Browse
Submit Data
Databases
API
Help

Dataset Information

31 Views

0 Connections

0 Citations

0 Reanalyses

0 Downloads

Omics score: 0

Automated Detection and Classification of Oral Lesions Using Deep Learning to Detect Oral Potentially Malignant Disorders.

ABSTRACT: Oral cancer is the most common type of head and neck cancer worldwide, leading to approximately 177,757 deaths every year. When identified at early stages, oral cancers can achieve survival rates of up to 75-90%. However, the majority of the cases are diagnosed at an advanced stage mainly due to the lack of public awareness about oral cancer signs and the delays in referrals to oral cancer specialists. As early detection and treatment remain to be the most effective measures in improving oral cancer outcomes, the development of vision-based adjunctive technologies that can detect oral potentially malignant disorders (OPMDs), which carry a risk of cancer development, present significant opportunities for the oral cancer screening process. In this study, we explored the potential applications of computer vision techniques in the oral cancer domain within the scope of photographic images and investigated the prospects of an automated system for detecting OPMD. Exploiting the advancements in deep learning, a two-stage model was proposed to detect oral lesions with a detector network and classify the detected region into three categories (benign, OPMD, carcinoma) with a second-stage classifier network. Our preliminary results demonstrate the feasibility of deep learning-based approaches for the automated detection and classification of oral lesions in real time. The proposed model offers great potential as a low-cost and non-invasive tool that can support screening processes and improve detection of OPMD.

SUBMITTER: Tanriver G

PROVIDER: S-EPMC8199603 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Json Xml

Similar Datasets

Deep Learning Predicts the Malignant-Transformation-Free Survival of Oral Potentially Malignant Disorders.

Project description:Machine-intelligence platforms for the prediction of the probability of malignant transformation of oral potentially malignant disorders are required as adjunctive decision-making platforms in contemporary clinical practice. This study utilized time-to-event learning models to predict malignant transformation in oral leukoplakia and oral lichenoid lesions. A total of 1098 patients with oral white lesions from two institutions were included in this study. In all, 26 features available from electronic health records were used to train four learning algorithms-Cox-Time, DeepHit, DeepSurv, random survival forest (RSF)-and one standard statistical method-Cox proportional hazards model. Discriminatory performance, calibration of survival estimates, and model stability were assessed using a concordance index (c-index), integrated Brier score (IBS), and standard deviation of the averaged c-index and IBS following training cross-validation. This study found that DeepSurv (c-index: 0.95, IBS: 0.04) and RSF (c-index: 0.91, IBS: 0.03) were the two outperforming models based on discrimination and calibration following internal validation. However, DeepSurv was more stable than RSF upon cross-validation. External validation confirmed the utility of DeepSurv for discrimination (c-index-0.82 vs. 0.73) and RSF for individual survival estimates (0.18 vs. 0.03). We deployed the DeepSurv model to encourage incipient application in clinical practice. Overall, time-to-event models are successful in predicting the malignant transformation of oral leukoplakia and oral lichenoid lesions.

| S-EPMC8657223 | biostudies-literature

Expression of p63 in potentially malignant and malignant oral lesions.

Project description:BACKGROUND:p63, a member of p53 family, known to be expressed in embryonic tissues and basal regenerative layers of many epithelial tissues in the adult, is also expressed in various benign and malignant lesions of body including lesions of oral cavity. To evaluate the expression of p63 and compare the expression qualitatively and quantitatively in normal buccal mucosa, epithelial dysplasia, oral submucous fibrosis (OSMF), and oral squamous cell carcinoma (OSCC). METHODS:The study material consisted of 45 archival cases which were divided into Group I with 5 cases of normal buccal mucosa, Group II with 15 cases of epithelial dysplasia, and Group III with 10 cases of OSMF and 15 cases of OSCC. Immunohistochemical expression of p63 was assessed by using mean, standard deviation, and analysis of variance. RESULTS:Overexpression of p63 was seen in epithelial dysplasia, OSMF, and squamous cell carcinoma with an increased suprabasal expression in cases of epithelial dysplasia. The mean labeling index (LI) of p63 was found to be in increasing order from normal oral mucosa (33.75%), OSMF (57.37%), epithelial dysplasia (63.87%) to squamous cell carcinoma (69.76%). CONCLUSION:The results suggest a possible role of p63 in oral carcinogenesis, and an increased LI as well as increased suprabasal expression of this gene in dysplastic lesions may have a potential to be utilized as a marker for premalignancy.

