Grades Of Oral Epithelial Dysplasia Research Articles

P53 Abnormal Oral Epithelial Dysplasias are Associated With High Risks of Progression and Local Recurrence—A Retrospective Study in a Longitudinal Cohort

Grading of oral epithelial dysplasia (OED) can be challenging with considerable intraobserver and interobserver variability. Abnormal immunohistochemical (IHC) staining patterns of the tumor suppressor protein, p53, have been recently shown to be potentially associated with progression in OED. We retrospectively identified 214 oral biopsies from 203 patients recruited in a longitudinal study between 2001 and 2008 with a diagnosis of reactive, nondysplastic lesions, low-grade lesions (mild OED and moderate OED) and high-grade lesions (HGLs; severe OED/carcinoma in situ). Tissue microarrays were constructed from the most representative area of the pathology. Three consecutive sections were sectioned and stained for hematoxylin and eosin, p53 IHC, and p16 IHC. The staining results were reviewed by 2 pathologists blinded to clinical outcome. Samples were categorized into p53 abnormal OED (n = 46), p53 conventional OED (n = 118), and p53 human papillomavirus (HPV) OED (HPV associated) (n = 12) using a previously published pattern-based approach. All cases of p53 HPV OED (HPV associated) were identified in HGLs. In contrast, cases of p53 abnormal OED were observed in mild OED (9.5%), moderate OED (23%), and severe OED/carcinoma in situ (51%). None of the 27 reactive or nondysplastic lesions showed abnormal p53 staining patterns. Among the 135 low-grade lesions, 23 cases (17.0%; 2 mild OEDs and 21 moderate OEDs) progressed to HGL or squamous cell carcinoma, with 11 cases showing progression within the first 3 years. Remarkably, 82% (9/11) of these faster progressors showed abnormal p53 patterns. Survival analysis revealed that p53 abnormal OED had significantly poorer progression-free probability (P < .0001) with hazard ratio of 11.24 (95% CI, 4.26-29.66) compared with p53 conventional OED. Furthermore, p53 abnormal OED had poorer local recurrence–free survival compared with p53 wild-type OED (P = .03). The study supports that OED with p53 abnormal pattern is at high risk for progression and recurrence independent of the dysplasia grade.

The Correlation of p53, CK13, CK17, and Ki67 Immunostaining Patterns in Assisting the Histopathologic Grading of Oral Epithelial Dysplasia

The Correlation of p53, CK13, CK17, and Ki67 Immunostaining Patterns in Assisting the Histopathologic Grading of Oral Epithelial Dysplasia

Understanding interobserver variability of pathologists to improve oral epithelial dysplasia grading.

This study aimed to understand reasons for interobserver variability in the grading of oral epithelial dysplasia (OED) through a survey of pathologists to provide insight for improvements in the reliability and reproducibility of OED diagnoses. The study design included quantitative and qualitative methodology. A pre-validated 31-item questionnaire was distributed to general, head and neck, and oral and maxillofacial histopathology specialists worldwide. A total of 132 pathologists participated and completed the questionnaire. Over two-thirds used the three-tier grading system for OED, while about a third used both binary and three-tier systems. Regular reporters of OED preferred the three-tier system and grading architectural features. Continuing education significantly aided recognition of architectural and cytological changes. Irregular epithelial stratification and drop-shaped rete ridges had the lowest prognostic value and recognition scores, while loss of epithelial cell cohesion had the highest. Most participants used clinical information and often sought a second opinion when grading OED. Our study has found that frequency of OED reporting and attendance of CME/CPD can play an important role in grading OED. Variations in the prognostic value of individual histological features and the use of clinical information may further contribute to interobserver variability.

Histopathological risk assessment in multisite epithelial dysplasia: A meta‐analysis

AbstractObjectiveHistopathological grading of oral epithelial dysplasia (OED) is the current standard for stratifying cancer progression risk but is associated with subjectivity and variability. This problem is not commonly seen regarding the grading of epithelial dysplasia in other sites. This systematic review aims to compare grading systems for oral, anal, penile, and cervical epithelial dysplasia to determine their predictive accuracy for recurrence and malignant transformation (MT) outcomes.MethodsThe review protocol was registered in PROSPERO (CRD42023403035) and was reported according to the PRISMA checklist. A comprehensive search was performed in the main databases and gray literature. The risk of bias in individual studies was analyzed using the Joanna Briggs Institute checklist for each study design.ResultsForty‐six studies were deemed eligible and included in this systematic review, of which 45 were included in the quantitative analysis. Meta‐analysis revealed that the binary system demonstrated a higher predictive ability for MT/recurrence of OED compared to multilevel systems. Higher predictive accuracy of MT was also observed for binary grading systems in anal intraepithelial neoplasia.ConclusionsNo significant difference was found between the current grading systems of epithelial dysplasia in different body parts. However, binary grading systems have shown better clinical outcomes.

