Feasibility study of ResNet-50 in the distinction of intraoral neural tumors using histopathological images.

BACKGROUND: Neural tumors are difficult to distinguish based solely on cellularity and often require immunohistochemical staining to aid in identifying the cell lineage. This article investigates the potential of a Convolutional Neural Network for the histopathological classification of the three most prevalent benign neural tumor types: neurofibroma, perineurioma, and schwannoma. METHODS: A model was developed, trained, and evaluated for classification using the ResNet-50 architecture, with a database of 30 whole-slide images stained in hematoxylin and eosin (106, 782 patches were generated from and divided among the training, validation, and testing subsets, with strategies to avoid data leakage). RESULTS: The model achieved an accuracy of 70% (64% normalized), and showed satisfactory results for differentiating two of the three classes, reaching approximately 97% and 77% as true positives for neurofibroma and schwannoma classes, respectively, and only 7% for perineurioma class. The AUROC curves for neurofibroma and schwannoma classes was 0.83%, and 0.74% for perineurioma. However, the specificity rate for the perineurioma class was greater (83%) than in the other two classes (neurofibroma with 61%, and schwannoma with 60%). CONCLUSION: This investigation demonstrated significant potential for proficient performance with a limitation regarding the perineurioma class (the limited feature variability observed contributed to a lower performance).

Relationship between aggressive features of oral squamous cell carcinoma and the immunoexpression of CX3CR1, CX3CL1 and ITGAV.

OBJECTIVE: We aimed to describe the association between CX3CR1, CX3CL1, and ITGAV immunoexpression with PNI and adverse oncologic outcomes in patients with OSCC. STUDY DESIGN: Expression CX3CR1, CX3CL1, and ITGAV was assessed by immunohistochemistry in a cohort of 50 paraffin-embedded resections of OSCC. Survival analysis, Cox, and binary logistic regressions were undertaken to determine the impact on patient survival and predictive value for PNI. RESULTS: CX3CL1 positive nerves exhibited a significant association with tumor budding (TB) (P = .043), whereas nerves positive for ITGAV were associated with PNI (P = .021), T3-T4 tumor size (P = .029), and III-IV stage (P = .044). Cases with ITGAV-positive nerves exhibited an odds ratio of 9.603 (P = .008) for PNI, whereas cases with CX3CL1-positive nerves exhibited and odds ratio of 4.682 (P = .033) for TB. A trend toward decreased 5-year overall survival (P = .078) and 5-year disease-specific survival (P = .09) was observed in relation to ITGAV-positive nerves. However, no independent predictors for poor survival were identified. CONCLUSIONS: The expression of ITGAV was associated with PNI and advanced disease, whereas the expression of CX3CL1 was related to TB, suggesting that ITGAV and CX3CL1 are involved in their respective developments. Therefore, further investigations are encouraged to assess the potential utility of targeted therapies against CX3CL1 receptors in OSCC.

Artificial intelligence and radiomics in the diagnosis of intraosseous lesions of the gnathic bones: A systematic review.

BACKGROUND: The purpose of this systematic review (SR) is to gather evidence on the use of machine learning (ML) models in the diagnosis of intraosseous lesions in gnathic bones and to analyze the reliability, impact, and usefulness of such models. This SR was performed in accordance with the PRISMA 2022 guidelines and was registered in the PROSPERO database (CRD42022379298). METHODS: The acronym PICOS was used to structure the inquiry-focused review question "Is Artificial Intelligence reliable for the diagnosis of intraosseous lesions in gnathic bones?" The literature search was conducted in various electronic databases, including PubMed, Embase, Scopus, Cochrane Library, Web of Science, Lilacs, IEEE Xplore, and Gray Literature (Google Scholar and ProQuest). Risk of bias assessment was performed using PROBAST, and the results were synthesized by considering the task and sampling strategy of the dataset. RESULTS: Twenty-six studies were included (21 146 radiographic images). Ameloblastomas, odontogenic keratocysts, dentigerous cysts, and periapical cysts were the most frequently investigated lesions. According to TRIPOD, most studies were classified as type 2 (randomly divided). The F1 score was presented in only 13 studies, which provided the metrics for 20 trials, with a mean of 0.71 (±0.25). CONCLUSION: There is no conclusive evidence to support the usefulness of ML-based models in the detection, segmentation, and classification of intraosseous lesions in gnathic bones for routine clinical application. The lack of detail about data sampling, the lack of a comprehensive set of metrics for training and validation, and the absence of external testing limit experiments and hinder proper evaluation of model performance.

Barriers to early diagnosis and management of oral cancer in Latin America and the Caribbean.