| S-EPMC4623214 | biostudies-literature

Gene expression changes associated with malignant transformation of oral potentially malignant disorders

Project description:A large number of oral squamous cell carcinomas (OSCCs) are believed to be preceded by oral potentially malignant disorders (OPMD) that have an increased likelihood of malignant transformation compared to clinically normal mucosa. This study was performed to identify differentially expressed genes between OPMDs that underwent malignant transformation (MT) and those that did not, termed ‘non-transforming’ (NT) cases. Total RNA was extracted from formalin-fixed paraffin-embedded tissue biopsies of 20 OPMD cases with known clinical outcomes (10 MT vs. 10 NT). Samples were assessed for quantity, quality and integrity of RNA prior to sequencing. Analysis for differential gene expression between MT and NT was performed using statistical packages in R. Genes were considered to be significantly differentially expressed if the False Discovery Rate corrected p-value was < 0.05. RNA yield was variable but RNA purity was good (A260/A280 >1.90). Analysis of RNA-Sequencing outputs revealed 41 genes (34 protein-coding; 7 non-coding) that were significantly differentially expressed between MT and NT cases. The log2 fold change for the statistically significant differentially expressed genes ranged from -2.63 to 2.48, with 23 protein-coding genes being downregulated and 11 protein-coding genes being upregulated in MT cases compared to NT cases. Several candidate genes that may play a role in malignant transformation of OPMD have been identified. Experiments to validate these candidates are underway. It is anticipated that this work will contribute to better understanding of the aetiopathogenesis of OPMD and development of novel biomarkers.

2020-08-14 | GSE156208 | GEO

Oral HPV16 Prevalence in Oral Potentially Malignant Disorders and Oral Cavity Cancers.

Project description:The role of human papillomavirus type 16 (HPV16) in oral potentially malignant disorders (OPMD) and oral cavity carcinoma (OC) is still under debate. We investigated HPV16 prevalence in unstimulated saliva, oral rinse samples, oral swabs and tumour biopsies collected from OPMD (n = 83) and OC (n = 106) patients. HPV16 genotype, viral load, physical status (episomal vs. integrated) and tumour p16INK4a expression were determined. Oral HPV16 prevalence was higher in OC than in OPMD, but this difference was not statistically significant (7.5% (8/106) versus 3.6% (3/83), odds ratio (OR): 2.18, 95% confidence interval (CI): 0.56, 8.48, p = 0.26). There was a significant association (p < 0.05) between oral HPV16 infection and heavy tobacco consumption. Real-time PCR results indicated that no integration events occurred in either OPMD or OC cases based on the HPV16 E2/E6 ratio. HPV16 positive OPMD and OC patients had similar HPV16 E2 and E6 viral loads. The inter-rater agreement between tumour p16INK4a expression and oral HPV16 infection was considered as fair (k = 0.361) for OC. Our data suggest that the involvement of HPV16 in oral carcinogenesis is limited.

| S-EPMC7072384 | biostudies-literature

Accuracy of autofluorescence in diagnosing oral squamous cell carcinoma and oral potentially malignant disorders: a comparative study with aero-digestive lesions.

Project description:Presently, various studies had investigated the accuracy of autofluorescence in diagnosing oral squamous cell carcinoma (OSCC) and oral potentially malignant disorders (OPMD) with diverse conclusions. This study aimed to assess its accuracy for OSCC and OPMD and to investigate its applicability in general dental practice. After a comprehensive literature search, a meta-analysis was conducted to calculate the pooled diagnostic indexes of autofluorescence for premalignant lesions (PML) and malignant lesions (ML) of the oral cavity, lung, esophagus, stomach and colorectum and to compute indexes regarding the detection of OSCC aided by algorithms. Besides, a u test was performed. Twenty-four studies detecting OSCC and OPMD in 2761 lesions were included. This demonstrated that the overall accuracy of autofluorescence for OSCC and OPMD was superior to PML and ML of the lung, esophagus and stomach, slightly inferior to the colorectum. Additionally, the sensitivity and specificity for OSCC and OPMD were 0.89 and 0.8, respectively. Furthermore, the specificity could be remarkably improved by additional algorithms. With relatively high accuracy, autofluorescence could be potentially applied as an adjunct for early diagnosis of OSCC and OPMD. Moreover, approaches such as algorithms could enhance its specificity to ensure its efficacy in primary care.

| S-EPMC4945954 | biostudies-literature

Differentiating malignant and benign eyelid lesions using deep learning.

