OBJECTIVE: To develop and validate a modified deep learning (DL) model based on nnU-net for classifying and segmenting five-class jaw lesions using cone-beam computed tomography (CBCT).
METHODS: A total of 368 CBCT scans (37 168 slices) were used to train a multi-class segmentation model. The data underwent manual annotation by two oral and maxillofacial surgeons (OMSs) to serve as ground truth. Sensitivity, specificity, precision, F1-score, and accuracy were used to evaluate the classification ability of the model and doctors, with or without artificial intelligence assistance. The dice similarity coefficient (DSC), average symmetric surface distance (ASSD) and segmentation time were used to evaluate the segmentation effect of the model.
RESULTS: The model achieved the dual task of classifying and segmenting jaw lesions in CBCT. For classification, the sensitivity, specificity, precision, and accuracy of the model were 0.871, 0.974, 0.874 and 0.891, respectively, surpassing oral and maxillofacial radiologists (OMFRs) and OMSs, approaching the specialist. With the model\'s assistance, the classification performance of OMFRs and OMSs improved, particularly for odontogenic keratocyst (OKC) and ameloblastoma (AM), with F1-score improvements ranging from 6.2% to 12.7%. For segmentation, the DSC was 87.2% and the ASSD was 1.359 mm. The model\'s average segmentation time was 40 ± 9.9 s, contrasting with 25 ± 7.2 min for OMSs.
CONCLUSIONS: The proposed DL model accurately and efficiently classified and segmented five classes of jaw lesions using CBCT. In addition, it could assist doctors in improving classification accuracy and segmentation efficiency, particularly in distinguishing confusing lesions (e.g., AM and OKC).

UNASSIGNED: Various stemness markers (SOX2, OCT4, and NANOG) have been studied in odontogenic cysts and tumors. However, studies on SALL4 having similar properties of stemness has not been documented. Additionally, insight into fascin as a migratory molecule is less explored. In this study, the expression of SALL4 and fascin were evaluated in ameloblastoma, adenomatoid odontogenic tumor (AOT), odontogenic keratocyst (OKC), dentigerous cyst (DC), radicular cyst (RC), and calcifying odontogenic cyst (COC).
UNASSIGNED: Semi-quantitative analysis of fascin and SALL4 immuno-positive cells was done in a total of 40 cases of ameloblastoma (11 plexiform, 12 follicular, 12 unicystic, and 5 desmoplastic) variants, 6 cases of AOT, 15 each of OKC, DC, RC and 5 of COC. Chi-square test was applied to evaluate the association between SALL4 and fascin expression in odontogenic cysts and tumors.
UNASSIGNED: Fascin immunopositivity was observed in peripheral ameloblast-like cells, and weak or absent in stellate reticulum-like cells. A moderate to weak immune-reactivity to SALL4 was observed in the cytoplasm of ameloblastoma, epithelial cells of dentigerous and radicular cysts, having a marked inflammatory infiltrate, which is an interesting observation. COC and AOT had negative to weak expressions. No recurrence has been reported.
UNASSIGNED: Expression of fascin in ameloblastomas elucidate their role in motility and localized invasion. Its expression in less aggressive lesions like DC, COC, AOT will incite to explore the other functional properties of fascin. SALL4 expression in the cytoplasm of odontogenic cysts and tumors may represent inactive or mutant forms which requires further validation.

Intravascular papillary endothelial hyperplasia (IPEH) represents an uncommon reactive endothelial hyperplastic proliferation. A 46-year-old man experienced increased volume in the right maxilla, elevation of the nasal ala, and swelling of the hard palate with a reddish hue for 3 months. Computed tomography revealed an expansive hypodense region and cortical bone destruction associated with an impacted supernumerary tooth and an endodontically treated tooth. Under the differential diagnoses of a radicular cyst, dentigerous cyst, and ameloblastoma, an exploratory aspiration and incisional biopsy were performed. This revealed the formation of blood vessels of various diameters lined by endothelium, forming intravascular papillae positive for CD-34. The definitive diagnosis was IPEH, and the patient was treated by embolization and surgery. Histological analysis confirmed the presence of IPEH associated with an odontogenic cyst. After 12 months of follow-up, no recurrence was observed. Also, we reviewed case reports of IPEH affecting the maxilla and mandible. Fourteen intraosseous cases were reported in the maxilla and mandible, with a preference for males and affecting a wide age range. Complete surgical excision was the treatment of choice, and recurrences were not reported. The pathogenesis of IPEH is controversial and may originate from trauma or inflammatory processes. To the best of our knowledge, this is the first report of an association of IPEH with an odontogenic cyst. The importance of IPEH in the differential diagnosis of intraosseous lesions in the jaws is emphasized, and preoperative semiotic maneuvers are needed to prevent surgical complications.

