{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T19:22:13Z","timestamp":1792783333934,"version":"4.5.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["General Research Fund of the Research Grant Council of Hong Kong (Reference no. 15102222)."],"award-info":[{"award-number":["General Research Fund of the Research Grant Council of Hong Kong (Reference no. 15102222)."]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Hong Kong Polytechnic University","id":[{"id":"https:\/\/ror.org\/0030zas98","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Radiol med"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Ultrasound (US) is widely used for assessing lymph node (LN) status, but its diagnostic accuracy remains highly operator dependent. A robust computer-assisted diagnostic model may enhance clinical performance and improve inter-operator and inter-center consistencies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>To develop and validate a multimodal fusion model, ViT-Rad, that combines radiomics features and deep learning features derived from vision transformers (ViT) for the classification of benign and malignant LNs in US images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Between February 2016 and November 2023, a total of 1647 ultrasound images were retrospectively collected for analysis. In this multicenter study, we constructed ViT-Rad, a three-module neural network integrating ViT-based global contextual features and radiomics features extracted from manually delineated regions of interest. To address potential cross-center domain shift, we further employed weak\/strong augmentation and a few-shot domain adaptation strategy using limited labeled external-center samples.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The model was trained and evaluated on a dataset from Center 1 (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u20091273; mean\u2009\u00b1\u2009SD age, 57\u2009\u00b1\u200914\u00a0years), and its generalizability was tested on an external dataset from Center 2 (\n                      <jats:italic>n<\/jats:italic>\n                      \u2009=\u2009374; mean\u2009\u00b1\u2009SD age, 52\u2009\u00b1\u200918\u00a0years). ViT-Rad achieved an AUC of 0.95 [95% CI 0.91, 0.98] and an accuracy of 0.90 [95% CI 0.85, 0.95] on the internal test set, outperforming conventional radiomics models (AUC\u2009=\u20090.79, 95% CI 0.71, 0.89;\n                      <jats:italic>P<\/jats:italic>\n                      \u2009=\u2009.006). With domain adaptation, its AUC on the external set increased from 0.73 [95% CI 0.69, 0.79] to 0.85 [95% CI 0.81, 0.90]. These findings suggest improved adaptation-assisted external performance under cross-center domain shift.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>By combining radiomics and ViT-derived features, ViT-Rad effectively integrates domain-specific and global contextual information, improving internal diagnostic performance and showing improved external adaptability after few-shot domain adaptation for LN classification on US images.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s11547-026-02257-2","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T08:06:26Z","timestamp":1790582786000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ViT-radiomics fusion for lymph node classification in ultrasound images: a multicenter study"],"prefix":"10.1007","author":[{"given":"Xinyang","family":"Han","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingguo","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon Takadiyi","family":"Gunda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziman","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ann Dorothy","family":"King","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Winnie Chiu-Wing","family":"Chu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Cai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5979-6072","authenticated-orcid":false,"given":"Michael Tin-Cheung","family":"Ying","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"issue":"6","key":"2257_CR1","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1097\/00004424-200206000-00005","volume":"37","author":"A Ahuja","year":"2002","unstructured":"Ahuja A, Ying M (2002) An overview of neck node sonography. Investig Radiol 37(6):333\u2013342. https:\/\/doi.org\/10.1097\/00004424-200206000-00005","journal-title":"Investig Radiol"},{"issue":"5","key":"2257_CR2","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.2214\/AJR.05.0936","volume":"186","author":"S Alvarez","year":"2006","unstructured":"Alvarez S, A\u00f1orbe E, Alcorta P, L\u00f3pez F, Alonso I, Cort\u00e9s J (2006) Role of sonography in the diagnosis of axillary lymph node metastases in breast cancer: a systematic review. AJR Am J Roentgenol 186(5):1342\u20131348","journal-title":"AJR Am J Roentgenol"},{"issue":"2","key":"2257_CR3","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1053\/j.sult.2022.02.003","volume":"43","author":"E Avery","year":"2022","unstructured":"Avery E, Sanelli PC, Aboian M, Payabvash S (2022) Radiomics: a primer on processing workflow and analysis. Semin Ultrasound CT MR 