Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

Atrial fibrillation (AF) is the most common cardiac arrhythmia and currently affects more than 650,000 people in the United Kingdom alone. Catheter ablation (CA) is the only AF treatment with a long-term curative effect as it involves destroying arrhythmogenic tissue in the atria. However, its succe...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Laila Muizniece, Adrian Bertagnoli, Ahmed Qureshi, Aya Zeidan, Aditi Roy, Marica Muffoletto, Oleg Aslanidi
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	atrial fibrillation catheter ablation patient imaging reinforcement learning deep learning Physiology QP1-981
Acceso en línea:	https://doaj.org/article/bf2617f95aa8437db656e5dc4257b67b
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:bf2617f95aa8437db656e5dc4257b67b
record_format	dspace
spelling	oai:doaj.org-article:bf2617f95aa8437db656e5dc4257b67b2021-11-09T12:16:00ZReinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation1664-042X10.3389/fphys.2021.733139https://doaj.org/article/bf2617f95aa8437db656e5dc4257b67b2021-08-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fphys.2021.733139/fullhttps://doaj.org/toc/1664-042XAtrial fibrillation (AF) is the most common cardiac arrhythmia and currently affects more than 650,000 people in the United Kingdom alone. Catheter ablation (CA) is the only AF treatment with a long-term curative effect as it involves destroying arrhythmogenic tissue in the atria. However, its success rate is suboptimal, approximately 50% after a 2-year follow-up, and this high AF recurrence rate warrants significant improvements. Image-guidance of CA procedures have shown clinical promise, enabling the identification of key patient anatomical and pathological (such as fibrosis) features of atrial tissue, which require ablation. However, the latter approach still suffers from a lack of functional information and the need to interpret structures in the images by a clinician. Deep learning plays an increasingly important role in biomedicine, facilitating efficient diagnosis and treatment of clinical problems. This study applies deep reinforcement learning in combination with patient imaging (to provide structural information of the atria) and image-based modelling (to provide functional information) to design patient-specific CA strategies to guide clinicians and improve treatment success rates. To achieve this, patient-specific 2D left atrial (LA) models were derived from late-gadolinium enhancement (LGE) MRI scans of AF patients and were used to simulate patient-specific AF scenarios. Then a reinforcement Q-learning algorithm was created, where an ablating agent moved around the 2D LA, applying CA lesions to terminate AF and learning through feedback imposed by a reward policy. The agent achieved 84% success rate in terminating AF during training and 72% success rate in testing. Finally, AF recurrence rate was measured by attempting to re-initiate AF in the 2D atrial models after CA with 11% recurrence showing a great improvement on the existing therapies. Thus, reinforcement Q-learning algorithms can predict successful CA strategies from patient MRI data and help to improve the patient-specific guidance of CA therapy.Laila MuiznieceAdrian BertagnoliAdrian BertagnoliAhmed QureshiAya ZeidanAditi RoyAditi RoyMarica MuffolettoOleg AslanidiFrontiers Media S.A.articleatrial fibrillationcatheter ablationpatient imagingreinforcement learningdeep learningPhysiologyQP1-981ENFrontiers in Physiology, Vol 12 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	atrial fibrillation catheter ablation patient imaging reinforcement learning deep learning Physiology QP1-981
spellingShingle	atrial fibrillation catheter ablation patient imaging reinforcement learning deep learning Physiology QP1-981 Laila Muizniece Adrian Bertagnoli Adrian Bertagnoli Ahmed Qureshi Aya Zeidan Aditi Roy Aditi Roy Marica Muffoletto Oleg Aslanidi Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation
description	Atrial fibrillation (AF) is the most common cardiac arrhythmia and currently affects more than 650,000 people in the United Kingdom alone. Catheter ablation (CA) is the only AF treatment with a long-term curative effect as it involves destroying arrhythmogenic tissue in the atria. However, its success rate is suboptimal, approximately 50% after a 2-year follow-up, and this high AF recurrence rate warrants significant improvements. Image-guidance of CA procedures have shown clinical promise, enabling the identification of key patient anatomical and pathological (such as fibrosis) features of atrial tissue, which require ablation. However, the latter approach still suffers from a lack of functional information and the need to interpret structures in the images by a clinician. Deep learning plays an increasingly important role in biomedicine, facilitating efficient diagnosis and treatment of clinical problems. This study applies deep reinforcement learning in combination with patient imaging (to provide structural information of the atria) and image-based modelling (to provide functional information) to design patient-specific CA strategies to guide clinicians and improve treatment success rates. To achieve this, patient-specific 2D left atrial (LA) models were derived from late-gadolinium enhancement (LGE) MRI scans of AF patients and were used to simulate patient-specific AF scenarios. Then a reinforcement Q-learning algorithm was created, where an ablating agent moved around the 2D LA, applying CA lesions to terminate AF and learning through feedback imposed by a reward policy. The agent achieved 84% success rate in terminating AF during training and 72% success rate in testing. Finally, AF recurrence rate was measured by attempting to re-initiate AF in the 2D atrial models after CA with 11% recurrence showing a great improvement on the existing therapies. Thus, reinforcement Q-learning algorithms can predict successful CA strategies from patient MRI data and help to improve the patient-specific guidance of CA therapy.
format	article
author	Laila Muizniece Adrian Bertagnoli Adrian Bertagnoli Ahmed Qureshi Aya Zeidan Aditi Roy Aditi Roy Marica Muffoletto Oleg Aslanidi
author_facet	Laila Muizniece Adrian Bertagnoli Adrian Bertagnoli Ahmed Qureshi Aya Zeidan Aditi Roy Aditi Roy Marica Muffoletto Oleg Aslanidi
author_sort	Laila Muizniece
title	Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation
title_short	Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation
title_full	Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation
title_fullStr	Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation
title_full_unstemmed	Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation
title_sort	reinforcement learning to improve image-guidance of ablation therapy for atrial fibrillation
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/bf2617f95aa8437db656e5dc4257b67b
work_keys_str_mv	AT lailamuizniece reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT adrianbertagnoli reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT adrianbertagnoli reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT ahmedqureshi reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT ayazeidan reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT aditiroy reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT aditiroy reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT maricamuffoletto reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation AT olegaslanidi reinforcementlearningtoimproveimageguidanceofablationtherapyforatrialfibrillation
_version_	1718441052165111808

Reinforcement Learning to Improve Image-Guidance of Ablation Therapy for Atrial Fibrillation

Ejemplares similares