OBJECTIVE: This study aimed to explore perceived barriers to early diagnosis and management of oral cancer, as well as potential pathways for improvement in Latin America and the Caribbean (LAC). METHODS: This cross-sectional study used a self-administered online questionnaire created via the Research Electronic Data Capture platform. The survey was distributed to health professionals trained in Oral Medicine, Oral Pathology, Oral and Maxillofacial Surgery, and Dentists with clinical and academic expertise in oral potentially malignant disorder (OPMD) and oral cancer. Data obtained were systematically organized and analyzed descriptively using Microsoft Excel. RESULTS: Twenty-three professionals from 21 LAC countries participated. Major barriers included the limited implementation of OPMD and oral cancer control plans (17.4%), low compulsory reporting for OPMD (8.7%) and oral cancer (34.8%), unclear referral pathways for OPMD (34.8%) and oral cancer (43.5%), and a shortage of trained professionals (8.7%). Participants endorsed the utility of online education (100%) and telemedicine (91.3%). CONCLUSION: The survey highlights major perceived barriers to early diagnosis and management of OPMD and oral cancer in LAC, as well as potential avenues for improvement.

Malignant tumors affecting the head and neck region in ancient times: Comprehensive study of the CRAB Database.

In the modern world, cancer is a growing cause of mortality, but archeological studies have shown that it is not exclusive to modern populations. The aim of this study is to examine the epidemiologic, social, and clinicopathologic features of head and neck cancers in ancient populations. To do this, we extracted all records that described malignant lesions in the head and neck region available in the Cancer Research in Ancient Bodies Database (CRAB). The estimated age, sex, physical condition of the remains (skeletonized, mummified), anatomic location of tumors, geographic location, chronology, tumor type, and methods of tumor diagnosis were collected. One hundred and sixty-seven cases were found, mostly originating from Europe (51.5%). Most records were of adults between 35 and 49 years of age (37.7%). The most involved site was the skullcap (60.4%), and the most common malignancies were metastases to the bone (65.3%) and multiple myeloma (17.4%). No primary soft tissue malignancies were registered. The results of our study indicate that head and neck cancers were present in ancient civilizations, at least since 500,000 BCE. The available data can help to improve the current understanding of the global distribution of head and neck cancer and its multidimensional impacts on populations in the contemporary world.

Medication-related osteonecrosis in torus palatinus: Report of a case and literature review.

BACKGROUND: Medication-related osteonecrosis of the jaw bones have been frequently reported. However, its occurrence in torus palatinus is very rare with only 10 cases published in the English-language literature. CASE REPORT: We describe an additional case in a 79-year-old woman, who was referred for evaluation of a painful swelling with areas of suppuration on the hard palate. CONCLUSION: Conservative treatment was performed and after spontaneous sequestrectomy, total healing was achieved.

Malignant tumors affecting the head and neck region in ancient times: Comprehensive study of the CRAB Database

Abstract In the modern world, cancer is a growing cause of mortality, but archeological studies have shown that it is not exclusive to modern populations. The aim of this study is to examine the epidemiologic, social, and clinicopathologic features of head and neck cancers in ancient populations. To do this, we extracted all records that described malignant lesions in the head and neck region available in the Cancer Research in Ancient Bodies Database (CRAB). The estimated age, sex, physical condition of the remains (skeletonized, mummified), anatomic location of tumors, geographic location, chronology, tumor type, and methods of tumor diagnosis were collected. One hundred and sixty-seven cases were found, mostly originating from Europe (51.5%). Most records were of adults between 35 and 49 years of age (37.7%). The most involved site was the skullcap (60.4%), and the most common malignancies were metastases to the bone (65.3%) and multiple myeloma (17.4%). No primary soft tissue malignancies were registered. The results of our study indicate that head and neck cancers were present in ancient civilizations, at least since 500,000 BCE. The available data can help to improve the current understanding of the global distribution of head and neck cancer and its multidimensional impacts on populations in the contemporary world.

Oral manifestations of amyloidosis and the diagnostic applicability of oral tissue biopsy.

BACKGROUND: Amyloidosis exhibits a variable spectrum of systemic signs and oral manifestations that can be difficult to diagnose. This study aimed to characterize the clinical, demographic, and microscopic features of amyloidosis in the oral cavity. METHODS: This collaborative study involved three Brazilian oral pathology centers and described cases with a confirmed diagnosis of amyloidosis on available oral tissue biopsies. Clinical data were obtained from medical records. H&E, Congo-red, and immunohistochemically stained slides were analyzed. RESULTS: Twenty-six oral biopsies from 23 individuals (65.2% males; mean age: 59.6 years) were included. Oral involvement was the first sign of the disease in 67.0% of cases. Two patients had no clinical manifestation in the oral mucosa, although the histological analysis confirmed amyloid deposition. Amyloid deposits were distributed in perivascular (88.0%), periacinar and periductal (80.0%), perineurial (80.0%), endoneurial (33.3%), perimuscular (88.2%), intramuscular (94.1%), and subepithelial (35.3%) sites as well as around fat cells (100.0%). Mild/moderate inflammation was found in 65.4% of cases and 23.1% had giant cells. CONCLUSIONS: Amyloid deposits were consistently found in oral tissues, exhibiting distinct deposition patterns. Oral biopsy is less invasive than internal organ biopsy and enables the reliable identification of amyloid deposits even in the absence of oral manifestations. These findings corroborate the relevance of oral biopsy for the diagnosis of amyloidosis.