An Update on the Use of Artificial Intelligence in Digital Pathology for Oral Epithelial Dysplasia Research.

Oral epithelial dysplasia (OED) is a precancerous histopathological finding which is considered the most important prognostic indicator for determining the risk of malignant transformation into oral squamous cell carcinoma (OSCC). The gold standard for diagnosis and grading of OED is through histopathological examination, which is subject to inter- and intra-observer variability, impacting accurate diagnosis and prognosis. The aim of this review article is to examine the current advances in digital pathology for artificial intelligence (AI) applications used for OED diagnosis. We included studies that used AI for diagnosis, grading, or prognosis of OED on histopathology images or intraoral clinical images. Studies utilizing imaging modalities other than routine light microscopy (e.g., scanning electron microscopy), or immunohistochemistry-stained histology slides, or immunofluorescence were excluded from the study. Studies not focusing on oral dysplasia grading and diagnosis, e.g., to discriminate OSCC from normal epithelial tissue were also excluded. A total of 24studies were included in this review. Nineteen studies utilized deep learning (DL) convolutional neural networks for histopathological OED analysis, and 4 used machine learning (ML) models. Studies were summarized by AI method, main study outcomes, predictive value for malignant transformation, strengths, and limitations. ML/DL studies for OED grading and prediction of malignant transformation are emerging as promising adjunctive tools in the field of digital pathology. These adjunctive objective tools can ultimately aid the pathologist in more accurate diagnosis and prognosis prediction. However, further supportive studies that focus on generalization, explainable decisions, and prognosis prediction are needed.

Quantitative assessment Cyclooxygenase – 2 immunohistochemical expression in different grades of oral epithelial dysplasia

Oral leukoplakia (OLP) is one the most common potentially malignant disorders account 0.2 to 4.9% of malignant transformation and dysplastic lesions vary from 3-6% this rate of malignant conversion depends on the different grades of epithelial dysplasia. Recent literature suggests that increased levels of COX-2 in potentially malignant disorders and malignant tumors show prominent genetic evidence in tumorigenesis. Assessment of Cyclooxygenase-2 – 2 (COX-2) immunohistochemical expression in different grades of oral epithelial dysplasia. Materials and Methodology A total of forty formalin-fixed, paraffin-embedded tissue blocks were obtained from departmental archives which are histopathological diagnoses of different grades of oral epithelial dysplasia each grade ten samples was included. Stained with COX-2 and positive cells were counted and tabulated for statistical analysis. Results Comparison between genders in oral leukoplakia males was more when compared with females. The mean age in mild epithelial dysplasia was more when compared with moderate and severe epithelial dysplasia. Expression of COX-2 was increased from mild to severe epithelial dysplasia increases. The mean number of positive cells was increased. A comparison of all groups was not statistically significant (p≥0.05). Conclusion: Oral leukoplakia (OLP) is one the most common potentially malignant disorders which accounts for 0.2 to 4.9% of malignant transformation. COX-2 can be used for early detection and prognostic makers in different grades of oral epithelial dysplasia. Keywords: Cyclooxygenase, Expression, Oral leukoplakia, Potentially malignant transformation

Association of podoplanin expression to histopathological grades of oral epithelial dysplasia and oral squamous cell carcinoma.

