Detection Of Oral Cancer Research Articles

Heuristic strategy using hybrid deep learning with transfer learning for oral cancer detection

Oral cancer becomes the most disastrous ailment that affects the oral cavity parts of the mouth. Oral cancer diagnosis is the main challenge in the medical field. It becomes expensive and less capable of classifying oral cancer. In some cases, it may cause unnecessary morbidity and mortality. Recently, the detection of malignant and premalignant oral lesions has been a critical process owing to their low image resolution and lower acquisition time. Thus, a novel hybrid deep learning with meta-heuristic-based optimization is proposed. The pre-processing occurs by median filtering and Contrast Limited Adaptive Histogram Equalization (CLAHE). The CLAHE method is utilized to reduce unwanted noise. Finally, the classification is done by a proposed hybrid-based deep learning model termed as Recurrent Deep Belief Network (RDBN), in which the Deep Belief Network (DBN) is incorporated with the Recurrent Neural Network (RNN). Here, the RDBN helps to increase the performance classification. Furthermore, the hyperparameters of the RDBN model, such as learning rate, epochs and hidden neurons, are tuned using the proposed Hybrid Beetle-Barnacle Swarm Optimization (HBBSO) algorithm, where the Barnacles Mating Optimizer (BMO) is superimposed with Beetle Swarm Optimization (BSO) algorithms. In the given proposed model, the selected features are extracted by the optimization algorithms. Here, the parameters are fine-tuned to get the better optimal solution. From the experimental outcome, the developed model has acquired 5.2% better than PSO-RDBN, 5.6% improved than GWO-RDBN, 3.2% enhanced than BSO-RDBN and 3.5% superior to BMO-RDBN regarding accuracy. Thus, the proposed model achieves higher results for detecting oral cancer with enhanced classification performance than the existing approaches.

Needs assessment for interprofessional education module on prevention and early detection of oral cancer among dental interns: a cross- sectional survey

BackgroundThe challenges associated with ensuring widespread system changes to enable early diagnosis and prevention of oral cancer could benefit from interprofessional practice. A needs assessment study was conducted to inform the Interprofessional Education and Collaborative Practice (IPECP) course related to oral cancer. The primary objectives of this study were 1) to establish a tool assess the knowledge attitude and practice (KAP) related to prevention and early detection of oral cancer of health professional students, and 2) to assess the same KAP of pre-licensure dental students. Additional objectives were to consider the possibility that dental students would demonstrate good scores related to early detection and prevention of oral cancer thus indicating their readiness for interprofessional learning and collaborative practice.MethodsTwo questionnaires were utilized for this study which included 1) Readiness for interprofessional learning was assessed using the pre- validated tool of Readiness for Interprofessional Learning Scale (RIPLS) 2) A questionnaire to assess the KAP related to early diagnosis and prevention of oral cancer which was developed, validated, and evaluated. Statistical analysis includes, descriptive statistics, Mann–Whitney U test, Ordered logistic regression and Probit analysis. p value was set at < 0.05.ResultsA total of 130 dental students (74.6% female) were included in the study. Mean scores related to KAP were 15.96 ± 1.394, 4.70 + 1.146, 7.02 ± 1.019 respectively. The mean score of RIPLS was 73.15 ± 15.961. The probability of overall samples to have good RIPLS scores was around 0.68 to 0.76 (Male 0.68—0.82 & Female 0.68 -0.74). The percentage of students having good knowledge score was 93.8%, good attitude score was around 54.6% and good practice score was around 90%.ConclusionKnowledge and practice related to prevention and early detection of oral cancer were scored highly. Attitude scores were lower in a relatively higher proportion of participants and needed to be addressed in the curriculum. RIPLS score indicates a positive attitude towards interprofessional learning.

