{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T12:18:49Z","timestamp":1783945129401,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T00:00:00Z","timestamp":1783900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000072","name":"National Institute of Dental and Craniofacial Research","doi-asserted-by":"crossref","award":["1R01DE031319-01"],"award-info":[{"award-number":["1R01DE031319-01"]}],"id":[{"id":"10.13039\/100000072","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Renaissance Health Service Corporation"},{"name":"Delta Dental of Michigan"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Oral potentially malignant disorders (OPMDs) such as leukoplakia and erythroplakia may harbor dysplasia or progress to oral squamous cell carcinoma (OSCC), yet visual inspection alone is unreliable for risk assessment. Cytology offers a minimally invasive adjunct, but conventional approaches depend on manual feature extraction and subjective review. Herein we report a deep learning (DL) object detection model that directly classifies four cell phenotypes: differentiated squamous epithelial (DSE) cells, small round (SR) cells, leukocytes, and lone nuclei. The DL model produced cytology-derived parameters that correlated strongly with histopathologic diagnoses across 692 subjects with OPMDs, OSCC, and healthy controls, including declining DSE cell proportion and increasing SR cells and leukocytes with disease severity (\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.0001). The oral cancer numerical index (OCNI) achieved AUROC values up to 0.99 for malignant versus healthy lesions, with excellent reliability (intra-class correlation coefficient\u2009\u2265\u20090.96). This reproducible, minimally invasive test provides a robust platform for early detection and surveillance of OPMDs.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-47538-y","type":"journal-article","created":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T23:46:11Z","timestamp":1783899971000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning single-cell analysis for cytologic evaluation of oral potentially malignant disorders"],"prefix":"10.1038","volume":"16","author":[{"given":"Michael P.","family":"McRae","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kritika S.","family":"Rajsri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nadarajah","family":"Vigneswaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A. Ross","family":"Kerr","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spencer W.","family":"Redding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin H.","family":"Thornhill","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Craig","family":"Murdoch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul M.","family":"Speight","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nancy","family":"Ruel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachelle","family":"Wolk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan R.","family":"Ruff","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John T.","family":"McDevitt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,13]]},"reference":[{"key":"47538_CR1","unstructured":"Elston, D. M. Leukoplakia and erythroplakia: Premalignant squamous lesions of the oral cavity, (2025). https:\/\/emedicine.medscape.com\/article\/1840467-overview"},{"key":"47538_CR2","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1016\/j.adaj.2017.07.032","volume":"148","author":"MW Lingen","year":"2017","unstructured":"Lingen, M. W. et al. Evidence-based clinical practice guideline for the evaluation of potentially malignant disorders in the oral cavity: A report of the American Dental Association. J Am. Dent. Assoc 148, 712\u2013727. https:\/\/doi.org\/10.1016\/j.adaj.2017.07.032 (2017).","journal-title":"J Am. Dent. Assoc"},{"key":"47538_CR3","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.cden.2017.08.004","volume":"62","author":"MA Huber","year":"2018","unstructured":"Huber, M. A. Adjunctive diagnostic techniques for oral and oropharyngeal cancer discovery. Dent. Clin. North Am. 62, 59\u201375. https:\/\/doi.org\/10.1016\/j.cden.2017.08.004 (2018).","journal-title":"Dent. Clin. North Am."