43(2):142\u2013146. https:\/\/doi.org\/10.1053\/j.sult.2022.02.003","journal-title":"Semin Ultrasound CT MR"},{"issue":"10","key":"2257_CR4","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1002\/bjs.10920","volume":"105","author":"I Balasubramanian","year":"2018","unstructured":"Balasubramanian I, Fleming CA, Corrigan MA, Redmond HP, Kerin MJ, Lowery AJ (2018) Meta-analysis of the diagnostic accuracy of ultrasound-guided fine-needle aspiration and core needle biopsy in diagnosing axillary lymph node metastasis. Br J Surg 105(10):1244\u20131253. https:\/\/doi.org\/10.1002\/bjs.10920","journal-title":"Br J Surg"},{"key":"2257_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109913","volume":"189","author":"E Chilet-Martos","year":"2025","unstructured":"Chilet-Martos E, Vila-Franc\u00e9s J, Bagan JV, Vives-Gilabert Y (2025) Automated classification of oral cancer lesions: vision transformers vs radiomics. Comput Biol Med 189:109913. https:\/\/doi.org\/10.1016\/j.compbiomed.2025.109913","journal-title":"Comput Biol Med"},{"issue":"3","key":"2257_CR6","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44(3):837\u2013845","journal-title":"Biometrics"},{"key":"2257_CR7","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S (2020) An image is worth 16\u00d716 words: transformers for image recognition at scale. arXiv preprint https:\/\/arxiv.org\/abs\/2010.11929"},{"issue":"2","key":"2257_CR8","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1148\/radiol.2015151169","volume":"278","author":"RJ Gillies","year":"2016","unstructured":"Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278(2):563\u2013577. https:\/\/doi.org\/10.1148\/radiol.2015151169","journal-title":"Radiology"},{"issue":"1","key":"2257_CR9","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1186\/s12885-025-13447-y","volume":"25","author":"X Han","year":"2025","unstructured":"Han X, Qu J, Chui M-L, Gunda ST, Chen Z, Qin J, King AD, Chu WC-W, Cai J, Ying MT-C (2025) Artificial intelligence performance in ultrasound-based lymph node diagnosis: a systematic review and meta-analysis. BMC Cancer 25(1):73. https:\/\/doi.org\/10.1186\/s12885-025-13447-y","journal-title":"BMC Cancer"},{"issue":"3","key":"2257_CR10","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1148\/radiology.148.3.6878708","volume":"148","author":"JA Hanley","year":"1983","unstructured":"Hanley JA, McNeil BJ (1983) A method of comparing the areas under receiver operating characteristic curves derived from the same cases. Radiology 148(3):839\u2013843. https:\/\/doi.org\/10.1148\/radiology.148.3.6878708","journal-title":"Radiology"},{"issue":"1","key":"2257_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-024-12533-x","volume":"24","author":"W Li","year":"2024","unstructured":"Li W, Li Y, Gao S, Huang N, Kojima I, Kusama T, Ou Y, Iikubo M, Niu X (2024) Integrating lipid metabolite analysis with MRI-based transformer and radiomics for early and late stage prediction of oral squamous cell carcinoma. BMC Cancer 24(1):795. https:\/\/doi.org\/10.1186\/s12885-024-12533-x","journal-title":"BMC Cancer"},{"issue":"2","key":"2257_CR12","doi-asserted-by":"publisher","first-page":"774","DOI":"10.1007\/s00330-022-09122-6","volume":"33","author":"M Lin","year":"2023","unstructured":"Lin M, Tang X, Cao L, Liao Y, Zhang Y, Zhou J (2023) Using ultrasound radiomics analysis to diagnose cervical lymph node metastasis in patients with nasopharyngeal carcinoma. Eur Radiol 33(2):774\u2013783. https:\/\/doi.org\/10.1007\/s00330-022-09122-6","journal-title":"Eur Radiol"},{"issue":"1","key":"2257_CR13","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-025-01934-6","volume":"16","author":"S Luo","year":"2025","unstructured":"Luo S, Chen X, Yao M, Ying Y, Huang Z, Zhou X, Liao Z, Zhang L, Hu N, Huang C (2025) Intratumoral and peritumoral ultrasound-based radiomics for preoperative prediction of HER2-low breast cancer: a multicenter retrospective study. Insights Imaging 16(1):53. https:\/\/doi.org\/10.1186\/s13244-025-01934-6","journal-title":"Insights Imaging"},{"key":"2257_CR14","doi-asserted-by":"publisher","DOI":"10.2174\/0115734056272324231115103747","author":"S Lyu","year":"2024","unstructured":"Lyu S, Zhang M, Yang L, Zhang B, Gao L, Yang L, Zhang Y (2024) Application of machine-learning based on radiomics features in differential diagnosis of superficial lymphadenopathy. Curr Med Imaging. https:\/\/doi.org\/10.2174\/0115734056272324231115103747","journal-title":"Curr Med Imaging"},{"issue":"3","key":"2257_CR15","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.232554","volume":"312","author":"ZA Magnuska","year":"2024","unstructured":"Magnuska ZA, Roy R, Palmowski M, Kohlen M, Winkler BS, Pfeil T, Boor P, Schulz V, Krauss K, Stickeler E, Kiessling F (2024) Combining radiomics and autoencoders to distinguish benign and malignant breast tumors on US images. Radiology 312(3):e232554. https:\/\/doi.org\/10.1148\/radiol.232554","journal-title":"Radiology"},{"key":"2257_CR16","doi-asserted-by":"crossref","unstructured":"Qu J, Han X, Xiao T, Ai J, Wu J, Zhao T, Qin J, King AD, Chu WC-W, Cai J (2025) Adapting vision-language foundation model for next generation medical ultrasound image analysis. arXiv preprint