To determine the expression of podoplanin, and to correlate it with histopathological grades in oral epithelial dysplasia and oral squamous cell carcinoma cases. The retrospective, analytical, cross-sectional study was conducted at the City Laboratory, Peshawar, Pakistan, and comprised specimen block data of histologically diagnosed cases of oral benign lesions, dysplastic lesions and oral squamous cell carcinoma from January 2017 to August 2021. Two sections (4um) were cut from each specimen block for Haematoxylin and Eosin staining and immunohistochemistry. The slides were re-evaluated by two pathologists for confirmation of the diagnosis, and podoplanin marker was applied to cases selected using immunohistochemistry. Data was analysed using SPSS 22. Of the 80 cases identified, 68(85%) were analysed. There were 20(29.4%) benign cases; 11(55%) females and 9(45%) males with mean age 39.90±16.23 years, 20(29.4%) oral dysplastic cases; 14(70%) males and 6(30%) females with mean age 57.75±12.02 years, and 28(41.2%) oral squamous cell carcinoma cases; 17(61%) males and 11(39%) females with mean age 50.55±14.80 years. Podoplanin expression in oral epithelial dysplasia cases was significant (p=0.028), while it was not significant in the other 2 groups (p>0.05). Podoplanin when used along with histopathological evaluation could aid as an adjuvant technique in the diagnosis and grading of oral epithelial dysplasia.

Oral epithelial dysplasia detection and grading in oral leukoplakia using deep learning

BackgroundThe grading of oral epithelial dysplasia is often time-consuming for oral pathologists and the results are poorly reproducible between observers. In this study, we aimed to establish an objective, accurate and useful detection and grading system for oral epithelial dysplasia in the whole-slides of oral leukoplakia.MethodsFour convolutional neural networks were compared using the image patches from 56 whole-slide of oral leukoplakia labeled by pathologists as the gold standard. Sequentially, feature detection models were trained, validated and tested with 1,000 image patches using the optimal network. Lastly, a comprehensive system named E-MOD-plus was established by combining feature detection models and a multiclass logistic model.ResultsEfficientNet-B0 was selected as the optimal network to build feature detection models. In the internal dataset of whole-slide images, the prediction accuracy of E-MOD-plus was 81.3% (95% confidence interval: 71.4–90.5%) and the area under the receiver operating characteristic curve was 0.793 (95% confidence interval: 0.650 to 0.925); in the external dataset of 229 tissue microarray images, the prediction accuracy was 86.5% (95% confidence interval: 82.4–90.0%) and the area under the receiver operating characteristic curve was 0.669 (95% confidence interval: 0.496 to 0.843).ConclusionsE-MOD-plus was objective and accurate in the detection of pathological features as well as the grading of oral epithelial dysplasia, and had potential to assist pathologists in clinical practice.

Expression of CLLD7 and CHC1L Proteins in Oral Epithelial Dysplasia in a Group of Thai Patients.

Previous study showed aberrant CLLD7 and CHC1L protein expression in oral squamous cell carcinoma (OSCC) compared to normal oral mucosa (NOM). This study aimed to evaluate the expression of these proteins in oral epithelial dysplasia (OED). Forty specimens of OED and 11 NOM were used. The expression of CLLD7 and CHC1L was determined by immunohistochemistry. In each case, at least 1000 cells were counted. Presence of nuclear, cytoplasmic, and/or membrane staining of CLLD7 and CHC1L were considered positive. Percentages of total positive cells and positive cells at different locations were recorded. SPSS version 18 was used to compare variation between groups with statistical significance at p<0.05. No significant differences in the percentages of total positive cells of CLLD7 and CHC1L were found between NOM and all grades of OED. Nevertheless, there were significant differences in subcellular staining of these two proteins. In CLLD7, the nuclear staining of the moderate and the severe OED groups was significantly lower than that of the NOM group (p<0.05). The percentages of membrane staining of CHC1L in moderate and severe OED were significantly higher than that of NOM (p<0.001). In addition, the nuclear staining of CHC1L in each grade of OED was significantly lower than that of NOM (p<0.05). The subcellular mislocalization of CLLD7 and CHC1L in OED suggests that the expression of these potential tumor suppressor proteins might be dysregulated during the dysplastic process. The distinct membrane staining of CHC1L observed in OED but not in NOM is a useful characteristic that can be used to separate OED from NOM. Thus, CHC1L may be a good marker to assist in the diagnosis of OED.

Immunohistochemical Evaluation of E- Cadherin in Oral Epithelial Dysplasia and Oral Squamous Cell Carcinoma.

