Three-dimensional jawbone image segmentation method and device based on CBCT and terminal equipment

Abstract

The invention relates to the field of image processing, and provides a three-dimensional jawbone image segmentation method based on CBCT, and the method comprises the steps of extracting a plurality of image sub-sequences from a to-be-segmented CBCT image, inputting the image sub-sequences into a trained convolutional neural network model, and correspondingly obtaining a plurality of segmentationresults; integrating the segmentation results to obtain a three-dimensional jaw bone segmentation result of the CBCT image to be segmented, wherein the trained convolutional neural network model is obtained through the following steps: constructing a convolutional neural network model; preprocessing the CBCT image with the segmented and marked jawbone, extracting an image sub-sequence from the CBCT image as a training sample, and training the convolutional neural network model. Meanwhile, the invention further provides a corresponding three-dimensional jaw image segmentation device based on CBCT and terminal equipment. The embodiment provided by the invention is suitable for extracting the image of the three-dimensional jawbone region from the CBCT image.

Description

Technical field[0001]The invention relates to the field of image processing, in particular to a CBCT-based three-dimensional jaw image segmentation method, a CBCT-based three-dimensional jaw image segmentation device, a terminal device and a corresponding storage medium.Background technique[0002]Maxillofacial fracture is a common type of trauma in traffic accidents, accidental injuries, competitive sports and other accidents. Because of its complex and diverse anatomical structure, it is more difficult to diagnose with only clinical symptoms and signs, and imaging aids are often needed. Among them, the three-dimensional image of cone beam CT (CBCT) can show the position and displacement direction of the fracture more clearly and intuitively, and has the advantages of low radiation dose, high spatial resolution, and convenient application that traditional CT does not have. In recent years, it has been widely used in the auxiliary examination of maxillofacial tumors, plastic surgery a...

AI Technical Summary

Problems solved by technology

There are two main disadvantages in the existing methods: 1) The segmentation results are inaccurate, because the threshold method and the region growing method have poor segmentation results when the edges are not clear; 2) The process is time-consuming, requiring doctors to conduct multi-angle, layer-by-layer Setting parameters

Images