{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T14:19:09Z","timestamp":1788272349305,"version":"build-2803163510"},"reference-count":37,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T00:00:00Z","timestamp":1785715200000},"content-version":"vor","delay-in-days":2,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Automatic segmentation of ultrasound\u2010based thyroid nodules can assist physicians in more efficiently and accurately assessing thyroid diseases. However, thyroid ultrasound imaging presents certain unique challenges, such as blurred boundaries of nodules, strong heterogeneity in tissue echoes, and limited contrast between the lesions and adjacent normal thyroid tissue, which hinder the precise identification of nodules in clinical\u00a0assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To overcome these obstacles, we propose a deep hybrid convolutional network, named UTNseg, for precisely automatic segmentation of ultrasound\u2010based thyroid\u00a0nodules.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>UTNseg contains four newly designed modules upon TransUNet: (1) the spatial\u2010channel feature strong capture (STransformer) module is designed to reinforce the ability of encoder on capturing spatial and channel features, (2) the redundant feature map utilization (RMU) module is devised to mitigate redundant information in the skip connections, (3) the composite convolution (CConv) module is newly designed to further preserve the key multi\u2010scale features of the target thyroid nodules, (4) the lightweight edge refinement (LER) module is newly proposed to refine the initial segmentation outputs. UTNseg was evaluated on two publicly available ultrasound datasets of thyroid nodules (TN3K with 3493 images and DDTI with 637 images). Datasets were divided at the patient level, with 4000 training images (2000 images from TN3K and 2000 images from DDTI, augmented by random rotation, scaling, and horizontal flipping on 445 images), 761 validation images (698 images from TN3K and 63 images from DDTI), and 924 test images (795 images from TN3K and 129 images from DDTI). Additionally, separate experiments were performed on these two datasets in comparative experiments. And the performance was compared with six state\u2010of\u2010the\u2010art segmentation methods (U\u2010Net, TransUNet, TRFENet, UNeXt, TRFE+ and BPAT\u2010UNet). Evaluation metrics mainly included Dice similarity coefficient (DSC) and 95th percentile Hausdorff distance (HD95). Statistical significance level was analyzed through the Wilcoxon signed\u2010rank test, and the effect size was quantified by Cohen's . Holm\u2010Bonferroni correction was employed to correct for multiple\u00a0comparisons.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the TN3K dataset, UTNseg achieved 79.52% DSC and 16.32 HD95. On the DDTI dataset, UTNseg achieved 86.21% DSC and 12.76 HD95. On the hybrid dataset, UTNseg achieved 80.77% DSC and 14.56 HD95. These results showed that UTNseg achieved superior performance. Compared with state\u2010of\u2010the\u2010art approaches, UTNseg was statistically significant (), and the corresponding effect sizes were mostly medium or large, further quantifying the practical importance of the\u00a0improvements.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>UTNseg demonstrated excellent segmentation performance on the public dataset. Statistical significance and effect size analysis both indicate that the improvements are reliable and have practical\u00a0significance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70548","type":"journal-article","created":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T12:54:38Z","timestamp":1785761678000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Ultrasound\u2010based thyroid nodule segmentation with deep hybrid convolutional network"],"prefix":"10.1002","volume":"53","author":[{"given":"Fan","family":"Lu","sequence":"first","affiliation":[{"name":"School of Future Science and Engineering Soochow University Suzhou Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering Soochow University Suzhou Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Binbin","family":"Jiang","sequence":"additional","affiliation":[{"name":"Key laboratory of Carcinogenesis and Translational Research (Ministry of Education\/Beijing) Department of Ultrasonography Peking University Cancer Hospital &amp; Institute Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Key laboratory of Carcinogenesis and Translational Research (Ministry of Education\/Beijing) Department of Ultrasonography Peking University Cancer Hospital &amp; Institute Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ge","family":"Ren","sequence":"additional","affiliation":[{"name":"Department of Health Technology and Informatics The Hong Kong Polytechnic University Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Health Technology and Informatics The Hong Kong Polytechnic University Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidong","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Medical Ultrasound The Affiliated Suzhou Hospital of Nanjing Medical University, Suzhou Municipal Hospital Suzhou Jiangsu China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Medical Information and Engineering Xuzhou Medical University Xuzhou China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Future Science and Engineering Soochow