Can artificial intelligence-driven cephalometric analysis replace manual tracing? A systematic review and meta-analysis.

OBJECTIVES: This systematic review and meta-analysis aimed to investigate the accuracy and efficiency of artificial intelligence (AI)-driven automated landmark detection for cephalometric analysis on two-dimensional (2D) lateral cephalograms and three-dimensional (3D) cone-beam computed tomographic (CBCT) images. SEARCH METHODS: An electronic search was conducted in the following databases: PubMed, Web of Science, Embase, and grey literature with search timeline extending up to January 2024. SELECTION CRITERIA: Studies that employed AI for 2D or 3D cephalometric landmark detection were included. DATA COLLECTION AND ANALYSIS: The selection of studies, data extraction, and quality assessment of the included studies were performed independently by two reviewers. The risk of bias was assessed using the Quality Assessment of Diagnostic Accuracy Studies-2 tool. A meta-analysis was conducted to evaluate the accuracy of the 2D landmarks identification based on both mean radial error and standard error. RESULTS: Following the removal of duplicates, title and abstract screening, and full-text reading, 34 publications were selected. Amongst these, 27 studies evaluated the accuracy of AI-driven automated landmarking on 2D lateral cephalograms, while 7 studies involved 3D-CBCT images. A meta-analysis, based on the success detection rate of landmark placement on 2D images, revealed that the error was below the clinically acceptable threshold of 2 mm (1.39 mm; 95% confidence interval: 0.85-1.92 mm). For 3D images, meta-analysis could not be conducted due to significant heterogeneity amongst the study designs. However, qualitative synthesis indicated that the mean error of landmark detection on 3D images ranged from 1.0 to 5.8 mm. Both automated 2D and 3D landmarking proved to be time-efficient, taking less than 1 min. Most studies exhibited a high risk of bias in data selection (n = 27) and reference standard (n = 29). CONCLUSION: The performance of AI-driven cephalometric landmark detection on both 2D cephalograms and 3D-CBCT images showed potential in terms of accuracy and time efficiency. However, the generalizability and robustness of these AI systems could benefit from further improvement. REGISTRATION: PROSPERO: CRD42022328800.

Analysis of mandible trabecular structure using digital periapical radiographs to assess low bone quality in postmenopausal women.

PURPOSE: To analyze the quality of mandibular trabecular structure in postmenopausal women using periapical radiographs. Postmenopausal women are subjected to low bone quality; hence, early detection methods are needed. In addition to bone mineral density (BMD), trabecular architecture must be assessed to determine bone quality. The mandible represents bone quality and allows the assessment of trabecular structure from periapical radiographs. MATERIAL AND METHODS: Lumbar (BMDL) and femoral BMD (BMDF) examinations were performed using dual-energy X-ray absorptiometry (DXA) in 31 postmenopausal women and divided into normal, osteopenia, and osteoporotic groups. Periapical radiographs were taken at both posterior sites of the mandible. The region of interest was taken 2 mm from the apical root of the first molar. Trabecular parameters consisting of trabecular thickness (Tb.Th) and bone percentage (BA/TA) were measured using BoneJ. RESULTS: Both trabecular parameters were significantly correlated with BMDF [BA/TA ​​(r = 0.3796; p < 0.05) and Tb.Th (r = 0.508; p < 0.05)]. BA/TA and Tb.Th were significantly different between the osteoporosis and normal groups (p < 0.05) contrast to osteopenia and normal groups (p > 0.05). CONCLUSION: Changes in mandibular trabeculae structure in postmenopausal women can be assessed using periapical radiographs.

Alteration of mucosa cell maturation pattern after exposure to different radiographic imaging methods

Aim: Dental imaging has been widely used for diagnosis in dentistry. However, dental X-ray may induce cytotoxicity leading to apoptosis in oral mucosa cells. The present study aimed to observe the maturation pattern of buccal and gingival cells after exposure to X-ray radiation from analog/digital panoramic scanning and cone beam computed tomography (CBCT). Methods: The research samples were 40 subjects who fulfilled the inclusion and exclusion criteria. The subjects were divided into the exposed (patients who received analog/digital panoramic radiography or CBCT) and controlled (patients who had no radiography examinations) groups, with 10 subjects in each group. Exfoliative cytology smears were obtained from buccal mucosa and gingiva before exposure (or on day 0 for the control group) and 10 days later. The cells were stained with the Papanicolaou method. Then, the superficial, intermediate, and parabasal cells were counted in each glass slide. Results: No significant differences (p > 0.05) were observed among all cell types between day 0 and 10 in the control group. Meanwhile, after exposure to three kinds of radiography examinations, the frequency of intermediate cells in buccal mucosa and gingiva increased (p < 0.05), but that of superficial cells decreased (p < 0.05) significantly. No significant difference was found in the parabasal cells (p > 0.05). The frequency differences between intermediate and superficial cells showed no significant difference between the buccal mucosa and gingiva. Conclusion: Analog/digital panoramic radiography and CBCT exposure can induce cytotoxicity by altering the maturation pattern of buccal mucosa cells and gingiva, so it is strongly recommended to only perform these procedures if necessary and avoid repeated exposure to the same patient