priori shape constraint-based BCA-UNet liver segmentation method

Abstract

The invention relates to the technical field of computer vision, in particular to a priori shape constraint-based BCA-UNet liver segmentation method, which comprises the following steps of: inputtinga liver CT image, preprocessing the liver CT image to obtain a preprocessed liver CT image, inputting the preprocessed liver CT image into a trained liver segmentation model, and obtaining a BCAUNet liver segmentation model; obtaining liver segmentation results. According to the method, the optimized active contour loss function is adopted to calculate the loss of the high-dimensional features, the features between the two networks are fused to serve as the attention signal of the next layer, the attention signal is used for constraining the segmentation network (BCAUNet, error back propagation is optimized layer by layer, and the loss of edge contours is avoided. Besides, the liver segmentation model is sensitive to the edge contour of the image so that the segmentation precision can be enhanced and the surface distance error can be reduced.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a BCA-UNet liver segmentation method based on prior shape constraints. Background technique [0002] Accurate liver segmentation is crucial in clinical applications, such as pathological diagnosis of liver diseases, surgical planning, and postoperative evaluation. But liver segmentation is still a challenging task. First, there are problems such as blurred edges and uneven gray levels in the liver image; second, liver segmentation based on deep convolutional neural networks has the problem of loss of liver edge contour information caused by pooling operations and superimposed convolution operations. Finally, the 3D liver data segmentation method has the problem of consuming large computing resources. [0003] Existing liver segmentation methods can be divided into model-driven traditional methods and data-driven deep learning methods. The main idea of ​​the model-drive...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, the present invention provides a BCA-UNet liver segmentation method based on prior shape constraints for the defects such as insufficient feature information extraction and fuzzy liver edge contour in the existing Unet network liver segmentation method

Images