{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T08:29:32Z","timestamp":1764664172800,"version":"3.46.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Radiol Exp"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Detection of axillary lymph node (LN) involvement is essential for staging breast cancer and optimizing treatment. This proof-of-concept two-center study explored the feasibility of magnetic resonance imaging (MRI) radiomics-based machine learning models to predict LN involvement and compare their performance with node reporting and data system (Node-RADS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>We retrospectively included breast cancer patients undergoing preoperative multiparametric MRI and LN dissection (January 2020\u2013September 2024). Stable radiomic features (intraclass correlation coefficient\u2009\u2265\u20090.75) were extracted from contrast-enhanced, subtracted, and T2-weighted sequences. Five machine learning models were trained for binary LN involvement classification, using histopathology as a reference standard. The best-performing model was externally validated on an independent cohort. Performance metrics included sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and area under the receiver operating characteristic curve (AUROC). Node-RADS (scores\u2009&gt;\u20092 indicating LN involvement) was used for comparison in the external dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Of 93 cases, 40 (43%) were LN involvement-positive; 17 stable features were selected for model development. The best-performing model achieved 81% AUROC (95% confidence interval 78\u201385%), 75% accuracy (70\u201379%), 52% sensitivity (41\u201362%), 92% specificity (86\u201398%), 85% PPV (76\u201395%), and 72% NPV (68\u201376%) on the internal dataset. External validation (18 cases) showed promising results: 94% AUROC (89\u221299%), 89% sensitivity (52\u2013100%), 100% specificity (66\u2013100%); in this small cohort, accuracy, sensitivity, and specificity did not differ significantly\n                      <jats:italic>versus<\/jats:italic>\n                      Node-RADS, with moderate agreement (Cohen \u03ba\u2009=\u20090.47).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>In this preliminary series, the model showed performance metrics in predicting LN involvement comparable to Node-RADS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Relevance statement<\/jats:title>\n                    <jats:p>Radiomics-based MRI models may represent a promising investigational tool for noninvasive axillary LN assessment in breast cancer. The performance comparable to Node-RADS suggests a potential to support clinical decision-making in the context of axillary de-escalation surgery.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Key Points<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Radiomics uses MRI to predict breast cancer LN involvement non-invasively and accurately.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Radiomics and Node-RADS showed comparable performance.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Radiomics could reduce invasive procedures, supporting personalized treatments in breast cancer care.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Graphical Abstract<\/jats:title>\n                  <\/jats:sec>","DOI":"10.1186\/s41747-025-00660-4","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T08:24:49Z","timestamp":1764663889000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Radiomics-based MRI models for predicting breast cancer axillary lymph node involvement in comparison with Node-RADS: a proof-of-concept study"],"prefix":"10.1186","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-6626-2478","authenticated-orcid":false,"given":"Roberto","family":"Maroncelli","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Veronica","family":"Rizzo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcella","family":"Pasculli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sara","family":"Coppola","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chiara","family":"De Nardo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Moschetta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carlo","family":"Catalano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Federica","family":"Pediconi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"660_CR1","doi-asserted-by":"publisher","first-page":"e231","DOI":"10.1634\/theoncologist.2019-0427","volume":"25","author":"MA Marino","year":"2020","unstructured":"Marino MA, Avendano D, Zapata P, Riedl CC, Pinker K (2020) LN imaging in patients with primary breast cancer: concurrent diagnostic tools. Oncologist 25:e231\u2013e242. https:\/\/doi.org\/10.1634\/theoncologist.2019-0427","journal-title":"Oncologist"},{"key":"660_CR2","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.seminoncol.2020.03.006","volume":"47","author":"F Magnoni","year":"2020","unstructured":"Magnoni F, Galimberti V, Paganelli G et al (2020) Axillary surgery in breast cancer: an updated historical perspective. Semin Oncol 47:194\u2013200. https:\/\/doi.org\/10.1016\/j.seminoncol.2020.03.006","journal-title":"Semin Oncol"},{"key":"660_CR3","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1177\/030089161109700503","volume":"97","author":"S Barni","year":"2011","unstructured":"Barni