Differentially expressed extracellular matrix genes functionally separate ameloblastoma from odontogenic keratocyst.

BACKGROUND: Ameloblastoma and odontogenic keratocyst (OKC) are odontogenic tumors that develop from remnants of odontogenic epithelium. Both display locally invasive growth characteristics and high predilection for recurrence after surgical removal. Most ameloblastomas harbor BRAFV600E mutation while OKCs are associated with PATCH1 gene mutation but distinctive indicators of ameloblastoma growth characteristics relative to OKC are still unclear. The aim of this study was to assess hub genes that underlie ameloblastoma growth characteristics using bioinformatic analysis, ameloblastoma samples and mouse xenografts of human epithelial-derived ameloblastoma cells. METHODS: RNA expression profiles were extracted from GSE186489 gene expression dataset acquired from Gene Expression Ominibus (GEO) database. Galaxy and iDEP online analysis tools were used to identify differentially expressed genes that were further characterized by gene ontology (GO) and pathway analysis using ShineyGO. The protein-protein interaction (PPI) network was constructed for significantly upregulated differentially expressed genes using online database STRING. The PPI network visualization was performed using Cytoscape and hub gene identification with cytoHubba. Top ten nodes were selected using maximum neighborhood component, degree and closeness algorithms and analysis of overlap was performed to confirm the hub genes. Epithelial-derived ameloblastoma cells from conventional ameloblastoma were transplanted into immunocompromised mice to recreate ameloblastoma in vivo based on the mouse xenograft model. The top 3 hub genes FN1, COL I and IGF-1 were validated by immunostaining and quantitative analysis of staining intensities to ameloblastoma, OKC samples and mouse ameloblastoma xenografts tissues. RESULTS: Seven hub genes were identified among which FN1, COL1A1/COL1A2 and IGF-1 are associated with extracellular matrix organization, collagen binding, cell adhesion and cell surface interaction. These were further validated by positive immunoreactivity within the stroma of ameloblastoma samples but both ameloblastoma xenograft and OKC displayed only FN1 and IGF-1 immunoreactivity while COL 1 was unreactive. The expression levels of both FN1 and IGF-1 were much lower in OKC relative to ameloblastoma. CONCLUSION: This study further validates a differentially upregulated expression of matrix proteins FN1, COL I and IGF-1 in ameloblastoma relative to OKC. It suggests that differential stromal architecture and growth characteristics of ameloblastoma relative to OKC could be an interplay of differentially upregulated genes in ameloblastoma.

Exceptional Evolution of a Squamous Odontogenic Tumor in the Jaw: Molecular Approach.

A squamous odontogenic tumor (SOT) is an epithelial locally benign neoplasia derived from the periodontium of the jaws. It is considered a lesion of low incidence. Predominantly, it affects the mandible, although both jaw bones may be involved. Here, we discuss the malignant clinical evolution of an SOT lesion in an 80-year-old female patient. The patient exhibited an expansive triangular lesion at the inferior right quadrant. Surgery was performed and an SOT was diagnosed (2019). Two years after, the lesion grew, and the analysis of the biopsy revealed SOT malignization with pleomorphic atypical squamous cells, characteristics of a squamous cell carcinoma (2021). Massive DNA sequencing of formalin-fixed-paraffin-embedded specimens of the initial and relapsed tumors indicated pathogenic mutations in RET and POLE genes in both tumors, loss of ALK, and gain of CDKN1B and MAP2K in the relapse. In addition, the clinical, radiographic, and microscopic features of this neoplasm are discussed and compared with those already published. The case presented contributes to the better understanding of this SOT tumor entity and to indicates its malignant evolution, together with its biological behavior and its histologic, clinical, and radiographic features. Also, it aims to stress the importance of deeper genetic analyses in rare diseases to uncover mutations that help to select a personalized treatment.

Unicystic ameloblastoma: Clinico-radiological and histopathological correlation with management.

