Abstract
Large-scale electrophysiological simulations to obtain electrocardiograms (ECG) carry the potential to produce extensive datasets for training of machine learning classifiers to, e.g., discriminate between different cardiac pathologies. The adoption of simulations for these purposes is limited due to a lack of ready-to-use models covering atrial anatomical variability. We built a bi-atrial statistical shape model (SSM) of the endocardial wall based on 47 segmented human CT and MRI datasets using Gaussian process morphable models. Generalization, specificity, and compactness metrics were evaluated. The SSM was applied to simulate atrial ECGs in 100 random volumetric instances. The first eigenmode of our SSM reflects a change of the total volume of both atria, the second the asymmetry between left vs. right atrial volume, the third a change in the prominence of the atrial appendages. The SSM is capable of generalizing well to unseen geometries and 95% of the total shape variance is covered by its first 24 eigenvectors. The Pwaves in the 12-lead ECG of 100 random instances showed a duration of 109.7±12.2ms in accordance with large cohort studies. The novel bi-atrial SSM itself as well as 100 exemplary instances with rule-based augmentation of atrial wall thickness, fiber orientation, inter-atrial bridges and tags for anatomical structures have been made publicly available. This novel, openly available bi-atrial SSM can in future be employed to generate large sets of realistic atrial geometries as a basis for in silico big data approaches.
Highlights
A wide range of machine learning approaches have already been proposed for classifying cardiovascular pathologies based on the 12-lead electrocardiogram (ECG) (Hannun et al, 2019; Perez Alday et al, 2020; Strodthoff et al, 2020)
The resulting P wave durations obtained with the proposed statistical shape model (SSM) of 104.8 ± 8.5 ms are in agreement with the P wave durations of 100-105 ms reported for individuals with a low atrial fibrillation risk in an extensive cohort study based on 285,933 ECGs (Nielsen et al, 2015)
It implies that the additional P wave duration variability observed in individuals with increased atrial fibrillation risk (92-116 ms range covering 20-80% percentiles in Nielsen et al (2015)) is either due to pathological anatomical variability not represented in the healthy dataset used to build this SSM or due to non-anatomical, functional changes such as conduction velocity slowing due to fibrotic infiltration of the atrial tissue (Caixal et al, 2020)
Summary
A wide range of machine learning approaches have already been proposed for classifying cardiovascular pathologies based on the 12-lead electrocardiogram (ECG) (Hannun et al, 2019; Perez Alday et al, 2020; Strodthoff et al, 2020). Expert annotations are commonly relied upon to generate the ground truth labels describing the underlying pathologies for clinical datasets coming along with inter- and intra-observer variabilities significantly affecting the reliability of the ground truth labels (Hannun et al, 2019). These limitations call for simulated synthetic ECG as a source for large, representative and well controlled datasets. These datasets can be used to directly deduce diagnostic criteria visually (Andlauer et al, 2018) or to train machine learning classifiers to discriminate between different cardiac diseases and healthy individuals (Andlauer et al, 2018). The advantage of using simulated over clinical data lies in the precisely known ground truth of the underlying pathology that was defined for the simulation, and in the possibility to generate a virtually infinite amount of signals for each pathology class
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
