Method for establishing convolutional neural network data set for training and recognizing cardiac blood vessel type

Abstract

The invention discloses a method for establishing a convolutional neural network data set for training and recognizing a cardiac blood vessel type. The method comprises the steps that cardiac coronaryartery data after desensitization are acquired and stored in the form of a single static picture; in the single static picture, a corresponding color is used to mark a blood vessel under the currentbody position to form a coarse plot; pixel level marking is carried out on information marked in the coarse plot to form a fine plot; the color of the blood vessel in the fine plot is recognized, so that the picture becomes a single-channel image from a three-channel image; the single-channel image is stored as a binary image; and based on the desensitized cardiac coronary artery data, the coarseplot, the fine plot, the single-channel image and the binary image, the convolutional neural network data set which trains and recognizes the cardiac blood vessel type is established. According to theinvention, unified processing is carried out on the data; the data in the data set are real and diverse; the data set has the advantages of large data volume, rich data type, standard format and small error rate, and can be used for training neural networks with different functions; and manual intervention is reduced.

Description

technical field [0001] The invention relates to a method for establishing a convolutional neural network data set for training and identifying cardiovascular types and the data set, belonging to the technical field of communication. Background technique [0002] Artificial neural network is a computing model proposed in the field of artificial intelligence. It abstracts the human brain neuron network from the perspective of information processing, establishes a simple model, and forms different networks according to different connection methods to solve the problem of artificial intelligence. Certain problems in domains such as image recognition. Convolutional Neural Network (CNN) is a kind of artificial neural network. It is a feedforward neural network. Artificial neurons can respond to surrounding units and can perform large-scale image processing, that is, input a picture, and convolutional neural network The network performs a certain transformation on this picture and...

AI Technical Summary

Problems solved by technology

Segmentation networks trained with general-purpose image datasets cannot be used for identification and segmentation of coronary arteries

Images