{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T08:31:45Z","timestamp":1772181105659,"version":"3.50.1"},"reference-count":36,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Cancers"],"abstract":"<jats:p>Background\/Objectives: Oral squamous cell carcinoma (OSCC) carries a risk of late metastasis not only in advanced stages but also in early stages. In this study, we built and tested radiomics-based machine learning (ML) models for predicting the risk of metastasis from early OSCC on 18F-FDG positron emission tomography (PET). Methods: Patients diagnosed with T1 or T2 squamous cell carcinoma who underwent a preoperative 18F-FDG PET-CT examination at a single institution between 2016 and December 2022 were included in this retrospective study. The presence or absence of late cervical lymph node metastasis was confirmed for all patients. Among the radiomics features extracted from the images, we selected those that were useful for predicting late metastasis and used them to create ML models. We then verified the prediction accuracy of the models. Results: A total of 109 subjects were included, of which 31 had late lymph node metastasis and 78 were without metastasis. The most accurate ML model created using radiomics features selected from the subject cases had an area under the curve of 0.977 and accuracy of 87.5%. Conclusions: We confirmed that ML models using radiomics features extracted from PET images can be useful for predicting late metastasis in patients with early-stage OSCC.<\/jats:p>","DOI":"10.3390\/cancers17213573","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T13:19:29Z","timestamp":1762348769000},"page":"3573","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Evaluation of the Ability to Predict Subsequent Metastasis of Early Oral Squamous Cell Carcinoma Using PET Radiomics Machine Learning Models"],"prefix":"10.3390","volume":"17","author":[{"given":"Yutaka","family":"Nikkuni","sequence":"first","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hideyoshi","family":"Nishiyama","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0034-7771","authenticated-orcid":false,"given":"Masaki","family":"Takamura","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taichi","family":"Kobayashi","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marie","family":"Soga","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5543-957X","authenticated-orcid":false,"given":"Makiko","family":"Ike","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7341-4840","authenticated-orcid":false,"given":"Kouji","family":"Katsura","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8421-0253","authenticated-orcid":false,"given":"Takafumi","family":"Hayashi","sequence":"additional","affiliation":[{"name":"Division of Oral and Maxillofacial Radiology, Graduate School of Medical and Dental Sciences, Niigata University, Niigata 951-8510, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"key":"ref_1","unstructured":"World Health Organization (2025, July 29). International Agency for Research on Cancer. Cancer Factsheets, Available online: https:\/\/gco.iarc.who.int\/today\/en\/fact-sheets-cancers."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Blatt, S., Kr\u00fcger, M., Sagheb, K., Barth, M., K\u00e4mmerer, P.W., Al-Nawas, B., and Sagheb, K. (2022). Tumor Recurrence and Follow-Up Intervals in Oral Squamous Cell Carcinoma. J. Clin. Med., 23.","DOI":"10.3390\/jcm11237061"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"179","DOI":"10.1016\/j.ijom.2023.08.004","article-title":"Management of clinically node-negative early-stage oral cancer: Network meta-analysis of randomized clinical trials","volume":"53","author":"Alkhutari","year":"2024","journal-title":"Int. J. Oral. Maxillofac. Surg."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"W150","DOI":"10.2214\/AJR.14.13830","article-title":"FDG PET\/CT for Management and Assessing Outcomes of Squamous Cell Cancer of the Oral Cavity","volume":"205","author":"Pasha","year":"2015","journal-title":"AJR Am. J. Roentgenol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1016\/j.mri.2012.06.010","article-title":"Radiomics: The process and the challenges","volume":"30","author":"Kumar","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1148\/radiol.2015151169","article-title":"Radiomics: Images Are More than Pictures, They Are Data","volume":"278","author":"Gillies","year":"2016","journal-title":"Radiology"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"znae297","DOI":"10.1093\/bjs\/znae297","article-title":"Machine learning prediction of early recurrence after surgery for gallbladder cancer","volume":"111","author":"Catalano","year":"2024","journal-title":"Br. J. Surg."