Early Detection Of Oral Cancer Research Articles

Unveiling the Potential of VELScope in Potentially Malignant Oral Lesion Early Detection for Future Dental Diagnosis Technology

Introduction: Oral lesions range from innocuous to possibly dangerous, including oral cancer, which is the world's 16th most common malignancy. Early detection of oral cancer can enhance a patient's life expectancy by a decade, emphasizing the need of diagnostic instruments like VELScope. VELScope is a portable device that employs blue light to examine oral tissue, exposing natural fluorescence and emphasizing aberrant regions that would otherwise be invisible without the use of specialized equipment. Objectives: This review looks at the possibility of the VELScope for identifying oral lesions, since it has the potential to be a future dental diagnostic tool. Method: We began with 88 findings and reduced them down to 33 research regarding VELScope technology published in the previous five years. Following screening, we chose ten articles using the same criteria for all research. Results: VELScope uses fluorescence to identify both obvious and concealed oral lesions, which is especially useful when collagen loss occurs in normal tissues. While using autofluorescence requires knowledge, it assists in analyzing margins in probable pre- malignant oral conditions. VELScope, despite its limitations, has promise for early cancer diagnosis as technology develops. Conclusion: When utilized for early diagnosis, VELScope helps to reduce oral cancer mortality, reaching an 83% 5-year survival rate. While it has limits, continuous technical improvements have the potential to improve its accuracy, making it a vital tool for accurate early diagnosis and lowering oral cancer mortality.

Improving detection of oral lesions: Eye tracking insights from a randomized controlled trial comparing standardized to conventional approach.

Early detection of oral cancer (OC) or its precursors is the most effective measure to improve outcome. The reasons for missing them on conventional oral examination (COE) or possible countermeasures are still unclear. In this randomized controlled trial, we investigated the effects of standardized oral examination (SOE) compared to COE. 49 dentists, specialists, and dental students wearing an eye tracker had to detect 10 simulated oral lesions drawn into a volunteer's oral cavity. SOE had a higher detection rate at 85.4% sensitivity compared to 78.8% in the control (p = 0.017) due to higher completeness (p < 0.001). Detection rate correlated with examination duration (p = 0.002). A standardized approach can improve systematics and thereby detection rates in oral examinations. It should take at least 5 min. Perceptual and cognitive errors and improper technique cause oral lesions to be missed. Its wide implementation could be an additional strategy to enhance early detection of OC.

Prevalence and risk factors of oral potentially malignant disorders in Indonesia: a cross-sectional study undertaken in 5 provinces

Detection of subjects with oral potentially malignant disorders in a population is key to early detection of oral cancer (OC) with consequent reduction of cancer-related morbidity and mortality. Our aim was to investigate the prevalence and associated risk factors for OPMD in representative provinces of Indonesia. This cross-sectional study was undertaken in five Indonesian provinces: West Java (WJ), Jakarta (JKT), West Papua (WP), West Kalimantan (WK) and Banda Aceh (BA). Respondents answered a previously validated questionnaire including information on ethnicity, occupation, socioeconomic status (SES), oral health practices, and behaviours associated with oral cancer. An oral examination was undertaken using WHO standardized methodology. Data were analysed using ANOVA, Chi-Square, and logistic regression to assess association between risk factors and mucosal disease. A total of 973 respondents between the ages of 17 and 82 years was enrolled (WJ 35.5%,JKT 13.3% WP 18.3%, WK 9%, BA 23.9%). Tobacco smoking (14.8%), Betel quid (BQ) chewing (12.6%) and alcohol drinking (4%) varied geographically. A well-established OPMD was detected in 137 (14.1%) respondents and 2 (0.2%) presented with chronic ulceration later diagnosed as OC. Leukoplakia was the most common OPMD found (9.7%), while the prevalence of oral submucous fibrosis (OSMF), not previously described in the nation, was 2.3%. Poor knowledge of OC risk factors, poor oral hygiene behaviours, low-income SES and ethnicity were significantly associated with the presence of an OPMD. There is a previously under-reported high prevalence of OPMD in Indonesia. Overall, we found a strong correlation between the presence of an OPMD and individual habituation to known risk factors.

Salivary Biomarkers for Oral Cancer Detection: An Exploratory Systematic Review.