Diagnostic performance of artificial intelligence in detecting oral potentially malignant disorders and oral cancer using medical diagnostic imaging: a systematic review and meta-analysis

ObjectiveOral cancer is a widespread global health problem characterised by high mortality rates, wherein early detection is critical for better survival outcomes and quality of life. While visual examination is the primary method for detecting oral cancer, it may not be practical in remote areas. AI algorithms have shown some promise in detecting cancer from medical images, but their effectiveness in oral cancer detection remains Naïve. This systematic review aims to provide an extensive assessment of the existing evidence about the diagnostic accuracy of AI-driven approaches for detecting oral potentially malignant disorders (OPMDs) and oral cancer using medical diagnostic imaging.MethodsAdhering to PRISMA guidelines, the review scrutinised literature from PubMed, Scopus, and IEEE databases, with a specific focus on evaluating the performance of AI architectures across diverse imaging modalities for the detection of these conditions.ResultsThe performance of AI models, measured by sensitivity and specificity, was assessed using a hierarchical summary receiver operating characteristic (SROC) curve, with heterogeneity quantified through I2 statistic. To account for inter-study variability, a random effects model was utilized. We screened 296 articles, included 55 studies for qualitative synthesis, and selected 18 studies for meta-analysis. Studies evaluating the diagnostic efficacy of AI-based methods reveal a high sensitivity of 0.87 and specificity of 0.81. The diagnostic odds ratio (DOR) of 131.63 indicates a high likelihood of accurate diagnosis of oral cancer and OPMDs. The SROC curve (AUC) of 0.9758 indicates the exceptional diagnostic performance of such models. The research showed that deep learning (DL) architectures, especially CNNs (convolutional neural networks), were the best at finding OPMDs and oral cancer. Histopathological images exhibited the greatest sensitivity and specificity in these detections.ConclusionThese findings suggest that AI algorithms have the potential to function as reliable tools for the early diagnosis of OPMDs and oral cancer, offering significant advantages, particularly in resource-constrained settings.Systematic Review Registrationhttps://www.crd.york.ac.uk/, PROSPERO (CRD42023476706).

Assessing Artificial Intelligence in Oral Cancer Diagnosis: A Systematic Review

Background: With the use of machine learning algorithms, artificial intelligence (AI) has become a viable diagnostic and treatment tool for oral cancer. AI can assess a variety of information, including histopathology slides and intraoral pictures. Aim: The purpose of this systematic review is to evaluate the efficacy and accuracy of AI technology in the detection and diagnosis of oral cancer between 2020 and 2024. Methodology: With an emphasis on AI applications in oral cancer diagnostics, a thorough search approach was used to find pertinent publications published between 2020 and 2024. Using particular keywords associated with AI, oral cancer, and diagnostic imaging, databases such as PubMed, Scopus, and Web of Science were searched. Among the selection criteria were actual English-language research papers that assessed the effectiveness of AI models in diagnosing oral cancer. Three impartial reviewers extracted data, evaluated quality, and compiled the findings using a narrative synthesis technique. Results: Twelve papers that demonstrated a range of AI applications in the diagnosis of oral cancer satisfied the inclusion criteria. This study showed encouraging results in lesion identification and prognostic prediction using machine learning and deep learning algorithms to evaluate oral pictures and histopathology slides. The results demonstrated how AI-driven technologies might enhance diagnostic precision and enable early intervention in cases of oral cancer. Conclusion: Unprecedented prospects to transform oral cancer diagnosis and detection are provided by artificial intelligence. More resilient AI systems in oral oncology can be achieved by joint research and innovation efforts, even in the face of constraints like data set variability and regulatory concerns.

A bioinspired porous and electroactive reduced graphene oxide hydrogel based biosensing platform for efficient detection of tumor necrosis factor-α.

Oral cancer is one of the leading cancer types, which is frequently diagnosed at an advanced stage, giving patients a poor prognosis and fewer therapeutic choices. To address this gap, exploiting biosensors utilizing anti-biofouling hydrogels for early-stage oral cancer detection in non-invasive body fluids is gaining utter importance. Herein, we have demonstrated the fabrication of an innovative electrochemical immunosensor for the rapid, label-free, non-invasive, and affordable detection of tumor necrosis factor-α (TNF-α), a biomarker associated with oral cancer progression in artificial saliva samples. The gold screen-printed electrodes (gSPEs) are modified with a green synthesized porous and electroactive reduced graphene oxide (rGO) hydrogel utilizing L-cystine (L-cys) as both in situ reducing and surface functionalization agent, followed by covalent immobilization of anti-TNF-α and blocking of residual sites with bovine serum albumin (BSA) to fabricate the BSA/anti-TNF-α/L-cys_rGO hydrogel/gSPE immunosensing platform. The fabricated platform demonstrates excellent performance, with a low limit of detection of 1.20 pg mL-1, a broad linear range from 1 to 200 pg mL-1, and a high sensitivity of 2.10 μA pg-1 mL cm-2 carried out with differential pulse voltammetry (DPV) technique. Moreover, it exhibits specificity towards TNF-α, even in the presence of potential interferents and other cancer biomarkers. Besides, the biosensor showed good reproducibility and repeatability with a relative standard deviation (%RSD) of 5.11% and 1.85%, respectively. Thus, integrating the L-cys_rGO hydrogel in the immunosensor design offers enhanced performance, paving the way for its application in early-stage oral cancer diagnosis.

