An ECG Vector Reconstruction Method Based on Unsupervised Learning

Abstract

An ECG vector reconstruction method based on unsupervised learning, by using a neural network, the ECG vector is reconstructed from the input standard 12-lead ECG. In the training process, the method of mapping the standard 12-leads to the ECG vector first, and then using the projection method to restore the 12-lead ECG solves the problem that the traditional method relies on the correspondence between the 12-leads and the ECG vector The problem of data significantly improves the utilization efficiency of data and reduces the cost of data. During the reconstruction, the neural network is used to recalculate the projection vector to reconstruct the ECG vector to the 12-lead ECG, and the regularization term is used in the final loss calculation module to constrain the projection vector, while solving the individual differences of the ECG The interpretability and accuracy of the reconstruction process are guaranteed. In the final loss calculation module, multi-order differential loss is used to avoid low-frequency problems such as baseline interference on the basis of ensuring morphological characteristics.

Description

technical field [0001] The invention relates to the technical field of electrocardiographic signal processing, in particular to an electrocardiographic vector reconstruction method based on unsupervised learning. Background technique [0002] The electrocardiogram has been invented for more than 100 years since it was invented in 1885. Among the electrocardiograms composed of various leads, the conventional 12-lead electrocardiogram is the most widely used today. [0003] The ECG vector diagram is the spatial ECG vector ring formed by the depolarization of the heart, and the three-dimensional ECG vector ring is called the three-dimensional ECG vector. The graphics generated by the projection of the three-dimensional ECG vector to the frontal plane, the transverse plane and the side are called planar ECG vector diagrams. At present, the medical community has reached a consensus that the vector cardiogram is superior to the electrocardiogram in the diagnosis of ventricular hy...

AI Technical Summary

Problems solved by technology

[0006] Design the reconstruction method of the projection matrix through the projection relationship between the ECG vector and the leads: In actual situations, due to the difference in body posture of different people, when the ECG lead line is placed on the body surface of the subject, compared with the standard placement method There is a positional deviation. Although the collected 12-lead ECG does not affect the final diagnosis, it will cause relatively large errors in the reconstruction of the vector cardiogram, which will affect the final diagnosis.

Moreover, since the collection of ECG will have various interference problems such as baseline drift, these interferences are easily overlooked by physicians in the interpretation of 12-lead ECG, but the ECG reconstructed according to the projection matrix often has obvious electrical axis offset, etc. and other issues have a non-negligible impact on the actual interpretation

[0007] Using the hybrid ECG collected synchronously from the 12-lead ECG and the vector ECG as the supervised training data to train the neural network to reconstruct the ECG vector: this kind of data has high requirements on the acquisition equipment, and the data cost in the actual clinical data It is also relatively high, and since the collected ECG and 12-lead ECG have various interferences such as baseline drift, in order to enable the neural network to have the ability to filter interference, a large-scale data set is required

And because the method of reconstructing the ECG vector based on the neural network does not consider modeling the interference, the fitting effect of this method is not ideal even in the mixed ECG

Due to the lack of fitting ability, data interference and high data cost, the current supervised learning method is used to train the neural network for ECG vector reconstruction, and the effect is not ideal.

[0008] The above two methods are sensitive to the noise of ECG acquisition. Although signal processing methods such as filtering can be used to preprocess the ECG to reduce the influence of interference, the ECG filtering algorithm will be more or less Affect the morphological characteristics of the ECG. For example, the EMG filtering algorithm will have a greater impact on the shape of the small q wave and the notch of the QRS complex. Combining the various shortcomings of the above two methods, how can we only use the unlabeled It is particularly important to design a method for finely reconstructing the 12-lead ECG for low-cost data such as the 12-lead ECG