Work

Periodontal bone loss analysis via keypoint detection with heuristic post-processing

Year: 2026

Type: article

Abstract: Objectives: This study proposes a deep learning framework and an annotation methodology for the automatic detection of periodontal bone loss landmarks, associated conditions, and staging. Methods 192 periapical radiographs were collected and annotated using a stage agnostic methodology, labelling clinically relevant landmarks regardless of disease presence or extent. We propose a heuristic post-processing module that aligns predicted keypoints to tooth boundaries using an auxiliary instance segmentation model. An evaluation metric, Percentage of Relative Correct Keypoints ( P R C K ), is proposed to capture keypoint performance in dental imaging domains. Four donor pose estimation models were adapted with fine-tuning for our keypoint problem. Results Post-processing improved fine-grained localisation, raising average P R C K 0.05 by + 0.028 , but reduced coarse performance for P R C K 0.25 by − 0.0523 and P R C K 0.5 by − 0.0345 . Orientation estimation shows excellent performance for auxiliary segmentation when filtered with either stage 1 object detection model. Periodontal staging was detected sufficiently, with the best mesial and distal Dice scores of 0.508 and 0.489 , while furcation involvement and widened periodontal ligament space tasks remained challenging due to scarce positive samples. Scalability is implied with similar validation and external set performance. Conclusion The annotation methodology enables stage agnostic training with balanced representation across disease severities for some detection tasks. The P R C K metric provides a domain-specific alternative to generic pose metrics, while the heuristic post-processing module consistently corrected implausible predictions with occasional catastrophic failures. Clinical significance: The proposed framework demonstrates the feasibility of clinically interpretable periodontal bone loss assessment, with the potential to reduce diagnostic variability and clinician workload.

Source: Computers in Biology and Medicine

DOI: 10.1016/j.compbiomed.2026.111515