Oral epithelial dysplasia: Classifications and clinical relevance in risk assessment of oral potentially malignant disorders

Ranganathan, Kannan; Kavitha, Loganathan

doi:10.4103/jomfp.jomfp_13_19

Cited by 138 publications

(43 citation statements)

References 96 publications

(149 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The presence and grade of oral epithelial dysplasia (OED) are currently the gold standard marker of MT 1,8–10 . However, prognosticating OL remains a challenge because of the limitations of OED 11,12 . Many would agree that some degree of subjectivity is involved in OED grading based on experience, medical and social history, or even particular histological features that one may believe to be preponderant over others.…”

Section: Introductionmentioning

confidence: 99%

“…1,[8][9][10] However, prognosticating OL remains a challenge because of the limitations of OED. 11,12 Many would agree that some degree of subjectivity is involved in OED grading based on experience, medical and social history, or even particular histological features that one may believe to be preponderant over others. Such subjectivity may constitute an important element of bias in the lack of reproducibility of OED as a biomarker of MT.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Oral epithelial dysplasia grading: Comparing the binary system to the traditional 3‐tier system, an actuarial study with malignant transformation as outcome

Sperandio

Warnakulasuriya

Soares

et al. 2022

J Oral Pathology Medicine

View full text Add to dashboard Cite

Background: Establishing the risk of malignant transformation (MT) in oral leukoplakia is usually based on grading oral epithelial dysplasia (OED) on biopsy tissue, for which two systems are proposed: a 3-tier and a binary system. Only very few actuarial studies have tested the accuracy of such methods in predicting MT, especially for the binary system. This study aimed to assess the accuracy of the two grading systems in predicting MT in a cohort of oral leukoplakia (OL) from Brazil, with follow-up data. Methods:The sample comprised 878 individuals diagnosed with OL from 2005 to 2018. Follow-up data were obtained both locally and from the regional cancer registry. All lesions were graded using both the 3-tier and the binary systems. Kaplan-Meier curves (Log-rank Mantel-Cox) were used to assess risk and kappa to assess interobserver agreement.Results: Thirty-five individuals underwent MT (4%). Both systems demonstrated prognostic value, though the 3-tier system proved superior, with OR 9.23 (3.42-23.69), PPV 0.152, NPV 0.98, compared to binary OR 3.49 (1.79-6.79), PPV 0.079, NPV 0.976. Interobserver agreement was also superior in the 3-tier system (0.47, p < 0.05) compared to the binary system (0.139, p = 0.39). Combining the two systems enhanced prognostic values (OR 14.28, PPV 0.217, NPV 0.981). Conclusion:The 3-tier system presented superior prognostic value to the binary system. Combining both systems to double-grade intermediate lesions might enhance risk assessment.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Oral epithelial dysplasia grading: Comparing the binary system to the traditional 3‐tier system, an actuarial study with malignant transformation as outcome

Sperandio

Warnakulasuriya

Soares

et al. 2022

J Oral Pathology Medicine

View full text Add to dashboard Cite

show abstract

“…The proper assessment of cytological and architectural criteria aims to provide an objective OED grading, but studies report interobserver agreement among 62% and 90% 15,27 . The authors acknowledge that support systems for OED grading should overcome this percentage but particularities in the data curation and the investigated disorders should be considered.…”

Section: Discussionmentioning

confidence: 99%

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

Araújo,

Silva,

Moraes

et al. 2023

J Oral Pathology Medicine

View full text Add to dashboard Cite

BackgroundDysplasia grading systems for oral epithelial dysplasia are a source of disagreement among pathologists. Therefore, machine learning approaches are being developed to mitigate this issue.MethodsThis 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.ResultsThe 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.ConclusionThe 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).

show abstract

“…Oral SCCs are commonly well or moderately differentiated, and poorly differentiated cases are much less [1]. It was recently proposed that the characteristics of oral carcinogenesis differ from those of carcinogenesis of the uterine cervix or esophagus because oral SCC retains the maturation and differentiation characteristics of the stratified squamous epithelium [15][16][17]. It is thus reasonable to consider that the characteristics of oral LEC should be distinguished from LECs occurring at other sites.…”

Section: Discussionmentioning

confidence: 99%

A Case Report of Tongue Lymphoepithelial Carcinoma with a Histological Diagnostic Dilemma

et al. 2021

View full text Add to dashboard Cite

Most head and neck lymphoepithelial carcinomas (LECs) arise in the nasopharynx and harbor Epstein–Barr virus (EBV). LEC is also a rare subtype of the oral squamous cell carcinoma (SCC). Morphologically, LEC is defined as resembling non-keratinizing nasopharyngeal carcinoma, undifferentiated subtype. The histological features and pathogenesis of oral LEC are not established. We describe a case of tongue LEC with histopathological diagnostic difficulties. A 72-year-old Japanese female presented with a whitish change on her left-side tongue. The diagnosis was atypical epithelium; neoplastic change could not be ruled out by a biopsy. Although the lesion was monitored at our hospital per her request, invasive carcinoma was detected 11 months later. Microscopically, conventional SCC was observed with the characteristic features as LEC confined to the deep part of the lesion. We briefly discuss this unusual histological finding and make a novel proposal for distinguishing oral LEC from LECs in other regions based on these histological findings.

show abstract

Oral epithelial dysplasia: Classifications and clinical relevance in risk assessment of oral potentially malignant disorders

Cited by 138 publications

References 96 publications

Oral epithelial dysplasia grading: Comparing the binary system to the traditional 3‐tier system, an actuarial study with malignant transformation as outcome

Oral epithelial dysplasia grading: Comparing the binary system to the traditional 3‐tier system, an actuarial study with malignant transformation as outcome

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

A Case Report of Tongue Lymphoepithelial Carcinoma with a Histological Diagnostic Dilemma

Contact Info

Product

Resources

About