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).

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.

BACKGROUND: Odontogenic keratocysts (OKCs) are locally aggressive and have a high rate of recurrence, but the pathogenesis of OKCs is not fully understood. We aimed to investigate the serum metabolomic profile of OKCs and discover potential biomarkers.
METHODS: Metabolomic analysis was performed on 42 serum samples from 22 OKC patients and 20 healthy controls (HCs) using gas chromatography‒mass spectrometry to identify dysregulated metabolites in the OKC samples. LASSO regression and receiver operating characteristic (ROC) curve analyses were used to select and validate metabolic biomarkers and develop diagnostic models.
RESULTS: A total of 73 metabolites were identified in the serum samples, and 24 metabolites were dysregulated in the OKC samples, of which 4 were upregulated. Finally, a diagnostic panel of 10 metabolites was constructed that accurately diagnosed OKCs (sensitivity of 100%, specificity of 100%, area under the curve of 1.00).
CONCLUSIONS: This study is the first to investigate the metabolic characteristics and potential metabolic biomarkers in the serum of OKC patients using GC‒MS. Our study provides further evidence to explore the pathogenesis of OKC.

Odontogenic keratocyst (OKC) is a common jaw cyst with a high recurrence rate. OKC combined with basal cell carcinoma as well as skeletal and other developmental abnormalities is thought to be associated with Gorlin syndrome. Moreover, OKC needs to be differentiated from orthokeratinized odontogenic cyst and other jaw cysts. Because of the different prognosis, differential diagnosis of several cysts can contribute to clinical management. We collected 519 cases, comprising a total of 2 157 hematoxylin and eosin-stained images, to develop digital pathology-based artificial intelligence (AI) models for the diagnosis and prognosis of OKC. The Inception_v3 neural network was utilized to train and test models developed from patch-level images. Finally, whole slide image-level AI models were developed by integrating deep learning-generated pathology features with several machine learning algorithms. The AI models showed great performance in the diagnosis (AUC = 0.935, 95% CI: 0.898-0.973) and prognosis (AUC = 0.840, 95%CI: 0.751-0.930) of OKC. The advantages of multiple slides model for integrating of histopathological information are demonstrated through a comparison with the single slide model. Furthermore, the study investigates the correlation between AI features generated by deep learning and pathological findings, highlighting the interpretative potential of AI models in the pathology. Here, we have developed the robust diagnostic and prognostic models for OKC. The AI model that is based on digital pathology shows promise potential for applications in odontogenic diseases of the jaw.

The aim of this study was to evaluate the clinical efficacy of alcohol-based therapy for patients with large odontogenic keratocysts (OKCs). The study was implemented as a retrospective, single-center study. Patients treated with ethanol-based therapy for odontogenic keratocyst were retrospectively evaluated for baseline and postoperative data. The pre- and postoperative clinical situation and the extent of radiographic shrinkage were compared. The event is defined as the achievement of >50% reduction in cyst volume. The cyst reduction rate calculated on panoramic radiographs ranged from 7.4% to 99.9% (mean [standard deviation] 55.3% [27.9%]) and was statistically significant (P < 0.05). Specifically, it has been found that, radiographically, 47.6% of patients achieved >50% reduction in cyst volume within 12 months. The continuous cortical bone was rebuilt, and the cyst cavity was filled with regenerated trabecular bone. The 22 included patients presented with nonclinical problems, had no need for further intervention, and exhibited persistent impaction of the teeth. The results of this study demonstrated that ethanol-based therapy triggered marked radiographic reductions of large OKC, indicating that using this technique is efficient.

