An Efficient Method of Tooth Segmentation Under Massive Medical Data

To accurately and efficiently complete tooth segmentation from a large amount of oral medical data, the burden doctors should be reduced. An automatic seed picking method based on 2D projection occlusal plane was proposed. First, authors establish two-dimensional data set for segmentation. Then, this article built prediction network teeth seeds YOLOv4 to realize position as well recognition categories. Finally, according statistical optimal position, are calculated mapped back three-dimensional space by reverse transformation final up seeds. Furthermore, combined with previous work division line detection, 3D dental model realized. The experimental results show that proposed has high accuracy real-time performance, which significantly reduces human-computer interaction in