Different efforts have been made to find better and less invasive methods for the diagnosis and prediction of oral cancer, such as the study of saliva as a source of biomarkers. The aim of this study was to perform a scoping review about salivary molecules that have been assessed as possible biomarkers for the diagnosis of oral squamous cell carcinoma (OSCC). A search was conducted using EBSCO, PubMed (MEDLINE), Scopus, and Web of Science. The research question was as follows: which molecules present in saliva have utility to be used as biomarkers for the early detection of oral cancer? Sixty-two studies were included. Over 100 molecules were assessed. Most of the markers were oriented towards the early diagnosis of OSCC and were classified based on their ability for detecting OSCC and oral potentially malignant disorders (OPMDs), OSCC outcome prediction, and the prediction of the malignant transformation of OPMDs. TNF-α, IL-1β, IL-6 IL-8, LDH, and MMP-9 were the most studied, with almost all studies reporting high sensitivity and specificity values. TNF-α, IL-1β, IL-6 IL-8, LDH, and MMP-9 are the most promising salivary biomarkers. However, more studies with larger cohorts are needed before translating the use of these biomarkers to clinical settings.

Enhancing deep learning classification performance of tongue lesions in imbalanced data: mosaic-based soft labeling with curriculum learning

BackgroundOral potentially malignant disorders (OPMDs) are associated with an increased risk of cancer of the oral cavity including the tongue. The early detection of oral cavity cancers and OPMDs is critical for reducing cancer-specific morbidity and mortality. Recently, there have been studies to apply the rapidly advancing technology of deep learning for diagnosing oral cavity cancer and OPMDs. However, several challenging issues such as class imbalance must be resolved to effectively train a deep learning model for medical imaging classification tasks. The aim of this study is to evaluate a new technique of artificial intelligence to improve the classification performance in an imbalanced tongue lesion dataset.MethodsA total of 1,810 tongue images were used for the classification. The class-imbalanced dataset consisted of 372 instances of cancer, 141 instances of OPMDs, and 1,297 instances of noncancerous lesions. The EfficientNet model was used as the feature extraction model for classification. Mosaic data augmentation, soft labeling, and curriculum learning (CL) were employed to improve the classification performance of the convolutional neural network.ResultsUtilizing a mosaic-augmented dataset in conjunction with CL, the final model achieved an accuracy rate of 0.9444, surpassing conventional oversampling and weight balancing methods. The relative precision improvement rate for the minority class OPMD was 21.2%, while the relative F1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${F}_{1}$$\\end{document} score improvement rate of OPMD was 4.9%.ConclusionsThe present study demonstrates that the integration of mosaic-based soft labeling and curriculum learning improves the classification performance of tongue lesions compared to previous methods, establishing a foundation for future research on effectively learning from imbalanced data.

Oral carcinogenesis and non-invasive biomarkers for the diagnosis of oral squamous cell carcinoma.

Oral squamous cell carcinoma (OSCC) is the most prevalent cancer in Pakistani population because of consumption of different tobacco-containing products whether smoked or chewed. These patients commonly report at a late stage of the disease. The patient's survival only depends upon early-stage diagnosis. Literature has reported that there is an increased tendency of transformation of oral potentially malignant disorder (OPMD) into OSCC. Biopsy is the gold standard measure for diagnosis but for OPMD cases biopsy was not recommended and most of the times the patients were also not willing to have a biopsy done. So, along with the biopsy there is a need for non-invasive protein biomarker that might aid in the early detection of oral cancer as well as highlight the high-risk individuals. This short communication focuses on the role of early diagnostic biomarkers present in literature, such as synuclein-γ (SNCG), Squamous cell carcinoma antigen (SCCAg), p53, MMPs-12, and IL-6. Furthermore, application of these biomarkers in multi-centre longitudinal studies is needed to establish their role as a non-invasive diagnostic biomarker for OSCC.

