{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T21:51:21Z","timestamp":1773784281268,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:00:00Z","timestamp":1773705600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100013651","name":"Deutsche Wirbels\u00e4ulenstiftung","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013651","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["521771484"],"award-info":[{"award-number":["521771484"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Spinal tumor surgery requires rapid tissue diagnosis to guide surgical decisions and further treatment strategies, yet current intraoperative methods are time-intensive and require specialized expertise. No AI systems exist for real-time spinal tumor classification during surgery. We developed SpineXtract, the first AI-powered system for rapid intraoperative spinal tumor diagnosis using stimulated Raman histology (SRH) \u2014 a label-free Raman spectromics imaging technique without tissue processing available during surgery. We created a transformer-based classifier optimized for spinal tissue characteristics to identify common tumor types: meningioma, schwannoma, ependymoma, and metastasis. The system was tested in an international, multicenter, simulated, single-arm study using existing SRH datasets (44 patients, 142 slide-images) from three international institutions, with final pathological diagnosis as reference standard. SpineXtract achieved a 92.9% macro-average balanced accuracy (95% CI: 85.5\u201398.2) within 5\u2009minutes (tumor-specific accuracy range, 84.2\u201398.6%), while providing quantitative microscopic feedback for granular tissue analysis. Performance remained consistent across institutions (macro balanced accuracy 91.4\u201392.0%) and outperformed existing brain tumor classifiers by 15.6%. Our results demonstrate clinical applicability, enabling rapid intraoperative diagnosis with performance exceeding current methods, potentially transforming intraoperative diagnostic workflows in spinal tumor surgery.<\/jats:p>","DOI":"10.1038\/s41746-025-02279-6","type":"journal-article","created":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:07:23Z","timestamp":1773770843000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["AI-driven label-free Raman spectromics for intraoperative spinal tumor assessment"],"prefix":"10.1038","volume":"9","author":[{"given":"David","family":"Reinecke","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nina","family":"M\u00fcller","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna-Katharina","family":"Meissner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gina","family":"F\u00fcrtjes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lili","family":"Leyer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Claire","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrian","family":"Ion-Margineanu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nader","family":"Maarouf","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Smith","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Todd C.","family":"Hollon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhai","family":"Hou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abdulkader","family":"Al-Shughri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lisa I.","family":"K\u00f6rner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Georg","family":"Widhalm","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thomas","family":"Roetzer-Pejrimovsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matija","family":"Snuderl","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sandra","family":"Camelo-Piragua","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"John G.","family":"Golfinos","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roland","family":"Goldbrunner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel A.","family":"Orringer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Niklas","family":"von Spreckelsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Neuschmelting","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,3,17]]},"reference":[{"key":"2279_CR1","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.ejrad.2003.10.021","volume":"50","author":"JWM Van Goethem","year":"2004","unstructured":"Van Goethem, J. W. M., van den Hauwe, L., Ozsarlak, O., De Schepper, A. M. A. & Parizel, P. M. Spinal tumors. Eur. J. Radio. 50, 159\u2013176 (2004).","journal-title":"Eur. J. Radio."},{"key":"2279_CR2","doi-asserted-by":"publisher","first-page":"354","DOI":"10.4103\/ajns.AJNS_366_19","volume":"15","author":"M Asilt\u00fcrk","year":"2020","unstructured":"Asilt\u00fcrk, M., Abdallah, A. & Sofuoglu, E. \u00d6 Radiologic-histopathologic correlation of adult spinal tumors: a retrospective study. Asian J. Neurosurg. 15, 354\u2013362 (2020).","journal-title":"Asian J. Neurosurg."},{"key":"2279_CR3","first-page":"769753","volume":"2011","author":"LM Shah","year":"2011","unstructured":"Shah, L. M. & Salzman, K. L. Imaging of Spinal Metastatic Disease. Int. J. Surgical Oncol. 