Exploring the role of artificial intelligence in oral cancer diagnosis: Review

Oral cancer (OC) is the most common forms of head and neck cancer. Even with advancing research it still continues to have lowest survival rate globally. Histopathologiy still remains the gold standard for oral cancer diagnosis. But, it has few drawbacks being prone to errors (variability) and is time consuming leading to delay in diagnosis. In order to overcome these pitfalls there is a need for alternative diagnostic approaches which are faster and accurate at the same time. Considerable efforts have been focused on exploring the role of artificial intelligence (AI) in medical diagnostics in recent times. The role of AI in medical imaging and diagnosis seems promising. Key benefit of AI is better accuracy, rapid diagnosis and reduced manual visualization of slides. This review article focuses on the role of AI in oral cancer detection with emphasis on machine learning and deep learning methods, decision support systems. Future challenges, benefits and limitations of AI have also been discussed.

Salivary Genomic Biomarkers in Oral Cancer Detection

Salivary Genomic Biomarkers in Oral Cancer Detection

Assessing racial and ethnic disparities in time to surgery for patients with oral cavity cancers.

109 Background: Despite advances, challenges remain in the early detection and management of oral cancers. Studies have indicated that worse outcomes can be linked to disparities in sex, race, and ethnicity. Research indicates that despite a greater incidence of oral cancer among White patients, the five-year survival rate for Black patients is 52%, compared to 70% for their counterparts (1). While existing research focuses on racial and ethnic disparities in the time to diagnosis and prognosis, there is limited literature that discusses disparities in time to treat. As such, our study aims to evaluate potential racial, ethnic, and/or gender disparities in the time between diagnosis and surgery. Methods: We conducted a retrospective cohort study evaluating 185 patients with oral cancer at the University of Miami. Patient information was obtained from electronic medical records. We performed analysis of variance (ANOVA) with post hoc tests. Levene's test was used to assess the homogeneity of variances assumption. All statistical analyses were performed using SPSS version 26.0 (IBM Corp., Armonk, NY, USA), and p-values less than 0.05 were considered statistically significant. Results: The mean age at diagnosis was 68.50 years (SD =13.079 years), with the majority of patients (42%) diagnosed as Stage 1. Our cohort was 46% female and 54% male. 62% identified as White and Non-Hispanic/Latinx, 29% as White and Hispanic/Latinx, 6% as Black, and 3% as other race/ethnicities. We also assessed time to treat as a function of gender, race and ethnicity. We found there was no significant difference between men and women (x̄= 148 vs 136 days) in time to surgery. We also found no difference between Hispanic/Latinx patients and non Hispanic/Latinx patients (x̄= 163 vs 137 days). Although not statistically significant, there was a notable trend in the data that showed a longer time to surgery. Black patients had a much greater time to surgical intervention compared to White patients (x̄= 308 days vs 134 days) (Table). At the time of data cutoff, nearly 81% of patients were alive. Conclusions: In conclusion, despite lack of statistical significant, our study found higher trends to time to surgery between Hispanic/Latinx and non-Hispanic/Latinx, and even more so a much greater difference in time to surgery between Black and White patients. Further research is needed to elucidate these potential systematic, socio-economic or cultural barriers to ensure equitable access. 1. Surveillance, Epidemiology, and End Results (SEER) Program, National Cancer Institute. Days between diagnosis and surgery. Ethnicity Mean Standard Deviation N Black or African American 308.44 737.375 9 Other 20.33 .577 3 White 134.37 467.579 147 Total 142.08 481.112 159

Enhancing Oral Cancer Detection: A Systematic Review of the Diagnostic Accuracy and Future Integration of Optical Coherence Tomography with Artificial Intelligence.

