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 for precise alveolar bone loss quantification and intelligent periodontitis diagnosis 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, DGNet, was employed for tooth segmentation and anatomical key points localization, integrated with an anatomically-driven quantification algorithm. Performance was assessed using several validation datasets. Results The Q-Bone system demonstrated strong performance: tooth segmentation achieved an S-measure of 0.929, and key point localization reached a PRCK@0.5 of 0.994 in internal validation. The system showed high consistency with expert measurements, with an ICC of 0.973. It quantified alveolar bone loss with minimal bias (-0.238%) and assisted in periodontitis diagnosis, achieving a Kappa value of 0.955 for tooth-level diagnosis. Conclusions The Q-Bone system provides accurate, automated alveolar bone loss quantification and intelligent periodontitis diagnosis. It showed excellent generalization across multicenter and cross-device settings, making it a reliable tool for periodontitis diagnosis.