Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning
Atrial fibrillation (AF) is a common cardiac arrhythmia that affects 1% of the population worldwide and is associated with high levels of morbidity and mortality. Catheter ablation (CA) has become one of the first line treatments for AF, but its success rates are suboptimal, especially in the case o...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2021-05-01
|
Series: | Frontiers in Physiology |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fphys.2021.674106/full |
id |
doaj-ccd8b86af7a246cdb23e7a9e83729aac |
---|---|
record_format |
Article |
spelling |
doaj-ccd8b86af7a246cdb23e7a9e83729aac2021-05-26T06:53:26ZengFrontiers Media S.A.Frontiers in Physiology1664-042X2021-05-011210.3389/fphys.2021.674106674106Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep LearningMarica Muffoletto0Marica Muffoletto1Ahmed Qureshi2Aya Zeidan3Laila Muizniece4Xiao Fu5Jichao Zhao6Aditi Roy7Aditi Roy8Paul A. Bates9Oleg Aslanidi10School of Biomedical Engineering and Imaging Sciences, King's College London, London, United KingdomBiomolecular Modelling Laboratory, The Francis Crick Institute, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King's College London, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King's College London, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King's College London, London, United KingdomBiomolecular Modelling Laboratory, The Francis Crick Institute, London, United KingdomAuckland Bioengineering Institute, University of Auckland, Auckland, New ZealandSchool of Biomedical Engineering and Imaging Sciences, King's College London, London, United KingdomDepartment of Computer Science, University of Oxford, Oxford, United KingdomBiomolecular Modelling Laboratory, The Francis Crick Institute, London, United KingdomSchool of Biomedical Engineering and Imaging Sciences, King's College London, London, United KingdomAtrial fibrillation (AF) is a common cardiac arrhythmia that affects 1% of the population worldwide and is associated with high levels of morbidity and mortality. Catheter ablation (CA) has become one of the first line treatments for AF, but its success rates are suboptimal, especially in the case of persistent AF. Computational approaches have shown promise in predicting the CA strategy using simulations of atrial models, as well as applying deep learning to atrial images. We propose a novel approach that combines image-based computational modelling of the atria with deep learning classifiers trained on patient-specific atrial models, which can be used to assist in CA therapy selection. Therefore, we trained a deep convolutional neural network (CNN) using a combination of (i) 122 atrial tissue images obtained by unfolding patient LGE-MRI datasets, (ii) 157 additional synthetic images derived from the patient data to enhance the training dataset, and (iii) the outcomes of 558 CA simulations to terminate several AF scenarios in the corresponding image-based atrial models. Four CNN classifiers were trained on this patient-specific dataset balanced using several techniques to predict three common CA strategies from the patient atrial images: pulmonary vein isolation (PVI), rotor-based ablation (Rotor) and fibrosis-based ablation (Fibro). The training accuracy for these classifiers ranged from 96.22 to 97.69%, while the validation accuracy was from 78.68 to 86.50%. After training, the classifiers were applied to predict CA strategies for an unseen holdout test set of atrial images, and the results were compared to outcomes of the respective image-based simulations. The highest success rate was observed in the correct prediction of the Rotor and Fibro strategies (100%), whereas the PVI class was predicted in 33.33% of the cases. In conclusion, this study provides a proof-of-concept that deep neural networks can learn from patient-specific MRI datasets and image-derived models of AF, providing a novel technology to assist in tailoring CA therapy to a patient.https://www.frontiersin.org/articles/10.3389/fphys.2021.674106/fullatrial fibrillationpatient imagingcatheter ablationcomputational modellingdeep learningclassification algorithm |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Marica Muffoletto Marica Muffoletto Ahmed Qureshi Aya Zeidan Laila Muizniece Xiao Fu Jichao Zhao Aditi Roy Aditi Roy Paul A. Bates Oleg Aslanidi |
spellingShingle |
Marica Muffoletto Marica Muffoletto Ahmed Qureshi Aya Zeidan Laila Muizniece Xiao Fu Jichao Zhao Aditi Roy Aditi Roy Paul A. Bates Oleg Aslanidi Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning Frontiers in Physiology atrial fibrillation patient imaging catheter ablation computational modelling deep learning classification algorithm |
author_facet |
Marica Muffoletto Marica Muffoletto Ahmed Qureshi Aya Zeidan Laila Muizniece Xiao Fu Jichao Zhao Aditi Roy Aditi Roy Paul A. Bates Oleg Aslanidi |
author_sort |
Marica Muffoletto |
title |
Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning |
title_short |
Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning |
title_full |
Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning |
title_fullStr |
Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning |
title_full_unstemmed |
Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning |
title_sort |
toward patient-specific prediction of ablation strategies for atrial fibrillation using deep learning |
publisher |
Frontiers Media S.A. |
series |
Frontiers in Physiology |
issn |
1664-042X |
publishDate |
2021-05-01 |
description |
Atrial fibrillation (AF) is a common cardiac arrhythmia that affects 1% of the population worldwide and is associated with high levels of morbidity and mortality. Catheter ablation (CA) has become one of the first line treatments for AF, but its success rates are suboptimal, especially in the case of persistent AF. Computational approaches have shown promise in predicting the CA strategy using simulations of atrial models, as well as applying deep learning to atrial images. We propose a novel approach that combines image-based computational modelling of the atria with deep learning classifiers trained on patient-specific atrial models, which can be used to assist in CA therapy selection. Therefore, we trained a deep convolutional neural network (CNN) using a combination of (i) 122 atrial tissue images obtained by unfolding patient LGE-MRI datasets, (ii) 157 additional synthetic images derived from the patient data to enhance the training dataset, and (iii) the outcomes of 558 CA simulations to terminate several AF scenarios in the corresponding image-based atrial models. Four CNN classifiers were trained on this patient-specific dataset balanced using several techniques to predict three common CA strategies from the patient atrial images: pulmonary vein isolation (PVI), rotor-based ablation (Rotor) and fibrosis-based ablation (Fibro). The training accuracy for these classifiers ranged from 96.22 to 97.69%, while the validation accuracy was from 78.68 to 86.50%. After training, the classifiers were applied to predict CA strategies for an unseen holdout test set of atrial images, and the results were compared to outcomes of the respective image-based simulations. The highest success rate was observed in the correct prediction of the Rotor and Fibro strategies (100%), whereas the PVI class was predicted in 33.33% of the cases. In conclusion, this study provides a proof-of-concept that deep neural networks can learn from patient-specific MRI datasets and image-derived models of AF, providing a novel technology to assist in tailoring CA therapy to a patient. |
topic |
atrial fibrillation patient imaging catheter ablation computational modelling deep learning classification algorithm |
url |
https://www.frontiersin.org/articles/10.3389/fphys.2021.674106/full |
work_keys_str_mv |
AT maricamuffoletto towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT maricamuffoletto towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT ahmedqureshi towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT ayazeidan towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT lailamuizniece towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT xiaofu towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT jichaozhao towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT aditiroy towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT aditiroy towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT paulabates towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning AT olegaslanidi towardpatientspecificpredictionofablationstrategiesforatrialfibrillationusingdeeplearning |
_version_ |
1721426454085894144 |