Introduction: Optical Coherence Tomography (OCT) has emerged as an important imaging modality in non-invasive diagnosis for oral cancer and can provide real-time visualisation of tissue morphology with the required high resolution. This systematic review aims to assess the diagnostic accuracy of OCT in the detection of oral cancers, and to explore the potential integration of OCT with artificial intelligence (AI) and other imaging techniques to enhance diagnostic precision and clinical outcomes in oral healthcare. Methods: A systematic literature search was conducted across PubMed, Embase, Scopus, Google Scholar, Cochrane Central Register, and Web of Science from inception until August 2024. Studies were included if they employed OCT for oral cancer detection, reported diagnostic outcomes, such as sensitivity and specificity, and were conducted on human subjects. Data extraction and quality assessment were performed independently by two reviewers. The synthesis highlights advancements in OCT technology, including AI-enhanced interpretations. Results: A total of 9 studies met the inclusion criteria, encompassing a total of 860 events (cancer detections). The studies spanned from 2008 to 2022 and utilised various OCT techniques, including clinician-based, algorithm-based, and AI-driven interpretations. The findings indicate OCT's high diagnostic accuracy, with sensitivity ranging from 75% to 100% and specificity from 71% to 100%. AI-augmented OCT interpretations demonstrated the highest accuracy, emphasising OCT's potential in early cancer detection and precision in guiding surgical interventions. Conclusions: OCT could play a very prominent role as a new diagnostic tool for oral cancer, with very high sensitivity and specificity. Future research pointed towards integrating OCT with other imaging methods and AI systems in providing better accuracy of diagnoses, plus more clinical usability. Further development and validation with large-scale multicentre trials is imperative for the realisation of this potential in changing the way we practice oral healthcare.

Emerging Diagnostic Modalities in Oral Cancer Detection and Management

Oral cancer remains a significant global health concern, yet it is often detected at an advanced stage. The limitations of traditional diagnostic techniques have prompted increased research efforts towards the development of more efficient and early detection methods. Recent advancements in oral cancer diagnosis include the use of salivary biomarkers, optical imaging, liquid biopsy, advanced imaging, and AI algorithms. These non-invasive and painless sampling methods have shown high sensitivity and specificity, particularly in the case of salivary biomarkers. Clinical trials and cooperation are necessary to demonstrate the effectiveness of these technologies and gain approval from relevant authorities and acceptance among clinicians. This review highlights the potential of these new modalities in transforming the approach to oral cancer diagnosis, leading to early detection, accurate diagnosis, and quality treatment for patients, ultimately reducing the global burden of this disease.

Knowledge, Attitudes, Practices, and Perceptions of Brazilian Dentists About Oral Cancer.

Dentists play a pivotal role in the early detection of oral cancer. Consequently, they are expected to possess the knowledge and the capability to recognize the features of this disease. The objective of the study is to evaluate dentists from different regions of Brazil regarding their level of knowledge and self-confidence regarding oral cancer. An online self-administered questionnaire was completed by dentists across Brazil registered on the TelessaúdeRS-UFRGS platform. This questionnaire encompassed inquiries related to knowledge, attitudes, and practices regarding oral cancer. A total of 1291 dentists from all regions of the country responded to the questionnaire. The majority of participants were females (75.5%), with an average age of 36.3years, predominantly from the public sector (46.8%). A reasonable level of knowledge regarding oral cancer was observed among dentists, although 48.6% of these professionals felt uncertain about diagnosis procedures. Dentists less than 8years since graduation perceived themselves as more prepared to perform oral cancer diagnoses than those with more experience. Around 55% of participants had never performed a biopsy. Based on the obtained results, it is concluded that continuous education activities focused on oral cancer and implementing practical training during undergraduate studies are imperative. These strategies can improve professionals' self-confidence and diagnostic accuracy, thereby facilitating early disease diagnosis and, consequently, a more favorable prognosis.