Unicystic ameloblastoma is a distinct entity of ameloblastoma characterized by slow growth and locally aggressive behavior. This retrospective study aimed to assess the efficacy of different treatment modalities of unicystic ameloblastoma, focusing on clinico-radiological and histopathological features. Data from patients diagnosed with unicystic ameloblastoma were retrospectively analyzed. Patients were categorized into luminal and intraluminal (Group A) and mural (Group B) variants based on the Ackermann classification, which has a significant influence on their biological behavior, treatment approaches, and prognosis. Patients in Group A underwent enucleation with chemical cauterization, peripheral ostectomy, and iodoform packing, whereas those in Group B were treated with resection and reconstruction. Post-operatively, the patients were subjected to radiographic assessments via digital orthopantomogram at regular intervals. Because of the rarity of unicystic ameloblastoma, only 17 patients were included in the study (Group A: 9 patients; Group B: 8 patients), with a mean follow-up of 4.9 years (range: 1.4-11.8 years). The primary outcome measure was the absence of recurrence, which indicated treatment success. No patient in either group experienced recurrence within the follow-up period. This study provides evidence supporting the successful treatment of luminal and intraluminal variants of unicystic ameloblastoma in young individuals using a conservative approach. However, the more aggressive mural variant demonstrated favorable outcomes with radical treatment. These findings emphasize the importance of the Ackermann classification in guiding treatment decisions for unicystic ameloblastoma and contribute valuable insights into optimizing therapeutic strategies based on clinico-radiological and histopathological findings.

Factors Associated with Recurrence of Ameloblastoma: A Scoping Review.

PURPOSE: This scoping review aimed to identify factors associated with the recurrence of ameloblastoma. METHODS: Systematic searches were conducted in PubMed, Scopus, and EMBASE, based on the board research question: "What factors are related to the recurrence of ameloblastoma?". English-language observational studies addressing the risk and preventive factors associated with recurrent ameloblastoma were included and data were extracted. RESULTS: Eighty-three retrospective observational studies met the inclusion criteria. The identified prognostic factors for recurrence included: (1) Tumor size/diameter/volume, (2) cortical bone perforation/ soft tissue invasion, (3) multilocular radiolucency, (4) impacted tooth-involving lesions, (5) root resorption, (6) WHO classification - conventional (solid/multicystic) ameloblastoma, (7) histological subtype - mural invasion of unicystic ameloblastoma, (8) conservative treatment modalities - simple enucleation, curettage, and marsupialization, and (9) non-extraction/preservation of involved teeth. No strong evidence linked immunohistochemical expression to recurrence. Interestingly, BRAF p.V600E remained controversial in terms of recurrence, despite being a frequent finding in ameloblastoma. CONCLUSION: Certain clinical characteristics, radiographic findings, histological subtypes, and treatment choices of ameloblastoma can help identify patients at high risk of recurrence. Further prospective studies to evaluate the prognostic factor model and research on immunohistochemistry are required.

Differential Expression of Immunohistochemical Markers in Ameloblastoma & Ameloblastic Carcinoma: A Systematic Review and Meta-analysis of observational studies.

Background: Differentiating between ameloblastoma (AB) and ameloblastic carcinoma (AC) is difficult, especially when AB has atypical cytological characteristics or an uncommon clinical history. This systematic review and meta-analysis aimed to elucidate the differential expression of immunohistochemical markers between AB and AC. Methods: We conducted a thorough search of PUBMED and SCOPUS according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to identify cross-sectional studies that compared the expression of immunohistochemical markers in AB and AC. We used a random-effects model to analyze the risk ratios and their corresponding 95% confidence intervals (CIs). The quality of the included studies was assessed using the Newcastle-Ottawa scale. The Egger's test was used to assess publication bias. Results: In total, 301 articles were identified. After excluding irrelevant titles and abstracts, 86 articles were selected for full-text review. We categorized the 41 markers into proliferative and non-proliferative markers. Among non-proliferative markers, nuclear markers were differentially expressed in AB and AC. SOX2 was the only marker that significantly differentiated AB and AC, with an RR of -0.19 (CI 0.10-0.36, I2=0). Conclusion: The current evidence suggests the significance of SOX2 in differentiating between AB and AC, warranting prospective confirmation in well-defined extensive studies. We highlight the paucity of high-quality replicated studies of other markers in this field. Collaborative efforts with standardized techniques are necessary to generate clinically useful immunohistochemical markers.

