Coronary artery region segmentation system and method based on improved 3D Unet

Abstract

The invention discloses a coronary artery region segmentation method and system based on improved 3D Unet, and the method comprises the steps: inputting a to-be-segmented DICOM image, and carrying outthe preprocessing of the image; inputting the preprocessed image into a pre-trained coronary artery segmentation model, and obtaining and outputting an image in which a coronary artery region is segmented, wherein the coronary artery segmentation model is obtained by training a historical DICOM image, the coronary artery segmentation model is an improved 3D Unet model, each layer of down-samplingof the improved 3D Unet model is finally added into an incomplete module, and the number of residual blocks is increased by one layer as the network depth is increased by one layer; and the up-sampling process adopts a deconvolution process to amplify the picture. Compared with a traditional method in which a deconvolution process relates to a weight updating learning process, the method of the invention has higher adaptability to different tasks.

Description

technical field [0001] The invention relates to the technical field of image segmentation, in particular to an improved 3D Unet-based coronary artery region segmentation method and system. Background technique [0002] With the continuous development of computer vision technology, the potential of visual segmentation tasks in the field of medical images is gradually being explored. Thanks to the blowout growth of Internet resources today, medical image data has also become more abundant, which makes the deep learning technology driven by big data refresh the accuracy of medical image segmentation again. [0003] The heart is an important organ in our body. Having a healthy and stable working heart is a necessary condition for us to explore, create and perceive the world. However, various heart diseases also seriously threaten the lives of many people. To effectively treat and prevent these diseases, accurate calculation, modeling, and analysis of coronary artery structures...

AI Technical Summary

Problems solved by technology

[0005] For common organ segmentation tasks, the relatively large area of ​​​​the organ is more obvious. For the coronary artery segmentation problem, because the production method of blood vessels is not uniform, the shapes are also very different, and the size of the coronary artery area in different slices exists. huge difference, such as figure 1 As shown, it is a comparison chart of the size of the coronary artery area in different slices. It can be found that the segmentation problem is difficult. It can be seen that there are significant differences in the shape and size of the coronary artery area in different sequences of slices, which provides a guideline for the subsequent feature extraction. It is a huge challenge, and after testing, the segmentation accuracy of the traditional two-dimensional convolutional neural network is not ideal for the problem that the shape changes greatly, and the target area is much smaller than the size of the picture.

Images