S, Venturini M, Molino A et al (2011) Importance of adherence to guidelines in breast cancer clinical practice: the Italian experience (AIOM). Tumori 97:559\u2013563. https:\/\/doi.org\/10.1177\/030089161109700503","journal-title":"Tumori"},{"key":"660_CR4","doi-asserted-by":"publisher","first-page":"6116","DOI":"10.1007\/s00330-020-07572-4","volume":"31","author":"FHJ Elsholtz","year":"2021","unstructured":"Elsholtz FHJ, Asbach P, Haas M et al (2021) Introducing the node reporting and data system 1.0 (Node-RADS): a concept for standardized assessment of LNs in cancer. Eur Radiol 31:6116\u20136124. https:\/\/doi.org\/10.1007\/s00330-020-07572-4","journal-title":"Eur Radiol"},{"key":"660_CR5","doi-asserted-by":"publisher","first-page":"4021","DOI":"10.1007\/s00330-023-09834-9","volume":"34","author":"F Pediconi","year":"2024","unstructured":"Pediconi F, Maroncelli R, Belli P et al (2024) Performance of MRI for standardized LNs assessment in breast cancer: Are we ready for Node-RADS?. Eur Radiol 34:4021\u20134032. https:\/\/doi.org\/10.1007\/s00330-023-09834-9","journal-title":"Eur Radiol"},{"key":"660_CR6","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1038\/s41571-020-0400-1","volume":"17","author":"Y Liu","year":"2020","unstructured":"Liu Y, Guo Y, Xu Y et al (2020) Radiomics as predictive biomarkers for cancer outcomes. Nat Rev Clin Oncol 17:541\u2013554. https:\/\/doi.org\/10.1038\/s41571-020-0400-1","journal-title":"Nat Rev Clin Oncol"},{"key":"660_CR7","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1148\/rg.2021210053","volume":"41","author":"HL Chung","year":"2021","unstructured":"Chung HL, Le-Petross HT, Leung JWT (2021) Imaging updates to breast cancer LN management. Radiographics 41:1283\u20131299. https:\/\/doi.org\/10.1148\/rg.2021210053","journal-title":"Radiographics"},{"key":"660_CR8","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1007\/s10278-023-00757-6","volume":"36","author":"Y Chen","year":"2023","unstructured":"Chen Y, Wang L, Zhang J et al (2023) Deep learning radiomics of preoperative breast MRI for prediction of axillary LN metastasis. J Digit Imaging 36:1323\u20131331. https:\/\/doi.org\/10.1007\/s10278-023-00757-6","journal-title":"J Digit Imaging"},{"key":"660_CR9","doi-asserted-by":"publisher","first-page":"2045","DOI":"10.1245\/s10434-021-11095-4","volume":"29","author":"P Veronesi","year":"2022","unstructured":"Veronesi P, Intra M, Vento AR et al (2022) Advances in axillary lymph-node imaging in breast cancer. Ann Surg Oncol 29:2045\u20132054. https:\/\/doi.org\/10.1245\/s10434-021-11095-4","journal-title":"Ann Surg Oncol"},{"key":"660_CR10","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1200\/JCO.20.01590","volume":"39","author":"Y Jiang","year":"2021","unstructured":"Jiang Y, Wang H, Wu J et al (2021) Radiomics-based deep learning models for non-invasive cancer diagnosis. J Clin Oncol 39:1234\u20131243. https:\/\/doi.org\/10.1200\/JCO.20.01590","journal-title":"J Clin Oncol"},{"key":"660_CR11","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1186\/s13244-023-01415-8","volume":"14","author":"B Kocak","year":"2023","unstructured":"Kocak B, Baessler B, Bakas S et al (2023) The checklist for evaluation of radiomics research (CLEAR): a detailed reporting guideline for authors and reviewers, endorsed by the European Society of Radiology (ESR) and the European Society of Medical Imaging Informatics (EuSoMII). Insights Imaging 14:75 https:\/\/doi.org\/10.1186\/s13244-023-01415-8","journal-title":"Insights Imaging"},{"key":"660_CR12","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1186\/s41747-024-00471-z","volume":"8","author":"B Kocak","year":"2024","unstructured":"Kocak B, Borgheresi A, Ponsiglione A et al (2024) Explanation and elaboration with examples for CLEAR (CLEAR-E3): an EuSoMII Radiomics Auditing Group initiative. Eur Radiol Exp 8:72. https:\/\/doi.org\/10.1186\/s41747-024-00471-z","journal-title":"Eur Radiol Exp"},{"key":"660_CR13","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1093\/annonc\/mdv221","volume":"26","author":"AS Coates","year":"2015","unstructured":"Coates AS, Winer EP, Goldhirsch A et al (2015) Tailoring therapies\u2014improving the management of early breast cancer: St Gallen International Expert Consensus on the primary therapy of early breast cancer 2015. Ann Oncol 26:1533\u20131546. https:\/\/doi.org\/10.1093\/annonc\/mdv221","journal-title":"Ann Oncol"},{"key":"660_CR14","doi-asserted-by":"publisher","first-page":"328","DOI":"10.1148\/radiol.2020191145","volume":"295","author":"A Zwanenburg","year":"2020","unstructured":"Zwanenburg A, Valli\u00e8res M, Abdalah MA et al (2020) The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping. Radiology 295:328\u2013338. https:\/\/doi.org\/10.1148\/radiol.2020191145","journal-title":"Radiology"},{"key":"660_CR15","unstructured":"DeepTrace Technologies. Available via https:\/\/www.deeptracetech.com\/. Accessed 6 Aug 2025"},{"key":"660_CR16","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1093\/jnci\/djq008","volume":"102","author":"M de Boer","year":"2010","unstructured":"de Boer M, van Dijck JAAM, Bult P et al (2010) Breast cancer prognosis and occult LN metastases, isolated tumor cells, and micrometastases. J Natl Cancer Inst 102:410\u2013425. https:\/\/doi.org\/10.1093\/jnci\/djq008","journal-title":"J Natl Cancer