Sequential Factorized Autoencoder for Localizing the Origin of Ventricular Activation From 12-Lead Electrocardiograms

Abstract

Objective: This work presents a novel approach to handle the inter-subject variations existing in the population analysis of ECG, applied for localizing the origin of ventricular tachycardia (VT) from 12-lead electrocardiograms (ECGs).

Methods: The presented method involves a factor disentangling sequential autoencoder (f-SAE) - realized in both long short-term memory (LSTM) and gated recurrent unit (GRU) networks - to learn to disentangle the inter-subject variations from the factor relating to the location of origin of VT. To perform such disentanglement, a pair-wise contrastive loss is introduced.

Results: The presented methods are evaluated on ECG dataset with 1012 distinct pacing sites collected from scar-related VT patients during routine pace-mapping procedures. Experiments demonstrate that, for classifying the origin of VT into the predefined segments, the presented f-SAE improves the classification accuracy by 8.94% from using prescribed QRS features, by 1.5% from the supervised deep CNN network, and 5.15% from the standard SAE without factor disentanglement. Similarly, when predicting the coordinates of the VT origin, the presented f-SAE improves the performance by 2.25 mm from using prescribed QRS features, by 1.18 mm from the supervised deep CNN network and 1.6 mm from the standard SAE.

Conclusion: These results demonstrate the importance as well as the feasibility of the presented f-SAE approach for separating inter-subject variations when using 12-lead ECG to localize the origin of VT.

Significance: This work suggests the important research direction to deal with the well-known challenge posed by inter-subject variations during population analysis from ECG signals.

Fig. 1:

Schematics of a VT reentry circuit. A: An electrical ”short circuit” travels and exits through narrow strands of surviving tissue inside the scar tissue to depolarize the rest of the ventricles. B: Ablation procedure that cuts off this ”short circuit” by blocking its exit from the scar tissue.

Fig. 2:

(A) A diagram of a basic RNN cell. (B) A diagram of a basic LSTM cell. (C) A diagram of a basic GRU cell. (D) Illustration of the Sequential Autoencoder (SAE). (E) The proposed two-way factored Sequential Autoencoder (f-SAE).

Fig. 3:

Supervised fine-tuning network using the learned parameters from the f-SAE (light blue) for the localization of the origin of VT in the form of classification or regression task.

Fig. 4:

(Left) Illustration of experimental data and processing, in which 15-second ECG recordings are pre-processed for extraction of a successfully-paced QRS complex. (Right) The final input data for prediction represented as sequence of 12×100 (i.e. 12 leads × QRS beat).

Fig. 5:

(A) Schematics of the 10-segment division of the left ventricle. (B)-(D) Visualization of distribution of the ten segments on the LV endocardial surface model in three different views.

Fig. 6:

[Best viewed in color] The triangulated left ventricular (LV) endocardial surface on which all pacing sites are projected. The pacing sites for train, validation and test set are shown with different colors.

Fig. 7:

Training data distribution in bar diagrams. (A): Number of samples in each segment ID. (B): Number of unique patients in each segment ID. (C): Number of unique values along each of the x-, y-, and z-axes.

Fig. 8:

Training and validation loss over training epochs. Left: regularized reconstruction loss as defined in (14) of the unsupervised f-SAE (GRU). Middle: Classification loss during fine-tuning f-SAE (GRU) for segment classification. Right: Regression loss during fine-tuning of f-SAE (GRU) for coordinate regression.

Fig. 9:

Three examples of true pacing sites and the predicted locations using the presented methods and the three comparison methods as described in III-C. For brevity, actual and predicted sites are zoomed-in.

Fig. 10:

The confusion matrix for segment classification for the f-SAE (GRU) model.

Fig. 11:

Visualization of the distribution of pacing sites in the held-out test set (white dots) on the endocardial surface model in two different views. The red curve is manually drawn to demonstrate that many test set samples are located near segment boundaries.

Fig. 12:

The encoded representation, z₁ and z₂, from two ECG signals (left) are swapped to generate the signals (right) for two different cases (A) and (B).

Fig. 13:

The effects of α and β for VT localization accuracy for the presented f-SAE (GRU) model on test data.