Jeconias Câmara

O granuloma piogênico é uma lesão reacional benigna, não neoplásica, caracterizada por intensa proliferação vascular, geralmente associada a irritação local, trauma ou alterações hormonais. Clinicamente, apresenta-se como massa avermelhada, de superfície lisa ou lobulada, com sangramento fácil, sendo mais comum na gengiva. Possui maior incidência em mulheres, especialmente durante a gestação, quando é denominado granuloma gravídico. Este estudo teve como objetivo relatar um caso clínico de granuloma gravídico atendido na Atividade Curricular de Extensão de Estomatologia da Faculdade de Odontologia da Universidade Federal do Amazonas (UFAM), aprovado pelo CEP-UFAM (CAAE nº 89933825.6.0000.5020). Paciente do sexo feminino, 25 anos, apresentou lesão exofítica na papila gengival vestibular entre os dentes 31 e 41, assintomática, com sangramento espontâneo e evolução de aproximadamente um ano. Relatou aumento da lesão durante a gestação, sem regressão após o parto. Ao exame clínico, observou-se lesão pediculada, avermelhada, firme, indolor, medindo cerca de 16 × 11 mm, associada à presença de biofilme, cálculos dentários, gengiva edemaciada e apinhamento dentário. O exame radiográfico evidenciou cálculos dentários e discreta reabsorção horizontal da crista alveolar. A hipótese diagnóstica de granuloma gravídico foi estabelecida e realizada biópsia excisional. O exame histopatológico confirmou o diagnóstico. Após dez meses de acompanhamento, a paciente permanece sem sinais de recidiva.

Objective: This study aimed to evaluate the coherence between data heterogeneity and model complexity by comparing seven convolutional neural network (CNN) architectures—trained with and without ImageNet pretraining—in a multiclass framework for the histopathological classification of three odontogenic tumors: adenomatoid odontogenic tumor, ameloblastoma, and ameloblastic carcinoma. The goal was to investigate how transfer learning influences performance and diagnostic reliability in a clinically relevant context characterized by overlapping histological patterns. Methods: An international, multicenter cross-sectional dataset of 64 hematoxylin- and eosin-stained whole slide images was analyzed, including adenomatoid odontogenic tumor ( n = 16), ameloblastoma ( n = 27), and ameloblastic carcinoma ( n = 21). Seven CNN models (DenseNet121, EfficientNetV2B0, InceptionV3, MobileNet, ResNet50, VGG16, and Xception) were trained and tested on 455,107 patches (224 × 224 pixels). Performance was assessed using accuracy, balanced accuracy, sensitivity, specificity, F1-score, and AUC. Results: Without ImageNet pretraining, DenseNet121 achieved the highest performance (accuracy = 0.73, balanced accuracy = 0.74, AUC = 0.78, specificity = 0.84, sensitivity = 0.65), followed by EfficientNetV2B0 (accuracy = 0.67, balanced accuracy = 0.68, sensitivity = 0.54). When ImageNet pretraining was applied, performance improved across all architectures. EfficientNetV2B0 reached the best overall results (accuracy = 0.79, balanced accuracy = 0.81, AUC = 0.91, specificity = 0.88, sensitivity = 0.74), while DenseNet121 maintained consistent performance (accuracy = 0.72, balanced accuracy = 0.74, AUC = 0.85, specificity = 0.84, sensitivity = 0.64). Conclusion: Transfer learning with ImageNet weights enhanced the performance of most CNNs, with EfficientNetV2B0 showing the greatest responsiveness to pretraining and DenseNet121 demonstrating intrinsic robustness to initialization. These results highlight the potential of CNN-based frameworks to support the differential diagnosis of odontogenic tumors—an inherently challenging task due to morphological overlap—while establishing reproducible methodological baselines that contribute to the global development of explainable, ensemble-based, and clinically reliable AI systems in oral pathology.

A 16-year-old male patient exhibited a nodular lesion measuring 5.0 centimeters in its greatest diameter in the right parotid gland. This lesion had been present for a period of two years, without any associated symptoms. Upon palpation, the lesion was characterized as demarcated, firm, and painless. The patient underwent surgical excision, and the initial hypothesis was that the lesion was a pleomorphic adenoma (PA). Microscopically, the tumor exhibited a variable growth pattern between cribriform and micropapillary areas, with neoplastic cells positive for mammaglobin, S-100, and Pan-Trk. Immunohistochemistry was employed to substantiate the diagnosis of secretory carcinoma (SC). Two years following the surgical intervention, no signs of recurrence or complications have been observed. Although rare, secretory carcinoma (SC) in pediatric patients has been documented in the literature and can mimic benign neoplasms due to its mild characteristics.