Assessment of Awareness and Knowledge of Oral Potentially Malignant Disorders and Oral Cancer among Accredited Social Health Activist Workers from Randomly Selected Blocks of Thrissur District, Kerala, India: A Cross Sectional Study

Introduction: Oral and oropharyngeal cancers are prevalent in the head-and-neck region, with global rates decreasing. However, in India, they are rising due to a lack of knowledge about risk factors and symptoms. The Indian government launched the National Health Mission to provide accessible, affordable, and reliable primary health care. Accredited social health activist (ASHA) workers can link health services to rural people. This study aimed to evaluate the awareness level among these workers about potentially malignant oral disorders and oral cancer (OC). Materials and Methods: A predesigned semi-structured questionnaire-based descriptive cross-sectional study was conducted among 150 voluntary ASHA workers from randomly selected blocks of Thrissur district, Kerala, to collect the data. Results: Our study showed that the majority of ASHA workers (82.3%) were aware of the role of tobacco in OC. A substantial portion of workers (88.4%) expressed that early detection of OC is possible at its initial stage. Less than 10% (7.5%) of all the ASHA workers were educated by dentists, whereas almost three-quarters (75.5%) of ASHAs preferred primary health center health practitioners as primary representatives for early OC detection, despite their being poorly trained in the early diagnosis and detection of OC. Conclusion: India has made progress in controlling malignancies but still lags in reducing OC mortality rates. Spreading knowledge of contributory agents and early detection methods through ASHA workers could reduce the incidence and mortality of OC. Including more dentists in the public health system and training ASHA workers on early OC detection can play a major role in reducing its incidence.

DIAGNOSTIC BIOMARKERS IN ORAL CANCER: CURRENT APPROACHES

Oral cancer is due to over expression of growth of abnormal cells which rapidly multiply and divide. oral cancer is the sixth most common tumour in the world and the highest mortality and morbidity rate amongst all the human malignancies. Betal nut, chewing pan and smokeless tobacco, intake of alcohol and chronic viral infections like human papilloma virus are some of the etiological factors of oral cancer. The pathogenies of oral cancers depend upon the interaction between the genetic, epigenetic and carcinogenetic factors and their association with tumour growth and the progression of cancer. Genetic alteration changes give rise to a multiplex of oral mucosal changes like cellular and architectural and dysplastic changes which help in grading of tumour (well-differentiated, moderately differentiated and poorly differentiated) oral cancer. K-67 and cyclin D1 are strong genetic changes taking place in oral malignancies. Diagnostic biomarkers are an essential tool for the early detection and better prognosis of oral cancer. There are invasive and non-invasive procedures for the diagnosis of oral cancer which include invasive procedures like biopsy and the non-invasive or minimally invasive procedures are blood, plasma, serum and saliva. The oral cancer biomarkers can be detected by taking the samples from cancer patients and running the molecular laboratory techniques like real time PCR for liquid biopsy, DNA sequencing, hybridization technique, single nucleotide polymorphism analysis and immunofluorescence for FFPS.&#x0D; Methylation includes hypermethylation and hypomethylation in which there is a defect in the promotor region of CPG island. The methylation process takes place in the early phase of the initiation of cancer so it is an important biomarker for the early detection of oral cancer. HOXA9, NID2, P16 AND PTEN are the genes of interest for hypermethylation in early cancer detection.&#x0D; Viral infection load like Epstein bar virus (EBV)and human papilloma virus (HPV) DNA load have specific biomarkers which can help in the early detection of oral cancer when combines with hypermethylation. Interferon and microRNA related gene are also upregulated in tumour and a biomarker for early detection of oral cancer.

Proposal for Early Prevention Actions of Oral Neoplasms: A Multidisciplinary and Analytical Approach

The study aimed to identify factors contributing to oral cancer prevention in Latin America through an exploratory review of recent scientific literature on the disease's prevalence among adult populations. It utilized a comprehensive analysis of selected publications, focusing on demographic and clinical variables such as age, gender, geographical origin, oral topography, clinical extent, and the morphological type of observed lesions.Data analysis employed a descriptive and comparative methodology that helped categorize and assess case distribution. A higher susceptibility was noted in men aged 50 to 79, in contrast to women, whose prevalence was primarily between 50 and 54 years. The study also quantified key risk factors associated with oral cancer development.Preventive measures proposed were evaluated by a multidisciplinary panel of experts, including dentists, dental assistants, general practitioners, and nurses, using the PROMETHEE Method. This ensured an objective and structured evaluation, supporting informed and effective decision-making.The research emphasized the importance of prevention and early detection of oral cancer, highlighting that early diagnosis can significantly improve patient prognosis. It reinforced the need for implementing effective, well-founded strategies to combat this disease in the region.

