Intelligenza artificiale per la diagnosi precoce del cancro orale e dei disturbi potenzialmente maligni del cavo orale una scoping review
Contenuto principale dell'articolo
Abstract
Introduzione:
Il carcinoma squamoso orale (OSCC) rappresenta oltre il 90% delle neoplasie orali e presenta un tasso di sopravvivenza a cinque anni di circa il 50-65% quando diagnosticato in stadio avanzato. La maggior parte dei casi insorge in presenza di disturbi orali potenzialmente maligni (OPMD), tuttavia i tassi di diagnosi precoce restano inadeguati a livello globale.
Obiettivi:
Questa revisione sistematica di tipo scoping intende mappare le applicazioni dell’intelligenza artificiale (IA) nella diagnosi precoce dell’OSCC e degli OPMD, caratterizzare le modalità di imaging e le architetture algoritmiche utilizzate, sintetizzare le prestazioni diagnostiche riportate e identificare le lacune metodologiche persistenti.
Metodi:
In accordo con il framework di Arksey e O’Malley e l’estensione PRISMA-ScR, è stata condotta una ricerca strutturata su PubMed/MEDLINE, Scopus, Web of Science e la Cochrane Library. Sono stati inclusi studi pubblicati tra gennaio 2015 e maggio 2026 che applicano tecniche di machine learning (ML) o deep learning (DL) al rilevamento o alla classificazione di OSCC o OPMD.
Risultati:
Sessantotto studi hanno soddisfatto i criteri di inclusione, comprendendo analisi di fotografie cliniche, immagini istopatologiche, strisci citologici, tomografia a coerenza ottica e piattaforme multimodali. Le reti neurali convoluzionali profonde (CNN) con transfer learning hanno dominato la letteratura. Le prestazioni aggregate hanno mostrato una sensibilità mediana dell’87-95% e una specificità dell’81-96%.
Discussioni:
Il settore è caratterizzato da un persistente divario tra le prestazioni algoritmiche retrospettive e l’utilità clinica prospettica. I principali limiti includono dataset di piccole dimensioni, scarsa validazione esterna, limitata spiegabilità dei modelli e assenza di evidenze di livello regolatorio.
Conclusioni:
Gli strumenti di IA mostrano una promettente accuratezza diagnostica per OSCC e OPMD come ausili di screening point-of-care in contesti con risorse limitate. Tuttavia, l’impiego clinico su larga scala richiede validazione multicentrica prospettica, spiegabilità di livello regolatorio, dataset diversificati e curati e integrazione nei percorsi clinici stabiliti.
Downloads
Dettagli dell'articolo

Questo lavoro è fornito con la licenza Creative Commons Attribuzione - Non commerciale 4.0 Internazionale.
Riferimenti bibliografici
Globocan Collaborators. Global, regional, and national burden of lip and oral cavity cancer in 204 countries and territories, 2022: estimates from the Global Burden of Disease Study 2022. JAMA Oncol. 2023;9(10):1401-1416.
Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, et al. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024;74(3):229-263.
Vigneswaran N, Williams MD. Epidemiologic trends in head and neck cancer and aids in diagnosis. Oral Maxillofac Surg Clin North Am. 2014;26(2):123-141.
Milano AF. Oral cavity cancer incidence and survival trends: a population-based study. J Insur Med. 2024;51(2):77-91.
Karimi A, Jafari F, Ghasemi S, Hosseini SA. Survival outcomes and contributing factors in oral squamous cell carcinoma patients in Khuzestan province, southwest Iran. Front Oncol. 2024;14:1472190.
Warnakulasuriya S. Oral potentially malignant disorders: a comprehensive review on clinical aspects and management. Oral Oncol. 2020;102:104550.
Haj-Hosseini N, Lindblad J, Hasseus B, Kumar VV, Subramaniam N, Hirsch JM. Early detection of oral potentially malignant disorders: a review on prospective screening methods with regard to global challenges. J Maxillofac Oral Surg. 2024;23(1):23-32.
Kerr AR, Lodi G. Management of oral potentially malignant disorders. Oral Dis. 2021;27(8):2008-2025.
Sahoo RK, Sahoo KC, Dash GC, Kumar G, Baliarsingh SK, Panda B, et al. Diagnostic performance of artificial intelligence in detecting oral potentially malignant disorders and oral cancer using medical diagnostic imaging: a systematic review and meta-analysis. Front Oral Health. 2024;5:1494867.
Lau J, Abdulkarim A, Shen YY, Cantu H, Zhu D, Glogauer M. Adjunctive aids for the detection of oral squamous cell carcinoma and oral potentially malignant disorders: a systematic review of systematic reviews. Jpn Dent Sci Rev. 2024;60:53-72.
Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Comput Struct Biotechnol J. 2015;13:8-17.
Adeoye J, Zheng LW, Thomson P, Choi SW, Su YX. Applications of artificial intelligence in the field of oral and maxillofacial pathology: a systematic review and meta-analysis. BMC Oral Health. 2024;24(1):122.
Vinay V, Jodalli P, Chavan MS, Buddhikot CS, Luke AM, Ingafou MSH, et al. Artificial intelligence in oral cancer: a comprehensive scoping review of diagnostic and prognostic applications. Diagnostics. 2025;15(3):280.
Yashaswini HC, Shreyas CM, Sathvik GR, Shailesh BS, Siddappa LH. Deep learning-based oral cancer screening via smartphone imagery and real-time web interface. medRxiv. 2025.
Arksey H, O’Malley L. Scoping studies: towards a methodological framework. Int J Soc Res Methodol. 2005;8(1):19-32.
Levac D, Colquhoun H, O’Brien KK. Scoping studies: advancing the methodology. Implement Sci. 2010;5:69.
Tricco AC, Lillie E, Zarin W, O’Brien KK, Colquhoun H, Levac D, et al. PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation. Ann Intern Med. 2018;169(7):467-473.
Zhu X, Li Y, Zhang J, Liu M, Wang C. A tailored deep learning approach for early detection of oral cancer using a 19-layer CNN on clinical lip and tongue images. Sci Rep. 2025;15:23789.
Klauschen F, Muller KR, Binder A, Bockmayr M, Grundhewer M, Hagele M. Toward explainability in machine learning for cancer diagnosis and prognosis. J Natl Cancer Inst. 2024;116(4):543-556.
Ali GY, Hamdan FB, Alharbi AM, Basheer AA, Alghamdi SS, Alhammadi A, et al. Application and performance of artificial intelligence (AI) in oral cancer diagnosis and prediction using histopathological images: a systematic review. Cancers. 2023;15(13):3423.
Al-Rawi N, Sultan A, Rajai B, Shuaeeb H, Alnajjar M, Alketbi M, et al. The effectiveness of artificial intelligence in detection of oral cancer. Int Dent J. 2022;72(4):436-447.
Sahoo RK, Sahoo KC, Dash GC, Kumar G, Baliarsingh SK, Panda B, et al. Diagnostic performance of artificial intelligence in detecting oral potentially malignant disorders and oral cancer using medical diagnostic imaging: a systematic review and meta-analysis. Front Oral Health. 2024;5:1494867.
Kouketsu A, Sato I, Takahashi S, Asano A, Kusama M, Sakamoto M. Detection of oral cancer and oral potentially malignant disorders using an artificial intelligence-based system with single shot multibox detector. J Oral Maxillofac Surg Med Pathol. 2024;36(2):121-128.
Jerjes W, Upile T, Petrie A, Risco JM, Hamdoon Z, Gillison GS, et al. Clinicopathological parameters, recurrence, locoregional and distant metastasis in 115 T1-T2 oral squamous cell carcinoma patients. Head Neck Oncol. 2010;2:9.
Ramesh E, Ganesan A, Lakshmi KC, Natarajan PM. Artificial intelligence-based diagnosis of oral leukoplakia using deep convolutional neural networks Xception and MobileNet-v2. Front Oral Health. 2025;6:1414524.
Zhang C, Shan Q, Zhao Z, Li J, He Y. The global prevalence of oral leukoplakia: a systematic review and meta-analysis from 1996 to 2022. BMC Oral Health. 2023;23(1):645.
Warnakulasuriya S, Kujan O, Aguirre-Urizar JM, Bagan JV, Gonzalez- Moles MA, Kerr AR, et al. Oral potentially malignant disorders: a consensus report from an international seminar on nomenclature and classification convened by the WHO Collaborating Centre for Oral Cancer. Oral Dis. 2021;27(8):1862-1880.
Adeoye J, Hui L, Thomson P, Choi SW, Su YX. Multimodal artificial intelligence integrating oral images and clinical data for OPMD triage. Oral Oncol. 2024;152:106768.
Cimino MG, Campisi G, Galatolo FA, Neri P, Tozzo P, Parola M, Di Fede O. Explainable screening of oral cancer via deep learning and case-based reasoning. Smart Health. 2025;35:100538.
Collins GS, Dhiman P, Andaur Navarro CL, Ma J, Aldcroft A, Lam J, et al. Protocol for development of a reporting guideline (TRIPOD-AI) for diagnostic and prognostic prediction model studies using artificial intelligence. BMJ Open. 2021;11(7):e048008.