OBJECTIVES: This study aims to evaluate the changes in the mandibular canal following the treatment of large odontogenic keratocysts through decompression and curettage, providing a theoretical basis for sequential treatment. METHODS: Twenty patients were selected for each decompression and curettage treatment of large odontogenic keratocysts in the mandible. Postoperative follow-up with was conducted every three months, during which cone beam computed tomography (CBCT) scans were performed. Then, the data were imported into MIMICS software to observe 3D changes in the position and structure of the mandibular nerve canal, followed by a comparative analysis. RESULTS: The total displacement of the mandibular canal was (1.89±0.21) mm on the decompression side and (0.80±0.19) mm on the curettage side. Vertically, the displacement range of the mandibular canal on the decompression side (M=1.03, SD=0.17) was larger than on the curettage side (M=0.52, SD=0.010) within nine months post-operation. In the buccal-lingual direction, the ratio of the thickness of the buccal plate to the lingual plate gradually increased with time. The amount of bone reconstruction at the part of the mandibular nerve canal closest to the cyst was (1.75±0.15) mm on the decompression side and (1.45±0.09) mm on the curettage side after nine months. CONCLUSIONS The mandibular nerve canal showed varying degrees of recovery and "relocation" after two surgical procedures. Osteogenesis around the mandibular nerve canal was more remarkable after decompression than after curettage. Therefore, for large odontogenic keratocyst, decompression is recommended as the initial treatment, followed by secondary curettage nine months later.
Humans ; Odontogenic Cysts/diagnostic imaging* ; Retrospective Studies ; Cone-Beam Computed Tomography ; Decompression, Surgical/methods* ; Mandibular Nerve/surgery* ; Mandible/innervation* ; Curettage ; Male ; Female ; Adult ; Middle Aged

Objective To evaluate the accuracy of different convolutional neural networks (CNN),representative deep learning models,in the differential diagnosis of ameloblastoma and odontogenic keratocyst,and subsequently compare the diagnosis results between models and oral radiologists. Methods A total of 1000 digital panoramic radiographs were retrospectively collected from the patients with ameloblastoma (500 radiographs) or odontogenic keratocyst (500 radiographs) in the Department of Oral and Maxillofacial Radiology,Peking University School of Stomatology.Eight CNN including ResNet (18,50,101),VGG (16,19),and EfficientNet (b1,b3,b5) were selected to distinguish ameloblastoma from odontogenic keratocyst.Transfer learning was employed to train 800 panoramic radiographs in the training set through 5-fold cross validation,and 200 panoramic radiographs in the test set were used for differential diagnosis.Chi square test was performed for comparing the performance among different CNN.Furthermore,7 oral radiologists (including 2 seniors and 5 juniors) made a diagnosis on the 200 panoramic radiographs in the test set,and the diagnosis results were compared between CNN and oral radiologists. Results The eight neural network models showed the diagnostic accuracy ranging from 82.50% to 87.50%,of which EfficientNet b1 had the highest accuracy of 87.50%.There was no significant difference in the diagnostic accuracy among the CNN models (P=0.998,P=0.905).The average diagnostic accuracy of oral radiologists was (70.30±5.48)%,and there was no statistical difference in the accuracy between senior and junior oral radiologists (P=0.883).The diagnostic accuracy of CNN models was higher than that of oral radiologists (P<0.001). Conclusion Deep learning CNN can realize accurate differential diagnosis between ameloblastoma and odontogenic keratocyst with panoramic radiographs,with higher diagnostic accuracy than oral radiologists.
Humans ; Ameloblastoma/diagnostic imaging* ; Deep Learning ; Diagnosis, Differential ; Radiography, Panoramic ; Retrospective Studies ; Odontogenic Cysts/diagnostic imaging* ; Odontogenic Tumors

Odontogenic keratocyst (OKC) with secondary inflammation involving the maxillary sinus was presented. Radiological diagnosis of this case was made based on the various findings from the cone-beam computed tomography, computed tomography and magnetic resonance images. There were calcified materials and impacted tooth within the lumen of the lesion, which is not uncommon in OKC. Histopathologic findings confirmed this lesion as OKC with secondary inflammation.
Calcinosis ; Cone-Beam Computed Tomography ; Diagnostic Imaging ; Inflammation ; Magnetic Resonance Spectroscopy ; Maxilla ; Maxillary Sinus ; Odontogenic Cysts ; Tooth, Impacted

The odontogenic keratocyst (OKC) is a developmental odontogenic cyst typically occurring in the jaws. Since the first description of OKC was published in 1956, the lesion has been of particular interest because of its specific histopathologic features, high recurrence rate, and aggressive behavior. Recurrences most commonly arise within bone at the site of the original cyst. However, as lining cells may find their way into surrounding tissues either from implantation during surgery or from cortical perforation recurrences may arise at a distance from the original cyst. Here, we report a rare case of recurrent OKC which was first developed in mandible and recurred within the masticatory space.
Diagnostic Imaging ; Jaw ; Mandible ; Masticatory Muscles ; Odontogenic Cysts ; Recurrence