Inst"},{"key":"660_CR17","doi-asserted-by":"publisher","first-page":"664","DOI":"10.1007\/s12282-020-01202-z","volume":"28","author":"BI Song","year":"2021","unstructured":"Song BI (2021) A machine learning-based radiomics model for the prediction of axillary lymph-node metastasis in breast cancer. Breast Cancer 28:664\u2013671. https:\/\/doi.org\/10.1007\/s12282-020-01202-z","journal-title":"Breast Cancer"},{"key":"660_CR18","doi-asserted-by":"publisher","first-page":"7914","DOI":"10.1038\/s41598-022-11983-7","volume":"12","author":"S Bove","year":"2022","unstructured":"Bove S, Comes MC, Diotaiuti S et al (2022) An ultrasound-based radiomic approach to predict the nodal status in clinically negative breast cancer patients. Sci Rep 12:7914\u20137914. https:\/\/doi.org\/10.1038\/s41598-022-11983-7","journal-title":"Sci Rep"},{"key":"660_CR19","doi-asserted-by":"publisher","first-page":"567","DOI":"10.18632\/oncotarget.27891","volume":"12","author":"J Adams","year":"2021","unstructured":"Adams J, Simpson M, Patel A et al (2021) Clinical applications of radiomics in oncology: current state and future directions. Oncotarget 12:567\u2013577. https:\/\/doi.org\/10.18632\/oncotarget.27891","journal-title":"Oncotarget"},{"key":"660_CR20","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1148\/radiol.2021212146","volume":"303","author":"L Zhang","year":"2022","unstructured":"Zhang L, Chen B, Xu T et al (2022) Radiomics standardization for reproducibility and clinical validation. Radiology 303:123\u2013135. https:\/\/doi.org\/10.1148\/radiol.2021212146","journal-title":"Radiology"},{"key":"660_CR21","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s40477-020-00467-y","volume":"23","author":"V Chiappa","year":"2020","unstructured":"Chiappa V, Bogani G, Lorusso D et al (2020) The adoption of radiomics and machine learning improves the diagnostic processes of women with ovarian masses (the AROMA pilot study). J Ultrasound 23:567\u2013575. https:\/\/doi.org\/10.1007\/s40477-020-00467-y","journal-title":"J Ultrasound"},{"key":"660_CR22","doi-asserted-by":"publisher","first-page":"5457","DOI":"10.1158\/0008-5472.CAN-20-1657","volume":"80","author":"T Gong","year":"2020","unstructured":"Gong T, Wu Q, He X et al (2020) Integration of radiomics and machine learning for precision oncology. Cancer Res 80:5457\u20135466. https:\/\/doi.org\/10.1158\/0008-5472.CAN-20-1657","journal-title":"Cancer Res"},{"key":"660_CR23","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1002\/jemt.24191","volume":"88","author":"L Gao","year":"2024","unstructured":"Gao L, Liu W, Chen Y et al (2024) AutoLNMNet: automated network for estimating lymph-node metastasis in EGC using a pyramid vision transformer. Microsc Res Tech 88:315\u2013322. https:\/\/doi.org\/10.1002\/jemt.24191","journal-title":"Microsc Res Tech"},{"key":"660_CR24","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1016\/j.ygyno.2021.02.005","volume":"161","author":"V Chiappa","year":"2021","unstructured":"Chiappa V, Interlenghi M, De Iaco P et al (2021) Using radiomics and machine learning with ultrasonography for the differential diagnosis of myometrial tumors. Gynecol Oncol 161:838\u2013844. https:\/\/doi.org\/10.1016\/j.ygyno.2021.02.005","journal-title":"Gynecol Oncol"},{"key":"660_CR25","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1007\/s10278-022-00548-6","volume":"22","author":"C Hernandez","year":"2022","unstructured":"Hernandez C, Rios Velazquez E, Parmar C et al (2022) Validation challenges in machine learning applications for radiomics. J Comput Imaging 22:367\u2013378. https:\/\/doi.org\/10.1007\/s10278-022-00548-6","journal-title":"J Comput Imaging"}],"container-title":["European Radiology Experimental"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00660-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s41747-025-00660-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s41747-025-00660-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T08:24:51Z","timestamp":1764663891000},"score":1,"resource":{"primary":{"URL":"https:\/\/eurradiolexp.springeropen.com\/articles\/10.1186\/s41747-025-00660-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["660"],"URL":"https:\/\/doi.org\/10.1186\/s41747-025-00660-4","relation":{},"ISSN":["2509-9280"],"issn-type":[{"value":"2509-9280","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]},"assertion":[{"value":"19 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This two-center retrospective study was conducted according to Good Clinical Practice guidelines. In accordance with the guidelines stipulated by the two Institutional Review Boards (Ethics Committee of Sapienza Universit\u00e0 di Roma\u2014Policlinico Umberto I and Ethics Committee of the University of Bari), ethical approval was deemed unnecessary for the conduct of this study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"All patient data were handled in compliance with applicable data protection regulations and institutional review board standards.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"MM is a member of the Scientific Editorial Board of\n                      European Radiology Experimental\n                      (section: Breast) and, as such, did not participate in the selection or review processes for this article. The remaining authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"117"}}