An Overview of Infra-red Image Processing Based Oral Cancer Detection Technique

Oral cancer, a prevalent global health concern often diagnosed at advanced stages, demands early and accurate detection for improved patient outcomes and reduced healthcare costs. This paper investigates the utility of Infrared Imaging (IR) for early detection of oral cancer, emphasizing its capacity to capture temperature variations associated with pathological changes. Addressing challenges in acquiring IR images from the oral cavity, the study highlights the necessity for precise diagnostic tools. This system uses thermal imaging and machine learning to extract and analyze the temperature data for predictions. With promising results from a rigorous evaluation of 24 subjects, the system demonstrates a sensitivity of 66.67% and specificity of 66.67%, indicating room for improvement. The study underscores the importance of collaborative research and algorithm refinement, utilizing SVM classifiers and Fuzzy logic to enhance the system's diagnostic accuracy and impact on healthcare outcomes. The findings emphasize the critical role of IR technology in revolutionizing oral cancer screening systems, highlighting the need for continued research and collaboration to optimize its practical application.

Catching it early

Phillip Silver discusses the importance of raising awareness of symptoms to improve outcomes. Aims &amp; Objectives To understand the importance of early detection of oral cancer. To appreciate the need for increased public awareness. To recognise the benefits of screening in every appointment.

A Preliminary Study on Early Detection of Oral Cancer with Opportunistic Screening: Insights from Dental Surgeons in Sri Lanka

In Sri Lanka, opportunistic screening is encouraged as a cost-effective tool to bring down the prevalence of oral cancer, which is the most common cancer among males. The objectives of the study were to determine the practices, attitudes, and level of competency of dental surgeons regarding the early detection of oral cancer and oral potentially malignant disorders (OPMDs) through opportunistic screening. A prospective study was conducted online via a Google form using a pretested, self-administered questionnaire of 22 close-ended questions and 3 open-ended questions. Out of the 137 dental surgeons who responded, 88% (121/137) of the participants believed that screening high-risk target groups would be more effective in the early detection of oral cancer rather than opportunistic screening. Only 64% (88/137) of the participants frequently check for oral cancer and OPMDs when patients visit for dental treatment. Participants recalled an average of 34 patients (4628/137) with clinically suspicious lesions being diagnosed during examination at general dental practice during the past year, and 98% (134/137) of the participants believed that they should receive additional training in order to identify and diagnose clinically suspicious oral OPMDs and oral cancer. Opportunistic screening in general dental practice as an oral-cancer prevention strategy is appreciable, but due emphasis should be given to other prevention strategies such as population screening and screening high-risk target groups. The level of confidence of general dental practitioners in the early detection of oral cancer has to be raised in order to achieve higher standards in oral cancer prevention through opportunistic screening.

Expression of Budding Uninhibited by Benzimidazole Related-1 and Telomerase in Perilesional Area of Oral Squamous Cell Carcinoma

Objective: The premalignant lesions are regarded as intermediate conditions for subsequent cancer development. Even clinically, normal-appearing mucosa could harbor early precancerous genetic mutations. This study determines the immunohistochemical expression of Budding uninhibited by benzimidazole r elated-1 (BubR1) and Telomerase in the perilesional area of oral squamous cell carcinoma. Materials and methods: The study involved thirty-three formalin-fixed paraffin embedded blocks of the perilesional area of oral cancer. The stain distribution, subcellular localization, and intensity of these two markers in response to their cellular localization were d etermined and then related to Byrne’s grading system. Fisher’s exact test and spearman’s rho test were applied to a nalyze the data. P≤0.05 is considered significant. Results: BubR1 showed prominent, continuous distribution in the full thickness of perilesional samples (54.5%). The subcellular localization of BubR1 was significantly related to Byrne's grading system (P≤0.001). High discontinuous distribution of telomerase throughout the epithelia was detected (63.6%). Byrne's grading system showed high significant relations to both stain distribution and subcellular localization of telomerase, as P- values were .001 and .002, re spectively. Both markers showed high significant full thickness localization of buccal mucosa. Conclusions: Both makers overexpression through multiple layers of oral epithelia in the perilesional area might determine their valu able role in the early detection of oral cancer. Furthermore, the significant mixed subcellular localization of these markers in high-grade cancer could delineate their combined role in developing the second primary tumor.