Large Peripheral Osteomas and Dental Implants: A Case Report.

Peripheral osteoma of the jaw is a rare, benign, slow-growing lesion, which usually appears as a unilateral, pedunculated, radiopaque mass protruding from the periphery and is generally solitary. Multiple osteomas without any syndromic involvement are rare. In the present case, a 75-year-old male patient underwent implant placement in the edentulous posterior ridges of the maxilla and mandible. Over 7 years, multiple masses gradually proliferated in the buccal bone of the implant in three different sextants of the posterior region, reaching a size of 2.0 cm. Clinically and radiologically, these lesions were presumed to be peripheral osteomas and were surgically removed because the large mass made self-performed oral hygiene and maintenance of peri-implant health difficult. The histopathological evaluation confirmed that peripheral osteomas were both compact and cancellous. The patient did not exhibit any other clinical manifestations of Gardner syndrome. Whether dental implant placement and loading are involved in the occurrence of peripheral osteomas is unclear, but they might have affected the consistent growth of the mass as a reactive mechanism. After resection, the functional abilities of chewing and self-cleansing significantly improved. No recurrence of peripheral osteoma was observed after 1 year of follow-up, and peri-implant health was well maintained. Within the limitations of the present case report, multiple peripheral osteomas can occur adjacent to dental implants without any syndromic issues, and a large mass of PO can harm peri-implant health which requires surgical removal. It is speculated that dental implants may be associated with the slow and consistent growth of PO.

Diagnostic capability of artificial intelligence tools for detecting and classifying odontogenic cysts and tumors: a systematic review and meta-analysis.

OBJECTIVE: To evaluate the diagnostic capability of artificial intelligence (AI) for detecting and classifying odontogenic cysts and tumors, with special emphasis on odontogenic keratocyst (OKC) and ameloblastoma. STUDY DESIGN: Nine electronic databases and the gray literature were examined. Human-based studies using AI algorithms to detect or classify odontogenic cysts and tumors by using panoramic radiographs or CBCT were included. Diagnostic tests were evaluated, and a meta-analysis was performed for classifying OKCs and ameloblastomas. Heterogeneity, risk of bias, and certainty of evidence were evaluated. RESULTS: Twelve studies concluded that AI is a promising tool for the detection and/or classification of lesions, producing high diagnostic test values. Three articles assessed the sensitivity of convolutional neural networks in classifying similar lesions using panoramic radiographs, specifically OKC and ameloblastoma. The accuracy was 0.893 (95% CI 0.832-0.954). AI applied to cone beam computed tomography produced superior accuracy based on only 4 studies. The results revealed heterogeneity in the models used, variations in imaging examinations, and discrepancies in the presentation of metrics. CONCLUSION: AI tools exhibited a relatively high level of accuracy in detecting and classifying OKC and ameloblastoma. Panoramic radiography appears to be an accurate method for AI-based classification of these lesions, albeit with a low level of certainty. The accuracy of CBCT model data appears to be high and promising, although with limited available data.

A radiologic-pathologic study of the histopathologic variants of ameloblastomas and their proliferation indices.

