Dental CBCT three-dimensional tooth segmentation method based on deep learning

Abstract

The invention discloses a dental CBCT three-dimensional tooth segmentation method based on deep learning. According to the invention, the method includes performing semantic segmentation on teeth in each image in a CBCT image sequence, so that noise is removed; constructing a deep supervision coding-decoding network for denoising an oral CT image, mutually connecting coding and decoding sub-modules through a series of nested dense jump paths, and reducing semantic deficiency of feature maps in the coding and decoding sub-modules; the method specifically comprises the following four stages: stage 1, collecting and preprocessing a dental CBCT image; stage 2, constructing a model training set; stage 3, constructing a network segmentation model of a coding-decoding structure; and step 4, performing model training and evaluation. Experimental results show that the Dice similarity coefficient for individual three-dimensional tooth segmentation is 95.64%. Results show that the method provided by the invention provides an effective clinical application framework for digital dentistry.

Description

technical field [0001] The present invention provides a dental CBCT three-dimensional tooth segmentation method based on deep learning. The present invention aims at cone-beam computed tomography (CBCT) images of the dental cavity, constructs a deep learning semantic segmentation model to segment target teeth, and obtains a three-dimensional tooth model after denoising. Background technique [0002] Digital dentistry is advancing rapidly with rapid innovations in artificial intelligence and advances in cone-beam computed tomography (CT), intraoral and facial scanners, and three-dimensional (3D) printing of teeth. Digital dentistry increases the efficiency of dentists and improves the accuracy of orthodontic diagnosis, treatment and surgical guidance. A fundamental component of digital dentistry is the 3D segmentation of teeth, jaws, and skulls from CBCT images, and accurate tooth shapes facilitate medical evaluation simulations. It is a difficult task to automatically and ...

AI Technical Summary

Problems solved by technology

The process of tooth segmentation is image denoising, which preserves the teeth as much as possible. Traditional denoising methods such as median filtering, Wiener filtering, and histogram-based filtering, etc., are far from meeting the needs of dental diagnosis.

Images