentation of 3D ultrasound images of the thyroid. WFUMB Ultrasound Open 2:100055. https:\/\/doi.org\/10.1016\/j.wfumbo.2024.100055","journal-title":"WFUMB Ultrasound Open"},{"key":"2782_CR16","doi-asserted-by":"publisher","first-page":"1013317","DOI":"10.1117\/12.2254234","volume":"10133","author":"T Wunderling","year":"2017","unstructured":"Wunderling T, Gollaa B, Poudel P, Arens C, Friebe M, Hansen C (2017) Comparison of thyroid segmentation techniques for 3D ultrasound. Proc SPIE Med Imaging 10133:1013317. https:\/\/doi.org\/10.1117\/12.2254234","journal-title":"Proc SPIE Med Imaging"},{"key":"2782_CR17","doi-asserted-by":"publisher","DOI":"10.1186\/s12938-024-01215-1","volume":"23","author":"J Mi","year":"2024","unstructured":"Mi J, Wang R, Feng Q et al (2024) Three-dimensional visualization of thyroid ultrasound images based on multi-scale features fusion and hierarchical attention. Biomed Eng Online 23:31. https:\/\/doi.org\/10.1186\/s12938-024-01215-1","journal-title":"Biomed Eng Online"},{"key":"2782_CR18","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1002\/mp.13960","volume":"47","author":"J de Ruijter","year":"2020","unstructured":"de Ruijter J, van Sambeek M, van de Vosse F, Lopata R (2020) Automated 3D geometry segmentation of the healthy and diseased carotid artery in free-hand, probe tracked ultrasound images. Med Phys 47:1034\u20131047. https:\/\/doi.org\/10.1002\/mp.13960","journal-title":"Med Phys"},{"key":"2782_CR19","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1627721","volume":"16","author":"JS Lee","year":"2025","unstructured":"Lee JS, Ha EJ, Jeong HJ, Kim SY, Kim HK (2025) Levothyroxine supplementation after hemithyroidectomy in patients with low-risk differentiated thyroid cancer: risk factors and withdrawal strategy. Front Endocrinol (Lausanne) 16:1627721. https:\/\/doi.org\/10.3389\/fendo.2025.1627721","journal-title":"Front Endocrinol (Lausanne)"}],"container-title":["Updates in Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13304-026-02782-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13304-026-02782-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13304-026-02782-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T13:27:22Z","timestamp":1785504442000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13304-026-02782-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,31]]},"references-count":19,"alternative-id":["2782"],"URL":"https:\/\/doi.org\/10.1007\/s13304-026-02782-9","relation":{},"ISSN":["2038-131X","2038-3312"],"issn-type":[{"value":"2038-131X","type":"print"},{"value":"2038-3312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,31]]},"assertion":[{"value":"17 April 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors have no potential conflicts of interest to disclose.","order":1,"name":"Ethics","label":"Conflicts of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study was performed in accordance with the Helsinki declaration and was recommended by the Regional Ethical Committee (ID 504557) and the Institutional Data Protection Officer (ID 3012).","order":2,"name":"Ethics","label":"Ethical approval","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":4,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}]}}