OBJECTIVES: This study aimed to analyze the clinicoradiologic features and Ki-67 proliferation indices between the histopathologic variants of ameloblastomas (ABs) for possible associations. STUDY DESIGN: The diagnosis and histopathologic variant were confirmed for all cases by experienced Oral and Maxillofacial Pathologists. Immunohistochemistry for Ki-67 was performed on the most representative formalin-fixed paraffin-embedded tissue block. Demographic, clinical data and radiologic features were analyzed from patient records and available radiographic examinations. The investigators were blinded to the histopathologic variant and proliferation index when the clinicoradiologic features were assessed. RESULTS: The current study included 116 cases of AB in the final sample. The indolent behavior of the unicystic variant was supported by their low proliferation index and slow growth paired with low frequencies of cortical destruction, loss of teeth, root resorption, and encroachment on anatomical structures. In contrast, the comparatively high proliferation index of the plexiform variant correlated with their fast growth and pain. Furthermore, high radiologic frequencies of cortical destruction, loss of teeth, and encroachment of surrounding anatomical structures supported their more aggressive clinical course. CONCLUSION: Statistically significant differences were noted between certain variants and Ki-67, location, borders, locularity, and cortical destruction, providing better insight into their biological behavior.

Prefabricated Fibula Flap vs Bone-Driven and Delayed Implant Installation for Jaw Reconstruction.

Importance: Restoration of dental occlusion and oral rehabilitation is the ultimate goal of functional jaw reconstruction. Objective: To evaluate the prefabricated fibula flap (PFF) technique in occlusion-driven jaw reconstruction for benign or previously treated malignant disease. Design, Setting, and Participants: This cohort study was conducted from January 2000 to December 2019 at the University of Alberta Hospital and Institute of Reconstructive Sciences in Medicine in Edmonton, Alberta, Canada, among patients who underwent PFF or bone-driven and delayed osseointegrated implant installation (BDD). Patients were followed up for a minimum of 1 year after occlusal rehabilitation. Data were analyzed from July 2021 to June 2022. Exposures: Patients underwent BDD or PFF, which consists of osseointegrated dental implant installation and skin grafting of the fibular bone 3 to 6 months before jaw tumor resection or defect reconstruction. The implant osseointegration is completed at the time of jaw reconstruction, allowing for full reconstruction, loading, and restoration of the dental occlusion in the immediate postoperative period. Main outcomes and Measure: Safety, effectiveness, accuracy, timeliness of occlusal reconstruction, and aesthetic appeal were compared between PFF and BDD. Groups were compared for the following variables: postoperative complications, number of bony segments used, number of procedures needed, total operative time, time to occlusal rehabilitation, and number of implants installed, exposed, lost, and used (ie, exposed implants - lost implants). Aesthetic appeal was assessed using standardized full-face and profile digital photographs taken before and 6 to 12 months after the operation and analyzed by 3 naive raters. Results: Among 9 patients receiving PFF (mean [SD] age, 43.3 [13.0] years; 7 men [77.8%]) and 12 patients receiving BDD (mean [SD] age, 41.9 [18.0] years; 8 men [66.7%]), the overall complication rate was similar (4 patients [44.4%] vs 3 patients [25.0%], respectively; relative risk, 1.78 [95% CI, 0.52 to 6.04]). The number of patients with implant loss was similar between PFF and BDD groups (0 patients vs 3 patients [25.0%], respectively; difference, -25.0 percentage points [95% CI, -48.4 to 9.7 percentage points]). PFF had a clinically meaningful faster mean (SD) occlusal rehabilitation compared with BDD (12.1 [1.9] months vs 60.4 [23.1] months; difference, -48.3 months [95% CI, -64.5 to -32.0 months]). The mean (SD) difference in preoperative to postoperative aesthetic score was similar between PFF and BDD groups (-0.8 [1.5] vs -0.2 [0.8]; difference, -0.6 [95% CI, -1.6 to 0.4]). Conclusions and Relevance: This study found that PFF compared with BDD was a safe, effective, and aesthetic reconstructive option for patients with benign or previously treated jaw malignant tumors. This technique may provide rapid occlusal reconstruction and oral rehabilitation.

Tumor microenvironment of ameloblastoma with a focus on osteoclastogenesis, cell migration, and malignant transformation.