Cancers arising in the oral cavity are more commonly of squamous cell carcinomas. E-cadherin is a calcium-dependant transmembrane glycoprotein of the type-1 cadherin superfamily is an invasion/tumor suppressor gene, which plays a vital role in epithelial cell-cell adhesion. Epithelial E-cadherin expression loss increases tumor invasiveness and metastasis. To determine the expression of E-cadherin in oral epithelial dysplasia (OED) and oral squamous cell carcinoma (OSCC). Analysis of E-cadherin expression in 10 cases of normal mucosa, 15 cases of various grades of OED, 15 cases of OSCC. The data were calculated using Chi-square test and analysis of variance test (ANOVA). An intragroup comparison of staining intensity and staining location for OED showed a highly significant difference between mild and moderate grade (P < 0.001). A significant difference of staining intensity was noted among well and moderately differentiated grades, and well and poorly differentiated grades of OSCC. A comparison of staining location among well and poorly differentiated grades of OSCC was found to be significant. Expression loss is observed as the severity of the lesion progresses in both OSCC and OED. The increased loss of expression in oral squamous cell carcinoma poorer the prognosis.

Potential Immunohistochemical Biomarkers for Grading Oral Dysplasia: A Literature Review.

Oral cancer is a prevalent global health issue, with significant morbidity and mortality rates. Despite available preventive measures, it remains one of the most common cancers, emphasising the need for improved diagnostic and prognostic tools. This review focuses on oral potentially malignant disorders (OPMDs), precursors to oral cancer, specifically emphasising oral epithelial dysplasia (OED). The World Health Organisation (WHO) provides a three-tier grading system for OED, and recent updates have expanded the criteria to enhance diagnostic precision. In the prognostic evaluation of OED, histological grading is presently regarded as the gold standard; however, its subjectivity and unreliability in anticipating malignant transformation or recurrence pose notable limitations. The primary objective is to investigate whether specific immunohistochemical biomarkers can enhance OED grading assessment according to the WHO classification. Biomarkers exhibit significant potential for comprehensive cancer risk evaluation, early detection, diagnosis, prognosis, and treatment optimisation. Technological advancements, including sequencing and nanotechnology, have expanded detection capabilities. Some analysed biomarkers are most frequently chosen, such as p53, Ki-67, cadherins/catenins, and other proteins used to differentiate OED grades. However, further research is needed to confirm these findings and discover new potential biomarkers for precise dysplasia grading and minimally invasive assessment of the risk of malignant transformation.

Calibration improves the agreement in grading oral epithelial dysplasia-Findings from a National Workshop in Malaysia.

A major pitfall of many of the established oral epithelial dysplasia (OED) grading criteria is their lack of reproducibility and accuracy to predict malignant transformation. The main objective of this study was to determine whether calibration of practicing oral pathologists on OED grading could improve the reproducibility of the WHO 2017 and the binary OED grading systems. A nationwide online exercise was carried out to determine the influence of calibration on the reproducibility of the WHO 2017 and the binary OED grading systems. A significant improvement was observed in the inter-observer agreement for the WHO 2017 OED grading system (K 0.196 vs. 0.448; Kw 0.357 vs. 0.562) after the calibration exercise. The significant difference (p = 0.027) in the level of agreement between those with five or more years and less than 5 years of experience was no more observed (p = 0.426) after the calibration exercise. The percent agreement for binary grading was significantly higher (91.8%) for buccal mucosal lesions as compared to lesions on the tongue after the calibration exercise. This study validates the significance of calibration in improving the reproducibility of OED grading. The nationwide exercise resulted in a statistically significant improvement in the inter-observer agreement for the WHO 2017 OED grading system among a large number of oral pathologists. It is highly recommended that similar exercises should be organized periodically by professional bodies responsible for continuing education among oral pathologists to improve the reliability of OED grading for optimal treatment of oral potentially malignant disorders.

Prognostic importance of mitosis quantification and PHH3 expression in oral epithelial dysplasia.

