Tooth CT image segmentation method based on 3D multi-feature fusion

Abstract

The invention discloses a tooth CT image segmentation method based on 3D multi-feature fusion, and belongs to the technical field of image processing. The method comprises the following steps: firstly, performing image conversion processing on a CT image, and converting the CT image into a grey-scale map; then constructing a neural network model for tooth segmentation and training the neural network model, wherein a skeleton of the neural network model adopts a U-net network; and finally, carrying out CT image preprocessing on an image to be segmented to obtain a grayscale image, inputting thegrayscale image into the trained neural network model, and obtaining a segmentation result based on the output of the trained neural network model. According to the invention, the 3D multi-feature fusion tooth segmentation method is provided by combining the similarity of the upper and lower CT images, and the training precision of the neural network is improved; meanwhile, in combination with aCRF algorithm, redundant information generated by the neural network model is removed, so that the segmentation result is more accurate.

Description

technical field [0001] The invention relates to the technical field of medical CT (Computed Tomography, computerized tomography) image segmentation, in particular to a tooth CT image segmentation method based on neural network-based 3D multi-feature fusion. Background technique [0002] Medical CT image segmentation has great value in clinical applications, but compared with natural images, medical CT images have many defects: (1) low resolution and various artifacts on the image increase the difficulty of segmentation, (2) corresponding Tissues are difficult to calibrate. Today's segmentation methods are mainly divided into: neural network methods and non-neural network methods, and neural network methods are further divided into 2D neural network methods and 3D neural network methods. [0003] Non-neural network methods mainly use random forests for cascade segmentation (HAAR feature segmentation, HOG feature segmentation) and use Level Set (level set) for edge segmentati...

AI Technical Summary

Problems solved by technology

[0002] Medical CT image segmentation has great value in clinical applications, but compared with natural images, medical CT images have many defects: (1) low resolution and various artifacts on the image increase the difficulty of segmentation, (2) corresponding Tissue is difficult to calibrate

[0006] Two-dimensional neural networks have made great progress in medical image segmentation, but it is difficult to further improve, because 2D neural networks have some limitations: (1) The training set labels used by 2D neural networks are difficult to distinguish information between similarly located tissues

(2) The 2D image itself is difficult to accurately express the differences of different individuals

Good results can also be achieved in medical image segmentation, but due to the characteristics of medical images, this method still has many deficiencies and needs further improvement

Images