Pablo Agustin Vargas

Plasmablastic lymphoma (PBL) is an aggressive neoplasm in which MYC rearrangements are frequent, whereas concurrent BCL2 and/or BCL6 rearrangements are poorly characterized. We investigated MYC , BCL2 and BCL6 rearrangements in a Brazilian series of oral PBL. Thirty cases were confirmed morphologically and immunophenotypically; 23 were evaluable for fluorescence in situ hybridization. MYC rearrangement was detected in 56.5% of the cases. Three tumors harbored concurrent MYC / BCL2 rearrangements and one harbored MYC / BCL2 / BCL6 rearrangements (17.3%). Targeted review of the available sections from these four cases showed no evidence of residual low-grade B-cell lymphoma, follicular architecture, or morphologically distinct component suggesting transformation. These findings expand the cytogenetic spectrum of oral PBL, highlighting some molecular overlap with other high-grade B-cell lymphomas.

Objective: To report an uncommon case of oral chemical burn caused by occupational exposure to potassium hydroxide (KOH) managed with photobiomodulation (PBM). Case Report: A 50‐year‐old man experienced occupational exposure to KOH while working in a food factory. The accident occurred during maintenance of a pipeline that should have been empty; however, it was still carrying a 50% KOH solution. The patient presented with severe pain and impaired speech, nutrition, and hydration due to the extent of the lesions. Clinical examination revealed diffuse ulcerations affecting the lower labial semimucosa, upper and lower labial mucosa, and dorsal tongue. A clinical diagnosis of KOH‐induced chemical burn was established, and daily PBM therapy was initiated using red (660 nm) and infrared (850 nm) light‐emitting diodes (LEDs) to provide pain control and promote mucosal repair. Rapid improvement of signs and symptoms was observed throughout treatment, with complete mucosal healing achieved after eight sessions of PBM. Conclusion: This report describes, to the best of our knowledge, the first documented case of oral burn caused by KOH in an occupational setting, highlighting the severity of alkali‐induced lesions and the therapeutic potential of PBM therapy.

Purpose: To assess the diagnostic accuracy of Artificial Intelligence as a Medical Device (AIaMD) for cancer classification in clinical settings, according to the PIRT framework? Participants: adults with solid malignant neoplasms of the skin and/or mucosas; Index test: AIaMD; Comparator: conventional unassisted diagnostic methods; Reference standard: histopathology and/or clinical diagnosis; Target condition: skin and mucosal cancer. Methods: Following PRISMA-DTA guidelines, a systematic search of six electronic databases and grey literature was conducted for studies published before 30 March 2026. The protocol was registered in PROSPERO (CRD42025634932). Diagnostic performance metrics (sensitivity and specificity) were extracted or estimated from contingency tables. QUADAS-2 was used to evaluate risk of bias and applicability concerns. Meta-analysis was performed using a bivariate binomial generalized linear mixed model; heterogeneity was assessed with τ2 and 95% prediction intervals, and paired comparison and meta-regression for subgroup analysis were performed. Certainty of evidence was assessed using GRADE-DTA. Results: Among 25,080 retrieved records, 24 studies were included. Overall, 83.3% of the studies were prospective, and 87.5% were related to skin cancer. The meta-analysis included 17 studies for AIaMD and 9 for unassisted clinicians. Findings revealed a pooled sensitivity of 0.893 (95% CI 0.818–0.940, τ2: 1.32) and specificity of 0.749 (95% CI 0.586–0.862, τ2: 2.38) for AIaMD, compared to sensitivity of 0.849 (95% CI 0.751–0.913, τ2: 0.620) and specificity of 0.777 (95% CI 0.624–0.880, τ2: 1.22) for clinicians. In eight paired studies, there was no significant difference in sensitivity (p = 0.74) or specificity (p = 0.85). Twenty-three of 24 (95.8%) studies had at least one domain at high risk of bias after QUADAS-2 evaluation, while GRADE-DTA indicated overall very low certainty of evidence. Conclusions: AIaMD performance was represented by high sensitivity but lower and highly variable specificity. Although clinically relevant differences cannot be excluded, AIaMD demonstrated no statistically significant differences in paired comparisons when compared to clinicians. Nonetheless, methodological limitations, factors influencing bias and applicability, and very low certainty of evidence warrant cautious interpretation and further research before real-world implementation.

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.