French Dentists’ knowledge, attitudes and practices toward oral cancer detection: A national survey

BackgroundFrance is ranked 6th in Europe in terms of oral cancer incidence. Dental surgeons are on the front line in examining the oral mucosa, but little is known about the knowledge, attitudes and practices of French dental surgeons with respect to lesions suspected of malignancy. MethodsAn online survey including 18 self-administered questions was widely shared on social media using major networks of French dentists. Items included socio-demographic characteristics of the respondents, their self-assessed knowledge, screening practices and training on oral cancer detection and care. ResultsA total of 676 dental surgeons participated in this survey. The vast majority, 92.8 %, were general dental surgeons, 83.9 % had a private practice and 49.1 % had less than 5 years of dental experience. Almost 55 % declared that they did not conduct systematic examinations of the oral mucosa and 45 % reported that they did conduct such examinations. In-hospital practice, lower patient age, dental surgeon experience, and specialty were all positively associated with systematic examination of the oral mucosa. Conversely, absence of a patient complaint, absence of an obvious lesion, lack of time, and lack of training/skills were all negatively associated. DiscussionThis is the first survey to analyze the practices of French dental surgeons in oral cancer screening. Only half of the respondents, the best trained, performed systematic oral mucosa examinations which objectively help to early detect mucosal cancer lesions. To improve oral cancer early detection, we recommend mandatory screening training programs for all dental students and dental surgeons.

Fabrication of nanomolecular platform based immunosensor for non-invasive electrochemical detection of oral cancer: An in vitro study

Silver nanoparticles (AgNPs)-Chitosan (Chi) functionalized cysteine (cys)-SAM (self-assembled monolayer) based electrochemical, label free, ultrasensitive, non-invasive immunosensing nanomolecular platform has been fabricated for the detection of novel OC biomarker S-100. This has been achieved through bio-functionalization of AgNPs-Chi/cys/mini gold slides by covalent immobilization of anti-S100 antibodies. Cyclic voltammetric (CV) studies establish successful fabrication of anti-S100/AgNPs-Chi/Au nanomolecular platform. Differential pulse voltammetric (DPV) measurements reveal that anti-S100/Chi-AgNPs/Au is able to sense 50 fg mL-1 – 500 ng mL-1 of S100 in buffer and in spiked saliva samples within 120 s interaction time having improved favorable shelf life and specificity. The fabricated platform is very selective and able to detect S100 in OC patient/s saliva samples warrants realization of simple non-invasive electrochemical immunosensor for in situ or on-site applications (especially for remote areas) for early diagnosis of OC while offering bio-compatibility at low cost.

Advances in Oral Exfoliative Cytology: From Cancer Diagnosis to Systemic Disease Detection.

Oral exfoliative cytology has emerged as a valuable tool in the early detection of oral cancer and other systemic diseases. This review comprehensively examines the current applications and recent advancements in oral exfoliative cytology techniques. We analyzed published literature from the past decade, focusing on methodological improvements, diagnostic accuracy, and emerging applications. Key findings include: (1) Enhanced cell collection and preparation methods have significantly improved sample quality and diagnostic reliability. (2) Integration of molecular markers and DNA analysis with traditional cytomorphological assessment has increased diagnostic sensitivity and specificity for oral cancer detection. (3) Novel applications in systemic disease detection, including diabetes and iron overload disorders, demonstrate the expanding utility of this technique. (4) Computer-assisted analysis and deep learning algorithms show promise in improving diagnostic accuracy and efficiency. Despite these advancements, challenges remain in standardization and widespread clinical implementation. This review provides a critical evaluation of oral exfoliative cytology's current status and future potential in oral and systemic disease diagnosis.

Innovative Progress: Artificial Intelligence in the Realm of Oral Cancer

In recent years, there has been a notable increase in the global incidence of oral cancer, leading to significant morbidity and mortality, especially when diagnosed at advanced stages. The integration: In recent years, there has been a notable increase in the global incidence of oral cancer, leading to significant morbidity and mortality, especially when diagnosed at advanced stages. The integration of technology holds great promise for early detection and diagnosis, facilitating improved patient management for clinicians. The emergence of artificial intelligence (AI) presents a potential breakthrough in oral cancer screening, as it can meticulously analyze vast datasets from various imaging modalities, offering valuable support in the field of oncology. This review focuses on a spectrum of AI techniques utilized for early detection and diagnosis of oral cancer. Additionally, AI techniques may be employed for the effective treatment of oral cancer. Using the abundance of information acquired, this article provides an in-depth overview and discussion of AI's value and benefits in oral cancer screening, early detection, disease prediction, and therapy, among other areas. Furthermore, it identifies present limits and forecasts the hopeful future of AI in oral cancer research.