Project description:Artificial intelligence as a screening tool for eyelid lesions will be helpful for early diagnosis of eyelid malignancies and proper decision-making. This study aimed to evaluate the performance of a deep learning model in differentiating eyelid lesions using clinical eyelid photographs in comparison with human ophthalmologists. We included 4954 photographs from 928 patients in this retrospective cross-sectional study. Images were classified into three categories: malignant lesion, benign lesion, and no lesion. Two pre-trained convolutional neural network (CNN) models, DenseNet-161 and EfficientNetV2-M architectures, were fine-tuned to classify images into three or two (malignant versus benign) categories. For a ternary classification, the mean diagnostic accuracies of the CNNs were 82.1% and 83.0% using DenseNet-161 and EfficientNetV2-M, respectively, which were inferior to those of the nine clinicians (87.0-89.5%). For the binary classification, the mean accuracies were 87.5% and 92.5% using DenseNet-161 and EfficientNetV2-M models, which was similar to that of the clinicians (85.8-90.0%). The mean AUC of the two CNN models was 0.908 and 0.950, respectively. Gradient-weighted class activation map successfully highlighted the eyelid tumors on clinical photographs. Deep learning models showed a promising performance in discriminating malignant versus benign eyelid lesions on clinical photographs, reaching the level of human observers.

| S-EPMC10011394 | biostudies-literature

Leptin receptor polymorphism Gln223Arg (rs1137101) in oral squamous cell carcinoma and potentially malignant oral lesions.

Project description:The purpose of this study was to assess the LEPR gene Gln223Arg polymorphism (rs1137101) in oral squamous cell carcinoma (OSCC) and in potentially malignant oral lesions (PMOL) in comparison to normal oral mucosa in a Brazilian population. Smokers (n?=?89) were selected from a representative sample of 471 individuals from the general population of Montes Claros, Brazil. Participants were age and gender matched to patients with OSCC (n?=?25) and oral epithelial dysplasia (n?=?25). We investigated the LEPR Gln223Arg polymorphism (A>G; rs1137101) in these groups. Genotype variants were assessed by RFLP-PCR, using MspI (HPAII) restriction endonuclease. The institutional review board of the Universidade Estadual de Montes Claros approved the study (process number 2667/2011). Written informed consent for this study was obtained from all participants. The GG genotype (Arg223Arg) appears to be the more relevant polymorphic variant in OSCC. It occurred, approximately, twice as frequently in OSCC patients than in the general population. In contrast, the A allele in its homozygosis form (Gln223Gln) is significantly associated with the development of PMOL; 80% of the samples from the PMOL group exhibit AA genotype. Our findings suggest new insights regarding LEPR gene variations in the development of OSCC and PMOL.

| S-EPMC4447719 | biostudies-literature

Malignant transformation rate based stratification model for oral potentially malignant disorders: A potential idea.

Project description:By the virtue of heterogeneous biological aggressiveness, oral potentially malignant disorders (OPMDs) comprise the ideal group of disorders for biological behavior-based classification system. Concerning the exponentially increasing incidence and mortality of oral squamous cell carcinoma (OSCC), it has now become a need of the hour to formulate a classification system for OPMDs that even a general dental surgeon could apply in everyday clinical practice. With this view in mind, efforts have been made to stratify various OPMDs based on their malignant transformation rate (MTR). Databases like PubMed, SCOPUS, Web of Science and CINHAL were used for searching the appropriate papers. Preferences were given to meta-analyses and cohort studies for determining the value of MTRs. In other cases, cross-sectional studies, case series and case reports were consulted for obtaining the values. Based on the MTRs obtained, we stratified all the OPMDs into 3 groups: Low risk group (MTR: 0-3%), Moderate risk group (MTR: 4-15%) and High risk group (MTR: above 15%), based on their MTRs available from the literature so far. The idea proposed in the paper can aid researchers and clinicians in identifying and planning treatment strategies that can be generalized to different OPMDs included in the same group. Since the paper is not based on a cohort study or a meta-analysis, the authors recommend a systematic review and meta-analysis to be carried out for a clinically applicable classification based on the proposed idea.

| S-EPMC7452235 | biostudies-literature

Cancer stem cell and its niche in malignant progression of oral potentially malignant disorders.

