Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

In Journal of endodontics ; h5-index 63.0

INTRODUCTION : Tooth segmentation on CBCT is a labour-intensive task, considering limited contrast resolution and potential disturbance by various artefacts. Fully automated tooth segmentation cannot be achieved by merely relying on CBCT intensity variations. This study aimed to develop and validate an artificial intelligence (AI)-driven tool for automated tooth segmentation on CBCT.

METHODS : Total of 433 DICOM images of single and double rooted teeth randomly selected from 314 anonymized CBCT scans were imported and manually segmented. An AI-driven tooth segmentation algorithm based on a feature pyramid network (FPN) was developed to automatically detect and segment teeth replacing manual user contour placement. The AI-driven tool was evaluated based on volume comparison, intersection over union (IoU), Dice score coefficient (DSC), morphologic surface deviation and total segmentation time.

RESULTS : Overall, AI-driven and clinical reference segmentations resulted in very similar segmentation volumes. The mean IoU for full tooth segmentation was 0.87 (±0.03) and 0.88 (±0.03) for semi-automated (SA) (clinical reference) vs fully automated AI-driven (F-AI) and refined AI-driven (R-AI) respectively. R-AI and F-AI showed an average median surface deviation from SA of 9.96 μm (±59.33) and 7.85 μm (±69.55) respectively. SA segmentations of single and double rooted teeth had a mean total time of 6.6 mins (±76.15s), F-AI of 0.5 mins (±8.64s) (12 times faster) and R-AI of 1.2 mins (±33.02s) (6 times faster).

CONCLUSION : This study demonstrated a unique fast and accurate approach for AI-driven automated tooth segmentation on CBCT. Results may open doors for AI-driven applications in surgical and treatment planning in oral healthcare.

Lahoud Pierre, EzEldeen Mostafa, Beznik Thomas, Willems Holger, Leite André, Van Gerven Adrian, Jacobs Reinhilde