Deep learning-enabled 3D multimodal fusion of cone-beam CT and intraoral mesh scans for clinically applicable tooth-bone reconstruction
DDMF automatically fuses cone-beam CT (CBCT) and intraoral scans into 3D tooth crown-root-bone models: deep networks segment both scans, and a curvature-based jaw split, two-stage registration and crown replacement merge them, reaching a 0.17 mm average surface distance to expert models.
Sep 1, 2023