Journal of Oral Pathology & Medicine

Current Issue Highlights

EffiSegNet: Advances in Automated Segmentation of Actinic Cheilitis and Lip Squamous Cell Carcinoma in Clinical Photographs
October 2026: 55(9):1073-1080
Background
Actinic cheilitis (AC) is a potentially malignant oral disorder linked to lip squamous cell carcinoma (LSCC). Clinical diagnosis is hindered by lesion heterogeneity. While AI tools have shown promise in oral lesion detection and diagnosis, image segmentation remains underexplored. This study developed and externally validated a deep learning segmentation model for digital photographs of lip lesions.
Methods
A total of 489 clinical photographs from one institution were used for training/internal testing, and 82 external images from two independent institutions (UFPB and UFMG) served as external validation. EffiSegNet‑B0 used Image Net‑pretrained EfficientNet‑B0 encoder, with stage features aggregated via Ghost Modules. Manual segmentation masks comprised the clinically affected lip region and were used as ground truth. Performance was assessed using accuracy, sensitivity (recall), precision, Dice Similarity Coefficient (DSC) and intersection over union (IoU).
Results
The model achieved high accuracy (> 95%) on both internal and external datasets. DSCs were 0.888 (95% CI: 0.871–0.904) for internal test and 0.875 (95% CI: 0.862–0.888) for external validation, while IoU values were 0.802 (95% CI: 0.777–0.828) and 0.782 (95% CI: 0.763–0.801), respectively. No performance decline was observed on external validation data. The model remained robust to lesion variations (ulceration, crusting, and keratinization).
Conclusion
EffiSegNet-B0 demonstrated high accuracy and adaptability in segmenting lip lesions, reinforcing its potential for clinical image analysis applications. The proposed model generalizes well across different institutions and lesion phenotypes, consistently extracting the complete region of interest. This proof-of-concept study supports its promise as a tool for automated lip lesion segmentation in heterogeneous clinical settings.
Correlation Between Prognostic Indicators, HPV Status, and Cancer Stem Cell Markers in a Population of Human Tongue Carcinomas
October 2026: 55(9):1065-1072
Background
Oral squamous cell carcinoma (OSCC) is a significant public health issue. While tobacco and alcohol are established risk factors, the role of human papillomavirus (HPV) in oral carcinogenesis remains debated. Cancer stem cells (CSCs) are implicated in tumor aggressiveness and therapy resistance. This study investigated the correlation between HPV infection, CSC marker expression (CD44, CD98, ALDH1), and clinicopathological parameters in tongue SCCs.
Methods
A retrospective cohort of 1047 OSCC cases (2013–2018) was reviewed. From 452 tongue SCCs, 83 formalin-fixed paraffin-embedded specimens were randomly selected. HPV DNA detection was performed using qPCR with generic and type-specific primers (HPV 6, 11, 16, 18). Immunohistochemical expression of CD44, CD98, and ALDH1 was evaluated and quantified using digital image analysis (IHC Profiler). Statistical analyses included Kaplan–Meier survival curves, Kruskal-Wallis, Chi-square, and Spearman correlation tests.
Results
HPV DNA was detected in 2/83 cases (2.4%): one HPV16-positive and one with co-infection (HPV6/18). CD44 expression was ubiquitously high, with no significant difference between -High and -Positive categories (p > 0.9999), but both were significantly higher than -Low and -Negative scores (p < 0.0001). ALDH1 exhibited a focal staining pattern. The ALDH1-High score was significantly less frequent than -Positive and -Low scores (p < 0.01) and showed a significant positive correlation with both advanced clinical stage (Spearman r: 0.5062; p = 0.0007) and higher tumor grade (Spearman r: 0.3352; p = 0.0322). CD98 was not detected. An inverse correlation was observed between HPV and clinical staging (Spearman r: −0.2377; p = 0.0305); however, due to the low number of HPV-positive cases, this finding must be interpreted with caution.
Conclusion
Our findings suggest a distinct CSC expression profile in this cohort, characterized by ubiquitous CD44 expression and a rare but highly aggressive ALDH1-High subpopulation, concomitant with low HPV detection. The strong positive correlation of ALDH1-High score with advanced stage and grade highlights its potential role as a key driver of tumor aggression, warranting further investigation as a prognostic marker.
Biocompatibility and Antifungal Effects of Chitosan Nanoparticles Loaded With Nystatin and Carvacrol Against Candida albicans
October 2026: 55(9):1052-1064
Background
Nanocarrier-based drug delivery systems enable the co-administration of antifungal agents, enhancing pharmacological efficacy and creating synergistic effects. This study aimed to evaluate the biocompatibility and antifungal properties of chitosan nanoparticles co-loaded with nystatin and carvacrol against Candida albicans.