Proliferative verrucous leukoplakia (PVL) is an aggressive and distinct oral disorder with a high potential for malignant transformation (MT). It presents as multifocal lesions that progress over time and frequently recur, often developing carcinomas. Accurately diagnosing PVL is crucial to distinguish it from other oral mucosa lesions that have a lower risk of cancer progression. However, due to the diverse histological features observed in PVL, identifying clinical criteria and histological patterns that can be applied by unfamiliar professionals is challenging. In this study, we present a case of PVL associated with dysplasia in a 53‐year‐old female patient. The patient exhibited macular and leukoplakic nonscrapable lesions disseminated throughout the oral cavity, with continuous growth. The diagnosis of PVL was established during an 18‐month follow‐up. This case highlights the difficulties faced by both clinicians and pathologists in diagnosing PVL, emphasizing the need for careful evaluation and accurate diagnosis, particularly in patients with unusual oral lesions, and highlighting the discrepancies observed in the application of available protocols to our particular case. Distinguishing PVL from similar conditions can be challenging due to overlapping clinical signs and indistinct histopathological features.

Objectives This multicenter study aimed to evaluate cases of non-syndrome and syndromic odontogenic keratocyst, as well as cases of recurrence within these two groups. Methods This descriptive, analytical, retrospective cross-sectional study evaluated the sex, age and presence of multiple lesions in 1,169 individuals seen at 10 Brazilian oral and maxillofacial pathology centers. Of these, 1,341 odontogenic keratocysts were analyzed regarding clinical diagnosis, size, site, imaging appearance, signs and symptoms, type of biopsy, treatment, and recurrence. Results There was a similar distribution by sex. The median age of non-syndromic and syndromic patients was 32 and 17.5 years, respectively. The posterior mandible was the site most affected by small and large lesions in both groups and in recurrent cases. Unilocular lesions were more frequent, also in recurrent cases. Mainly small lesions showed this imaging appearance. Signs and symptoms were absent in most cases. Conservative treatment was the most frequent modality in all age groups, regardless of the patient’s condition and recurrence. Recurrences were uncommon. Conclusion This study showed a higher frequency of non-syndromic keratocysts in the population. Clinicopathological features related to the involvement of multiple sites, age, and recurrence may differ between syndromic and non-syndromic cases. Furthermore, we found an association between lesion size and some clinical features and between the time interval to recurrence and the syndromic spectrum. Clinical relevance To contribute to a better understanding of the distribution and association between clinical, imaging, and sociodemographic characteristics in each spectrum of the lesion.

Background: Odontogenic tumors (OT) are composed of heterogeneous lesions, which can be benign or malignant, with different behavior and histology. Within this classification, ameloblastoma and ameloblastic carcinoma (AC) represent a diagnostic challenge in daily histopathological practice due to their similar characteristics and the limitations that incisional biopsies represent. From these premises, we wanted to test the usefulness of models based on artificial intelligence (AI) in the field of oral and maxillofacial pathology for differential diagnosis. The main advantages of integrating Machine Learning (ML) with microscopic and radiographic imaging is the ability to significantly reduce intra‐and inter observer variability and improve diagnostic objectivity and reproducibility.Methods: Thirty Digitized slides were collected from different diagnostic centers of oral pathology in Brazil. After performing manual annotation in the region of interest, the images were segmented and fragmented into small patches. In the supervised learning methodology for image classification, three models (ResNet50, DenseNet, and VGG16) were focus of investigation to provide the probability of an image being classified as class0 (i.e., ameloblastoma) or class1 (i.e., Ameloblastic carcinoma).Results: The training and validation metrics did not show convergence, characterizing overfitting. However, the test results were satisfactory, with an average for ResNet50 of 0.75, 0.71, 0.84, 0.65, and 0.77 for accuracy, precision, sensitivity, specificity, and F1‐score, respectively.Conclusions: The models demonstrated a strong potential of learning, but lack of generalization ability. The models learn fast, reaching a training accuracy of 98%. The evaluation process showed instability in validation; however, acceptable performance in the testing process, which may be due to the small data set. This first investigation opens an opportunity for expanding collaboration to incorporate more complementary data; as well as, developing and evaluating new alternative models.

Salivary gland neoplasms are usually uncommon and range from 2% to 6.5% of tumors that affect the head and neck region. It is possible to say that the approach to this topic is challenging, since they have a low incidence, creating determining factors for the execution of the retrospective study, such as the place of incidence, the histological type and the form of treatment. However, due to advances in laboratory techniques, it was possible to record new categories of lesions, which promoted heterogeneity and updates to the 4th WHO classification on salivary gland tumors. This fact makes it possible to adapt the best clinical management for the treatment of these lesions. The objective of the present research was to verify the epidemiological profile of benign lesions of the major and minor salivary glands through epidemiological studies obtained in the survey and the epidemiology of the national and world literature.