Assessment of accuracy and reproducibility of cephalometric identification performed by 2 artificial intelligence-driven tracing applications and human examiners.

OBJECTIVE: To assess the accuracy and reproducibility of cephalometric landmark identification performed by 2 artificial intelligence (AI)-driven applications (CefBot and WebCeph) and human examiners. STUDY DESIGN: Lateral cephalometric radiographs of 10 skulls containing 0.5 mm lead spheres directly placed at 10 cephalometric landmarks were obtained as the reference standard. Ten radiographs without spheres were obtained from the same skulls for identification of cephalometric points performed by the AI applications and 10 examiners. The x- and y-coordinate values of the cephalometric points identified by the AI applications and examiners were compared with those from the reference standard images using one-way analysis of variance and the Dunnet post-hoc test. The intraclass correlation coefficient (ICC) was used to evaluate reproducibility. Mean radial error (MRE) in identification was calculated with respect to the reference standard. Statistical significance was established at P < .05. RESULTS: Landmark identification by CefBot and the examiners did not exhibit significant differences from the reference standard on either axis (P > .05). WebCeph produced a significant difference (P < .05) in 4 and 6 points on the x- and y-axes, respectively. Reproducibility was excellent for CefBot and the examiners (ICC ≥ 0.9943) and good for WebCeph (ICC ≥ 0.7868). MREs of CefBot and the examiners were similar. CONCLUSION: With results similar to those of human examiners, CefBot demonstrated excellent reliability and can aid in cephalometric applications. WebCeph produced significant errors.

Radiographic perception of anatomical structures and bony changes in oncologic patients under antiresorptive therapy.

PURPOSE: To assess radiographic presentation of anatomical structures, bony changes and soft tissue calcifications on panoramic radiographs of oncologic patients under high dose antiresorptive drug therapy (ART) before exposure to dental extraction. METHODS: Panoramic radiographs of 57 patients under ART, taken previously to tooth extraction, and 57 control patients were evaluated by two oral radiologists regarding bone pattern, anatomical structures visibility, estimation of cortical width, mandibular cortical index (MCI), and presence of soft tissue calcifications. Parameters were compared between ART and age- and gender-matched healthy control groups. Bone patterns were further assessed by regions with or without tooth extractions and according to uneventful healing or MRONJ development. All comparisons were made using chi-square test with significance level set at 5%. RESULTS: Mandible and posterior maxilla presented more sclerotic bone patterns in patients under ART, regardless of tooth extraction and MRONJ development status (p < 0.05). Heterogeneous bone pattern was identified in two regions that both were subsequently affected by MRONJ. Anatomical structure visibility and presence of soft tissue calcifications was not different among groups (p > 0.05). ART patients showed significantly more C0 (thickening) and C1 MCI (p < 0.05). CONCLUSION: Sclerotic bone pattern and thicker mandibular cortices may represent a consequence of ART rather than MRONJ specific findings. Prospective studies on larger patient samples radiographically followed-up during the ART treatment are advised, with specific attention to heterogenous trabecular bone pattern as a possible MRONJ predictor.