Methods
Chitosan nanoparticles were synthesized and loaded with nystatin and carvacrol. Their antifungal activity was evaluated by determining the minimum inhibitory concentration (MIC) and checkerboard synergy assays, while antibiofilm activity was measured using a microtiter plate crystal violet assay. Biocompatibility was assessed through hemolysis testing of human red blood cells (HRBCs) and MTT cytotoxicity assays on human foreskin fibroblasts (HFF).
Results
The nanoparticles exhibited an average hydrodynamic diameter of 70 ± 1.2 nm with favorable polydispersity (0.21 ± 0.03). The MIC of co-loaded nanoparticles was significantly lower than that of single-drug loaded nanoparticles, and checkerboard assays confirmed strong synergy (FICI 0.16–0.5). Sub-MIC concentrations markedly reduced biofilm formation. At 1000 μg/mL, drug-loaded nanoparticles induced < 5% hemolysis, compared with 15.7% ± 2.7% for blank chitosan nanoparticles. HFF cell viability exceeded 90% across concentrations up to 1000 μg/mL at 24–72 h.
Conclusion
Co-loading nystatin and carvacrol into chitosan nanoparticles yielded a synergistic antifungal and antibiofilm effect against C. albicans, coupled with excellent hemocompatibility and minimal cytotoxicity, highlighting its potential as a topical therapeutic for oral candidiasis particularly where resistance to azoles is rising. Further in vivo studies are warranted.
Micronucleus Frequency Test in Epithelial Cells Desquamated From the Oral Mucosa of Patients With Fanconi Anemia
October 2026: 55(9):1045-1051
Background
Fanconi anemia (FA) is a rare genetic disorder predisposing patients to oral squamous cell carcinoma (OSCC). Hematopoietic stem cell transplantation (HSCT) corrects bone marrow failure but may increase the risk of malignancies. Exfoliative cytology and the micronucleus (MN) test provide noninvasive assessment of genomic instability.
Objective
To compare relative frequency of micronuclei (RFMN) in intact mucosa and OPMD lesions in FA patients, and to evaluate its correlation with time post-HSCT.
Methods
Forty-six FA patients were included: Group 1 (FA without HSCT, n = 14), Group 2 (FA post-HSCT without OPMD, n = 13), and Group 3 (FA post-HSCT with OPMD, n = 19). Exfoliative cytology samples were collected from buccal mucosa and OPMD lesions. MNs were manually counted to calculate RFMN. Nonparametric tests were applied to compare groups and the Wilcoxon signed-rank test for intraindividual comparisons. Spearman's correlation and linear regression were used to evaluate associations with age and time.
Results
RFMN in OPMD lesions (Group 3) was significantly higher than in the integrous mucosa of the same patients (median 8 MN/1000 cells, IQR 4–13; ~3.7-fold increase; p = 0.001). No significant differences were observed between Groups 1 and 2 in integrous mucosa. RFMN in integrous mucosa positively correlated with time post-HSCT (ρ = 0.694, p < 0.001), independent of age and GVHD presence.
Conclusion
FA patients, particularly post-HSCT with OPMD, exhibited markedly increased genomic instability. RFMN increases over time, including time post-HSCT, emphasizing the need for vigilant long-term oral monitoring in this high-risk population.
TMD Symptom Characteristics and Their Four-Dimensional Impact on Oral Health-Related Quality of Life
October 2026: 55(9):1034-1044
Background
This study examined how temporomandibular disorder (TMD) symptoms impact the four dimensions of Oral Health-related Quality of Life (OHRQoL) and identified symptom determinants contributing to high jaw disability and low OHRQoL.
Methods
Participants with pain-related (PT), intra-articular (IT), and combined TMD (CT) symptoms completed the Five TMD Symptoms-4D Screener, Jaw Functional Limitation Scale-8, and Oral Health Impact Profile for TMDs. TMD symptoms and impact were each assessed in four dimensions: duration-S1, frequency-S2, intensity-S3, and interference-S4; oral function-I1, orofacial pain-I2, orofacial esthetics-I3, and psychosocial impact-I4. Data were analyzed using the chi-squared test, nonparametric methods, and logistic regression (α = 0.05).
Results
Among the 272 participants (mean age 31.3 years), 5.5%, 18.0%, and 76.5% had PT, IT, and CT symptoms, respectively. Significant differences in global TMD severity (CT > IT/PT), duration (IT > CT > PT), frequency (IT > CT > PT), intensity (IT/CT > PT), jaw disability (PT/CT > IT), and global OHIP (PT/CT > IT) scores were observed. Additionally, significant differences were identified in I1 (CT > IT), I2 (PT/CT > IT), and I4 (PT/CT > IT) dimensions. Symptom-impact dimension correlations varied based on the type of TMD symptoms. PT, CT, and S4 were significantly associated with both high jaw functional limitation and low OHRQoL (ORs = 3.78–47.06).
Conclusions
TMD pain and symptom interference were key determinants of reduced OHRQoL, underscoring the need for symptom-specific assessment and individualized care.