Revolutionizing Oral Cancer Detection: An Approach Using Aquila and Gorilla Algorithms Optimized Transfer Learning-Based CNNs.

The early detection of oral cancer is pivotal for improving patient survival rates. However, the high cost of manual initial screenings poses a challenge, especially in resource-limited settings. Deep learning offers an enticing solution by enabling automated and cost-effective screening. This study introduces a groundbreaking empirical framework designed to revolutionize the accurate and automatic classification of oral cancer using microscopic histopathology slide images. This innovative system capitalizes on the power of convolutional neural networks (CNNs), strengthened by the synergy of transfer learning (TL), and further fine-tuned using the novel Aquila Optimizer (AO) and Gorilla Troops Optimizer (GTO), two cutting-edge metaheuristic optimization algorithms. This integration is a novel approach, addressing bias and unpredictability issues commonly encountered in the preprocessing and optimization phases. In the experiments, the capabilities of well-established pre-trained TL models, including VGG19, VGG16, MobileNet, MobileNetV3Small, MobileNetV2, MobileNetV3Large, NASNetMobile, and DenseNet201, all initialized with 'ImageNet' weights, were harnessed. The experimental dataset consisted of the Histopathologic Oral Cancer Detection dataset, which includes a 'normal' class with 2494 images and an 'OSCC' (oral squamous cell carcinoma) class with 2698 images. The results reveal a remarkable performance distinction between the AO and GTO, with the AO consistently outperforming the GTO across all models except for the Xception model. The DenseNet201 model stands out as the most accurate, achieving an astounding average accuracy rate of 99.25% with the AO and 97.27% with the GTO. This innovative framework signifies a significant leap forward in automating oral cancer detection, showcasing the tremendous potential of applying optimized deep learning models in the realm of healthcare diagnostics. The integration of the AO and GTO in our CNN-based system not only pushes the boundaries of classification accuracy but also underscores the transformative impact of metaheuristic optimization techniques in the field of medical image analysis.

Oral Disease Incidence in Patients Complaining of Stomatitis in Japan After a Sudden Increase in Public Awareness of the Condition

Aim/Background: Stomatitis is generally considered a mild disease; thus, patients are often satisfied with over-the-counter medications and do not visit hospitals. Following reports of tongue cancer in a famous actress with stomatitis in Japan, many patients complaining of stomatitis who did not usually visit hospitals flooded dental clinical offices/hospitals for several months. This study evaluated the differences in profile between patients who regularly visit the university hospital and those who are affected by social impact and wish to be screened for stomatitis and the effect of social impact on the number of new patients. Materials and Methods: “Stomatitis” search rates on Japanese websites were calculated using Google Keyword Planner. Using the hospital’s electronic health record, the profiles of new patients with a main complaint of stomatitis were investigated via the data visualization tool Qlik sense®. Results: During the 3-month rush period, in which keyword searches for “stomatitis” increased, the number of new patients with a main complaint of stomatitis increased two-fold compared with that during usual periods. The incidences of stomatitis and carcinoma were approximately 30% and 10%, respectively, for the rush and normal periods at initial diagnosis. Conclusion: High social interest in oral disease prompted latent patients with stomatitis to visit dental clinical offices/hospitals and consequently contributed to the early detection of oral cancer.

