Model-Based Feature Augmentation for Cardiac Ablation Target Learning From Images

Abstract

Abstract-Goal: We present a model-based feature augmentation scheme to improve the performance of a learning algorithm for the detection of cardiac radio-frequency ablation (RFA) targets with respect to learning from images alone. Methods: Initially, we compute image features from delayed-enhanced MRI (DE-MRI) to describe local tissue heterogeneities and feed them into a machine learning framework with uncertainty assessment for the identification of potential ablation targets. Next, we introduce the use of a patient-specific image-based model derived from DE-MRI coupled with the Mitchell-Schaeffer electrophysiology model and a dipole formulation for the simulation of intracardiac electrograms (EGM). Relevant features are extracted from these simulated signals which serve as a feature augmentation scheme for the learning algorithm. We assess the classifier's performance when using only image features and with model-based feature augmentation. Results: We obtained average classification scores of 97.2% accuracy, 82.4% sensitivity and 95.0% positive predictive value (PPV) by using a model-based feature augmentation scheme. Preliminary results also show that training the algorithm on the closest patient from the database, instead of using all the patients, improves the classification results. Conclusion: We presented a feature augmentation scheme based on biophysical cardiac electrophysiology modeling to increase the prediction scores of a machine learning framework for the RFA target prediction. Significance: The results derived from this study are a proof of concept that the use of model-based feature augmentation strengthens the performance of a purely image driven learning scheme for the prediction of cardiac ablation targets.

Using Machine Learning to Characterize Atrial Fibrotic Substrate From Intracardiac Signals With a Hybrid in silico and in vivo Dataset

“…Several studies used data-driven approaches with clinical data to characterize electrocardiogram signals measured on the body surface (Yaghouby et al, 2010 ; Rodrigues et al, 2017 ; Zhang et al, 2018 ; Petmezas et al, 2021 ). Sahli Costabal et al ( 2018 ) used a hybrid dataset approach to interpret activation times during AF and Lozoya et al ( 2019 ) showed how model-based feature augmentation can help to plan the targets for ablation therapy. We developed a detailed in silico setup as a perfectly controlled testing environment to understand intracardiac signals recorded with two different commercial catheters.…”

“…Machine learning has been extensively used in electrocardiogram analysis due to its potential to analyze big datasets and uncover mechanistic information about cardiac electrical function (Cabrera-Lozoya et al, 2017 ; Hannun et al, 2019 ; Lown et al, 2020 ; Luongo et al, 2020 ). While several studies aimed at quantifying AF mechanisms and automatically localize reentrant drivers using in silico or clinical electrograms (Schilling et al, 2015 ; McGillivray et al, 2018 ; Lozoya et al, 2019 ), less attention has been paid to the information that intracardiac electrograms can provide about the cardiac substrate based on the signal morphology due to the effect of fibrosis. Campos et al ( 2013 ) classified different types of fibrosis based on electrogram features using in silico experiments.…”

Cross-Culture Online Knowledge Validation and the Exclusive Practice of Stem Cell Therapy

“…On the other hand, physicians and offline channels of health information such as books, family and friends are not always available and have limited time. Furthermore, with the development of communication technology, there are many ways to share information (Lozoya et al, 2018). Information is presented digitally in many ways through pictures, videos, specialized applications, personalized notification, among others.…”

Putting machine learning into motion: applications in cardiovascular imaging

“…27 At present both of these approaches rely on explicit biophysical models derived from image segmentations, but recently this idea has been extended to use ML to select therapeutic targets; one example being the identification of sites for cardiac ablation on multi-modal imaging. 28 Sometimes cardiovascular disease classifications are straightforward and made by well-defined, if arbitrary, haemodynamic or volumetric criteria. To take two examples, pulmonary hypertension is defined by a resting mean pulmonary artery pressure of at least 25 mmHg and hypertrophic cardiomyopathy as a wall thickness of at least 15 mm that is not solely explained by abnormal loading conditions.…”