A CT medical image data enhancement method for cholelithiasis based on lightweight convolution neural network

A convolutional neural network and medical image technology, applied in the field of image processing, can solve problems such as undetected cholelithiasis CT medical images, achieve good visual effects and medical effects, improve effectiveness, and improve fitting capabilities
CN109544585APending Publication Date: 2019-03-29CHINA UNIV OF PETROLEUM (EAST CHINA)
0 Cites 8 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Current Assignee / Owner
CHINA UNIV OF PETROLEUM (EAST CHINA)
Publication Date
2019-03-29

Smart Images

  • Figure 1
    Figure 1
Patent Text Reader

Abstract

The invention provides a CT medical image data enhancement method for cholelithiasis based on a lightweight convolution neural network, which includes constructing CT medical image data enhancement convolution neural network for cholelithiasis, wherein The network consists of four convolution units; Firstly, CT medical image dataset of cholelithiasis is constructed as the input of neural network,and the image is enhanced by edge information and redundant information is removed. Then, the image is cut according to the segmentation threshold to form many image blocks, and the dataset is expanded by scaling, rotation and translation. Convolution neural network (CNN) is trained continuously with data set, and adaptive lifting neural network (ALN) is used to extract image features, perform stretch contrast, equalize histogram and reconstruct image. the Convolution neural network model which can be used to enhance CT medical images of cholelithiasis can be generated. The method can realizereal-time enhancement of cholelithiasis CT medical image data, and achieve good visual and medical effects.
Need to check novelty before this filing date? Find Prior Art

Description

Technical field

[0001] The invention relates to the field of image processing, in particular to a cholelithiasis CT medical image data enhancement method based on a lightweight convolutional neural network. Background technique

[0002] The process of image recognition includes preprocessing, feature extraction, feature matching, and similarity calculation. An important part of the preprocessing is the processing of image enhancement. Its purpose is to enhance the useful information in the image to improve the visual effect of the image, and is aimed at the application of a given image. Image data enhancement is a very important part, and its processing effect directly affects the subsequent image recognition process.

[0003] The gallstone disease involved in the present invention is a common digestive system disease, with various diseases, complicated pathogenic factors, high morbidity, and difficulty in dissolving and expelling stones. In addition, there are many types and for...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More