Oral cancer detection using convolutional neural network optimized by combined seagull optimization algorithm

Early diagnosis of oral cancer is crucial for improving patient outcomes and saving lives. However, inaccurate and improper diagnosis can hinder effective treatment. This paper presents a novel method for detecting oral cancer using an optimized version of Convolutional Neural Network (CNN). While basic CNNs have been widely used for image classification tasks, the incorporation of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm in optimizing the CNN architecture specifically for oral cancer detection is a unique approach that is provided in this study. By combining these algorithms, the proposed method optimizes the CNN's architecture, parameters, and training process specifically for oral cancer detection. This optimization enhances the performance and accuracy of the CNN in identifying cancerous regions in oral images. Unlike previous approaches, our method incorporates advanced image processing techniques, including noise reduction, contrast enhancement, and data augmentation, to enhance the quality of input data extracted from the Oral Cancer (Lips and Tongue) images (OCI) dataset. The optimized CNN architecture uses its ability to learn intricate patterns and features from the enhanced images, enabling more accurate identification of cancerous regions. To evaluate the effectiveness of our approach, we compare it against Textural analysis, FCM, CNN, R-CNN, and ResNet-101 using four measurement indices. Results demonstrate that our proposed CSOA-based CNN system achieves the highest accuracy rate (96.94%) compared to other methods, indicating its superior performance in oral cancer detection. Furthermore, our precision rate of 94.65% and recall rate of 91.60% highlight the model's high correctness and positive classification ability. Finally, our proposed method achieves the highest F1-score (88.55%), emphasizing its superiority over other comparative methods. Through our innovative integration of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm with CNN, coupled with advanced image processing techniques, we provide a reliable and effective solution for early detection of oral cancer.

Assessment of salivary levels of ErbB2 in oral squamous cell carcinoma.

Oral cancer is the sixth-most common cancer globally. The survival rate of oral cancer is 5 years, depending on the stage it is diagnosed. To diagnose in the early stage, specialised tumour markers may assist and also help in improving the survival rate of oral cancer. ErbB2 is a transmembrane cell surface receptor required in signal transduction and an essential part of signalling pathways that take part in controlling the basic cellular processes like cell cycle, migration, metabolism and survival, besides cellular proliferation and differentiation. It is over-expressed in oral squamous cell carcinoma (OSCC) and is directly proportional to the poor prognosis, as it is expressed at a very low concentration in a healthy individual. Due to this, ErbB2 could be used as a diagnostic marker in OSCC. Nowadays, the search for tumour expression in the saliva with the use of salivary biomarkers could aid in the diagnosis of the OSSC. To assess the expression of ErbB2 in the saliva of patients with oral squamous cell carcinoma by correlating the ErbB2 level in the disease group with the healthy group. To determine the diagnostic significance of ErbB2 in OSCC. The study comprises 20 salivary samples from OSCC patients and 20 salivary samples from healthy individuals. The salivary level of ErbB2 was estimated using Enzyme Linked Immunosorbent Assay. To analyse the data, SPSS (IBM SPSS Statistics for Windows, Version 26.0, Armonk, NY: IBM Corp. Released 2019) is used. The significance level is fixed at 5% (α = 0.05). P value <0.05 is considered to be statistically significant. To compare the mean values of mean and concentration, an unpaired/independent sample t-test was used. The mean age of OSCC and control were found to be 57 ± 8.13 and 26.6 ± 1.51, respectively. The mean age was compared between OSCC and control by the Chi-square test, and the P value was <0.01, which was found to be statistically significant. The salivary levels of ErbB2 in the OSCC and control groups were measured by an unpaired sample t-test. The mean salivary ErbB2 level in the OSCC group is 3.20 ng/ml ± 0.57, and in the control group, it is 2.43 ng/ml ± 0.13. When a pairwise comparison of ErbB2 concentration was performed between OSCC and control, it showed a statistically significant difference with a P value of 0.007, which is P < 0.05. The present study has demonstrated an increased salivary expression of ErbB2 in OSCC patients when compared to healthy individuals. This suggests that ErbB2 could aid in the diagnosis of OSCC and could be used as a diagnostic marker in the early detection of oral cancer, a finding that has to be further established with a larger sample size.