Oral epithelial dysplasia (OED) is diagnosed and graded using a range of histological features, making grading subjective and challenging. Mitotic counting and phosphohistone-H3 (PHH3) staining have been used for the prognostication of various malignancies; however, their importance in OED remains unexplored. This study conducts a quantitative analysis of mitotic activity in OED using both haematoxylin and eosin (H&E)-stained slides and immunohistochemical (IHC) staining for PHH3. Specifically, the diagnostic and prognostic importance of mitotic number, mitotic type and intra-epithelial location is evaluated. Whole slide images (WSI) of OED (n = 60) and non-dysplastic tissue (n = 8) were prepared for analysis. Five-year follow-up data was collected. The total number of mitosis (TNOM), mitosis type and intra-epithelial location was manually evaluated on H&E images and a digital mitotic count performed on PHH3-stained WSI. Statistical associations between these features and OED grade, malignant transformation and OED recurrence were determined. Mitosis count increased with grade severity (H&E: p < 0.005; IHC: p < 0.05), and grade-based differences were seen for mitosis type and location (p < 0.05). The ratio of normal-to-abnormal mitoses was higher in OED (1.61) than control (1.25) and reduced with grade severity. TNOM, type and location were better predictors when combined with histological grading, with the most prognostic models demonstrating an AUROC of 0.81 for transformation and 0.78 for recurrence, exceeding conventional grading. Mitosis quantification and PHH3 staining can be an adjunct to conventional H&E assessment and grading for the prediction of OED prognosis. Validation on larger multicentre cohorts is needed to establish these findings.

The use of deep learning state-of-the-art architectures for oral epithelial dysplasia grading: A comparative appraisal.

Dysplasia grading systems for oral epithelial dysplasia are a source of disagreement among pathologists. Therefore, machine learning approaches are being developed to mitigate this issue. This cross-sectional study included a cohort of 82 patients with oral potentially malignant disorders and correspondent 98 hematoxylin and eosin-stained whole slide images with biopsied-proven dysplasia. All whole-slide images were manually annotated based on the binary system for oral epithelial dysplasia. The annotated regions of interest were segmented and fragmented into small patches and non-randomly sampled into training/validation and test subsets. The training/validation data were color augmented, resulting in a total of 81,786 patches for training. The held-out independent test set enrolled a total of 4,486 patches. Seven state-of-the-art convolutional neural networks were trained, validated, and tested with the same dataset. The models presented a high learning rate, yet very low generalization potential. At the model development, VGG16 performed the best, but with massive overfitting. In the test set, VGG16 presented the best accuracy, sensitivity, specificity, and area under the curve (62%, 62%, 66%, and 65%, respectively), associated with the higher loss among all Convolutional Neural Networks (CNNs) tested. EfficientB0 has comparable metrics and the lowest loss among all convolutional neural networks, being a great candidate for further studies. The models were not able to generalize enough to be applied in real-life datasets due to an overlapping of features between the two classes (i.e., high risk and low risk of malignization).

Assessing Oral Epithelial Dysplasia Risk for Transformation to Cancer: Comparison Between Histologic Grading Systems Versus S100A7 Immunohistochemical Signature-based Grading.

While a 3-tier oral epithelial dysplasia grading system has been utilized for decades, it is widely recognized as a suboptimal risk indicator for transformation to cancer. A 2-tier grading system has been proposed, although not yet validated. In this study, the 3-tier and 2-tier dysplasia grading systems, and an S100A7 immunohistochemical signature-based grading system were compared to assess prediction of risk of transformation to oral cancer. Formalin-fixed, paraffin-embedded biopsy specimens with known clinical outcomes were obtained retrospectively from a cohort of 48 patients. Hematoxylin and eosin-stained slides were used for the 2- and 3-tier dysplasia grading, while S100A7 for biomarker signature-based assessment was based on immunohistochemistry. Inter-observer variability was determined using Cohen's kappa ( K ) statistic with Cox regression disease free survival analysis used to determine if any of the methods were a predictor of transformation to oral squamous cell carcinoma. Both the 2- and 3-tier dysplasia grading systems ranged from slight to substantial inter-observer agreement ( Kw between 0.093 to 0.624), with neither system a good predictor of transformation to cancer (at least P =0.231; ( P >>>0.05). In contrast, the S100A7 immunohistochemical signature-based grading system showed almost perfect inter-observer agreement ( Kw =0.892) and was a good indicator of transformation to cancer ( P =0.047 and 0.030). The inherent grading challenges with oral epithelial dysplasia grading systems and the lack of meaningful prediction of transformation to carcinoma highlights the significant need for a more objective, quantitative, and reproducible risk assessment tool such as the S100A7 immunohistochemical signature-based system.

