Objectives: Oral potentially malignant disorders may present as white, red, or mixed red-white lesions and require accurate early recognition. This study evaluated whether texture-analysis features extracted from clinical digital images could distinguish oral precancerous lesions from other oral mucosal lesions and normal mucosa using gray-level co-occurrence matrix (GLCM), gray-level run-length matrix (GLRLM), and wavelet analysis. Materials and Methods: Sixty-four clinical digital images were selected according to predefined inclusion and exclusion criteria. The dataset included leukoplakia, erythroplakia, oral submucous fibrosis, candidiasis, lichen planus, leukoderma, frictional keratosis, white spongy nevus, and normal mucosa. Regions of interest were extracted from each image, and texture features were derived using GLCM, GLRLM, and wavelet analysis. A support vector machine (SVM) classifier was then used to categorize images as oral precancerous lesions or non-precancerous/normal mucosa. Results: GLCM yielded the highest classification accuracy (88%), followed by GLRLM (81%) and wavelet analysis (79%). The corresponding sensitivity values were 77%, 64%, and 60%, and the specificity values were 93%, 90%, and 89%, respectively. The positive predictive values were 83% for GLCM, 75% for GLRLM, and 75% for wavelet analysis. Conclusion: GLCM-based texture features provided the best diagnostic performance in this dataset. These image-analysis methods may be useful as non-invasive adjuncts to conventional clinical examination and histopathological diagnosis; however, larger datasets and external validation are required before clinical implementation.

This study evaluated the efficacy of chitosan hydrogel with nanoencapsulated imiquimod 0.05% as a chemopreventive agent in an oral carcinogenesis model. Forty male rats were randomly assigned to four groups. Control (no treatment; n = 10); Hg (treatment with chitosan hydrogel; n = 10); Hgimq (treatment with hydrogel containing non-encapsulated imiquimod 0.05%; n = 10); HgNCimq (treatment with hydrogel developed with polymeric nanocapsules containing imiquimod at a concentration of 0.05%; n = 10). Carcinogenesis induction was performed using a 7,12-dimethylbenz[a]anthracene solution at a concentration of 0.5%. The treatment with the hydrogels was performed according to the groups. Compared with free imiquimod (Hgimq), nanoencapsulated imiquimod (HgNCimq) demonstrated superior chemopreventive efficacy. In the oral mucosa, HgNCimq completely prevented squamous cell carcinoma development and increased the proportion of animals without histopathological alterations (35% vs. 15%), while reducing epithelial dysplasia (5% vs. 50%) (p = 0.00). In the perioral skin, HgNCimq preserved normal histology in 80% of the animals compared with 55% in the Hgimq group (p = 0.03), supporting the enhanced therapeutic performance achieved through nanoencapsulation. In conclusion, this study demonstrated the promising potential of employing a nanotechnological hydrogel in preventing oral carcinogenesis.

Recently, the WHO 5th edition has modified the new architectural and cytological features for the diagnosis of oral epithelial dysplasia (OED). However, the correlation of these histopathological features with malignant transformation (MT) and recurrence (RE) of the lesions remains controversial. There is no study investigated the association between architectural and cytological features of the 5th WHO criteria with a reliable diagnostic marker for MT in OED. Therefore, this study aimed to correlate the 5th edition WHO histopathological diagnostic criteria of OED with the immunohistochemical expression of CK13/CK17, one of reliable diagnostic markers for MT in OED. A total of 32 samples of leukoplakia, erythroplakia, and erythroleukoplakia which histologically proved OED were included in the study. The specimens were graded according to 5th edition WHO criteria and categorized as 15 mild OED and 17 moderate to severe OED. The architectural and cytological features from the 5th WHO diagnostic criteria for OED were collected. The CK13/CK17 immunohistochemistry was performed. The CK13 and CK17 expression was graded semi-quantitatively. The association between architectural and cytological features with CK13/CK17 immunohistochemical expression and with histopathological diagnosis were analyzed. Eight histopathological features: irregular epithelial stratification, reduced keratinocyte cohesion, abnormal variation in nuclear size and shape, abnormal variation in cell size and shape, single cell keratinization and increased nuclear size were significantly correlated with CK13 weak/CK17 strong expression pattern and the diagnosis of moderate to severe OED (p < 0.05). Larger samples are required to enhance the accuracy in the diagnosis and prediction in the OED lesions.