BACKGROUND: Odontogenic tumors arise in the jawbone and originate from cells associated with tooth development. Therefore, understanding odontogenic tumors requires knowledge of all aspects of dental research, including tooth development and eruption. Ameloblastoma is the most common odontogenic tumor. HIGHLIGHT: Although a benign tumor, ameloblastoma progresses with marked jawbone resorption. Because of its locally aggressive features, it can be treated surgically by resecting the surrounding bone. From a molecular pathology perspective, several genetic mutations and dysregulated signaling pathways involved in ameloblastoma tumorigenesis have been identified. Histopathologically, ameloblastomas consist of peripheral ameloblast-like cells and an inner stellate reticulum. The stromal region consists of fibrovascular connective tissue, showing a characteristic sparse myxoid histology. In general, the tumor microenvironment, including the surrounding non-tumor cells, contributes to tumorigenesis and progression. In this review, we focus on the tumor microenvironment of ameloblastomas. In addition, we present some of our recent studies on osteoclastogenesis, tubulin acetylation-induced cell migration, and hypoxia-induced epithelial-mesenchymal transition in ameloblastomas. CONCLUSION: Further research on ameloblastomas can lead to the development of new treatments and improve patients' quality of life.

Clinicopathological characteristics and diagnostic accuracy of BRAF mutations in ameloblastoma: A Bayesian network analysis.

OBJECTIVE: This Bayesian network meta-analysis was performed to analyze the associations between clinicopathological characteristics and BRAF mutations in ameloblastoma (AM) patients and to evaluate the diagnostic accuracy. MATERIALS AND METHODS: Four electronic databases were searched from 2010 to 2024. The search terms used were specific to BRAF and AM. Observational studies or randomized controlled trials were considered eligible. The incidence of BRAF mutation and corresponding clinicopathological features in AM patients were subjected to Bayesian network analyses and diagnostic accuracy evaluation. RESULTS: A total of 937 AM patients from 20 studies were included. The pooled prevalence of BRAF mutations in AM patients was 72%. According to the Bayesian network analysis, BRAF mutations are more likely to occur in younger (odds ratio [OR], 2.3; credible interval [CrI]: 1.2-4.5), mandible site (OR, 3.6; 95% CrI: 2.7-5.2), and unicystic (OR, 1.6; 95% CrI: 1.1-2.4) AM patients. Similarly, higher diagnostic accuracy was found in the younger, mandible, and unicystic AM groups. CONCLUSIONS: The incidence, risk, and diagnostic accuracy of BRAF mutation in AM were greater in younger patients, those with mandible involvement, and those with unicystic AM than in patients with other clinicopathological features. In addition, there was a strong concordance in the diagnostic accuracy between molecular tests and immunohistochemical analysis.

Targeted therapies in ameloblastomas and amelobastic carcinoma-A systematic review.

Targeted therapy has the potential to be used in the neoadjuvant setting for odontogenic tumors, reducing the morbidities associated with major surgery. In this regard, the aim of this study was to summarize the current evidence on the different forms of targeted therapy, effectiveness, and drawbacks of this course of treatment. Four databases were searched electronically without regard to publication date or language. Grey literature searches and manual searches were also undertaken. Publications with sufficient clinical data on targeted therapy for odontogenic tumors were required to meet the criteria for eligibility. The analysis of the data was descriptive. A total of 15 papers comprising 17 cases (15 ameloblastomas and 2 ameloblastic carcinomas) were included. Numerous mutations were found, with BRAF V600E being most common. Dabrafenib was the most utilized drug in targeted therapy. Except for one case, the treatment reduced the size of the lesion (16/17 cases), showing promise. Most of the adverse events recorded were mild, such as skin issues, voice changes, abnormal hair texture, dry eyes, and systemic symptoms (e.g., fatigue, joint pain, and nausea). It is possible to reach the conclusion that targeted therapy for ameloblastoma and ameloblastic carcinoma may be a useful treatment strategy, based on the findings of the included studies.

New perspectives in the differential diagnosis of jaw lesions: Machine learning and inflammatory biomarkers.

