Oral malignancy ranks among the most prevalent cancers worldwide. Dentists, as frontline healthcare specialists, play a crucial role in detecting benign and potentially malignant oral conditions, including oral cancers. The high prevalence and often delayed detection of oral carcinoma pose serious global health concerns. Early detection and management are key goals set by the World Health Organization (WHO).
Recent Technological Advances
Recent advancements in optical imaging systems, such as tissue-fluorescence imaging and optical coherence tomography, have shown considerable efficiency in detecting oral cancers. Additionally, extensive research is directed toward nanoparticle-based immunosensors, DNA analysis, and salivary proteomics. These innovations hold promise in transforming the landscape of oral cancer diagnostics.
Like what you’re learning? Download a brochure for our online, postgraduate Oral Pathology and Radiology degree program.
Moving Beyond Traditional Biopsies
Traditionally, biopsies have been the gold standard for definitive cancer diagnosis, involving the pathological examination of tissue samples. However, this process is invasive, challenging for general practitioners (GPs) to perform, and can be discomforting for patients. To improve the safety and effectiveness of oral cancer screening, there is a push toward developing non-invasive or minimally invasive, simple, and repeatable screening procedures.
Tissue-Fluorescence Imaging
Advantages:
- Non-invasive
- Simple
- Convenient
- Real-time results
- Repeatable using optical instruments
How Does Fluorescence Visualization Work?
Fluorescence visualization (FV) uses blue light (400–460 nm) to illuminate key biomolecules like flavin adenine dinucleotide (FAD), nicotinamide adenine dinucleotide (NADH), and collagen cross-links (CCL). Normal mucosa appears as apple-green autofluorescence through a selective filter. This phenomenon is known as fluorescence visualization retention (FVR).
Abnormal tissues, such as high-risk lesions (HRL) and inflammatory diseases, exhibit decreased autofluorescence and appear dark brown, a condition termed fluorescence visualization loss (FVL). FVL occurs due to the absorption of specific wavelengths of blue light, attributed to decreases in FAD and NADH, breakdown of CCL, and angiogenesis. Currently, the evaluation of FV is visual and subjective.
Saliva as a Diagnostic Biomaterial
Saliva presents a promising medium for early cancer detection due to its non-invasive sampling and easy collection methods. Advances in molecular biology have led to the discovery of potential salivary biomarkers for detecting oral cancers. These biomarkers, which are molecular signatures indicative of normal or pathological processes and responses to treatment, can provide valuable information for detection, diagnosis, and prognosis of diseases.
Recent Findings in Salivaomics
‘Salivaomics’ encompasses a broad range of technologies used to analyze different types of molecules in saliva. Numerous protein and mRNA salivary biomarkers have been identified for detecting oral squamous cell carcinoma (OSCC). However, none have yet been validated for current clinical use. Continued research in this area is critical for developing reliable, non-invasive diagnostic tools for oral cancer.
The Advent of AI in Oral Cancer Detection
Recent advancements in AI, particularly in machine learning (ML) and deep learning (DL), have opened new avenues for non-invasive cancer diagnostics. These technologies can analyze vast amounts of data, identify patterns, and make highly accurate predictions, which are invaluable in the early detection of oral cancer.
Machine Learning and Deep Learning: In oral cancer detection, ML models are trained using large datasets of medical images, patient records, and other relevant data. These models can then identify suspicious lesions or abnormalities that may indicate cancer.
Deep Learning: A subset of ML, DL uses neural networks with multiple layers to process complex data. DL models can analyze medical images, such as X-rays, CT scans, and histopathological slides, to detect minute changes that might be indicative of cancerous growths. Studies have shown that DL models can achieve accuracy levels comparable to, and sometimes exceeding, those of experienced pathologists.
Tissue-Fluorescence Imaging and AI: One of the promising AI applications in oral cancer detection is tissue-fluorescence imaging. This technique uses blue light to illuminate tissue and identify abnormalities based on their autofluorescence properties. AI algorithms can enhance the detection process by analyzing the fluorescence patterns to distinguish between normal and potentially malignant tissues.
