METHODS: Archives of our institute were reviewed. Cases diagnosed as odontogenic myxoma were retrieved. Demographic, clinical, radiographic, and histopathological features of these cases were analyzed. In addition, immunohistochemical markers including vimentin, Ki-67, Bcl-2, and CD117 were performed. The correlation between immunohistochemical profiles and clinicopathological characteristics was evaluated.
RESULTS: Sixteen cases of odontogenic myxoma were discovered. Fourteen cases were central type while two cases were peripheral type. The mean age of patients was 34.6 years with male-to-female ratio of 1:2.2. Mandible (68.8 %) was more affected than the maxilla (31.2 %). Bony expansion or jaw swelling (43.8 %) was the most common clinical feature. Most cases (71.4 %) presented with multilocular radiolucency. Histopathologically, tumors show stellate and spindle-shaped cells in a myxoid stroma with varying amounts of collagen fiber. All cases were positive for vimentin and Bcl-2. Half of the cases showed positive for Ki-67. Mast cells were presented in most cases (75.0 %). A significant correlation was found between the immunoexpression level of Bcl-2 and border of lesion in radiograph (p = 0.024).
CONCLUSIONS: This study contributes to better understanding of the characteristics of odontogenic myxoma. Clinicians and pathologists should be aware of odontogenic myxoma, as its clinical and histopathological features may overlap with other tumors. The expression of Bcl-2 and presence of mast cell in this tumor may relate to its growth and aggressiveness. Despite its benign nature, odontogenic myxoma exhibits high recurrence, especially in lesion managed conservatively.
MATERIAL AND METHODS: An online search was performed of the PubMed, Science Direct, and Scopus databases. Based on the selection process, 12 studies were included in this review.
RESULTS: Eleven studies utilized a CNN model for detection tasks, 5 for classification tasks, and 3 for segmentation tasks in the context of tooth numbering on panoramic radiographs. Most of these studies revealed high performance of various CNN models in automating tooth numbering. However, several studies also highlighted limitations of CNNs, such as the presence of false positives and false negatives in identifying decayed teeth, teeth with crown prosthetics, teeth adjacent to edentulous areas, dental implants, root remnants, wisdom teeth, and root canal-treated teeth. These limitations can be overcome by ensuring both the quality and quantity of datasets, as well as optimizing the CNN architecture.
CONCLUSION: CNNs have demonstrated high performance in automated tooth numbering on panoramic radiographs. Future development of CNN-based models for this purpose should also consider different stages of dentition, such as the primary and mixed dentition stages, as well as the presence of various tooth conditions. Ultimately, an optimized CNN architecture can serve as the foundation for an automated tooth numbering system and for further artificial intelligence research on panoramic radiographs for a variety of purposes.