Contribution of public oral pathology services to the diagnosis of oral and oropharyngeal cancer in Brazil.

This study aimed to evaluate the contribution of oral and maxillofacial pathology laboratories (OMPLs) in Brazilian public universities to the diagnosis of lip, oral cavity, and oropharyngeal squamous cell carcinoma (SCC). A cross-sectional study was performed using biopsy records from a consortium of sixteen public OMPLs from all regions of Brazil (North, Northeast, Central-West, Southeast, and South). Clinical and demographic data of patients diagnosed with lip, oral cavity, and oropharyngeal SCC between 2010 and 2019 were collected from the patients' histopathological records. Of the 120,010 oral and maxillofacial biopsies (2010-2019), 6.9% (8,321 cases) were diagnosed as lip (0.8%, 951 cases), oral cavity (4.9%, 5,971 cases), and oropharyngeal (1.2%, 1,399 cases) SCCs. Most cases were from Brazil's Southeast (64.5%), where six of the OMPLs analyzed are located. The predominant profile of patients with lip and oral cavity SCC was Caucasian men, with a mean age over 60 years, low schooling level, and a previous history of heavy tobacco consumption. In the oropharyngeal group, the majority were non-Caucasian men, with a mean age under 60 years, had a low education level, and were former/current tobacco and alcohol users. According to data from the Brazilian National Cancer Institute, approximately 9.9% of the total lip, oral cavity, and oropharyngeal SCCs reported over the last decade in Brazil may have been diagnosed at the OMPLs included in the current study. Therefore, this data confirms the contribution of public OMPLs with respect to the important diagnostic support they provide to the oral healthcare services extended by the Brazilian Public Health System.

Oral squamous cell carcinomas and oral potentially malignant disorders: A Latin American study.

OBJECTIVE: To determine the frequency of oral squamous cell carcinoma (OSCC) associated or not with oral potentially malignant disorders (OPMD), and the epidemiological profile and traditional risk factors in Latin America. METHODS: A retrospective observational study was conducted in 17 Latin American centres. There were included cases of OSCC, analysing age, gender, OSCC and their association with previous OPMD. Clinicopathological variables were retrieved. The condition of sequential-OSCC versus OSCC-de novo (OSCC-dn) was analysed concerning the aforementioned variables. Quantitative variables were analysed using Student's t-test, and qualitative variables with chi-square. RESULTS: In total, 2705 OSCC were included with a mean age of 62.8 years old. 55.8% were men. 53.75% of the patients were smokers and 38% were common drinkers. The lateral tongue border was the most affected site (24.65%). There were regional variations in OPMD, being leukoplakia the most frequent. Of the overall 2705 OSCC cases, 81.4% corresponded to OSCC-dn, while s-OSCC were 18.6%. Regarding lip vermillion SCC, 35.7% corresponded to de novo lip SCC and 64.3% were associated with previous OPMD. CONCLUSIONS: In Latin America, OSCC-dn seems to be more frequent with regional variations of some clinical and histopathological features. Further prospective studies are needed to analyse this phenomenon.

Clinicopathological Features of Metastasis to the Oral and Maxillofacial Region-Multicenter Study.

BACKGROUND: This study aimed to investigate the clinicopathological features of metastases in the oral and maxillofacial regions. METHODS: In this retrospective study, biopsy records were obtained from referral centers for oral and maxillofacial diagnosis in Brazil, Guatemala, Mexico, and South Africa. RESULTS: A total of 120 cases were evaluated. Of these, 53.78% affected female patients, with a mean age of 57.64 years. Intraosseous lesions were more frequent, particularly in the posterior region of the mandible (49.58%). Clinically, most cases presented with symptomatic swelling, with an average evolution time of 25 months. The clinical diagnostic hypothesis in most instances was that of a malignant lesion. Breast cancer was the most common primary tumor location in females, while lung origin was most common in males. In most cases, the primary cancer was an adenocarcinoma (44.73%). The follow-up period was available for 29 cases, and out of these, 20 had died due to the disease. CONCLUSION: Although this is a rare condition, clinicians should be aware that any oral lesions have the possibility of being metastatic, particularly in individuals with a previous history of cancer. The findings from this study could assist clinicians in prompt diagnosing these lesions and subsequent conducting oncologic assessments and treatment.

A primary oral mucosal melanoma of the hard palate with no recurrence: Report of a 10 years follow-up.