Ki-67 Expression as a Prognostic Marker: A Comparative Immunohistochemical Analysis of Oral Epithelial Dysplasia and Oral Squamous Cell Carcinoma.

Introduction Oral dysplasia is a frequent precancerous condition that may lead to oral cancer. The histopathologic abnormalities exhibited in a chronic, progressive, and premalignant condition of the oral mucosa are referred to as oral epithelial dysplasia (OED). It might show up as erythroplakia, leukoplakia, or leukoerythroplakia. OED is a premalignancy histologic marker that predicts a higher likelihood of squamous cell carcinoma development. Aims and objectives The aim of this study is to identify an association between Ki-67 protein expression and histological grading of OED and oral squamous cell carcinoma (OSCC) and to compare the expression of Ki-67 in different grades of OED and OSCC with the prognosis. Materials and methods The current retrospective research is focused on evaluating epithelial dysplasia and analyzing the function of Ki-67 as a prognostic marker after receiving institutional ethical approval. Group I - normal oral mucosa (NOM), Group II - OED, and Group III - OSCC were included in the study. For statistical analysis, SPSS Statistics version 21.0 (IBM Corp. Released 2021. IBM SPSS Statistics for Windows, Version 28.0. Armonk, NY: IBM Corp) was utilized. The Cox regression model was employed to look at interactions between various prognostic variables. At p<0.05, differences were deemed statistically significant. Results Ki-67 expression was confined to the basal layers in the normal oral epithelium and in the basal, suprabasal, and spinous layers in OED.Ki-67 positive cells were mostly found on the perimeter of well, moderate, and poorly differentiated OSCC tumor nests with Ki-67 positive cells scattered throughout OSCC.According to statistical analysis, there is a substantial difference in expression between OEDand NOM, OSCC and NOM, and OED and OSCC. Conclusion Our study showed that there is a progressive increase in Ki-67 expression across various grades of OED, and the highest expression was noted in OSCC. Early identification and prompt treatment will help in improving the quality of life of such patients.

Salivary Interleukin Levels in Oral Squamous Cell Carcinoma and Oral Epithelial Dysplasia: Findings from a Sri Lankan Study.

The incidence of oral squamous cell carcinoma (OSCC), and its precursor, oral epithelial dysplasia (OED), is on the rise, especially in South Asia. OSCC is the leading cancer in males in Sri Lanka, with >80% diagnosed at advanced clinical stages. Early detection is paramount to improve patient outcome, and saliva testing is a promising non-invasive tool. The aim of this study was to assess salivary interleukins (lL1β, IL6, and IL8) in OSCC, OED and disease-free controls in a Sri Lankan study cohort. A case-control study with OSCC (n = 37), OED (n = 30) patients and disease-free controls (n = 30) was conducted. Salivary lL1β, IL6, and IL8 were quantified using enzyme-linked immuno-sorbent assay. Comparisons between different diagnostic groups and potential correlations to risk factors were assessed. Salivary levels for the three tested interleukins increased from disease-free controls through OED, and were highest in OSCC samples. Furthermore, the levels of IL1β, IL6, and IL8 increased progressively with OED grade. The discrimination between patients (OSCC and OED) and controls, as assessed by AUC of receiver operating characteristic curves, was 0.9 for IL8 (p = 0.0001) and 0.8 for IL6 (p = 0.0001), while IL1β differentiated OSCC from controls (AUC 0.7, p = 0.006). No significant associations were found between salivary interleukin levels and smoking, alcohol, and betel quid risk factors. Our findings suggest that salivary IL1β, IL6, and IL8 are associated with disease severity of OED, and are potential biomarkers for predicting disease progression in OED, and the screening of OSCC.

FGFR1 is an important prognostic factor in oral leukoplakia and tongue squamous cell carcinoma.

