Abstract
To the Editor:
After carefully reading the article by Adeoye et al. (2024), we would like to point out the suitability and usefulness of the deep learning system as a predictor of epithelial dysplasia (ED) in oral leukoplakia (OL).
ED is not a clinical disorder like OL. It involves histopathological data, which should qualify and quantify a series of maturational and proliferative alterations in the squamous epithelium of the oral mucosa (Odell et al. 2021; Aguirre-Urizar and Warnakulasuriya 2023).
ED analysis is the “gold standard” in the prognostic assessment of the risk of malignant development of OL. For the evaluation and grading of ED, from 1 or several biopsy specimens, of an oral potentially malignant disorder (OPMD), it is necessary to analyze its histopathology (Aguirre-Urizar et al. 2021; Warnakulasuriya et al. 2021; Pimenta-Barros et al. 2024). The clinical diagnosis of OL always requires the histopathological diagnosis for 3 main reasons: 1) to confirm the clinical diagnosis of OL, 2) to rule out other oral mucous disorders, and 3) to assess the presence and degree of ED.
I believe the approach of this work starts from an impossible premise, which makes this clinically based methodology unable to reliably diagnose ED. All cases with ED reported in this publication are “nonhomogeneous,” which usually show ED. In contrast, cases without ED were all “homogeneous,” which do not usually show ED.
Unfortunately, and despite being an invasive technique, currently we still do not have any methodology that surpasses the effectiveness of the histopathological study in assessing the risk of malignant development of an OPMD such as OL.
Author Contributions
J.M. Aguirre-Urizar, I. Lafuente-Ibañez de Mendoza, contributed to conception and design, data acquisition, analysis, and interpretation, drafted and critically revised the manuscript. Both authors gave final approval and agree to be accountable for all aspects of the work.
Footnotes
Declaration of Conflicting Interests
The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Funding
The authors received no financial support for the research, authorship, and/or publication of this article.