The risks of artificial intelligence: A narrative review and ethical reflection from an Oral Medicine group.

As a relatively new tool, the use of artificial intelligence (AI) in medicine and dentistry has the potential to significantly transform the healthcare sector. AI has already demonstrated efficacy in medical diagnosis across several specialties, used successfully to detect breast, lung and skin cancer. In Oral Medicine, AI may be applied in a similar fashion, used in the detection and diagnosis of oral cancers and oral potentially malignant diseases. Despite its promise as a transformative diagnostic aid, the use of AI in healthcare presents significant safety, reliability and ethical concerns. There is no formal consensus on the safe and ethical implementation of AI systems in healthcare settings, but the literature converges on several key principles of ethical AI use including transparency, justice and fairness, non-maleficence, responsibility and privacy. This article provides a narrative review of the key ethical issues surrounding AI use in medicine, and reflects on these, providing view-points of a bioethicist and Oral Medicine clinicians from several units.

Comparative Bibliometric Analysis of Established and Emerging Databases on Salivary Biomarkers for Early Oral Cancer Diagnosis.

Salivary biomarkers play an important role in the preventive strategy for oral cancer detection at an early stage. The aim of this study was to carry out a comparative quantitative analysis of the research material on the topic in one established database, Scopus and another emerging database, Dimensions. An electronic search was performed in Scopus and Dimensions in April 2024 with the search subjects "Saliva," "Biomarkers," "Diagnosis," and "Oral Cancer." The retrieved data were analyzed using Biblioshiny for RStudio and MS Excel. The search yielded 229 and 158 documents in Scopus and Dimensions, respectively. The data were studied to understand the coverage, concentration, and diversion of research articles. The analysis revealed high singularity index for Scopus and low overlap percentage between the two databases. Scopus was found to have higher citation count per article, however, the citation correlation between Scopus and Dimensions was found to be strong. Author productivity was found to be low in both the databases. Scopus and Dimensions vary in their scope, volume of data, and coverage policies. Both the databases have complimentary coverage on salivary biomarkers for oral cancer diagnosis. However, Scopus has a greater number of articles, sources, and citations resulting in better coverage of the topic.

A systematic review on the early detection of oral cancer using artificial intelligence and electronic tongue technology

This systematic review examines the role of artificial intelligence (AI) and electronic tongue (e-tongue) technology in the early detection of oral cancer. A comprehensive search of PubMed, Scopus, and Web of Science databases identified 500 articles, of which 20 met the inclusion criteria and were included in the review. The included studies encompassed diverse methodologies, AI models, and e-tongue technologies, with a total of 5,000 participants across various populations. AI-driven models, particularly those utilizing deep learning algorithms, demonstrated high sensitivity (&gt;85%) and specificity (&gt;80%) in detecting oral cancer biomarkers. E-tongue technologies, such as mass spectrometry and optical sensors, contributed to enhanced diagnostic accuracy, with area under the curve (AUC) values exceeding 0.85 in several studies. While promising, challenges such as study heterogeneity, validation in large-scale trials, and implementation barriers require further attention. The findings highlight the transformative potential of AI and e-tongue technology in revolutionizing oral cancer screening and management, with implications for improving patient outcomes and reducing healthcare costs. Future research should focus on standardization, validation, and real-world implementation to harness the full benefits of these innovative approaches in clinical practice.

Accelerate oral cancer detection in high-risk patients

Accelerate oral cancer detection in high-risk patients

Investigating the Potential of Non-Invasive Breath Test Analysis for Early Detection of Oral Cancer: A Systematic Review

Investigating the Potential of Non-Invasive Breath Test Analysis for Early Detection of Oral Cancer: A Systematic Review