Medical image segmentation method and system based on AS-UNet

Abstract

The invention discloses a medical image segmentation method and system based on AS-UNet. According to the invention, an edge attention network framework is provided, edges are enhanced, and missing values are reduced. The method comprises the following steps: obtaining a mask edge image through a mask edge extraction algorithm, and connecting the mask edge image to the last three layers of the UNet expansion path to reinforce edge information; and a new attention module being introduced into the BAB, channel attention and space attention being combined, feature response being activated, acquisition of key information in the image being enhanced, and the target area segmentation capability of the network being improved. According to the method, a region and boundary combination loss function is used, so that the segmentation precision is improved, and meanwhile, parameters are reduced during testing. And network parameters in the AS-UNet are continuously updated through forward and backward feedback during training under the action of the combined loss function, so that the trained model can abandon the added parameters of the BAB part during testing, and the time cost of prediction is reduced.

Description

technical field [0001] The invention belongs to the field of artificial intelligence image segmentation, and mainly relates to an AS-UNet-based medical image segmentation method and system. Background technique [0002] In recent years, deep learning technology has been widely used in the field of medical images, and how to automatically identify and segment lesions in medical images is one of the most concerned issues. Due to various human organs, complex shapes of lesions, image noise interference and many other reasons, the objects waiting for segmentation of organ lesions tend to have unclear segmentation edges and large missing values. [0003] At present, many scholars have carried out related research on medical image segmentation methods. Among them, UNet is the most typical and widely used method. It uses the contraction path to obtain feature information, and uses the expansion path to achieve precise positioning. It has been used in various data sets. better perf...

AI Technical Summary

Problems solved by technology

The shapes of cells and organs are complex and diverse, and there may be overlapping clusters, resulting in a high probability of mis-segmentation, which affects medical judgment. Moreover, most methods use region-based Dice as a loss function, which ensures the integrity of the region but is easy to lose Edge details; Second, the model is complex

More and more network models are improved based on UNet, but complex models and redundant parameters will cause difficulties in the deployment stage, which is not conducive to actual operation

Images