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102060","DOI":"10.1016\/j.artmed.2021.102060","article-title":"Machine learning in oral squamous cell carcinoma: Current status, clinical concerns and prospects for future-A systematic review","volume":"115","author":"Alabi","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1111\/jop.13089","article-title":"Machine learning and treatment outcome prediction for oral cancer","volume":"49","author":"Chu","year":"2020","journal-title":"J. Oral. Pathol. Med."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"104635","DOI":"10.1016\/j.ijmedinf.2021.104635","article-title":"Comparison of time-to-event machine learning models in predicting oral cavity cancer prognosis","volume":"157","author":"Adeoye","year":"2022","journal-title":"Int. J. Med. Inform."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2619","DOI":"10.1002\/hed.27487","article-title":"Radiomics analysis of intraoral ultrasound images for prediction of late cervical lymph node metastasis in patients with tongue cancer","volume":"45","author":"Konishi","year":"2023","journal-title":"Head Neck"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"6429","DOI":"10.1007\/s00330-021-07731-1","article-title":"Machine learning-based MRI texture analysis to predict occult lymph node metastasis in early-stage oral tongue squamous cell carcinoma","volume":"31","author":"Yuan","year":"2021","journal-title":"Eur. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.oooo.2021.12.122","article-title":"Development of a radiomics and machine learning model for predicting occult cervical lymph node metastasis in patients with tongue cancer","volume":"134","author":"Kubo","year":"2022","journal-title":"Oral. Surg. Oral. Med. Oral. Pathol. Oral. Radiol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1002\/jmri.28019","article-title":"Magnetic Resonance Imaging-Based Radiomics Features Associated with Depth of Invasion Predicted Lymph Node Metastasis and Prognosis in Tongue Cancer","volume":"56","author":"Wang","year":"2022","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1209","DOI":"10.1016\/j.bjoms.2022.05.011","article-title":"Maximum standardised uptake value is prognostic in patients with early-stage squamous cell carcinoma of the tongue","volume":"60","author":"Lin","year":"2022","journal-title":"Br. J. Oral. Maxillofac. Surg."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tellman, R.S., Donders, D.N.V., Arens, A.I.J., Boeve, K., Brouwers, A.H., Eerenstein, S.E.J., van Egmond, S.L., Nulent, T.J.W.K., Klop, W.M.C., and Lacko, M. (2025). [18F]FDG PET\/CT to reduce the need for sentinel lymph node biopsy in early-stage oral cancer: PETN0-study protocol. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0325032"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1007\/s11282-021-00581-z","article-title":"Laterality on FDG-PET\/CT in clinically node-negative early-stage oral squamous cell carcinoma: A retrospective analysis of patients with late neck metastasis","volume":"38","author":"Minamitake","year":"2022","journal-title":"Oral Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s11282-022-00600-7","article-title":"Radiomics analysis of [18F]-fluoro-2-deoxyglucose positron emission tomography for the prediction of cervical lymph node metastasis in tongue squamous cell carcinoma","volume":"39","author":"Kudoh","year":"2023","journal-title":"Oral Radiol."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Pfaehler, E., Schindele, A., Dierks, A., Busse, C., Brumberg, J., K\u00fcbler, A.C., Buck, A.K., Linz, C., Lapa, C., and Brands, R.C. (2025). Value of PET radiomic features for diagnosis and reccurence prediction of newly diagnosed oral squamous cell carcinoma. Sci. Rep., 20.","DOI":"10.1038\/s41598-025-02305-3"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1016\/j.oooo.2024.01.016","article-title":"Magnetic resonance imaging-based radiomics and deep learning models for predicting lymph node metastasis of squamous cell carcinoma of the tongue","volume":"138","author":"Wang","year":"2024","journal-title":"Oral Surg. Oral Med. Oral Pathol. Oral Radiol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"107165","DOI":"10.1016\/j.oraloncology.2024.107165","article-title":"Diagnosis of lymph node metastasis in oral squamous cell carcinoma by an MRI-based deep learning model","volume":"161","author":"Yang","year":"2025","journal-title":"Oral Oncol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1007\/s00424-025-03067-7","article-title":"Current methods in explainable artificial intelligence and future prospects for integrative physiology","volume":"477","author":"Finzel","year":"2025","journal-title":"Pflugers Arch."