Transfer Learning From Simulations on a Reference Anatomy for ECGI in Personalized Cardiac Resynchronization Therapy

Abstract

Abstract-Goal: Non-invasive cardiac electrophysiology (EP) model personalisation has raised interest for instance in the scope of predicting EP cardiac resynchronization therapy (CRT) response. However, the restricted clinical applicability of current methods is due in particular to the limitation to simple situations and the important computational cost. Methods: We propose in this manuscript an approach to tackle these two issues. First, we analyse more complex propagation patterns (multiple onsets and scar tissue) using relevance vector regression and shape dimensionality reduction on a large simulated database. Second, this learning is performed offline on a reference anatomy and transferred onto patient-specific anatomies in order to achieve fast personalised predictions online. Results: We evaluated our method on a dataset composed of 20 dyssynchrony patients with a total of 120 different cardiac cycles. The comparison with a commercially available electrocardiographic imaging (ECGI) method shows a good identification of the cardiac activation pattern. From the cardiac parameters estimated in sinus rhythm, we predicted 5 different paced patterns for each patient. The comparison with the body surface potential mappings (BSPM) measured during pacing and the ECGI method indicates a good predictive power. Conclusion: We showed that learning offline from a large simulated database on a reference anatomy was able to capture the main cardiac EP characteristics from non-invasive measurements for fast patient-specific predictions. Significance: The fast CRT pacing predictions are a step forward to a noninvasive CRT patient selection and therapy optimisation, to help clinicians in these difficult tasks.

ECG Adapted Fastest Route Algorithm to Localize the Ectopic Excitation Origin in CRT Patients

“…further demonstrated the ability of ECGI to accurately detect electrical dyssynchrony and identify the latest activation site with 9.1 ± 0.6 mm in Langendorff-perfused pig hearts (Bear et al, 2018). As a representative of model-based approaches, an offline created database of realistic forward simulations with different EP setups was shown to facilitate estimation of clinically relevant parameters, such as pacing configuration and CV profile (Giffard-Roisin et al, 2018). Such an offline strategy aiming at the real-time performance is computationally efficient, whilst enjoying an essential extensibility with every suitable clinical case.…”

“…For this study, we used the euclidean norm as the distance function, i.e., c(falsey~nl,yml)=||falsey~nl-falsey~ml||L2. Similar to Giffard-Roisin et al (2018), both test and measured BSPMs signals were normalized beforehand in order to reduce the influence of torso inhomogeneities on the ECG amplitude. To this end, we scaled all BSPMs signals column-wise by subtracting the mean and component-wise scaling to unit variance (preprocessing scale function from sciki-learn (Pedregosa et al, 2011) was used).…”

Deep Learning Formulation of ECGI for Data-Driven Integration of Spatiotemporal Correlations and Imaging Information

“…However, it will require to simulate more data to train the model, as we will have more hyperparameters to optimise. We will also explore transfer learning to apply it on clinical data [5].…”

Evaluation of Pattern Recognition Techniques in Response to Cardiac Resynchronization Therapy (CRT)

“…The possibility of prediction based on intelligent algorithms is a step forward to identifying candidates for CRT. These operations are non-invasive and used for optimizing the treatment process, and they can significantly help doctors provided that they are properly operated [9]. After the implant, there are very few and sometimes impossible ways to overcome the cases of no response [10].…”