OBJECTIVE: Odontogenic keratocysts exhibit frequent recurrence, distinctive histopathological traits, a tendency towards aggressive clinical behavior, and a potential linkage to the nevoid basal cell carcinoma syndrome. The aim of this systematic review is to compile insights concerning the control of this condition and assess the effectiveness of various treatment approaches in reducing the likelihood of recurrence.
METHODS: The following systematic review adhered to the PRISMA guidelines. The systematic revision was registered on PROSPERO and  structured around the questions related to the population, intervention, control, outcome and study design (PICOS).
RESULTS: After conducting a search on the PubMed database, we initially identified 944 records. After using end-note software to remove duplicate entries, results totally with 462 distinct records. A thorough review of the titles and abstracts of these articles led to the selection of 50 papers for in-depth examination. Ultimately, following the application of our eligibility criteria, we incorporated 11 articles into our primary outcome analysis.
CONCLUSIONS: Among the studies examined, the most common location for these lesions was found to be in the area of the mandibular ramus and the posterior region of the mandible. In cases where the exact location wasn\'t specified, the mandible emerged as the predominant site. When we considered the characteristics of these lesions in studies that mentioned locularity, most were described as unilocular in two studies, while in two other studies, the prevalence of multilocular lesions was observed. Risk factors associated with keratocyst recurrence include younger patient age, the presence of multilocular lesions, larger lesion size, and a longer anteroposterior dimension. Certain treatment methods have demonstrated a lack of relapses. These include the use of 5-fluorouracil, marsupialization, enucleation with peripheral ostectomy or resection, enucleation and curettage, as well as resection without creating continuity defects. However, it is important to note that further research is essential. Prospective studies and randomized trials are needed to collect more comprehensive evidence regarding the effectiveness of various treatment approaches and follow-up protocols for managing odontogenic keratocysts.
CONCLUSIONS: Odontogenic keratocysts still enter into differential diagnoses with other lesions that affect the jaw bones such as ameloblastama and other tumor forms, furthermore it is not free from recurrence, therefore the therapeutic approach to the lesion aimed at its elimination can influence both the possible recurrence and complications, knowledge of the surgical methods that offer the most predictable and clinically relevant result for the management of follow-up and recurrences.

BACKGROUND: Although numerous syndromic and non-syndromic odontogenic lesions of the jaws have been documented in the literature, there are very few cases of simultaneous benign and malignant jaw lesions.
METHODS: We present a case of right maxillary squamous cell carcinoma along with several benign odontogenic cystic lesions of the jaws and skeletal abnormalities that meet the criteria for Gorlin-Goltz syndrome.
UNASSIGNED: With a review of the literature, the specifics of management and follow-up are discussed.

BACKGROUND: Odontogenic lesions constitute a heterogeneous group of lesions. CLIC4 protein regulates different cellular processes, including epithelial-mesenchymal transition and fibroblast-myofibroblast transdifferentiation. This study analyzed CLIC4, E-cadherin, Vimentin, and α-SMA immunoexpression in epithelial odontogenic lesions that exhibit different biological behavior.
METHODS: It analyzed the immunoexpression of CLIC4, E-cadherin, and Vimentin in the epithelial cells, as well as CLIC4 and α-SMA in the mesenchymal cells, of ameloblastoma (AM) (n = 16), odontogenic keratocyst (OKC) (n = 20), and adenomatoid odontogenic tumor (AOT) (n = 8). Immunoexpressions were categorized as score 0 (0% positive cells), 1 (< 25%), 2 (≥ 25% - < 50%), 3 (≥ 50% - < 75%), or 4 (≥ 75%).
RESULTS: Cytoplasmic CLIC4 immunoexpression was higher in AM and AOT (p < 0.001) epithelial cells. Nuclear-cytoplasmic CLIC4 was higher in OKC\'s epithelial lining (p < 0.001). Membrane (p = 0.012) and membrane-cytoplasmic (p < 0.001) E-cadherin immunoexpression were higher in OKC, while cytoplasmic E-cadherin expression was higher in AM and AOT (p < 0.001). Vimentin immunoexpression was higher in AM and AOT (p < 0.001). Stromal CLIC4 was higher in AM and OKC (p = 0.008). Similarly, α-SMA immunoexpression was higher in AM and OKC (p = 0.037). Correlations in these proteins\' immunoexpression were observed in AM and OKC (p < 0.05).
CONCLUSIONS: CLIC4 seems to regulate the epithelial-mesenchymal transition, modifying E-cadherin and Vimentin expression. In mesenchymal cells, CLIC4 may play a role in fibroblast-myofibroblast transdifferentiation. CLIC4 may be associated with epithelial odontogenic lesions with aggressive biological behavior.