BACKGROUND: Primary oral mucosal melanoma (OMM) represents an extremely rare and aggressive tumor that arises from malignant transformation and clonal expansion of melanocytes in the oral cavity. The prognosis of patients affected by OMM is quite unfavorable, with survival rates lower than those described for patients with cutaneous melanoma. CASE REPORT: Here, we report a case of OMM in a 59-year-old Caucasian woman, who was referred for evaluation of a large asymptomatic pigmented lesion on the left side of the hard palate under the removable total denture. Incisional biopsy was performed, and histopathological analysis revealed the proliferation of spindle-shaped and pigmented epithelioid cells, with cellular pleomorphism. These cells were positive for Melan A, S-100, HMB-45, SOX-10, and Ki-67 confirming the diagnosis of OMM. The patient underwent partial maxillectomy and adjuvant radiotherapy. After treatment, she was rehabilitated with a palatal obturator prosthesis and has been in follow-up for 10 years with no evidence of disease. Due to the rarity in the oral cavity and the nonspecific signs and symptoms, the diagnosis of OMM is difficult and often overlooked. CONCLUSION: Therefore, multidisciplinary management from diagnosis, treatment, and rehabilitation is important to increase the expectation of cure.

Human Papillomavirus-Associated Oral Epithelial Dysplasia: Report of 5 Illustrative Cases from Latin America.

BACKGROUND: Human papillomavirus-associated oral epithelial dysplasia (HPV-OED) is a distinct oral epithelial disorder characterized by viral cytopathic changes caused by transcriptionally active high-risk HPV. The aim of the present study was to report 5 additional cases from Latin America. METHODS: Clinical data from five patients with HPV-OED were obtained from the archives of three oral pathology services from Brazil and Chile. All cases were submitted to morphological, p16 expression and in situ hybridization (ISH) for HPV analyses. RESULTS: Four patients were male and one patient was female, with a mean age of 55.4 years. Four patients were HIV seropositive and two were smokers. Three cases affected the buccal mucosa and commissure, one of which had an additional plaque in the soft palate, and one case each occurred on the floor of mouth and lower labial mucosa. Most cases presented as well-demarcated white plaques with a verrucous surface. One case presented multiple lesions ranging from normal to white-colored slightly elevated plaques with a cobblestone surface. Peripheral mucosal pigmentation was observed in two cases. All five cases presented with the characteristic microscopic features of HPV-OED, including severe dysplasia with numerous karyorrhectic and apoptotic cells, full-thickness "block positivity" for p16 and high Ki-67 index (> 90%) sharply demarcated from the adjacent non-dysplastic epithelium. Wide-spectrum DNA ISH-HPV was positive in 4 cases. All patients were treated with conservative surgical excision with no signs of recurrence after a mean of 39-month follow-up. CONCLUSION: This represents the first series of HPV-OED from Latin America; most cases presented as well-demarcated papillary white plaques affecting the buccal mucosa and commissure of HIV-positive middle-aged men, two of them exhibiting peripheral pigmentation caused by reactive melanocytes. The typical microscopic findings of HPV-OED were observed in all cases, which also showed strong p16 positivity in a continuous band through the full thickness of the epithelium and high Ki67.

Deep learning applied to the histopathological diagnosis of ameloblastomas and ameloblastic carcinomas.

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.

The use of deep learning state-of-the-art architectures for oral epithelial dysplasia grading: A comparative appraisal.

BACKGROUND: Dysplasia grading systems for oral epithelial dysplasia are a source of disagreement among pathologists. Therefore, machine learning approaches are being developed to mitigate this issue. METHODS: This cross-sectional study included a cohort of 82 patients with oral potentially malignant disorders and correspondent 98 hematoxylin and eosin-stained whole slide images with biopsied-proven dysplasia. All whole-slide images were manually annotated based on the binary system for oral epithelial dysplasia. The annotated regions of interest were segmented and fragmented into small patches and non-randomly sampled into training/validation and test subsets. The training/validation data were color augmented, resulting in a total of 81,786 patches for training. The held-out independent test set enrolled a total of 4,486 patches. Seven state-of-the-art convolutional neural networks were trained, validated, and tested with the same dataset. RESULTS: The models presented a high learning rate, yet very low generalization potential. At the model development, VGG16 performed the best, but with massive overfitting. In the test set, VGG16 presented the best accuracy, sensitivity, specificity, and area under the curve (62%, 62%, 66%, and 65%, respectively), associated with the higher loss among all Convolutional Neural Networks (CNNs) tested. EfficientB0 has comparable metrics and the lowest loss among all convolutional neural networks, being a great candidate for further studies. CONCLUSION: The models were not able to generalize enough to be applied in real-life datasets due to an overlapping of features between the two classes (i.e., high risk and low risk of malignization).