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"419","DOI":"10.1007\/s00259-014-2933-1","article-title":"Zone-size nonuniformity of 18F-FDG PET regional textural features predicts survival in patients with oropharyngeal cancer","volume":"42","author":"Cheng","year":"2015","journal-title":"Eur. J. Nucl. Med. Mol. Imaging"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3111","DOI":"10.1245\/s10434-009-0621-3","article-title":"Metabolic tumor volumes by [18F]-fluorodeoxyglucose PET\/CT correlate with occult metastasis in oral squamous cell carcinoma of the tongue","volume":"16","author":"Chung","year":"2009","journal-title":"Ann. Surg. Oncol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1093\/jjco\/hyae169","article-title":"The value of a nomogram based on 18F-FDG PET\/CT metabolic parameters and metabolic heterogeneity in predicting distant metastasis in gastric cancer","volume":"55","author":"Zhang","year":"2025","journal-title":"Jpn. J. Clin. Oncol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.ejrad.2018.07.028","article-title":"Metabolic tumor heterogeneity analysis by F-18 FDG PET\/CT predicts mediastinal lymph node metastasis in non-small cell lung cancer patients with clinically suspected N2","volume":"106","author":"Pahk","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.oraloncology.2018.01.030","article-title":"Heterogeneity and irregularity of pretreatment 18F-fluorodeoxyglucose positron emission tomography improved prognostic stratification of p16-negative high-risk squamous cell carcinoma of the oropharynx","volume":"78","author":"Cheng","year":"2018","journal-title":"Oral Oncol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1097\/RLU.0000000000002530","article-title":"Prognostic Value of Tumor Heterogeneity and SUVmax of Pretreatment 18F-FDG PET\/CT for Salivary Gland Carcinoma With High-Risk Histology","volume":"44","author":"Cheng","year":"2019","journal-title":"Clin. Nucl. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"668","DOI":"10.1007\/s11282-023-00686-7","article-title":"Volume-based 18F-fluorodeoxyglucose positron emission tomography\/computed tomography parameters correlate with delayed neck metastasis in clinical early-stage oral squamous cell carcinoma","volume":"39","author":"Yamakawa","year":"2023","journal-title":"Oral Radiol."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1186\/s40644-016-0095-z","article-title":"Utility of SUVmax on 18 F-FDG PET in detecting cervical nodal metastases","volume":"16","author":"Lim","year":"2016","journal-title":"Cancer Imaging"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Alqutub, A., Alqutub, A., Bakhshwin, A., Mofti, Z., Alqutub, S., Alkhamesi, A.A., Nujoom, M.A., Rammal, A., Merdad, M., and Marzouki, H.Z. (2024). Histopathological predictors of lymph node metastasis in oral cavity squamous cell carcinoma: A systematic review and meta-analysis. Front. Oncol., 14.","DOI":"10.3389\/fonc.2024.1401211"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Bjerkli, I.H., Laurvik, H., Nginamau, E.S., S\u00f8land, T.M., Costea, D., Uhlin-Hansen, H.H.L., Hadler-Olsen, E., and Steigen, S.E. (2020). Tumor budding score predicts lymph node status in oral tongue squamous cell carcinoma and should be included in the pathology report. PLoS ONE, 15.","DOI":"10.1371\/journal.pone.0239783"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"E112","DOI":"10.1177\/0145561319848669","article-title":"Tumor Budding and Worse Pattern of Invasion Can Predict Nodal Metastasis in Oral Cancers and Associated With Poor Survival in Early-Stage Tumors","volume":"98","author":"Chatterjee","year":"2019","journal-title":"Ear Nose Throat J."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Noda, Y., Ishida, M., Ueno, Y., Fujisawa, T., Iwai, H., and Tsuta, K. (2022). Novel pathological predictive factors for extranodal extension in oral squamous cell carcinoma: A retrospective cohort study based on tumor budding, desmoplastic reaction, tumor-infiltrating lymphocytes, and depth of invasion. BMC Cancer, 22.","DOI":"10.1186\/s12885-022-09393-8"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Mittlmeier, L.M., Brendel, M., Beyer, L., Albert, N.L., Todica, A., Zacherl, M.J., Wenter, V., Herlemann, A., Kretschmer, A., and Ledderose, S.T. (2021). Feasibility of Different Tumor Delineation Approaches for 18F-PSMA-1007 PET\/CT Imaging in Prostate Cancer Patients. Front. Oncol., 11.","DOI":"10.3389\/fonc.2021.663631"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"6232","DOI":"10.1097\/JS9.0000000000002715","article-title":"Intratumoral and peritumoral habitat radiomics of MRI predicts pathologic complete response to neoadjuvant chemoimmunotherapy in oral squamous cell carcinoma","volume":"111","author":"Yuan","year":"2025","journal-title":"Int. J. Surg."}],"container-title":["Cancers"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/21\/3573\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T13:34:11Z","timestamp":1762349651000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-6694\/17\/21\/3573"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":36,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["cancers17213573"],"URL":"https:\/\/doi.org\/10.3390\/cancers17213573","relation":{},"ISSN":["2072-6694"],"issn-type":[{"value":"2072-6694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]}}}