Can narrowing of the mandibular canal on pre-operative panoramic radiography predict close anatomical contact of the mandibular canal with the mandibular third molar? A meta-analysis

Automatic visualization of the mandibular canal in relation to an impacted mandibular third molar on panoramic radiographs using deep learning segmentation and transfer learning techniques

OBJECTIVE

The aim of this study was to create and assess a deep learning model using segmentation and transfer learning methods to visualize the proximity of the mandibular canal to an impacted third molar on panoramic radiographs.

STUDY DESIGN

The panoramic radiographs containing the mandibular canal and impacted third molar were collected from 2 hospitals (Hospitals A and B). A total of 3200 areas were used for creating and evaluating learning models. A source model was created using the data from Hospital A, simulatively transferred to Hospital B, and trained using various amounts of data from Hospital B to create target models. The same data were then applied to the target models to calculate the Dice coefficient, Jaccard index, and sensitivity.

RESULTS

The performance of target models trained using 200 or more data sets was equivalent to that of the source model tested using data obtained from the same hospital (Hospital A).

CONCLUSIONS

Sufficiently qualified models could delineate the mandibular canal in relation to an impacted third molar on panoramic radiographs using a segmentation technique. Transfer learning appears to be an effective method for creating such models using a relatively small number of data sets.

[Surgical treatment tactics in patients with third molars located close to mandibular canal]

The tight fit of the roots of the third molars to the mandibular canal is the main predisposing factor of injury to the inferior alveolar nerve during tooth extraction surgery. Surgical treatment of 92 patients diagnosed with pericoronitis, retention of the third molar of the mandible, close fit of the roots of the third molar to the mandibular canal was performed. Four types of close fit of the roots of the third molars to the mandibular canal were revealed, according to CBCT, OPTG and clinical data. Most cases of paresthesia after the removal of the third molars are associated with an anatomical variation in the structure of the mandibular canal, in which the canal walls are partially formed by the cement of the tooth root. Two variants of postoperative management of the surgical wound are proposed, when an open section of the neurovascular bundle is detected at the bottom of the hole.

Does Mandibular Gonial Angle Influence the Eruption Pattern of the Lower Third Molar? A Three-Dimensional Study

Lower third molars (M3M) are the most frequent impacted teeth. The aim of this study was to evaluate the correlation between M3M position and gonial angle. A retrospective cross-sectional study was conducted. The study population included patients with unilateral or bilateral M3M and underwent Cone Beam Computed Tomography. A morphometric analysis of the mandible was performed after three-dimensional reconstruction, recording gonial angle (GA), ramus high, ramus width, ramus divergency, and retromolar space. GA was the primary predictor variable. The primary outcome variable was the position of M3M analyzed in sagittal, axial, and coronal planes. Descriptive, bivariate, and multiple regression statistics were performed (p < 0.05). Study sample included 172 patients (mean age: 26.3 ± 4.6 years); 266 M3Ms were analyzed. The average GA was 122.6° ± 4.8°. A reduced GA value was significantly associated with a deeply impacted M3M in the ramus. With a progressive decrease of GA, M3M assumed a more horizontal position closer to the mandibular canal (p < 0.05). A lower GA showed a reduced retromolar space with more complex impacted M3M (p < 0.05). The results confirm a statistically significant correlation between GA and the position of M3M. Higher incidence of impacted M3M was related to a reduction of the GA value.