Q-Bone system: an intelligent quantitative system for alveolar bone loss to assist the diagnosis of periodontitis - model development and validation.

OBJECTIVES

To develop and validate the Q-Bone system, an intelligent quantitative system for anatomically driven assessment of alveolar bone loss and assistance in the diagnosis of periodontitis across multiple clinical centers and imaging devices.

METHODS

This study included 1,273 periodontitis cases from four clinical centers using diverse imaging devices. A multitask deep learning model, Deep Gradient Network (DGNet), was employed for tooth segmentation and anatomical keypoint localization, and was integrated with an anatomically driven, curvature-based quantification algorithm for alveolar bone resorption ratio (ABRR) measurement. Performance was evaluated using internal and multicenter external datasets, including patient-level agreement analysis for Stage, Grade, and Extent.

RESULTS

The Q-Bone system demonstrated strong performance: tooth segmentation achieved an S-measure of 0.929, and keypoint localization reached a PRCK@0.5 of 0.994 in internal validation. Tooth-level ABRR showed high agreement with specialist measurements, with an ICC of 0.973 and minimal bias (- 0.238%). In the multicenter clinical validation cohort (n = 174), agreement between Q-Bone and the specialist reference standard was high at the patient level, with Cohen's κ values of 0.9351 for Stage, 0.9367 for Grade, and 0.9770 for Extent. For the ordinal outcomes of Stage and Grade, linear weighted κ values were 0.9508 and 0.9515, respectively.

CONCLUSIONS

The Q-Bone system enables automated tooth segmentation, anatomical keypoint localization, tooth-level quantification of alveolar bone loss, and patient-level assessment across Stage, Grade, and Extent. It showed high agreement with specialist reference standards across multicenter and cross-device settings, supporting its applicability as a standardized imaging-based assistance tool for periodontal evaluation.