Early diagnosis is the most important determinant of oral and oropharyngeal squamous cell carcinoma (OPSCC) outcomes, yet most of these cancers are detected late, when outcomes are poor. Typically, nonspecialists such as dentists screen for oral cancer risk, and then they refer high-risk patients to specialists for biopsy-based diagnosis. Because the clinical appearance of oral mucosal lesions is not an adequate indicator of their diagnosis, status, or risk level, this initial triage process is inaccurate, with poor sensitivity and specificity. The objective of this study is to provide an overview of emerging optical imaging modalities and novel artificial intelligence–based approaches, as well as to evaluate their individual and combined utility and implications for improving oral cancer detection and outcomes. The principles of image-based approaches to detecting oral cancer are placed within the context of clinical needs and parameters. A brief overview of artificial intelligence approaches and algorithms is presented, and studies that use these 2 approaches singly and together are cited and evaluated. In recent years, a range of novel imaging modalities has been investigated for their applicability to improving oral cancer outcomes, yet none of them have found widespread adoption or significantly affected clinical practice or outcomes. Artificial intelligence approaches are beginning to have considerable impact in improving diagnostic accuracy in some fields of medicine, but to date, only limited studies apply to oral cancer. These studies demonstrate that artificial intelligence approaches combined with imaging can have considerable impact on oral cancer outcomes, with applications ranging from low-cost screening with smartphone-based probes to algorithm-guided detection of oral lesion heterogeneity and margins using optical coherence tomography. Combined imaging and artificial intelligence approaches can improve oral cancer outcomes through improved detection and diagnosis.

The sensitive and specific detection of premalignant and malignant lesions is a crucial and indispensable prerequisite for optimal treatment outcome and prognosis. Surgical biopsy, which is currently the primary diagnostic tool, often causes patient anxiety and discomfort, undesirable side effects, and sampling errors. For example, multiple prostate biopsies miss up to 30% of cancer present at the time of biopsy.^{1, 2, 3} An urgent need exists to develop cost-effective, minimally invasive imaging technologies to identify premalignancy and malignancy with high sensitivity and specificity.⁴ Optical imaging tools such as reflectance confocal microscopy, optical coherence tomography (OCT), and optical coherence microscopy (OCM) are promising diagnostic tools for detecting cancer at an early stage.⁵ Optical imaging is particularly useful for in vivo applications because it uses near-infrared wavelengths $\left(770\text{to}1300\mathrm{nm}\right)$ that avoid predominant absorption in tissue.⁶

Background: In vivo, non‐invasive optical coherence tomography (OCT) permits high‐resolution imaging of tissue surfaces and subsurfaces, with the potential capability for detection and mapping of epithelial pathologies.Purpose: To evaluate the clinical capability of non‐invasive in vivo OCT for diagnosing oral dysplasia and malignancy.Experimental Design: In 50 patients with oral lesions, conventional clinical examination was followed by OCT imaging, then standard biopsy and histopathology. Two blinded, pre‐standardized investigators separately diagnosed each lesion based on (1) OCT and (2) histopathology.Results: Intra‐ and inter‐observer agreement between diagnoses based on histopathology and imaging data was excellent, with κ values between 0.844 and 0.896. Sensitivity and specificity were also very good.Conclusions: These data demonstrate the excellent capability of in vivo OCT for detecting and diagnosing oral premalignancy and malignancy in human subjects. Lasers Surg. Med. 41:353–357, 2009.

Background and Objective: Oral cancer results in 10,000 U.S. deaths annually. Improved highly sensitive diagnostics allowing early detection of oral cancer would benefit patient survival and quality of life. Objective was to investigate in vivo non‐invasive optical coherence tomography (OCT) techniques for imaging and diagnosing neoplasia‐related epithelial, sub‐epithelial changes throughout carcinogenesis.Study Design/Materials and Methods: In the standard hamster cheek pouch model for oral carcinogenesis (n = 36), in vivo OCT was used to image epithelial and sub‐epithelial change. OCT‐ and histopathology‐based diagnoses on a scale of 0 (healthy) to 6 (squamous cell carcinoma, SCC) were performed at all stages throughout carcinogenesis by two blinded investigators.Results: Epithelial, sub‐epithelial structures were clearly discernible using OCT. OCT diagnosis agreed with the histopathological gold standard in 80% of readings.Conclusion: In vivo OCT demonstrates excellent potential as a diagnostic tool in the oral cavity. Lasers Surg. Med. 35:269–275, 2004.

Deep learning has become a powerful tool in solving image classification problems¹ and has been widely used in medical image analysis.² Convolutional neural networks (CNNs) show the potential for automated classification of different cancer lesions, such as lung cancer,³ skin cancer,⁴ and breast cancer.⁵ But the lack of interpretability and explainability makes CNNs less understandable.⁶ To push the envelope of CNN-based medical diagnostic methods, more rigorous neural network models and training methods must be developed to provide both visually interpretable and explainable analysis.^{7 – 9}

Oral cancer is a highly prevalent cancer; 377,713 new cases and 177,757 deaths are reported each year worldwide.¹ India alone accounts for more than 33% (135,929) of new cases and 20% (75,290) of deaths, according to Globocan 2020.¹ The second most common cancer in India is oral cancer,² and its pervasiveness is increasing rapidly. From 2018 to 2020, the number of new cases increased by 12% (from 119,992 to 135,929) according to comparisons from Globocan 2018 and Globocan 2020.^1,3 According to the World Health Organization, the estimated number of new cases and deaths in Asia will increase to 374,000 and 208,000 by 2040.⁴ It is a growing problem and a leading cause of mortality in specific regions such as India.^5,6 Detecting oral cancer at an early stage is believed to be the most effective way of (1) reducing the individual burden, (2) decreasing morbidity and mortality, and (3) improving quality of life.⁷ Most high-risk individuals live in resource-limited settings that lack trained specialists and health services.^8,9 Conventional oral examination and biopsy, the clinical and gold standard for oral lesion detection, are not ideal as screening tools in these regions.¹⁰ Therefore, the chances of survival are reduced due to delayed diagnosis.¹¹