Positional assessment of lower third molar and mandibular canal using explainable artificial intelligence.

OBJECTIVE: The aim of this study is to automatically assess the positional relationship between lower third molars (M3i) and the mandibular canal (MC) based on the panoramic radiograph(s) (PR(s)). MATERIAL AND METHODS: A total of 1444 M3s were manually annotated and labeled on 863 PRs as a reference. A deep-learning approach, based on MobileNet-V2 combination with a skeletonization algorithm and a signed distance method, was trained and validated on 733 PRs with 1227 M3s to classify the positional relationship between M3i and MC into three categories. Subsequently, the trained algorithm was applied to a test set consisting of 130 PRs (217 M3s). Accuracy, precision, sensitivity, specificity, negative predictive value, and F1-score were calculated. RESULTS: The proposed method achieved a weighted accuracy of 0.951, precision of 0.943, sensitivity of 0.941, specificity of 0.800, negative predictive value of 0.865 and an F1-score of 0.938. CONCLUSION: AI-enhanced assessment of PRs can objectively, accurately, and reproducibly determine the positional relationship between M3i and MC. CLINICAL SIGNIFICANCE: The use of such an explainable AI system can assist clinicians in the intuitive positional assessment of lower third molars and mandibular canals. Further research is required to automatically assess the risk of alveolar nerve injury on panoramic radiographs.

Assessment of Accessory Canals and Foramina in the Mandibular Arch Using Cone-Beam Computed Tomography and a New Classification for Mandibular Accessory Canals.

OBJECTIVES: The objectives of the study include the following: (i) to assess the presence of accessory canals and foramina in the body of the mandible using cone-beam computed tomography (CBCT), (ii) to evaluate the location, number, diameter, and length of accessory canals in the body of the mandible, and (iii) to propose a new classification for mandibular accessory canals based on the location. METHODS: A total of 50 (25 males and 25 females) CBCT scans were analyzed in three anatomical planes and three-dimensional (3D) reconstructions for the exact number, location, diameter, and accessory length canals and accessory foramina in the body of the mandible. The statistical analysis used was an independent t-test. RESULTS: Out of 50 CBCT scans, a total of 243 accessory canals and 245 accessory foramina were found. About 53% of accessory canals and foramina were found in males, while 47% were observed in females; 89% were evident in the anterior region, and only 11% were in the posterior region. The majority (64%) of the medial lingual canals had a diameter greater than or equal to 1 mm, while only 32% of accessory canals had a diameter of less than 1 mm (p < 0.05). The mean length of median lingual canals in females was 1.2910 ± 0.2582 mm and 2.6438 ± 0.5288 mm in male subjects. Mandibular accessory canals are classified broadly into anterior and posterior accessory canals, which have further subdivisions. CONCLUSION: CBCT plays a dynamic role in determining the mandible location of various neurovascular structures, including accessory canals and foramina. Female subjects were observed with more accessory canals and foramina and more common in the anterior region than in the posterior region.