This study aimed to assess the diagnostic performance of a machine learning approach that utilized radiomic features extracted from Cone Beam Computer Tomography (CBCT) images and inflammatory biomarkers for distinguishing between Dentigerous Cysts (DCs), Odontogenic Keratocysts (OKCs), and Unicystic Ameloblastomas (UAs). This retrospective study involves 103 patients who underwent jaw lesion surgery in the Maxillofacial Surgery Unit of Federico II University Of Naples between January 2018 and January 2023. Nonparametric Wilcoxon-Mann-Whitney and Kruskal Wallis tests were used for continuous variables. Linear and non-logistic regression models (LRM and NLRM) were employed, along with machine learning techniques such as decision tree (DT), k-nearest neighbor (KNN), and support vector machine (SVM), to predict the outcomes. When individual inflammatory biomarkers were considered alone, their ability to differentiate between OKCs, UAs, and DCs was below 50 % accuracy. However, a linear regression model combining four inflammatory biomarkers achieved an accuracy of 95 % and an AUC of 0.96. The accuracy of single radiomics predictors was lower than that of inflammatory biomarkers, with an AUC of 0.83. The Fine Tree model, utilizing NLR, SII, and one radiomic feature, achieved an accuracy of 94.3 % (AUC = 0.95) on the training and testing sets, and a validation set accuracy of 100 %. The Fine Tree model demonstrated the capability to discriminate between OKCs, UAs, and DCs. However, the LRM utilizing four inflammatory biomarkers proved to be the most effective algorithm for distinguishing between OKCs, UAs, and DCs.

Molecular pathogenesis of ameloblastoma.

Ameloblastoma (AM) is a benign, although aggressive, epithelial odontogenic tumour originating from tooth-forming tissues or remnants. Its aetiopathogenesis remains unclear; however, molecular analysis techniques have allowed researchers to progress in understanding its genetic basis. The high frequency of BRAF p.V600E as a main driver mutation in AM is well established; nevertheless, it is insufficient to explain its tumourigenesis. In this review, we aimed to integrate the current knowledge about the biology of AM and to describe the main genetic alterations reported, focusing on the findings of large-scale sequencing and gene expression profiling techniques. Current evidence shows that besides BRAF mutation and activation of the MAPK pathway, alterations in Hedgehog and Wnt/ß-catenin pathway-related genes are also involved in AM pathogenesis. Recently, a tumour suppressor gene, KMT2D, has been reported as mutated by different research groups. The biological impact of these mutations in the pathogenesis of AM has yet to be elucidated. Further studies are needed to clarify the impact of these findings in the identification of novel biomarkers that could be useful for diagnosing, classifying, and molecular targeting this neoplasm.

Calcifying Odontogenic Cyst Demonstrates Recurrent WNT Pathway Mutations and So-Called Adenoid Ameloblastoma-Like Histology: Evidence Supporting Its Classification as a Neoplasm.

Calcifying odontogenic cyst (COC), once called calcifying cystic odontogenic tumor, is classified under the category of odontogenic cysts. However, the proliferative capacity of the lesional epithelium and consistent nuclear ß-catenin expression raise questions about its current classification. This study aimed to determine whether COC would be better classified as a neoplasm in the histologic and molecular context. Eleven odontogenic lesions diagnosed as COC or calcifying cystic odontogenic tumor were included in this study. The growth patterns of the lesional epithelium were analyzed histologically in all cases. ß-catenin immunohistochemistry and molecular profiling using Sanger sequencing and whole-exome sequencing were performed in 10 cases. Of the 11 cases studied, histologic features reminiscent of so-called adenoid ameloblastoma were observed in 72.7% (8/11), and small islands of clear cells extended into the wall in 36.4% (4/11). Intraluminal and/or mural epithelial proliferation was found in 72.7% of the cases (8/11). Nuclear ß-catenin expression was observed focally in all 10 cases studied, mainly highlighting epithelial cells forming morules and adjacent to dentinoid. CTNNB1 hotspot mutations were detected in 60.0% of the cases (6/10). All the remaining cases had frameshift mutations in tumor-suppressor genes involved in the WNT pathway, including APC and NEDD4L. Recurrent WNT pathway mutations leading to nuclear translocation of ß-catenin and distinct epithelial growth patterns found in COC are the neoplastic features shared by its solid counterpart, dentinogenic ghost cell tumor, supporting its classification as a tumor rather than a cyst.

