Three-dimensional liver image semantic segmentation method based on context attention strategy

Abstract

The invention relates to a three-dimensional liver image semantic segmentation method based on a context attention strategy. The method comprises the following steps: selecting a medical image data set to be subjected to liver segmentation, and dividing the medical image data set into a training set and a test set; preprocessing the three-dimensional liver image in the training set; in the encoding stage, obtaining a feature map of the liver by using a residual structure, a convolutional network and cavity convolution; in a decoding stage, obtaining a segmented image of the liver by using a context attention strategy module, transpose convolution and a depth supervision mechanism; and carrying out post-processing on the liver image obtained after semantic segmentation. The method has the characteristic of improving the semantic segmentation effect of the three-dimensional liver image, realizes a better automatic segmentation effect, and can assist doctors in diagnosis.

Description

technical field [0001] The invention relates to a method for semantic segmentation of three-dimensional medical images, in particular to a method for semantic segmentation of three-dimensional liver images based on a contextual attention strategy. Background technique [0002] The liver is located in the abdomen of the human body and is the largest important solid organ in the abdomen. However, diseases such as liver cancer related to the liver have become one of the most common diseases with the highest mortality in the world, which poses a great threat to human health and life. . In recent years, computed tomography (CT) has become the most widely used medical imaging method for discovering, diagnosing and treating liver tumors. It is necessary to know the shape and position of the liver in CT images in detail before the operation, so the precise segmentation of the liver has become the primary task of liver cancer treatment. However, the size, shape, and location of tum...

AI Technical Summary

Problems solved by technology

However, the two-dimensional convolutional network cannot make full use of the spatial information in the medical image data, and lacks the processing of the information between the slices of the three-dimensional medical data, so the boundary of the segmentation result is relatively rough, and the overall effect of the segmentation is not as good as that of the three-dimensional segmentation.

However, these studies have not processed the information between slices of medical image data, and the fusion of low-level semantic features and high-level semantic features of the target is not fully utilized.

Images