Background: Oral potentially malignant disorders (OPMDs) have a complex, but not consistently consistent, risk of transformation to oral squamous cell carcinoma (OSCC). The histopathologic grading of dysplasia is the traditional means of prognosis although there is considerable inter-observer variability and the tool has poor predictive value. Thus, image-based AI-based methods such as computational pathomics (CP), clinical-photograph deep learning (CDL), and optical or spectroscopic image analysis via machine learning (ML) or deep learning (DL) have been proposed as potential non-invasive risk stratification methods. Aim of the review is to identify the current state of the evidence for AI applications in the field of image-based diagnosis and treatment of OPMDs, their methodological characteristics and predictive accuracy, and priorities for future research. Methods: the scoping review was conducted using Joanna Briggs Institute methodology and PRISMA-ScR guidelines. The PubMed/MEDLINE, Scopus, Web of Science and Embase databases were searched between January 2018 and March 2026. Inclusion criteria were studies that used quantitative image analysis, ML or DL to diagnose, prognosticate, or stratify risk of OPMD in OPMD cohorts. A pre-piloted form was used to extract data which were then synthesized descriptively. Results: the 423 records identified included 24 (16 primary image-based studies and 8 contextual reviews) that met the inclusion criteria. The majority of studies were retrospective (15/16), and computational pathomics (n = 10), clinical-photograph deep learning and optical/spectroscopic imaging (n = 4) were emphasized. There was no study that used the conventional radiologic radiomics (CT, MRI, CBCT, or PET/CT) in OPMD cohorts. Overall, predictive performance was good, with AUROC values ranging from 0.73 to 0.96 for the detection of malignant transformation, 0.94 to 0.97 for OPMD versus OSCC discrimination, and 0.90 to 0.97 for dysplasia grading. Only 44% contained external validation, only 6% were prospective, and only limited adherence was made to IBSI, TRIPOD-AI and CLAIM standards. Conclusions: AI-based image recognition for OPMDs shows good predictive performance, and it has yet to be developed to a mature stage of the process. Future multicentre study, image standardisation, external validation and better reporting standards are needed. Remarkably, radiologic radiomics is an important and unexplored research gap in OPMD risk prediction.

Oral leukoplakia (OL) is a potentially malignant lesion, but only a proportion of cases undergo transformation to carcinoma (7.2% to 9.5%). The aim of this study was to analyze the possible differences and the role of immune cells in homogeneous and non-homogeneous OL at different grades of dysplasia. The infiltration density of T and B lymphocytes, macrophages, plasma cells, and cells expressing CD9 antigen was assessed semi-quantitatively in 50 OL cases using a 4-point scale-score 1 (<5%), score 2 (6-10%), score 3 (11-15%) and score 4 (16-20%)-via manual counting by two morphologists. Both clinical types of OL that showed dysplasia had noticeably higher proportions of CD138+ and CD68+ immune cells. Statistical analysis confirmed that only non-homogeneous OL with dysplasia showed an increase in the infiltration density of CD3+ and CD20+ lymphocytes. There was a statistically significant moderate positive correlation between the amount of CD9+ cells in the lamina propria and the number of labeled epithelial layers in OL of different thicknesses. Expression of CD138 and CD9 proteins in epithelial and connective tissue cells in OL indicates active epithelial-mesenchymal interaction during the premalignant stage of OL, but the expression of these markers in epithelial and immune cells was completely the opposite. The evaluation of CD3, CD20, CD9, CD138, and CD68 antigen expression, particularly in non-homogeneous leukoplakia, improves the accuracy of malignancy risk assessment in patients with dysplasia.

Oral leukoplakia (OLK) is the most prevalent oral precancerous lesion, with its occurrence and progression linked to local irritants and systemic factors. Among these, chronic inflammatory microenvironment significantly promotes OLK. Conventional drug treatments have notable limitations and a high recurrence risk, underscoring the urgent need to identify reliable molecular markers and to develop effective, safe targeted therapies for OLK. This study identified abnormal overexpression of scavenger receptor A (SR-A) in the oral mucosal epithelium of patients with OLK, and low molecular weight fucoidan (LMWF) induces apoptosis in human oral precancerous lesion cells (dysplastic oral keratinocyte [DOK]) and inhibits their growth and activity. Further analyses confirmed that LMWF binds to SR-A with a binding energy of -4.4 kcal/mol through non-covalent interactions, forming a thermally stable structure. In vivo experiments showed that LMWF alleviates the pathological severity of OLK in rat models of OLK by targeting SR-A. Immunohistochemical staining showed that interleukin-1 (IL-1), transforming growth factor beta (TGF-β), protein kinase B (AKT), and Fos proto-oncogene (FOS) levels were higher in the model group; LMWF can still inhibit the expression of inflammatory cytokines to a certain extent after SR-A knockdown. Additionally, LMWF modulated IL-1, TGF-β, JUN, and FOS, thereby affecting the MAPK signaling pathway. Major histocompatibility complex class II (MHC-II) was identified as the downstream target of LMWF binding to SR-A. In summary, LMWF inhibits OLK progression by targeting SR-A to modulate the MAPK/MHC-II signaling axis and the associated genes, offering a new theoretical foundation for the development of targeted therapies for OLK.