From Full and Partial Intraoral Scans to Crown Proposal: A Classification-Guided Restoration Assistance Pipeline

2026-05-14

AI Summary

This work addresses the challenges of segmenting partial intraoral scans and preserving occlusal detail in end-to-end crown generation. The authors propose a classification-guided, end-to-end pipeline that first employs a Dynamic Graph CNN (DGCNN) for semantic tooth-type classification, followed by robust segmentation via RANSAC+ICP registration and graph-cut optimization. Subsequently, a DGCNN-based embedding retrieves morphologically similar crowns from a database, which are then refined through spline-guided alignment and context-aware fitting using the Blender Python API. Evaluated on 17 tooth classes, the method achieves a macro-averaged Dice Similarity Coefficient of 0.9249 (exceeding 0.9468 for key teeth) and a centroid error below 0.28 mm. High-fidelity, clinically editable crown drafts are generated within 2.5–3.5 minutes.

Abstract

Single-unit crown restoration is among the most common procedures in clinical dentistry, with CAD/CAM workflows now designing crowns directly from intraoral scans. Partial scans are often preferred over full-arch scans for single-unit cases due to fewer stitching errors, yet most segmentation networks trained on full arches fail on partial scans, while end-to-end generative crown methods often produce over-smoothed surfaces that lose occlusal detail. We propose an end-to-end pipeline that takes a raw intraoral scan and target FDI tooth number as input and outputs an initial, patient-specific crown proposal for clinician refinement. The pipeline has three phases: (I) data preparation and pose standardization; (II) segmentation routed by scan type; and (III) crown proposal generation via context-aware retrieval and Blender-based fitting. We address partial-scan segmentation through a classify-then-align strategy: a DGCNN classifier categorizes the scan into one of five anatomical types, then coarse-to-fine RANSAC+ICP registration standardizes the jaw coordinate frame, followed by graph-cut optimization to refine tooth-gingival boundaries. Trained on 1,958 partial scans, the pipeline achieves macro-average DSC 0.9249, Recall 0.8919, and Precision 0.9615 across 17 semantic classes; a fine-tuned full-arch model reaches DSC 0.9347. The prepared tooth and its mesial and distal neighbors achieve DSC 0.9468-0.9569 with sub-millimeter Centroid Errors (0.2666-0.2774 mm). These centroids anchor a retrieval module using DGCNN embeddings and cosine similarity over neighboring and opposing teeth, followed by spline-guided alignment and Blender Python API refinement. The pipeline produces a preliminary crown shell in 2.5-3.5 minutes, offering a practical alternative to end-to-end generative approaches.

Problem

• crown restoration
• partial intraoral scan
• tooth segmentation
• occlusal detail
• CAD/CAM

Innovation

• partial intraoral scan
• classification-guided segmentation
• context-aware crown retrieval
• DGCNN embedding
• Blender-based refinement