OBJECTIVE: To analyze the three-dimensional radiographic characteristics of calcifying odontogenic cyst and calcifying epithelial odontogenic tumor using spiral computed tomography (CT) and cone-beam computed tomography (CBCT).
METHODS: Clinical records, histopathological reports, and CBCT or non-enhanced spiral CT images of 19 consecutive patients with calcifying odontogenic cyst (COC) and 16 consecutive patients with calcifying epithelial odontogenic tumor (CEOT) were retrospectively acquired, and radiographic features, including location, size, expansion, internal structure and calcification, were analyzed.
RESULTS: Among the 19 COC cases (12 males and 7 females, with an average age of 27 years), 89.5% (17/19) of the lesions originated from the anterior and premolar areas, 100.0% of them exhibited cortex expansion, and 78.9% had discontinued cortex. Among the 16 CEOT cases (3 males and 13 females, with an average age of 36 years), 81.3% (13/16) of the lesions were in the premolar and molar areas, 56.3% of them exhibited cortex expansion, and 96.8% had discontinued cortex. According to the distribution of internal calcifications, these lesions were divided into: Ⅰ (non-calcification type): absence of calcification; Ⅱ (eccentric marginal type): multiple calcifications scattered along one side of the lesion; Ⅲ (diffused type): numerous calcifications diffusely distributed into the lesion; Ⅳ (plaque type): with a ≥ 5 mm calcified patch; Ⅴ (peri-coronal type): multiple calcifications clustered around impacted teeth. Calcifications were present in 73.7% of COC lesions, including 9 type Ⅱ, 3 type Ⅲ and 2 type Ⅳ lesions, and 42.8% of CEOT lesions had calcification images, including 2 type Ⅲ and 5 type Ⅴ lesions. Six COC lesions had odontoma-like images. Moreover, 8 of 9 type Ⅰ CEOTs were histologically Langerhans cell-rich subtype, which had a smaller size (with an average mesiodistal diameter of 17.8 mm) and were not associated with impacted teeth.
CONCLUSIONS: COC lesions tended to originate from the anterior part of the jaw and exhibit cortex expansion, and were sometimes associated with odontoma. CEOT commonly occurred in the posterior jaw and had discontinued cortex. Two lesions had significantly different calcification map. Over 70% of COC lesions had calcification images, which were mostly scattered along one side of the cysts, far from the impacted teeth. Approximately 60% of CEOT lesions exhibited smaller size and non-calcification, and the remaining CEOT cases often had calcification images clustered around the impacted teeth.

BACKGROUND: Nevoid basal cell carcinoma syndrome (NBCCS, Gorlin syndrome) is a rare autosomal dominantly inherited disorder that is characterized by multisystem disorder such as basal cell carcinomas, keratocystic odontogenic tumors and skeletal abnormalities. Bilateral and/or unilateral ovarian fibromas have been reported in individuals diagnosed with NBCCS.
METHODS: A 22-year-old female, presented with low back pain, and was found to have bilateral giant adnexal masses on pelvic ultrasonography, which had been suspected to be malignant ovarian tumors. Positron emission tomography/computed tomography showed multiple intracranial calcification and skeletal abnormalities. The left adnexa and right ovarian tumor were resected with laparotomy, and pathology revealed bilateral ovarian fibromas with marked calcification. We recommended the patient to receive genetic testing and dermatological examination. No skin lesion was detected. Germline testing identified pathogenic heterozygous mutation in PTCH1 (Patched1).
CONCLUSIONS: The possibility of NBCCS needs to be considered in patients with ovarian fibromas diagnosed in an early age. Skin lesions are not necessary for the diagnosis of NBCCS. Ovarian fibromas are managed with surgical excision with an attempt at preserving ovarian function. Follow-up regime and counseling on options for future fertility should be offered to patients.

