Background: The accurate assessment of infraosseous periodontal defects is crucial for effective diagnosis and treatment planning. Cone-beam computed tomography (CBCT) enables detailed imaging of these defects; however, to leverage their full potential, CBCT images must be reconstructed in 3 dimensions (3D). Manual and semi-automatic (SA) segmentation methods are time-consuming and prone to human error. This study aimed to evaluate the performance of a deep learning (DL) model in segmenting mandibular infraosseous periodontal defects on CBCT scans.
Methods: A multi-stage Segmentation Residual Network (SegResNet)-based DL model was used to segment CBCT scans from patients with stages III to IV periodontitis. Linear and volumetric measurements of infraosseous defects from DL-generated 3D models were compared to those obtained using SA segmentation. The depth (INFRA), width (WIDTH), angle (ANGLE), and volume of 48 infraosseous defects were assessed on both DL and SA segmentations.
Results: Measurements made on the DL and SA segmentations correlated strongly. The intraclass correlation coefficient (ICC) was 0.941 (p < 0.0001) for INFRA, 0.943 (p < 0.0001) for WIDTH, 0.889 (p < 0.0001) for ANGLE, and 0.948 (p < 0.0001) for defect volume. These results indicate high reliability of the DL model in capturing key characteristics of infraosseous periodontal defects.
Conclusions: These findings support the use of DL-based CBCT segmentation as a valuable tool for enhancing periodontal diagnosis. However, as this study was limited to mandibular defects, applicability to maxillary cases remains to be validated.
Keywords: 3D visualization; artificial intelligence; cone‐beam computed tomography; deep learning; infraosseous defects; periodontal defects; segmentation.
Periodontitis can cause severe bone loss around teeth, leading to the formation of complex defects that are challenging to diagnose and to treat. Cone‐beam computed tomography (CBCT) provides detailed 3D imaging of these defects, but current methods for segmenting CBCT scans and acquiring 3D models are time‐consuming and prone to human error. This study evaluated the ability of artificial intelligence (AI) to automatically segment infraosseous periodontal defects on CBCT images. Using a SegResNet‐based deep learning model, the manuscript compared AI‐generated 3D models to the results of traditional semi‐automatic segmentation methods. The depth, width, angle, and volume of 48 infraosseous defects were measured, assessing whether AI could match human accuracy. The AI model performed exceptionally well, with strong statistical agreement between AI and human‐generated measurements. By improving the way periodontal defects are visualized and measured, AI‐powered CBCT analysis could help dentists make better treatment decisions, reduce variability in diagnosis, and reduce the complication rates.
© 2026 The Author(s). Journal of Periodontology published by Wiley Periodicals LLC on behalf of American Academy of Periodontology.