Semi-supervised clustering of fractionated electrograms for electroanatomical atrial mapping

Abstract

Background: Electrogram-guided ablation procedures have been proposed as an alternative strategy consisting of either mapping and ablating focal sources or targeting complex fractionated electrograms in atrial fibrillation (AF). However, the incomplete understanding of the mechanism of AF makes difficult the decision of detecting the target sites. To date, feature extraction from electrograms is carried out mostly based on the time-domain morphology analysis and non-linear features. However, their combination has been reported to achieve better performance. Besides, most of the inferring approaches applied for identifying the levels of fractionation are supervised, which lack of an objective description of fractionation. This aspect complicates their application on EGM-guided ablation procedures.

Methods: This work proposes a semi-supervised clustering method of four levels of fractionation. In particular, we make use of the spectral clustering that groups a set of widely used features extracted from atrial electrograms. We also introduce a new atrial-deflection-based feature to quantify the fractionated activity. Further, based on the sequential forward selection, we find the optimal subset that provides the highest performance in terms of the cluster validation. The method is tested on external validation of a labeled database. The generalization ability of the proposed training approach is tested to aid semi-supervised learning on unlabeled dataset associated with anatomical information recorded from three patients.

Results: A joint set of four extracted features, based on two time-domain morphology analysis and two non-linear dynamics, are selected. To discriminate between four considered levels of fractionation, validation on a labeled database performs a suitable accuracy (77.6 %). Results show a congruence value of internal validation index among tested patients that is enough to reconstruct the patterns over the atria to located critical sites with the benefit of avoiding previous manual classification of AF types.

Conclusions: To the best knowledge of the authors, this is the first work reporting semi-supervised clustering for distinguishing patterns in fractionated electrograms. The proposed methodology provides high performance for the detection of unknown patterns associated with critical EGM morphologies. Particularly, obtained results of semi-supervised training show the advantage of demanding fewer labeled data and less training time without significantly compromising accuracy. This paper introduces a new method, providing an objective scheme that enables electro-physiologist to recognize the diverse EGM morphologies reliably.

Keywords: Atrial fibrillation; Electrogram-guided ablation; Feature extraction; Spectral clustering.

Fig. 1

Proposed methodology. Block scheme of the proposed methodology of clustering EGM features to locate critical EGM morphologies in AF

Fig. 2

EGM classes. Exemplary of signals from EGM DB1 showing the four considered fractionation levels (class labels): $\#0$, $\#1$, $\#2$, and $\#3$

Fig. 3

Intraventricular EGM morphology analysis. a Detection of atrial deflections. b Example of the adaptative threshold and c LAW detection

Fig. 4

Boxplots of the distribution of features values obtained on the DB1 for all considered levels of fractionation (0, 1, 2 and 3). Top row—the selected feature subset ${\mathit{\Xi }}^{\ast }$; bottom row— the rejected feature subset. Red crosses mark outliers. All selected features have almost non-overlapping boxplots. This fact illustrates the ability of each feature in separating the classes. Results of Spearman correlation $\mathit{\rho }$ between each feature and the classes of fractionation is shown

Fig. 5

3D scatter plots of the most relevant features extracted from DB1: ${\mathit{\xi }}_2$, ${\mathit{\xi }}_7,$ and ${\mathit{\xi }}_8$. a Labeled by experts and b Inferred labels by clustering. Both plots resembles the same structure. Clustering tends to locate labels within well-confined class boundaries

Fig. 6

Clustering scatter plots and electroanatomical maps for three patients (DB2): a– c 3D scatter plots for each patient of the most relevant features: ${\mathit{\xi }}_2$, ${\mathit{\xi }}_7,$ and ${\mathit{\xi }}_8$. Clusters are represented by colors and resembles the structure in all three examined patients. d– f: View of the posterior wall of the left atrium. The clustering results are used to display an electro-anatomical maps for each patient. The maps show the distribution of reconstructed EGM patterns over the atrium. Critical sites with hith level of fractionation are color coded in red