Role of Salivary Biomarkers in Oral Cancer Detection- A Systematic Review

Saliva is an informative biological fluid that has gained a lot of interest because of its physiologic diagnostic medium. The salivary secretions are under control of sympathetic and parasympathetic stimulation. It contains enzymes, proteins, biochemicals. It has been suggested to be ultrafiltrate of blood. The recent findings suggest that saliva could be used as a biomarker in diagnosing oral cancer. The study of saliva as a biological matrix has been identified as a new landmark initiative in search of a useful biomarker to diagnose oral cancer through and transcriptomes. Most oral cancers are oral squamous cell carcinoma using saliva for early oral cancer detection in the search for new clinical markers is a promising approach because of its noninvasive sampling and easy collection method. Identification of this salivary biomarker could help to screen patients at risk, predict disease outcome and effectively contribute to planning treatment strategies. Biomarkers in saliva can be used as for diagnostic &amp; response to treatment in oral squamous cell carcinoma.in this review, we explored their application in this increasingly common disease. A systematic review of the literature was performed based on the English titles listed in the PubMed, EBSCO, Cochrane, Science Direct, ISI web Science, and SciELO databases using the keywords. This article may help to identify the potential biomarkers for screening and the molecular pathology analysis in the high-risk patients with the OSCC.

VELscope: The challenge for the detection of orally potentially malignant lesions

Early detection of oral cancer is crucial in improving survival rate; Identification and detection of oral potentially malignant disorders (OPMD) allow delivery of interventions to reduce the evolution of these disorders to malignancy. A variety of new and emerging diagnostic aids and adjunctive techniques are currently available to potentially assist in the detection of OPMD such as the autofluorescence technique.Pathologists utilize the autofluorescence approach to investigate body mucosa and screen for changes in tissue, which could lead to the earlier detection of pre-malignant, cancer, or other disease processes. Early identification is the most effective way to ensure treatment effectiveness, boost survival rates, and maintain a high quality of life. Autofluorescence examination of oral tissues using the VELscope has suggested as an adjunctive tool for cancer detection and diagnosis. The aim of our study was to evaluate the efficacy of the VELscope system autofluorescence to image the tissue of potentially malignant oral lesions. Also, to assess the diagnostic accuracy, sensitivity and specificity of this method.

A CNN-based approach for joint segmentation and quantification of nuclei and NORs in AgNOR-stained images

Background and ObjectiveOral cancer is the sixth most common kind of human cancer. Brush cytology for counting Argyrophilic Nucleolar Organizer Regions (AgNORs) can help early mouth cancer detection, lowering patient mortality. However, the manual counting of AgNORs still in use today is time-consuming, labor-intensive, and error-prone. The goal of our work is to address these shortcomings by proposing a convolutional neural network (CNN) based method to automatically segment individual nuclei and AgNORs in microscope slide images and count the number of AgNORs within each nucleus. MethodsWe systematically defined, trained and tested 102 CNNs in the search for a high-performing solution. This included the evaluation of 51 network architectures combining 17 encoders with 3 decoders and 2 loss functions. These CNNs were trained and evaluated on a new AgNOR-stained image dataset of epithelial cells from oral mucosa containing 1,171 images from 48 patients, with ground truth annotated by specialists. The annotations were greatly facilitated by a semi-automatic procedure developed in our project. Overlapping nuclei, which tend to hide AgNORs, thus affecting their true count, were discarded using an automatic solution also developed in our project. Besides the evaluation on the test dataset, the robustness of the best performing model was evaluated against the results produced by a group of human experts on a second dataset. ResultsThe best performing CNN model on the test dataset consisted of a DenseNet-169 + LinkNet with Focal Loss (DenseNet-169 as encoder and LinkNet as decoder). It obtained a Dice score of 0.90 and intersection over union (IoU) of 0.84. The counting of nuclei and AgNORs achieved precision and recall of 0.94 and 0.90 for nuclei, and 0.82 and 0.74 for AgNORs, respectively. Our solution achieved a performance similar to human experts on a set of 291 images from 6 new patients, obtaining Intraclass Correlation Coefficient (ICC) of 0.91 for nuclei and 0.81 for AgNORs with 95% confidence intervals of [0.89, 0.93] and [0.77, 0.84], respectively, and p-values < 0.001, confirming its statistical significance. Our AgNOR-stained image dataset is the most diverse publicly available AgNOR-stained image dataset in terms of number of patients and the first for oral cells. ConclusionsCNN-based joint segmentation and quantification of nuclei and NORs in AgNOR-stained images achieves expert-like performance levels, while being orders of magnitude faster than the later. Our solution demonstrated this by showing strong agreement with the results produced by a group of specialists, highlighting its potential to accelerate diagnostic workflows. Our trained model, code, and dataset are available and can stimulate new research in early oral cancer detection.