Adenomatoid odontogenic tumor: A histopathologic profile of 43 cases with evidence supporting a mixed odontogenic origin.

BACKGROUND: Adenomatoid Odontogenic Tumor (AOT) accounts for 3% of all odontogenic tumors. It has been classified by WHO as an odontogenic tumor of purely epithelial origin. The current study attempts to establish the origin of the tumor along with detailed histopathological and clinicoradiographic analysis of 43 cases of AOT. MATERIAL AND METHODS: Forty-three cases were reviewed from the departmental archives for demographic data, radiographic features and histological features. Further, histopathological slides were stained with Picrosirius Red (PSR) and observed under polarised light. RESULTS: A majority of the cases were seen in the anterior jaws (76.7%), and were less than 3 cms (76.7%) in greatest dimension. Equal number of cases were of follicular and extra-follicular location while one was peripheral. Predominantly solid histological pattern was noted in 53.5%. Varied sub-patterns were observed with most cases exhibiting solid nodules and strands of tumor cells. Few cases showed melanin pigmentation. Over a third of cases (37.2%) showed dentigerous cyst like areas and one case each showed features of ossifying fibroma and focal cemento-osseous dysplasia. Tumor droplets, hyaline rings within duct-like structures, dentinoid material and osteodentin showed reddish yellow birefringence when observed under polarised microscopy post PSR staining. CONCLUSION: This study highlights the diverse histopathological variation of AOT with evidence to reclassify it as a mixed odontogenic tumor based on the polarising microscopic findings with PSR staining.

Application of machine learning in the preoperative radiomic diagnosis of ameloblastoma and odontogenic keratocyst based on cone-beam CT.

OBJECTIVES: Preoperative diagnosis of oral ameloblastoma (AME) and odontogenic keratocyst (OKC) has been a challenge in dentistry. This study uses radiomics approaches and machine learning (ML) algorithms to characterize cone-beam CT (CBCT) image features for the preoperative differential diagnosis of AME and OKC and compares ML algorithms to expert radiologists to validate performance. METHODS: We retrospectively collected the data of 326 patients with AME and OKC, where all diagnoses were confirmed by histopathologic tests. A total of 348 features were selected to train six ML models for differential diagnosis by a 5-fold cross-validation. We then compared the performance of ML-based diagnoses to those of radiologists. RESULTS: Among the six ML models, XGBoost was effective in distinguishing AME and OKC in CBCT images, with its classification performance outperforming the other models. The mean precision, recall, accuracy, F1-score, and area under the curve (AUC) were 0.900, 0.807, 0.843, 0.841, and 0.872, respectively. Compared to the diagnostics by radiologists, ML-based radiomic diagnostics performed better. CONCLUSIONS: Radiomic-based ML algorithms allow CBCT images of AME and OKC to be distinguished accurately, facilitating the preoperative differential diagnosis of AME and OKC. ADVANCES IN KNOWLEDGE: ML and radiomic approaches with high-resolution CBCT images provide new insights into the differential diagnosis of AME and OKC.

Ossifying fibroma mimiking jaw tumour: A radiographic dilema.

Fibro-osseous lesions (FOLs) of the craniomaxillofacial region comprise a group of developmental, dysplastic, and neoplastic alterations. FOLs include ossifying fibromas (OF), cemento-ossifying fibroma (COF), familial gigantiform cementoma (FGC), fibrous dysplasia (FD), and cemento-osseous dysplasia (COD). Evidence suggests that some FOL, especially FD and OF may have a risk of spontaneous malignant transformation. This report documents a rare case of malignant transformation of ossifying fibromas of the jaw and the probable cause for same. Although it is rare, the clinician should have a complete follow up to observe such changes among the patients having FOLs.