Abdomen ultrasonic image segmentation method

Abstract

The invention relates to an abdomen ultrasonic image segmentation method. The method comprises the following steps: S1, acquiring an abdomen ultrasonic image sample; S2, performing layered labeling onthe abdomen ultrasonic image sample; S3, constructing a U-NET neural network, and training the U-NET neural network by using the abdomen ultrasonic image sample subjected to layered labeling to obtain an ultrasonic image segmentation network model; and S4, based on the ultrasonic image segmentation network model, directly segmenting the abdominal ultrasonic image, and outputting a layered image of the abdominal ultrasonic image at one time. Compared with the prior art, the scale quantity and range of training samples are increased through data expansion, the step of cutting small images is avoided, meanwhile, computer storage resources are saved, end-to-end learning is conducted through the full convolutional neural network, the segmentation precision of all layers of the abdomen is higher, the segmentation results of all layers in the abdomen ultrasonic image can be output at a time, and the segmentation speed is effectively increased.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method for segmenting abdominal ultrasound images. Background technique [0002] Image segmentation is the technology and process of dividing the image into several specific and unique regions, and extracting the target of interest. By segmenting the abdominal ultrasound image, the main layers of the abdomen can be automatically distinguished: skin layer, fat Layer, subcutaneous muscle layer and peritoneum, thereby reducing the identification of artificial naked eyes, which is conducive to rapid guided ultrasound puncture. [0003] Since the neural network has the algorithm characteristics of simulating human perception, the segmentation performance is significantly improved compared with other algorithms. At present, the ultrasound image is usually segmented by means of the neural network, but this segmentation method generally adopts the mode of cutting into small im...

AI Technical Summary

Problems solved by technology

Therefore, part of the time is spent in the process of cutting the small images in the training process, and most of the time is spent in the process of cutting the small images and splicing them into the whole image in the test process, that is, there is a problem of complex segmentation and too much time. It leads to slow image segmentation; in addition, the small images after cutting need to be stored for training, which will cause additional waste of computer storage resources

Images