OBJECTIVE: We used proteomic sequencing and experimental verification to identify the potential ferroptosis-related proteins in ameloblastoma.
METHODS: Samples of ameloblastoma (n = 14) and normal gingival tissues (n = 5) were collected for proteomic sequencing to identify differentially expressed proteins (DEPs) in ameloblastoma. Ferroptosis-related genes were downloaded from FerrDb V2, which were then compared with DEPs to obtain ferroptosis-related DEPs (FR-DEPs). A functional enrichment analysis was performed, and a protein-protein interaction network was built. The hub proteins were screened using the Cytoscape software, and potential drugs targeting them were retrieved from the DrugBank database. A hub protein was selected for immunohistochemical validation, and its expression was assessed in ameloblastomas, odontogenic keratocysts, dentigerous cysts, and normal gingival tissues. The primary ameloblastoma cells were cultured to explore the effect of the protein on the migratory properties of the tumour cells.
RESULTS: A total of 58 FR-DEPs were screened, and six hub proteins were identified: mTOR, NFE2L2, PRKCA, STAT3, EGFR, and CDH1. Immunohistochemical analysis showed that mTOR expression was upregulated in ameloblastomas compared with that in odontogenic keratocysts, dentigerous cysts, and normal gingival tissues. p-mTOR was highly expressed in ameloblastomas, with a positivity rate of 83.3%. In addition, rapamycin, an inhibitor of mTOR, can inhibit the migratory capacity of primary cultured ameloblastoma cells.
CONCLUSIONS: Our results revealed the ferroptosis-related proteins in ameloblastomas and their underlying biological processes. Additionally, mTOR was overexpressed and was found to be associated with the aggressiveness of ameloblastomas, which may be a potential target for future treatments.

Enucleation, a surgical procedure, is commonly used to treat large jaw cysts, unicystic ameloblastomas and keratocysts. However, it remains unclear to what extent the jaw bone regenerates after enucleation. We aimed to evaluate the percentage and the survival analysis of jaw bone regeneration, in terms of cavity volume residual (CVR), in patients who underwent enucleation of large jaw cysts, unicystic ameloblastomas and keratocysts.
We collected data longitudinally from 75 patients who underwent jaw cystic lesions enucleation at the Stomatological Hospital of Xi\'an Jiaotong University, between January 2015 and June 2021. All patients had both preoperative and postoperative cone-beam computed tomography (CBCT) imaging data. CBCT images were analyzed using Image J. Changes in the CVR were assessed at various follow-up time points, and the Kaplan-Meier method was utilized to evaluate the CVR over time.
The patients had a mean age of 31.7 years (range: 5.5-72 years) with 58.66% of them being male. The postoperative CVR was 32.20% at three months, 21.10% at six months, 15.90% at 12 months, and 5.60% at 24 months. The percentage of CVR during follow-up periods for the initial size Quartile (Q)1 (212.54-1569.60 mm3) was substantially lower than those of Q2 and Q3 at and after seven months of follow-up and became statistically significant at the 12-month mark.
This study demonstrates that spontaneous bone regeneration can occur after enucleation of large jaw cysts, unicystic ameloblastomas and keratocysts, even without the use of filler materials. The initial size of the lesion had a significant impact on the outcome of cystic lesion enucleation over time. To minimize the risks associated with radiation exposure and expenses, we recommend reducing the frequency of CT imaging follow-ups for patients with small initial cavity sizes (ranging from 212.54 to 1569.60 mm3).

