Deep learning-based automated assessment of alveolar bone loss in CBCT for periodontitis

Clinical Snapshot

Key Findings

• P Value: Not reported in abstract

• Effect Size: DSC: teeth 95.85%, alveolar bone 95.75%, CEJ 86.18% (internal); external validation: teeth and alveolar bone DSC >95%, CEJ DSC >77%. Overall staging accuracy: 87.31% (Stage I: 97.01%; Stage II: 88.06%; Stage III/IV: 89.55%). Linear measurement agreement: ICC = 0.9266, Spearman's ρ = 0.9187

• Primary Outcome: Automated segmentation accuracy (DSC) and periodontitis staging accuracy of the CAD system compared with manual reference standard

• Nnt Or Sensitivity: Sensitivity and specificity not reported; staging accuracy used as surrogate. Time efficiency: 13.42-fold acceleration over manual workflow. Note: DSC and accuracy are not equivalent to sensitivity/specificity for diagnostic purposes

• Confidence Interval: Not reported for any metric

Clinical Application

The nnU-Net framework is open-source and computationally accessible, but clinical deployment would require integration with existing CBCT software platforms, regulatory approval as a medical device software, and validation on local equipment and patient populations. The 13.42-fold time reduction is compelling for high-volume specialist practices, but implementation costs and workflow integration challenges are not addressed In Australia, CBCT use in periodontology is guided by RACGP and Australian Dental Association (ADA) radiation safety principles, with CBCT generally reserved for complex or surgical periodontal cases rather than routine diagnosis. The TGA would classify this CAD system as a Class IIb or III medical device software (SaMD) under the Therapeutic Goods (Medical Devices) Regulations 2002, requiring conformity assessment before clinical use. There is no current PBS item for AI-assisted periodontal CBCT analysis. Australian specialist periodontal practice (RACDS/ANZAOMS context) may benefit from efficiency gains in staging complex cases, but the system would require validation on Australian patient populations and CBCT equipment configurations before adoption. The RACGP's 2023 guidelines on digital health and AI tools in general practice emphasise the need for local validation and clinician oversight of automated diagnostic tools. Adults with suspected or confirmed periodontitis undergoing CBCT imaging in specialist periodontal or oral radiology settings; most directly applicable to Stage I–IV periodontitis as classified by the 2018 AAP/EFP staging and grading system

Abstract

OBJECTIVES: 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. METHODS: 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. RESULTS: 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. CONCLUSION: The CAD system enables accurate automated segmentation and RBL quantification on CBCT images, with robust multicenter performance and substantial gains in efficiency. CLINICAL SIGNIFICANCE: This system offers a fast and reliable method for RBL assessment, supporting consistent diagnosis and monitoring of periodontitis.

References

1. 1.Wang, Y., Zheng, H., Duan, X., Li, Y., Jiang, J., Tang, K., Su, J., Zhang, X., Zheng, X., Zhan, X., & Huang, X. (2026). Deep learning-based automated assessment of alveolar bone loss in CBCT for periodontitis. Clinical Oral Investigations. https://doi.org/10.1088/1361-6560/ac8852