Objectives: This study aimed to investigate the clinicopathological features of malignant odontogenic tumors (MOTs) and to provide a comprehensive characterization that enhances the current understanding of this disease group. Methods: MOTs were retrieved from six Brazilian oral pathology services between 2007 and 2025. Demographic, clinical and radiographic data were collected from the charts, and the histological H&E-stained sections were revised by two blinded pathologists; previously available immunohistochemical and molecular findings were retrieved and reviewed in selected cases and the diagnosis was established according to the 2022 World Health Organization classification. Results: A total of 53 malignant odontogenic tumors were identified, predominantly affecting the mandible (83%), with a slight male predominance (male-to-female ratio, 1.12:1) and a mean age of 41.4 years. Ameloblastic carcinoma was the most frequent subtype (58.5%), followed by clear cell odontogenic carcinoma (18.9%), ameloblastic fibrosarcoma (13.2%), primary intraosseous carcinoma (7.5%), and ghost cell odontogenic carcinoma (1.9%). Conclusions: This multicenter review summarizes the main features of malignant odontogenic tumors. Although rare, these tumors often exhibit locally aggressive behavior, highlighting the need for early diagnosis, accurate histopathological evaluation, and standardized reporting with long-term follow-up.

Objective: To evaluate the efficacy of prophylactic photobiomodulation therapy (PBMT) in preventing oral mucositis (OM) and to assess serum and salivary methotrexate (MTX) levels as predictors of OM in adults receiving high‐dose methotrexate (HD‐MTX). Methods: This phase II randomized, double‐blind, placebo‐controlled trial enrolled adults with hematological malignancies undergoing a first HD‐MTX cycle at a tertiary cancer center in Brazil. Participants were randomized to PBMT or sham laser therapy, administered daily until MTX clearance or for up to five sessions. OM was assessed for 9 days using WHO criteria. Serum and salivary MTX concentrations were measured at 24, 48, and 72 h post‐infusion, along with urinary pH and serum creatinine. Results: Fifty‐three patients were randomized (PBMT n = 26; placebo n = 27). PBMT significantly reduced ulcerative OM (grade ≥ 2) at 96 h (11.5% vs. 51.9%), yielding a 77.7% relative risk reduction and a number needed to treat of 2 ( p < 0.01). Placebo recipients had an 8.97‐fold higher odds of severe OM. Serum MTX was not associated with OM, whereas salivary MTX increased disproportionately over time and independently correlated with OM severity. Conclusions: PBMT significantly reduced OM incidence and severity in adults receiving HD‐MTX. Salivary MTX is a promising non‐invasive biomarker for OM risk. Trial Registration: Trial was prospectively registered in the Brazilian Registry of Clinical Trials (ReBec, No. 12218)

Background: Peripheral nerve sheath tumors (PNSTs) of the head and neck (H&N) show histopathological overlap. Although convolutional neural networks (CNNs) have demonstrated feasibility in soft tissue tumor classification, limited intra-class variability related to perineurioma remains a critical constraint for rare tumor subtypes. Methods: This retrospective diagnostic accuracy study with internal validation included 30 patients diagnosed with PNSTs. Whole-slide images were digitized at 20× magnification and partitioned using a strict patient-wise split. Synthetic perineurioma patches were generated using a modified Pix2Pix-based Generative Adversarial Network (GAN) incorporating a bottleneck architecture and self-attention modules. Two morphology-driven augmentation strategies were evaluated: (1) intra-phenotypic expansion by cross-patient patch pairing within the sclerosing subtype and (2) inter-phenotypic interpolation by cross-phenotype patch pairing between sclerosing and intraneural variants. EfficientNetV2-B0 pre-trained on ImageNet was trained under three configurations: original dataset only, original + Experiment A synthetic patches, and original + Experiment B synthetic patches. All performance metrics were computed exclusively on an independent yet internal test set composed of original images. Results: GAN-based augmentation improved global classification performance compared with the baseline model trained on original images only (accuracy 0.733). Intra-phenotypic expansion increased accuracy to 0.767 and achieved the highest balanced accuracy (0.750) and macro-F1 (0.740). Inter-phenotypic interpolation yielded the highest overall accuracy and competitive multiclass agreement metrics. Perineurioma recall improved from 0.34 (baseline) to 0.51 with intra-phenotypic augmentation and 0.47 with inter-phenotypic interpolation, while specificity remained ≥ 0.999 across all strategies. Conclusions: Structured, pathology-informed GAN augmentation improved CNN classification of PNSTs, particularly for the morphologically heterogeneous perineurioma class. Intra-phenotypic expansion primarily improved rare-class sensitivity, whereas inter-phenotypic interpolation improved multiclass agreement and global robustness. These findings support morphology-driven synthetic enrichment as a clinically meaningful strategy to improve AI performance in underrepresented tumor entities and potentially support diagnostic decision-making in digital pathology environments.

Recurrent aphthous stomatitis is a common inflammatory condition of the oral mucosa characterized by painful ulcers that heal spontaneously but recur unpre