Objective: To analyze the imaging features of cone-beam CT (CBCT) of ameloblastoma (AB), odontogenic keratocyst (OKC) and dentigerous cysts (DC) associated with the mandibular impacted third molars,so as to provide useful information for differential diagnosis of these lesions. Methods: The patients who were with complete clinical data, pathological diagnosis and CBCT images from AB, OKC and DC around the mandibular impacted third molars were collected in Peking University Hospital of Stomatology from August 2016 to December 2021. A total of 109 patients (14 were diagnosed as AB, 23 were diagnosed as OKC and the others were diagnosed as dental cysts) were collected, including 73 males and 36 females. The age ranged from 11 to 70. The analyzed imaging features included location and internal density of the lesions, bone expansion, root resorption of adjacent teeth and types of the impacted teeth. The Chi square test was used to compare the gender of different lesions, and the Fisher\'s exact test was used to compare imaging features of lesions. When P<0.05, there was a significant difference among the three. Logistic regression analysis was performed to determine the imaging features that significantly contribute to correct imaging diagnosis. Corresponding P-values were calculated for all factors from multivariate models. Results: In the 23 cases of OKC, no special location was observed for the center of the lesion, heterogeneous high-density were seen in 21.7% of the cases, 56.5% of the cases had no significant bone expansion and the impacted teeth were not specially oriented. Among the 14 AB, 7 cases (7/14) were mainly located in the ramus of the mandible, and all cases (14/14) had buccal/lingual expansion of the jaw, 8 cases (8/14) presented root resorption of the adjacent teeth, and mesial impacted mandibular third molar were seen in 6 cases (6/14). Among the 72 DC, 88.9% (64/72) of the cases were mainly limited to the crown of the impacted third molar, 72.2% (52/72) of the cases had no obvious bone expansion, inverted impacted teeth were shown in 56.9% (41/72) of the cases. There was a significant difference among the three groups (χ2=7.30, P=0.026) in gender. AB and odontogenic cyst were more common in men than in women, while the incidence of OKC was roughly equal between men and women.There were significant differences in the location (P<0.001), internal density (P=0.001) of the lesions, bone expansion (P<0.001) and types of the impacted teeth (P<0.001), while no statistical difference was found for root resorption of adjacent teeth (P=0.153). Logistics regression analysis showed that the location of the lesion, internal density, bone expansion, root resorption of adjacent teeth and the types of impacted teeth had significant effects on the accurate diagnosis of the three kinds of lesions. Conclusions: Location, internal density, bone expansion and types of the impacted teeth played an important role in the correct imaging diagnosis. Further analysis indicates that when the classification of impacted teeth and the location of lesions are considered synchronously, DC can be differentiated from AB and OKC.
目的： 探讨发生于下颌阻生第三磨牙周围的成釉细胞瘤（ameloblastoma，AB）、牙源性角化囊肿（odontogenic keratocyst，OKC）及含牙囊肿的锥形束CT影像学特点，为临床诊断提供参考。 方法： 收集2016年8月至2021年12月北京大学口腔医学院·口腔医院医学影像科收治的109例有完整临床资料、病理诊断及锥形束CT影像，发生于下颌阻生第三磨牙周围的AB（14例）、OKC（23例）及含牙囊肿（72例）患者，其中男性73例，女性36例；患者年龄为11~70岁。分析病变部位、病变内密度、膨隆方向、邻牙牙根吸收及阻生牙的阻生类型等。应用χ2检验比较不同病变患者的性别差异，应用Fisher精确检验比较不同病变的影像学特征计数资料的差异，以单侧P<0.05为差异有统计学意义。通过logistic回归分析评估有助于正确影像诊断的重要影像学特征。计算多变量模型中对诊断有影响的所有因素的相应P值。 结果： 23例OKC患者的病变中心部位未见特殊偏好，21.7%（5/23）内部可见不均匀高密度影，56.5%（13/23）颌骨不膨隆，阻生牙位方向未见特殊偏好。14例AB患者中，7例（7/14）病变中心主要位于下颌支部位；14例（14/14）病变均出现颌骨膨隆；8例（8/14）邻牙牙根吸收；6例（6/14）阻生牙呈近中阻生。72例含牙囊肿患者中，88.9%（64/72）病变中心主要局限于阻生第三磨牙牙冠周围，72.2%（52/72）颌骨不膨隆，56.9%（41/72）阻生牙呈倒置阻生。3种病变的性别差异有统计学意义（χ2=7.30，P=0.026），AB及含牙囊肿男性较女性更多发，而OKC男女的发病率大致相等。Fisher精确检验结果显示，3种囊性病变的病变中心部位（P<0.001）、内部密度（P=0.001）、颌骨膨隆（P<0.001）及阻生牙阻生类型（P<0.001）的差异均有统计学意义，而邻牙牙根吸收差异无统计学意义（P=0.153）。 结论： 病变部位、病变内密度、颌骨膨隆以及阻生牙类型对准确诊断有明显作用。同时考虑病变部位和阻生牙类型，可将含牙囊肿与AB和OKC作出较准确的鉴别诊断。.