Ultrasonic cardiogram multi-mode multi-section classification method based on deep learning algorithm

The invention provides an echocardiogram multi-mode multi-section classification method based on a deep learning algorithm, and the method comprises the steps: collecting adult echocardiogram videos and images, carrying out the preprocessing of the adult echocardiogram videos and images, carrying out the marking of the preprocessed adult echocardiogram videos and images, generating an adult echocardiogram data set, and carrying out the classification of the adult echocardiogram data set. The adult echocardiogram data set is divided into a training set, a verification set and a test set. The method comprises the following steps: constructing an adult echocardiography section classification model based on a ResNet network, training the adult echocardiography section classification model through a training set, screening an optimal classification model through a verification set, performing performance evaluation on the optimal adult echocardiography section classification model based on a test set, and inputtin