},{"key":"47538_CR4","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1016\/j.adaj.2017.08.045","volume":"148","author":"MW Lingen","year":"2017","unstructured":"Lingen, M. W. et al. Adjuncts for the evaluation of potentially malignant disorders in the oral cavity: Diagnostic test accuracy systematic review and meta-analysis-a report of the American Dental Association. J Am. Dent. Assoc 148, 797-813.e752. https:\/\/doi.org\/10.1016\/j.adaj.2017.08.045 (2017).","journal-title":"J Am. Dent. Assoc"},{"key":"47538_CR5","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1111\/jop.12218","volume":"44","author":"A Rashid","year":"2015","unstructured":"Rashid, A. & Warnakulasuriya, S. The use of light-based (optical) detection systems as adjuncts in the detection of oral cancer and oral potentially malignant disorders: A systematic review. J. Oral Pathol. Med. 44, 307\u2013328. https:\/\/doi.org\/10.1111\/jop.12218 (2015).","journal-title":"J. Oral Pathol. Med."},{"key":"47538_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3390\/jimaging10100252","volume":"10","author":"T Mezei","year":"2024","unstructured":"Mezei, T., Kolcs\u00e1r, M., Jo\u00f3, A. & Gurzu, S. Image analysis in histopathology and cytopathology: From early days to current perspectives. J. Imaging 10, 1\u201323 (2024).","journal-title":"J. Imaging"},{"key":"47538_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102691","volume":"84","author":"H Jiang","year":"2023","unstructured":"Jiang, H. et al. Deep learning for computational cytology: A survey. Med. Image Anal. 84, 102691. https:\/\/doi.org\/10.1016\/j.media.2022.102691 (2023).","journal-title":"Med. Image Anal."},{"key":"47538_CR8","doi-asserted-by":"publisher","first-page":"474","DOI":"10.1016\/j.oooo.2015.05.023","volume":"120","author":"PM Speight","year":"2015","unstructured":"Speight, P. M. et al. Interobserver agreement in dysplasia grading: Toward an enhanced gold standard for clinical pathology trials. Oral Surg. Oral Med. Oral Pathol. Oral Radiol. 120, 474\u2013482. https:\/\/doi.org\/10.1016\/j.oooo.2015.05.023 (2015).","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"47538_CR9","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.oraloncology.2016.07.002","volume":"60","author":"TJ Abram","year":"2016","unstructured":"Abram, T. J. et al. Cytology-on-a-chip\u2019 based sensors for monitoring of potentially malignant oral lesions. Oral Oncol 60, 103\u2013111. https:\/\/doi.org\/10.1016\/j.oraloncology.2016.07.002 (2016).","journal-title":"Oral Oncol"},{"key":"47538_CR10","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1002\/cncy.22236","volume":"128","author":"MP McRae","year":"2020","unstructured":"McRae, M. P. et al. Point-of-care oral cytology tool for the screening and assessment of potentially malignant oral lesions. Cancer Cytopathol. 128, 207\u2013220. https:\/\/doi.org\/10.1002\/cncy.22236 (2020).","journal-title":"Cancer Cytopathol."},{"key":"47538_CR11","doi-asserted-by":"publisher","DOI":"10.1177\/0022034520973162","author":"MP McRae","year":"2020","unstructured":"McRae, M. P. et al. Nuclear F-actin cytology in oral epithelial dysplasia and oral squamous cell carcinoma. J. Dent. Res. https:\/\/doi.org\/10.1177\/0022034520973162 (2020).","journal-title":"J. Dent. Res."},{"key":"47538_CR12","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1158\/1940-6207.CAPR-09-0139","volume":"3","author":"SE Weigum","year":"2010","unstructured":"Weigum, S. E. et al. Nano-bio-chip sensor platform for examination of oral exfoliative cytology. Cancer Prev. Res. 3, 518\u2013528. https:\/\/doi.org\/10.1158\/1940-6207.CAPR-09-0139 (2010).","journal-title":"Cancer Prev. Res."},{"key":"47538_CR13","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1016\/j.oraloncology.2004.02.005","volume":"40","author":"TWJ Poate","year":"2004","unstructured":"Poate, T. W. J. et al. An audit of the efficacy of the oral brush biopsy technique in a specialist Oral Medicine unit. Oral Oncol. 40, 829\u2013834 (2004).","journal-title":"Oral Oncol."},{"key":"47538_CR14","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.14219\/jada.archive.1999.0055","volume":"130","author":"JJ Sciubba","year":"1999","unstructured":"Sciubba, J. J. Improving detection of precancerous and cancerous oral lesions: Computer-assisted analysis of the oral brush biopsy. J. Am. Dent. Assoc. 130, 1445\u20131457 (1999).","journal-title":"J. Am. Dent. Assoc."