Fibroblast growth factor receptor 1 is a potential prognostic factor for tongue squamous cell carcinoma and is associated with oral epithelial dysplasia grade in oral leukoplakia. Thirty cases of tongue squamous cell carcinoma and 30 cases of oral leukoplakia were analyzed. Fibroblast growth factor receptor 1 and phosphorylated Akt protein expression were analyzed by immunohistochemistry and quantified using a digital algorithm. Fibroblast growth factor receptor 1 gene amplification was analyzed by fluorescent in situ hybridizationin the tongue squamous cell carcinoma cases. Clinical appearance and dysplasia grade were correlated with oral leukoplakia malignant transformation. Oral leukoplakia cases presenting high fibroblast growth factor receptor 1 expression showed a higher risk of malignant transformation (p=0.016, HR: 7.3, 95% CI: 1.4-37.4). Phosphorylated Akt showed faint to no expression in oral leukoplakia, which did not correlate with dysplasia grade or malignant transformation. High expression of fibroblast growth factor receptor 1 and phosohorylated Akt were associated with poor overall survival and disease-free survival in tongue squamous cell carcinoma, although only fibroblast growth factor receptor 1 expression was significantly associated with poor overall survival (p=0.024; HR: 4.9, 95% CI: 1.2-19.9). Cases presenting double fibroblast growth factor receptor 1/phosphorylated Akt overexpression (n=8) showed markedly impaired overall survival (p=0.020; HR: 6.4, 95% CI: 1.3-31.1) and disease-free survival (p=0.001, HR: 13.0, 95% CI: 3.0-55.7). Fibroblast growth factor receptor 1 amplification was observed in 16.6% of tongue squamous cell carcinoma cases, being correlated with vascular and neural invasion (p=0.001 and 0.017, respectively), but not with fibroblast growth factor receptor 1 protein expression, overall survival, or disease-free survival. Fibroblast growth factor receptor 1 protein expression is an important prognostic factor in oral leukoplakia and tongue squamous cell carcinoma.

Deep learning approach to detect high-risk oral epithelial dysplasia: A step towards computer-assisted dysplasia grading

Introduction: Oral epithelial dysplasia (OED) is associated with high interobserver and intraobserver disagreement. With the exponential increase in the applicability of artificial intelligence tools such as deep learning (DL) in pathology, it would now be possible to achieve high accuracy and objectivity in grading of OED. In this research work, we have proposed a DL approach to epithelial dysplasia grading by creating a convolutional neural network (CNN) model from scratch. Materials and Methods: The dataset includes 445 high-resolution ×40 photomicrographs captured from histopathologically diagnosed cases of high-risk dysplasia (HR) and normal buccal mucosa (NBM) that were used to train, validate and test the two-dimensional CNN (2DCNN) model. Results: The whole dataset was divided into 60% training set, 20% validation set and 20% test set. The model achieved training accuracy of 97.21%, validation accuracy of 90% and test accuracy of 91.30%. Conclusion: The DL model was able to distinguish between normal epithelium and HR epithelial dysplasia with high grades of accuracy. These results are encouraging for researchers to formulate DL models to grade and classify OED using various grading systems.

Salivary miRNAs Expression in Potentially Malignant Disorders of the Oral Mucosa and Oral Squamous Cell Carcinoma: A Pilot Study on miR-21, miR-27b, and miR-181b

(1) Background: Oral potentially malignant disorders (OPMD) represent a fundamental challenge for clinicians, considering the possibility of progression into oral epithelial dysplasia (OED) and oral squamous cell carcinoma (OSCC). Several studies have examined the expression of miRNAs in humans as diagnostic and prognostic biomarkers. Among these, miR-21, miR-27b, and miR-181b proved to be promising. This cohort study evaluated the different expressions of those miRNAs in the saliva of patients with OPMD and OSCC. (2) Methods: Patients with a clinical diagnosis of OPMD and/or OSCC were enrolled; saliva samples were collected; miRNAs were extracted and quantified via qRT-PCR was performed. Data were analyzed by subgroups based on the histopathological diagnosis (OSCC and the grade of OED) using the ΔΔCt method. Saliva from 10 healthy donors was used as the control. One-way ANOVA and Kruskal-Wallis tests were performed to assess the differences between groups. (3) Results: 23 patients for the OPMD group (6 with no dysplasia, 7 with low-grade, and 10 with high-grade dysplasia) and 10 with OSCC were analyzed. MiR-21 did not show any variation among groups; miR-27b was under-expressed in dysplastic lesions (p = 0.046); miR-181b was upregulated in high-grade dysplasia (p = 0.006), increasing with the degree of dysplasia, and decreasing in OSCCs. (4) Conclusions: Salivary miR-27b and miR-181b could be promising biomarkers for oral dysplasia. Further studies are needed to clarify their feasibility.