University Suzhou Jiangsu China"},{"name":"Department of Health Technology and Informatics The Hong Kong Polytechnic University Hong Kong China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,3]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107974"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.105347"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109925"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107346"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2025.101598"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2025.3598048"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.114245"},{"key":"e_1_2_9_10_1","unstructured":"DosovitskiyA.An image is worth 16\u00d7$\\times$16 words: Transformers for image recognition at scale.arXiv preprint posted online June 3 2021. arXiv:2010.11929."},{"key":"e_1_2_9_11_1","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani A","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02129-z"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17506"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2025.104324"},{"key":"e_1_2_9_15_1","unstructured":"ChenJ LuY YuQ et\u00a0al.TransUNet: Transformers make strong encoders for medical image segmentation.arXivpreprint posted online Feb 8 2021. arXiv:2102.04306."},{"key":"e_1_2_9_16_1","unstructured":"BaoH DongL PiaoS WeiF.Beit: Bert pre\u2010training of image transformers.arXivpreprint arXiv:2106.08254.2021."},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"HuJ ShenL SunG.Squeeze\u2010and\u2010excitation networks. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition2018:7132\u20107141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"e_1_2_9_18_1","unstructured":"BaJL KirosJR HintonGE.Layer normalization.arXivpreprint posted online July 21 2016. arXiv:1607.06450."},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"HanK WangY TianQ GuoJ XuC XuC.Ghostnet: More features from cheap operations. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2020:1580\u20101589.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"CholletF.Xception: Deep learning with depthwise separable convolutions. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:1251\u20101258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_9_21_1","unstructured":"NairV HintonGE.Rectified linear units improve restricted boltzmann machines. In:Proceedings of the 27th International Conference on Machine Learning (ICML\u201010).2010:807\u2010814."},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"IslamM LiY RenH.Learning where to look while tracking instruments in robot\u2010assisted surgery. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2019:412\u2010420.","DOI":"10.1007\/978-3-030-32254-0_46"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"GongH ChenG WangR et\u00a0al.Multi\u2010task learning for thyroid nodule segmentation with thyroid region prior. In:2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).IEEE;2021:257\u2010261.","DOI":"10.1109\/ISBI48211.2021.9434087"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"PedrazaL VargasC Narv\u00e1ezF Dur\u00e1nO Mu\u00f1ozE RomeroE.An open access thyroid ultrasound image database. In:10th International Symposium on Medical Information Processing and Analysis. 9287.SPIE.2015:188\u2010193.","DOI":"10.1117\/12.2073532"},{"key":"e_1_2_9_25_1","unstructured":"LoshchilovI HutterF.SGDR: Stochastic gradient descent with warm restarts.arXiv preprint posted online May 3 2017. arXiv:1608.03983."},{"key":"e_1_2_9_26_1","doi-asserted-by":"crossref","unstructured":"RonnebergerO FischerP BroxT.U\u2010net: Convolutional networks for biomedical image segmentation. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention Springer;2015:234\u2010241.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"ValanarasuJMJ PatelVM.UNeXt: MLP\u2010based rapid medical image segmentation network. In:International Conference on Medical Image Computing and Computer Assisted Intervention.Springer.2022:23\u201033.","DOI":"10.1007\/978-3-031-16443-9_3"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106389"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2023.107614"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3002417"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12880-015-0068-x"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2930068"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.1.015006"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"issue":"2","key":"e_1_2_9_35_1","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm S","year":"1979","journal-title":"Scand J Stat"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203771587"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12020-024-03731-5"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0268550"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70548","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70548","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70548","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T13:42:59Z","timestamp":1788270179000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70548"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":37,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1002\/mp.70548"],"URL":"https:\/\/doi.org\/10.1002\/mp.70548","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"2026-01-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70548"}}