},{"key":"47538_CR15","first-page":"500","volume":"50","author":"JA Svirsky","year":"2002","unstructured":"Svirsky, J. A. et al. Comparison of computer-assisted brush biopsy results with follow up scalpel biopsy and histology. Gen. Dent. 50, 500\u2013503 (2002).","journal-title":"Gen. Dent."},{"key":"47538_CR16","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1158\/1940-6207.CAPR-15-0200","volume":"9","author":"LHM Pereira","year":"2016","unstructured":"Pereira, L. H. M. et al. Risk stratification system for oral cancer screening. Cancer Prev. Res. 9, 445. https:\/\/doi.org\/10.1158\/1940-6207.CAPR-15-0200 (2016).","journal-title":"Cancer Prev. Res."},{"key":"47538_CR17","doi-asserted-by":"publisher","first-page":"203","DOI":"10.14218\/CSP.2024.00025","volume":"3","author":"X-L Li","year":"2024","unstructured":"Li, X.-L. & Zhou, G. Deep learning in the diagnosis and prognosis of oral potentially malignant disorders. Cancer Screen. Prev. 3, 203\u2013213. https:\/\/doi.org\/10.14218\/CSP.2024.00025 (2024).","journal-title":"Cancer Screen. Prev."},{"key":"47538_CR18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-17602-4","volume":"12","author":"S Sukegawa","year":"2022","unstructured":"Sukegawa, S. et al. Effective deep learning for oral exfoliative cytology classification. Sci. Rep. 12, 13281. https:\/\/doi.org\/10.1038\/s41598-022-17602-4 (2022).","journal-title":"Sci. Rep."},{"key":"47538_CR19","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-67879-w","volume":"14","author":"S Sukegawa","year":"2024","unstructured":"Sukegawa, S. et al. Training high-performance deep learning classifier for diagnosis in oral cytology using diverse annotations. Sci. Rep. 14, 17591. https:\/\/doi.org\/10.1038\/s41598-024-67879-w (2024).","journal-title":"Sci. Rep."},{"key":"47538_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.107205","volume":"227","author":"SP Sunny","year":"2022","unstructured":"Sunny, S. P. et al. Oral epithelial cell segmentation from fluorescent multichannel cytology images using deep learning. Comput. Methods Programs Biomed. 227, 107205. https:\/\/doi.org\/10.1016\/j.cmpb.2022.107205 (2022).","journal-title":"Comput. Methods Programs Biomed."},{"key":"47538_CR21","doi-asserted-by":"publisher","DOI":"10.1186\/s13000-022-01245-0","volume":"17","author":"E Mitate","year":"2022","unstructured":"Mitate, E. et al. Application of the sliding window method and Mask-RCNN method to nuclear recognition in oral cytology. Diagn. Pathol. 17, 62. https:\/\/doi.org\/10.1186\/s13000-022-01245-0 (2022).","journal-title":"Diagn. Pathol."},{"key":"47538_CR22","doi-asserted-by":"publisher","first-page":"399","DOI":"10.18494\/SAM4293","volume":"35","author":"Y Shimomoto","year":"2023","unstructured":"Shimomoto, Y. et al. Cell nucleus detection in oral cytology using artificial intelligence. Sensors Mater. 35, 399\u2013409. https:\/\/doi.org\/10.18494\/SAM4293 (2023).","journal-title":"Sensors Mater."},{"key":"47538_CR23","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/0030-4220(72)90209-5","volume":"33","author":"TC Folsom","year":"1972","unstructured":"Folsom, T. C., White, C. P., Bromer, L., Canby, H. F. & Garrington, G. E. Oral exfoliative study: Review of the literature and report of a three-year study. Oral Surg. Oral Med. Oral Pathol. 33, 61\u201374. https:\/\/doi.org\/10.1016\/0030-4220(72)90209-5 (1972).","journal-title":"Oral Surg. Oral Med. Oral Pathol."},{"issue":"11","key":"47538_CR24","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.3390\/cancers11111813","volume":"11","author":"L Deuerling","year":"2019","unstructured":"Deuerling, L., Gaida, K., Neumann, H. & Remmerbach, T. W. Evaluation of the accuracy of liquid-based oral brush cytology in screening for oral squamous cell carcinoma. Cancers https:\/\/doi.org\/10.3390\/cancers11111813 1813  (2019).","journal-title":"Cancers"},{"key":"47538_CR25","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2010","unstructured":"Pan, S. J. & Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345\u20131359. https:\/\/doi.org\/10.1109\/TKDE.2009.191 (2010).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"47538_CR26","unstructured":"Soekhoe, D., van der Putten, P. & Plaat, A. in Advances in Intelligent Data Analysis XV. (eds Henrik Bostr\u00f6m, Arno Knobbe, Carlos Soares, & Panagiotis Papapetrou) 50\u201360 (Springer International Publishing)."