Artificial Intelligence in Oral Cancer: Fundamentals and Applications

Oral cancer is a major global health issue that accounts for over 177,000 deaths annually. In addition to poor survival rate due to late diagnosis, this cancer dramatically changes patient’s post-treatment quality of life. Consequently, new methods for early detection of oral cancer are highly demanded. Artificial intelligence (AI) is a branch of computer science concerned with building smart machines capable of performing tasks that commonly require human intelligence. Machine learning (ML) is a subset of AI that uses computational methods to automatically “learn” the patterns of data and improve itself through experience. AI and ML have shown promising results in the field of oral pathology. These algorithms can successfully detect oral squamous cell carcinoma (OSCC) in histopathological images after sufficient training. In addition, a combination of gene expression profiles, clinical variables and histological parameters have been used to feed ML models that estimate the prognosis of OSCC. Moreover, AI is able to distinguish between healthy, premalignant and cancerous lesions in intraoral images. In this review, we discuss the fundamentals of AI and ML as well as focusing on their applications in early diagnosis and prognosis determination of oral cancer.