2011, 769753 (2011).","journal-title":"Int. J. Surgical Oncol."},{"key":"2279_CR4","first-page":"559","volume":"121","author":"DA Novis","year":"1997","unstructured":"Novis, D. A. & Zarbo, R. J. Interinstitutional comparison of frozen section turnaround time. A College of American Pathologists Q-Probes study of 32868 frozen sections in 700 hospitals. Arch. Pathol. Lab Med 121, 559\u2013567 (1997).","journal-title":"Arch. Pathol. Lab Med"},{"key":"2279_CR5","doi-asserted-by":"publisher","first-page":"1162","DOI":"10.1016\/j.jos.2023.08.011","volume":"29","author":"Y Tanaka","year":"2024","unstructured":"Tanaka, Y. et al. Usefulness and limitations of intraoperative pathological diagnosis using frozen sections for spinal cord tumors. J. Orthop. Sci. 29, 1162\u20131167 (2024).","journal-title":"J. Orthop. Sci."},{"key":"2279_CR6","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1016\/j.clineuro.2018.02.025","volume":"167","author":"K Kobayashi","year":"2018","unstructured":"Kobayashi, K. et al. Accuracy of intraoperative pathological diagnosis using frozen sections of spinal cord lesions. Clin. Neurol. Neurosurg. 167, 117\u2013121 (2018).","journal-title":"Clin. Neurol. Neurosurg."},{"key":"2279_CR7","doi-asserted-by":"publisher","first-page":"e152","DOI":"10.1016\/j.wneu.2019.05.080","volume":"129","author":"KW Chang","year":"2019","unstructured":"Chang, K. W., Noh, S. hyun, Park, J.-Y., Cho, Y.-E. & Chin, D.-K. Retrospective Study on Accuracy of Intraoperative Frozen Section Biopsy in Spinal Tumors. World Neurosurg. 129, e152\u2013e157 (2019).","journal-title":"World Neurosurg."},{"key":"2279_CR8","doi-asserted-by":"publisher","first-page":"1857","DOI":"10.1126\/science.1165758","volume":"322","author":"CW Freudiger","year":"2008","unstructured":"Freudiger, C. W. et al. Label-free biomedical imaging with high sensitivity by stimulated Raman scattering microscopy. Science 322, 1857\u20131861 (2008).","journal-title":"Science"},{"key":"2279_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-016-0027","volume":"1","author":"DA Orringer","year":"2017","unstructured":"Orringer, D. A. et al. Rapid intraoperative histology of unprocessed surgical specimens via fibre-laser-based stimulated Raman scattering microscopy. Nat. Biomed. Eng. 1, 0027 (2017).","journal-title":"Nat. Biomed. Eng."},{"key":"2279_CR10","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1038\/s41591-019-0715-9","volume":"26","author":"TC Hollon","year":"2020","unstructured":"Hollon, T. C. et al. Near real-time intraoperative brain tumor diagnosis using stimulated Raman histology and deep neural networks. Nat. Med. 26, 52\u201358 (2020).","journal-title":"Nat. Med."},{"key":"2279_CR11","doi-asserted-by":"publisher","first-page":"828","DOI":"10.1038\/s41591-023-02252-4","volume":"29","author":"T Hollon","year":"2023","unstructured":"Hollon, T. et al. Artificial-intelligence-based molecular classification of diffuse gliomas using rapid, label-free optical imaging. Nat. Med. 29, 828\u2013832 (2023).","journal-title":"Nat. Med."},{"key":"2279_CR12","doi-asserted-by":"publisher","first-page":"1721","DOI":"10.1007\/s10143-021-01711-1","volume":"45","author":"J Straehle","year":"2022","unstructured":"Straehle, J. et al. Neuropathological interpretation of stimulated Raman histology images of brain and spine tumors: part B. Neurosurg. Rev. 45, 1721\u20131729 (2022).","journal-title":"Neurosurg. Rev."},{"key":"2279_CR13","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1186\/s40478-022-01411-x","volume":"10","author":"D Reinecke","year":"2022","unstructured":"Reinecke, D. et al. Novel rapid intraoperative qualitative tumor detection by a residual convolutional neural network using label-free stimulated Raman scattering microscopy. Acta Neuropathol. Commun. 10, 109 (2022).","journal-title":"Acta Neuropathol. Commun."},{"key":"2279_CR14","doi-asserted-by":"publisher","unstructured":"Reinecke, D. et al. Streamlined Intraoperative Brain Tumor Classification and Molecular Subtyping in Stereotactic Biopsies Using Stimulated Raman Histology and Deep Learning. Clinical Cancer Research OF1\u2013OF13 https:\/\/doi.org\/10.1158\/1078-0432.CCR-23-3842 (2024).","DOI":"10.1158\/1078-0432.CCR-23-3842"},{"key":"2279_CR15","doi-asserted-by":"publisher","unstructured":"Reinecke, D. et al. Fast intraoperative detection of primary CNS lymphoma and differentiation from common CNS tumors using stimulated Raman histology and deep learning. Neuro Oncol noae270 https:\/\/doi.org\/10.1093\/neuonc\/noae270 (2024).","DOI":"10.1093\/neuonc\/noae270"},{"key":"2279_CR16","doi-asserted-by":"publisher","first-page":"4220","DOI":"10.1002\/cncr.27390","volume":"118","author":"LM Duong","year":"2012","unstructured":"Duong, L. M. et al. Descriptive epidemiology of malignant and nonmalignant primary spinal cord, spinal meninges, and cauda equina tumors, United States, 2004-2007. Cancer 118, 4220\u20134227 (2012).","journal-title":"Cancer"},{"key":"2279_CR17","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/S0090-3019(03)00537-8","volume":"61","author":"P Conti","year":"2004","unstructured":"Conti, P., Pansini, G., Mouchaty, H., Capuano, C. & Conti, R. Spinal neurinomas: retrospective analysis and long-term outcome of 179 consecutively operated cases and review of the literature. Surgical Neurol. 