},{"key":"47538_CR27","unstructured":"Mazo, V. Tips for a successful proof of concept with deep learning, (2019). https:\/\/victoriamazo.medium.com\/tips-for-a-successful-proof-of-concept-with-deep-learning-bbf11dc7986f"},{"key":"47538_CR28","unstructured":"El-Naggar, A. K., Chan, J. K., Grandis, J. R., Takata, T. & Slootweg, P. J. WHO classification of tumours of the head and neck 4th edn (IARC, 2017)."},{"key":"47538_CR29","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1111\/j.1600-0714.2007.00584.x","volume":"37","author":"S Warnakulasuriya","year":"2008","unstructured":"Warnakulasuriya, S., Reibel, J., Bouquot, J. & Dabelsteen, E. Oral epithelial dysplasia classification systems: Predictive value, utility, weaknesses and scope for improvement. J. Oral Pathol. Med. 37, 127\u2013133. https:\/\/doi.org\/10.1111\/j.1600-0714.2007.00584.x (2008).","journal-title":"J. Oral Pathol. Med."},{"key":"47538_CR30","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1038\/nmeth.2089","volume":"9","author":"CA Schneider","year":"2012","unstructured":"Schneider, C. A., Rasband, W. S. & Eliceiri, K. W. NIH image to ImageJ: 25 years of image analysis. Nat. Methods 9, 671\u2013675. https:\/\/doi.org\/10.1038\/nmeth.2089 (2012).","journal-title":"Nat. Methods"},{"key":"47538_CR31","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","volume":"15","author":"TK Koo","year":"2016","unstructured":"Koo, T. K. & Li, M. Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropr. Med. 15, 155\u2013163. https:\/\/doi.org\/10.1016\/j.jcm.2016.02.012 (2016).","journal-title":"J. Chiropr. Med."},{"key":"47538_CR32","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.6918","volume":"7","author":"GJ Matheson","year":"2019","unstructured":"Matheson, G. J. We need to talk about reliability: Making better use of test-retest studies for study design and interpretation. PeerJ 7, e6918. https:\/\/doi.org\/10.7717\/peerj.6918 (2019).","journal-title":"PeerJ"},{"key":"47538_CR33","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1519\/15184.1","volume":"19","author":"JP Weir","year":"2005","unstructured":"Weir, J. P. Quantifying test-retest reliability using the intraclass correlation coefficient and the SEM. J. Strength Cond. Res. 19, 231\u2013240. https:\/\/doi.org\/10.1519\/15184.1 (2005).","journal-title":"J. Strength Cond. Res."},{"key":"47538_CR34","doi-asserted-by":"publisher","DOI":"10.1186\/s13550-018-0366-8","volume":"8","author":"R Baumgartner","year":"2018","unstructured":"Baumgartner, R., Joshi, A., Feng, D., Zanderigo, F. & Ogden, R. T. Statistical evaluation of test-retest studies in PET brain imaging. EJNMMI Res. 8, 13. https:\/\/doi.org\/10.1186\/s13550-018-0366-8 (2018).","journal-title":"EJNMMI Res."},{"key":"47538_CR35","doi-asserted-by":"publisher","DOI":"10.1186\/gb-2006-7-10-r100","volume":"7","author":"AE Carpenter","year":"2006","unstructured":"Carpenter, A. E. et al. CellProfiler: Image analysis software for identifying and quantifying cell phenotypes. Genome Biol. 7, R100. https:\/\/doi.org\/10.1186\/gb-2006-7-10-r100 (2006).","journal-title":"Genome Biol."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47538-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47538-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47538-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T12:01:52Z","timestamp":1783944112000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47538-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,13]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["47538"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-47538-y","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,13]]},"assertion":[{"value":"8 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"M.P. McRae has served as a paid consultant for OraLiva, Inc. and has equity interest. He has issued and pending patents related to this work. S.W. Redding has equity interest in OraLiva, Inc. and was a member of the Scientific Advisory Board. J.T. McDevitt has received grants from the National Institutes of Health for work performed as part of the current study. In addition, he has an ownership position and an equity interest in OraLiva, Inc. and has issued and pending patents. K.S. Rajsri has patents pending. All other authors declare no potential conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21741"}}