Browse
Submit Data
Databases
API
Help

Dataset Information

34 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

Machine learning in point-of-care automated classification of oral potentially malignant and malignant disorders: a systematic review and meta-analysis.

Project description:Machine learning (ML) algorithms are becoming increasingly pervasive in the domains of medical diagnostics and prognostication, afforded by complex deep learning architectures that overcome the limitations of manual feature extraction. In this systematic review and meta-analysis, we provide an update on current progress of ML algorithms in point-of-care (POC) automated diagnostic classification systems for lesions of the oral cavity. Studies reporting performance metrics on ML algorithms used in automatic classification of oral regions of interest were identified and screened by 2 independent reviewers from 4 databases. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed. 35 studies were suitable for qualitative synthesis, and 31 for quantitative analysis. Outcomes were assessed using a bivariate random-effects model following an assessment of bias and heterogeneity. 4 distinct methodologies were identified for POC diagnosis: (1) clinical photography; (2) optical imaging; (3) thermal imaging; (4) analysis of volatile organic compounds. Estimated AUROC across all studies was 0.935, and no difference in performance was identified between methodologies. We discuss the various classical and modern approaches to ML employed within identified studies, and highlight issues that will need to be addressed for implementation of automated classification systems in screening and early detection.

| S-EPMC9376104 | biostudies-literature

Field validation of deep learning based Point-of-Care device for early detection of oral malignant and potentially malignant disorders.

Project description:Early detection of oral cancer in low-resource settings necessitates a Point-of-Care screening tool that empowers Frontline-Health-Workers (FHW). This study was conducted to validate the accuracy of Convolutional-Neural-Network (CNN) enabled m(mobile)-Health device deployed with FHWs for delineation of suspicious oral lesions (malignant/potentially-malignant disorders). The effectiveness of the device was tested in tertiary-care hospitals and low-resource settings in India. The subjects were screened independently, either by FHWs alone or along with specialists. All the subjects were also remotely evaluated by oral cancer specialist/s. The program screened 5025 subjects (Images: 32,128) with 95% (n = 4728) having telediagnosis. Among the 16% (n = 752) assessed by onsite specialists, 20% (n = 102) underwent biopsy. Simple and complex CNN were integrated into the mobile phone and cloud respectively. The onsite specialist diagnosis showed a high sensitivity (94%), when compared to histology, while telediagnosis showed high accuracy in comparison with onsite specialists (sensitivity: 95%; specificity: 84%). FHWs, however, when compared with telediagnosis, identified suspicious lesions with less sensitivity (60%). Phone integrated, CNN (MobileNet) accurately delineated lesions (n = 1416; sensitivity: 82%) and Cloud-based CNN (VGG19) had higher accuracy (sensitivity: 87%) with tele-diagnosis as reference standard. The results of the study suggest that an automated mHealth-enabled, dual-image system is a useful triaging tool and empowers FHWs for oral cancer screening in low-resource settings.

| S-EPMC9395355 | 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

Dentists' Perception of Oral Potentially Malignant Disorders.

Project description:ObjectivesDentists play a major role in the diagnosis of oral potentially malignant disorders (OPMDs) that may lead to malignancy. Their knowledge on OPMDs and the risk factors associated with malignant disease needs to be sufficient. The aim of this study was to assess the level of knowledge, attitudes, and awareness of OPMDs amongst general dentists and dental specialists working in Saudi Arabia.Material and methodsQuestionnaires were distributed to dentists working in Saudi Arabia. A total of 303 dentists participated in the study. The questionnaire included 20 questions on knowledge, attitudes, and awareness of OPMDs.ResultsThe response rate was 55%. There was no significant difference between general dental practitioners and dental specialists regarding leukoplakia, which is the most common OPMD (P > .05) and in identifying tobacco and alcohol as the main risk factors for malignant transformation of OPMDs into cancer (P > .05). However, there was a significant difference (P < .05) between specialists (75.3%) and general practitioners (52.3%) in the diagnosis of OPMDs. There was a significant difference (P < .05) between specialists (63.5%) and general practitioners (28.0%) in recognising the likelihood of malignant transformation of proliferative verrucous leukoplakia. There was a significant difference between specialists (61.2%) and general practitioners (25.2%, P < .05) in recognising the erosive form or atrophic type of oral lichen planus, considering that it is more likely to undergo malignant transformation.ConclusionsDental specialists have better knowledge and awareness than general dentists regarding OPMDs. Improved continuous education programmes on the risk factors and diagnosis of OPMDs should be organised to train dentists.

| S-EPMC9275301 | 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

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

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

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