BACKGROUND: Orofacial cysts are pathologic cavities that could be symptomatic and may cause facial disfigurement. The only epidemiologic report of such lesions in Southeast Nigeria studied jaw cysts from 1987 to 1996. New studies reflecting recent research findings and classifications on the subject in Southeast Nigeria are lacking.
OBJECTIVE: To determine the prevalence and distribution of orofacial cysts in a tertiary hospital in Enugu, Southeast Nigeria.
METHODS: A 10-year retrospective study of patients with orofacial cysts diagnosed by histology was carried out.
RESULTS: Orofacial cysts constitute 9.5% (85) of 897 orofacial lesions identified. The male-to-female gender ratio was 1.2:1. The mean age (± standard deviation) at the onset of the cystic lesion was 28.58 (±16.98) years. Developmental odontogenic cysts 52.9% (45) and salivary cysts 18.8% (16) were the most common group of orofacial cysts. The most prevalent orofacial cysts were odontogenic keratocysts at 25.9% (22), mucoceles 16.5% (14), and dentigerous cysts 14.1% (12). Straw-colored aspirates 34.8% (16) and dark brown aspirates 28.3% (13) were the predominant cystic contents. The mandible 45.9% (39) and maxilla 27.1% (23) were the commonest sites for orofacial cysts, while the lip 9.4% (8) was the most frequent soft tissue site. A significant association exists between anatomical site and cyst type at a 95% confidence interval with P = 0.000, X2 = 247.17. Unilocular radiolucency 62.5% (20) and multilocular radiolucency 34.4% (11) were the most common radiographic features.
CONCLUSIONS: Developmental odontogenic cysts particularly odontogenic keratocysts were most prevalent while mucocele was the most common soft tissue cyst.

BACKGROUND: The glandular odontogenic cyst (GOC) is a benign developmental cyst of the jaws that is characterized by a high recurrence rate.
METHODS: A systematic review is presented of reported cases, case series, and retrospective studies of recurrent cases of glandular odontogenic cysts, to determine the overall and detailed demographic features with documentation of the specific histologic features of the initial presentation of each cyst. Searches of detailed databases were carried out to identify articles published in the English language from 1988 to 2023. The variables were demographics, patient symptoms, cyst location, radiographic features, histopathological findings, type of treatment, and minimum eight months of follow-up.
RESULTS: Eighteen cases were identified: with an equal gender presentation of 50% females and 50% males. The average age was 44.7. The mean size was 3.5 cm. The most common location was in the anterior mandible in 50% (n = 9) of cases, followed by the posterior mandible 27.8% (n = 5). Most patients were asymptomatic 55.6% (n = 10). The most common histologic features at first diagnosis were mucous cells in 88.9% (n = 16), variable thickness with 83.3% (n = 15), eosinophilic cuboidal cells 88.9% (n = 16), microcysts 83.3% (n = 15), and clear cells 77.8% (n = 14) cases.
CONCLUSIONS: GOC has an aggressive behavior. Evidence was not conclusive to link any single or combination of histologic features to recurrence, and the strongest correlation for recurrence was the type of treatment. Since this is an uncommon cyst, more cases are needed. Follow-up should continue for at least five years, because recurrences were higher between years 3 and 5.

OBJECTIVE: 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.
CONCLUSIONS: ML and radiomic approaches with high-resolution CBCT images provide new insights into the differential diagnosis of AME and OKC.

The high recurrence rate of odontogenic keratocysts (OKC) entails a large number of follow-up interventions after primary surgery. This study aimed to compare recurrent with primary OKC in regard to recurrence rate, treatment modality, radiographic and clinical findings. A single center retrospective cohort study with surgically treated OKC between 2012 and 2021 was conducted. The primary predictor was recurrence type of the lesion: primary (P-OKC), first recurrence (R1-OKC) and second recurrence (R2-OKC). The primary outcome variables were recurrence and time to recurrence. 68 surgeries were identified. Recurrence was not significantly associated with recurrence type (p = 0.906) but with the method of surgery (p < 0.001). Marsupialized R1-OKC recurred earlier than marsupialized P-OKC. Diameter was significantly associated with recurrence type (p = 0.002). R1-OKC had a smaller median diameter than P-OKC and R2-OKC were smaller than R1-and P-OKC. P-OKC were associated with teeth in 79% of surgeries, R1-OKC in 61% and R2-OKC in 27% (p = 0.007). Postoperative numbness was present after 40% of surgeries and decreased to 15% at follow-up, independently of recurrence type. Time to recurrence may be shorter for recurrent marsupialized OKC. Recurrent OKC are smaller and less often associated with teeth. Postoperative numbness after OKC surgery has a good prognosis.