61, 34\u201343 (2004).","journal-title":"Surgical Neurol."},{"key":"2279_CR18","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1093\/neuonc\/noab106","volume":"23","author":"DN Louis","year":"2021","unstructured":"Louis, D. N. et al. The 2021 WHO Classification of Tumors of the Central Nervous System: a summary. Neuro-Oncol. 23, 1231\u20131251 (2021).","journal-title":"Neuro-Oncol."},{"key":"2279_CR19","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1038\/modpathol.2014.109","volume":"28","author":"M Pekmezci","year":"2015","unstructured":"Pekmezci, M. et al. Morphologic and immunohistochemical features of malignant peripheral nerve sheath tumors and cellular schwannomas. Mod. Pathol. 28, 187\u2013200 (2015).","journal-title":"Mod. Pathol."},{"key":"2279_CR20","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1111\/bpa.12125","volume":"24","author":"DA Hilton","year":"2014","unstructured":"Hilton, D. A. & Hanemann, C. O. Schwannomas and their pathogenesis. Brain Pathol. 24, 205\u2013220 (2014).","journal-title":"Brain Pathol."},{"key":"2279_CR21","first-page":"170791","volume":"2013","author":"KM Krisht","year":"2013","unstructured":"Krisht, K. M. & Schmidt, M. H. Tanycytic ependymoma: a challenging histological diagnosis. Case Rep. Neurological Med. 2013, 170791 (2013).","journal-title":"Case Rep. Neurological Med."},{"key":"2279_CR22","doi-asserted-by":"publisher","first-page":"440","DOI":"10.2174\/1874325001206010440","volume":"6","author":"P Paholpak","year":"2012","unstructured":"Paholpak, P., Sirichativapee, W., Wisanuyotin, T., Kosuwon, W. & Jeeravipoolvarn, P. Prevalence of Known and Unknown Primary Tumor Sites In Spinal Metastasis Patients. Open Orthop. J. 6, 440\u2013444 (2012).","journal-title":"Open Orthop. J."},{"key":"2279_CR23","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1002\/ijc.33247","volume":"148","author":"S Izraely","year":"2021","unstructured":"Izraely, S. & Witz, I. P. Site-specific metastasis: A cooperation between cancer cells and the metastatic microenvironment. Int. J. Cancer 148, 1308\u20131322 (2021).","journal-title":"Int. J. Cancer"},{"key":"2279_CR24","doi-asserted-by":"publisher","first-page":"e078378","DOI":"10.1136\/bmj-2023-078378","volume":"385","author":"GS Collins","year":"2024","unstructured":"Collins, G. S. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ 385, e078378 (2024).","journal-title":"BMJ"},{"key":"2279_CR25","doi-asserted-by":"publisher","first-page":"e047709","DOI":"10.1136\/bmjopen-2020-047709","volume":"11","author":"V Sounderajah","year":"2021","unstructured":"Sounderajah, V. et al. Developing a reporting guideline for artificial intelligence-centred diagnostic test accuracy studies: the STARD-AI protocol. BMJ Open 11, e047709 (2021).","journal-title":"BMJ Open"},{"key":"2279_CR26","doi-asserted-by":"publisher","unstructured":"Grill, J.-B. et al. Bootstrap your own latent: A new approach to self-supervised Learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2006.07733 (2020).","DOI":"10.48550\/arXiv.2006.07733"},{"key":"2279_CR27","unstructured":"Khosla, P. et al. Supervised Contrastive Learning. in Advances in Neural Information Processing Systems vol. 33 18661\u201318673 (Curran Associates, Inc., 2020)."},{"key":"2279_CR28","unstructured":"Vaswani, A. et al. Attention is All you Need. in Advances in Neural Information Processing Systems vol. 30 (Curran Associates, Inc., 2017)."},{"key":"2279_CR29","unstructured":"(PDF) Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. ResearchGate https:\/\/www.researchgate.net\/publication\/2594015_Probabilistic_Outputs_for_Support_Vector_Machines_and_Comparisons_to_Regularized_Likelihood_Methods."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02279-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02279-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02279-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T18:07:25Z","timestamp":1773770845000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02279-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,17]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2279"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02279-6","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,17]]},"assertion":[{"value":"30 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"D.A.O., T.C.H., and A.I-M. are shareholders in Invenio Imaging, Inc. A.I-M. is employed by Invenio Imaging Inc.. M.S. is a scientific advisor and shareholder of Heidelberg Epignostix and Halo Dx, and a scientific advisor of Arima Genomics and InnoSIGN, and received research funding from Lilly USA, not related to this work. All other authors do not have any competing interests. Industry-affiliated authors had no access to ground truth generation processes (labeling, adjudication) and did not participate in outcome assessments.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"227"}}