Dental jaw three-dimensional model segmentation method and system

Abstract

The invention provides a dental three-dimensional model segmentation method and system. The method comprises the following steps: acquiring a manual feature of each vertex in a dental three-dimensional model; splicing the manual feature of each vertex with the Cartesian coordinates to obtain an input feature of each vertex; inputting each vertex input feature into a deep learning point cloud segmentation network in sequence to obtain a tooth position label of each vertex; and sequentially mapping the tooth position label of each vertex to the tooth jaw three-dimensional model to obtain boundary lines of two adjacent teeth and between the teeth and the gingiva. According to the method, multiple lightweight manual features are fused and used, compared with an algorithm only using normal and curvature information, multi-scale and multi-level local features of the tooth jaw model can be better captured, and the method can play a significant role in improving the precision of a tooth jaw segmentation task; and on the basis of manual features, the features of the three-dimensional dental model are further extracted by using deep learning, so that the network learning cost is reduced, and the dependence of a deep network on the number of training samples and the training period is reduced.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and in particular relates to a method and system for segmenting a three-dimensional model of teeth and jaws. Background technique [0002] Computer-aided design (CAD) has been widely used in the field of dentistry, such as orthodontic diagnosis, tooth restoration, tooth rearrangement, etc. The segmentation of the three-dimensional model of the jaw is the basis of dental CAD, and the accurate tooth segmentation results play a key role in the subsequent analysis and design. At present, the 3D model segmentation algorithms of teeth and jaws can be divided into traditional segmentation algorithms and segmentation algorithms based on deep learning according to whether purely manual features are used. [0003] Traditional jaw model segmentation algorithms generally rely on manually constructed features, such as normal vectors and curvature. Typical algorithms include curvature-based algorithm...

AI Technical Summary

Problems solved by technology

The existing algorithms based on artificial features and deep learning have their own advantages and disadvantages, and they have not been well combined

Images