Deep learning-based automated assessment of alveolar bone loss in CBCT for periodontitis.
Authors
Affiliations (9)
Affiliations (9)
- Clinical Research Center for Oral Tissue Deficiency Diseases of Fujian Province, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, 350002, China.
- Fujian Key Laboratory of Oral Diseases & Fujian Provincial Engineering Research Center of Oral Biomaterial& Stomatological Key laboratory of Fujian College and University, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, 350000, China.
- Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application, Fujian Normal University, Fuzhou, 350117, China.
- Department of Stomatology, Quanzhou First Hospital Affiliated to Fujian Medical University, Quzhou, 362000, China.
- Department of Stomatology, Nanping Second Hospital, Nanping, 353000, China.
- Department of Stomatology, Fujian Provincial Geriatric Hospital, Fuzhou, 350003, China.
- Clinical Research Center for Oral Tissue Deficiency Diseases of Fujian Province, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, 350002, China. [email protected].
- Fujian Key Laboratory of Oral Diseases & Fujian Provincial Engineering Research Center of Oral Biomaterial& Stomatological Key laboratory of Fujian College and University, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, 350000, China. [email protected].
- Fujian Provincial Engineering Technology Research Center of Photoelectric Sensing Application, Fujian Normal University, Fuzhou, 350117, China. [email protected].
Abstract
This study aimed to develop and validate a CBCT-based automated system for assessing radiographic alveolar bone loss (RBL) to improve the accuracy and efficiency of periodontitis diagnosis. A total of 110 patients (2,796 teeth) with Stage I-IV periodontitis from four center were included. The nnU-Net framework was used to segment teeth, alveolar bone, and the cemento-enamel junction (CEJ). RBL was calculated automatically using an edge-constrained shortest path algorithm. The model was trained on data from Center A and externally validated with datasets from Centers B-D. Linear periodontal measurements from 11 CBCT scans were compared between manual and CAD-based segmentation. An independent validation set was used to assess automated staging accuracy and time efficiency. The CAD system achieved Dice similarity coefficients (DSC) of 95.85% for teeth, 95.75% for alveolar bone, and 86.18% for the CEJ. External validation showed alveolar bone and tooth DSC values both above 95% and CEJ DSC values above 77%. Linear measurements showed strong agreement with manual segmentation (Spearman's ρ = 0.9187; ICC = 0.9266). For staging, the CAD system reached an overall accuracy of 87.31%, with 97.01% for Stage Ⅰ, 88.06% for Stage Ⅱ and 89.55% for Stage Ⅲ/Ⅳ. The CAD system represented a 13.42-fold acceleration compared with the manual workflow. The CAD system enables accurate automated segmentation and RBL quantification on CBCT images, with robust multicenter performance and substantial gains in efficiency. This system offers a fast and reliable method for RBL assessment, supporting consistent diagnosis and monitoring of periodontitis.