Salivary Biomarkers and AI: Salivaomics, the study of saliva’s molecular composition, is another area where AI is making significant strides. Saliva contains biomarkers that can indicate the presence of oral cancer. AI models can analyze these biomarkers to provide a non-invasive diagnostic tool. This method is particularly advantageous because saliva samples are easy to collect and cause no discomfort to patients.
Conclusion
The field of oral cancer detection is undergoing a significant transformation with the advent of non-invasive techniques that promise to enhance early diagnosis and treatment. While definitive, traditional biopsies are invasive and challenging for general practitioners to perform, they continue to be the gold standard. Tissue-fluorescence imaging offers a non-invasive, simple, real-time, and repeatable method of screening between possible normal and abnormal tissues, improving the accuracy and ease of oral cancer screening.
Simultaneously, the emerging field of salivaomics offers a promising non-invasive alternative by identifying salivary biomarkers indicative of oral cancer. Continued advancements in this area are essential for developing effective diagnostic and screening tools that can be easily implemented in clinical practice, ultimately improving patient outcomes and addressing global health concerns related to oral malignancies. Despite the promising advancements, there are challenges to widespread AI adoption in oral cancer detection. These include the need for large, diverse datasets to train AI models, integration with existing clinical workflows, and ensuring the interpretability and transparency of AI decisions.
Postgraduate Oral Pathology and Radiology Degree
Learn more about the clinical and didactic skills necessary to evaluate and manage patients with oral diseases by enrolling in Herman Ostrow School of USC’s online, competency-based certificate or master’s program in Oral Pathology and Radiology.
References:
- https://www.who.int/activities/promoting-cancer-early-diagnosis
- Chakraborty D, Natarajan C, Mukherjee A. Advances in oral cancer detection. Adv Clin Chem. 2019;91:181-200. doi: 10.1016/bs.acc.2019.03.006. Epub 2019 May 4. PMID: 31331489.
- Kumar G, Jena S, Jnaneswar A, Jha K, Suresan V, Singh A. Advancements in diagnostic techniques for oral cancer detection. Minerva Dent Oral Sci. 2022 Jun;71(3):192-198. doi: 10.23736/S2724-6329.21.04637-4. Epub 2021 Dec 1. PMID: 34851069.
- Chakraborty D, Natarajan C, Mukherjee A. Advances in oral cancer detection. Adv Clin Chem. 2019;91:181-200. doi: 10.1016/bs.acc.2019.03.006. Epub 2019 May 4. PMID: 31331489.
- Morikawa, T.; Shibahara, T.; Nomura, T.; Katakura, A.; Takano, M. Non-Invasive Early Detection of Oral Cancers Using Fluorescence Visualization with Optical Instruments. Cancers 2020, 12, 2771. https://doi.org/10.3390/cancers12102771
- Khurshid Z, Zafar MS, Khan RS, Najeeb S, Slowey PD, Rehman IU. Role of Salivary Biomarkers in Oral Cancer Detection. Adv Clin Chem. 2018;86:23-70. doi: 10.1016/bs.acc.2018.05.002. Epub 2018 Jul 23. PMID: 30144841.
- Aro K, Kaczor-Urbanowicz K, Carreras-Presas CM. Salivaomics in oral cancer. Curr Opin Otolaryngol Head Neck Surg. 2019 Apr;27(2):91-97. doi: 10.1097/MOO.0000000000000502. PMID: 30507690.
- Esteva, A., Kuprel, B., Novoa, R. A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118.
- Litjens, G., Kooi, T., Bejnordi, B. E., et al. (2017). A survey on deep learning in medical image analysis. Medical Image Analysis, 42, 60-88
- Lane, P. M., Gilhuly, T., Whitehead, P., et al. (2006). Simple device for the direct visualization of oral-cavity tissue fluorescence. Journal of Biomedical Optics, 11(2), 024006.
- Zhang, A., Sun, H., & Wang, X. (2012). Salivaomics: advancing disease diagnosis through saliva proteomics. Journal of Proteome Research, 11(12), 5783-5795.