https:\/\/arxiv.org\/abs\/2506.08849","DOI":"10.1016\/j.eswa.2026.132560"},{"key":"2257_CR17","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3575454","author":"J Qu","year":"2025","unstructured":"Qu J, Han X, Chui M-L, Pu Y, Gunda ST, Chen Z, Qin J, King AD, Chu WC-W, Cai J (2025) The application of deep learning for lymph node segmentation: a systematic review. IEEE Access. https:\/\/doi.org\/10.1109\/access.2025.3575454","journal-title":"IEEE Access"},{"key":"2257_CR18","doi-asserted-by":"crossref","unstructured":"Qu J, Han X, Pu Y, Chui ML, Gunda ST, Chen Z et al. (2026) Multiscale switch for semi-supervised and contrastive learning in medical ultrasound image segmentation. IEEE Transactions on Neural Networks and Learning Systems","DOI":"10.1109\/TNNLS.2026.3669814"},{"key":"2257_CR19","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1217309","volume":"13","author":"YL Tang","year":"2023","unstructured":"Tang YL, Wang B, Ou-Yang T, Lv WZ, Tang SC, Wei A, Cui XW, Huang JS (2023) Ultrasound radiomics based on axillary lymph nodes images for predicting lymph node metastasis in breast cancer. Front Oncol 13:1217309. https:\/\/doi.org\/10.3389\/fonc.2023.1217309","journal-title":"Front Oncol"},{"issue":"1","key":"2257_CR20","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-020-00887-2","volume":"11","author":"JE van Timmeren","year":"2020","unstructured":"van Timmeren JE, Cester D, Tanadini-Lang S, Alkadhi H, Baessler B (2020) Radiomics in medical imaging\u2014\u201chow-to\u201d guide and critical reflection. Insights Imaging 11(1):91. https:\/\/doi.org\/10.1186\/s13244-020-00887-2","journal-title":"Insights Imaging"},{"key":"2257_CR21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14050542","author":"M Vafaeezadeh","year":"2024","unstructured":"Vafaeezadeh M, Behnam H, Gifani P (2024) Ultrasound image analysis with vision transformers-review. Diagnostics (Basel). https:\/\/doi.org\/10.3390\/diagnostics14050542","journal-title":"Diagnostics (Basel)"},{"key":"2257_CR22","doi-asserted-by":"publisher","first-page":"1825","DOI":"10.1245\/s10434-011-2200-7","volume":"19","author":"SA Valente","year":"2012","unstructured":"Valente SA, Levine GM, Silverstein MJ, Rayhanabad JA, Weng-Grumley JG, Ji L, Holmes DR, Sposto R, Sener SF (2012) Accuracy of predicting axillary lymph node positivity by physical examination, mammography, ultrasonography, and magnetic resonance imaging. Ann Surg Oncol 19:1825\u20131830","journal-title":"Ann Surg Oncol"},{"issue":"11","key":"2257_CR23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0143308","volume":"10","author":"J Wang","year":"2015","unstructured":"Wang J, Kato F, Oyama-Manabe N, Li R, Cui Y, Tha KK, Yamashita H, Kudo K, Shirato H (2015) Identifying triple-negative breast cancer using background parenchymal enhancement heterogeneity on dynamic contrast-enhanced MRI: a pilot radiomics study. PLoS ONE 10(11):e0143308. https:\/\/doi.org\/10.1371\/journal.pone.0143308","journal-title":"PLoS ONE"},{"issue":"5","key":"2257_CR24","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.221157","volume":"307","author":"W Xu","year":"2023","unstructured":"Xu W, Jia X, Mei Z, Gu X, Lu Y, Fu CC, Zhang R, Gu Y, Chen X, Luo X, Li N, Bai B, Li Q, Yan J, Zhai H, Guan L, Gong B, Zhao K, Fang Q, Breast U (2023) Generalizability and diagnostic performance of ai models for thyroid US. Radiology 307(5):e221157. https:\/\/doi.org\/10.1148\/radiol.221157","journal-title":"Radiology"},{"key":"2257_CR25","unstructured":"Yin D, Hu L, Li B, Zhang Y (2023) Adapter is all you need for tuning visual tasks. arXiv preprint https:\/\/arxiv.org\/abs\/2311.15010"}],"container-title":["La radiologia medica"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11547-026-02257-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11547-026-02257-2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11547-026-02257-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T20:02:57Z","timestamp":1790625777000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11547-026-02257-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":25,"alternative-id":["2257"],"URL":"https:\/\/doi.org\/10.1007\/s11547-026-02257-2","relation":{},"ISSN":["1826-6983"],"issn-type":[{"value":"1826-6983","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"17 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This retrospective multicenter study involved human participants. The study protocol was reviewed and approved by the institutional review board\/ethics committee of The Hong Kong Polytechnic University. All procedures were performed in accordance with the ethical standards of the institutional and\/or national research committees and with the 1964 Helsinki declaration and its later amendments.","order":2,"name":"Ethics","label":"Research involving human participants and\/or animals","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The requirement for informed consent was waived by the institutional review board\/ethics committee of each participating center due to the retrospective nature of the study and the use of de-identified data.","order":3,"name":"Ethics","label":"Informed consent","group":{"name":"EthicsHeading","label":"Declarations"}}]}}