Project description:ObjectiveThe purpose of this study was to determine association between cancer stem cells (CSCs) and their niche with progression of oral potentially malignant disorders.Materials and methodsPatients with histologically confirmed oral potentially malignant disorders, stratified into high/low risk lesions based on the degree of dysplasia and oral cancer were included in this study. Immunohistochemical profiling of markers of CSCs (CD44), endothelial cells (CD31) and CSC-vascular niche cross-talk (CXCR4 and SDF1) were carried out. Statistical analysis was performed to correlate the relationship of markers with histopathology grade (ANOVA, and χ2 test, unpaired t test) using GraphPad InStat v3.06.ResultsThe study included 550 samples (349 patients) and analysis showed progressive increase in expression levels of CSC and its niche markers with increase in grade of dysplasia as compared to the normal cohort (p < 0.05). Co-expression analysis revealed that, in comparison to the normal cohort, a larger percentage of patients showed increased expression of CD31 and CD44 (CD31high/CD44high; p < 0.05) and of CXCR4 and SDF1 (CXCR4high/SDF1high; p = 0.04), suggesting an association of the CSCs and the vascular niche. Further, distribution of patients with CD44high/CXCR4high (p < 0.05) and CD31high/SDF1high (p = 0.01) was significantly increased in the high-risk group (18%), suggesting a correlation between CD44+/CXCR4+ cells, the vascular niche and progression of oral dysplastic lesions.ConclusionThe increased expression of CSCs, the vascular niche and their cross talk markers are associated with increase in severity of dysplasia suggesting their role in the progression of oral potentially malignant disorders and may hence be used in identifying high-risk OPMD.

| S-EPMC5880641 | biostudies-literature

Validation of a Point-of-Care Optical Coherence Tomography Device with Machine Learning Algorithm for Detection of Oral Potentially Malignant and Malignant Lesions.

Project description:Non-invasive strategies that can identify oral malignant and dysplastic oral potentially-malignant lesions (OPML) are necessary in cancer screening and long-term surveillance. Optical coherence tomography (OCT) can be a rapid, real time and non-invasive imaging method for frequent patient surveillance. Here, we report the validation of a portable, robust OCT device in 232 patients (lesions: 347) in different clinical settings. The device deployed with algorithm-based automated diagnosis, showed efficacy in delineation of oral benign and normal (n = 151), OPML (n = 121), and malignant lesions (n = 75) in community and tertiary care settings. This study showed that OCT images analyzed by automated image processing algorithm could distinguish the dysplastic-OPML and malignant lesions with a sensitivity of 95% and 93%, respectively. Furthermore, we explored the ability of multiple (n = 14) artificial neural network (ANN) based feature extraction techniques for delineation high grade-OPML (moderate/severe dysplasia). The support vector machine (SVM) model built over ANN, delineated high-grade dysplasia with sensitivity of 83%, which in turn, can be employed to triage patients for tertiary care. The study provides evidence towards the utility of the robust and low-cost OCT instrument as a point-of-care device in resource-constrained settings and the potential clinical application of device in screening and surveillance of oral cancer.

| S-EPMC8304149 | biostudies-literature

OmicsDI is part of the ELIXIR infrastructure

OmicsDI is an Elixir interoperability service. Learn more ›

Tweets

OmicsDI Databases

PRIDE
PeptideAtlas
MassIVE
JPOST Repository
Physiome Model Repository

EGA
EVA
ENA
LINCS
PAXDB
Cell Collective

MetaboLights
Metabolomics Workbench
MetabolomeExpress
GNPS
BioModels
FAIRDOMHub

ArrayExpress
dbGaP
ExpressionAtlas
GEO
NODE

Information

Databases
Help
API
Contact us
Code on GitHub
Terms of use
Submit Data