Screening method of tachycardia ECG based on deep feature fusion network

Abstract

A screening method of tachycardia ECG based on deep feature fusion network includes the following steps: step 1, data processing: preprocessing an original ECG image, removing baseline drift and powerline interference in the ECG; step 2, data reconstruction: carrying out frame selection separation of 12 leads in the preprocessed ECG image, and reorganizing and reconstructing a data set; step 3, model construction: constructing deep neural network; step 4, model training: inputting the processed and reconstructed data to the network, carrying out parameter adjustment, and training a model; andstep 5, model outputting: screening the tachycardia ECG by the trained model. The method can screen whether the situation is tachycardia according to the ECG.

Description

technical field [0001] The present invention relates to the fields of medical image analysis and machine learning, in particular to a screening for tachycardia applied to twelve-lead electrocardiograms, and belongs to the field of medical image analysis based on deep learning. Background technique [0002] Tachycardia refers to a heart rate exceeding 100 beats per minute, which is a relatively common clinical disease. In medicine, it can be divided into two types: physiological and pathological. Physiological tachycardia is generally related to physical activity, alcohol consumption, etc., which often does not require treatment. Pathological tachycardia is generally caused by anemia, heart disease, etc. Once it exceeds 140 beats per minute, it will cause harm or even sudden death. This requires early treatment, so how to accurately screen out tachycardia based on the electrocardiogram is very important. [0003] During routine ECG examination, 4 limb lead electrodes and V ...

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the inefficiency of existing ECG methods for identifying tachycardia

Images