OAOleg V. Aslanidi

Oleg V. Aslanidi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Oleg V. Aslanidi has a total of 203 co-authors. Here are the top co-authors by number of shared publications:

  • Mark Richard Boyett

    University of Manchester

    20 shared publications
  • Marta Varela

    Imperial College London

    14 shared publications
  • Henggui Zhang

    Biological Physics Group, School of Physics & Astronomy, University of Manchester , Manchester M13 9PL , UK

    11 shared publications
  • Henggui Zhang

    Key Laboratory of Medical Electrophysiology, Ministry of Education and Medical Electrophysiological Key Laboratory of Sichuan Province, Collaborative Innovation Center for Prevention of Cardiovascular Diseases, Institute of Cardiovascular Research, Southwest Medical University, Luzhou 646099, China

    11 shared publications
  • Jules C. Hancox

    Affiliation School of Physiology and Pharmacology, Cardiovascular Research Laboratories, University of Bristol, Bristol, United Kingdom

    9 shared publications
  • H. Zhang

    School of Physics and Astronomy, University of Manchester, Manchester, UK

    7 shared publications

Latest Publications

  • Open Access

    Role of reverse remodelling in recurrence of atrial fibrillation after patient-tailored catheter ablation

    by George Teodor Obada, Shaheim Ogbomo-Harmitt, Maria Deprez, Nele Vandersickel, Oleg Aslanidi

    Background and aims: Catheter ablation (CA) is a curative treatment for atrial fibrillation (AF), yet success rates remain sub-optimal, with ∼50% of patients with persistent AF experiencing recurrence after 1 year. This may be due to the self-perpetuating nature of AF, which remodels atrial structure and cellular properties, while successful treatment can induce reverse remodelling (RR). This study develops a patient-specific CA strategy to directly target re-entrant drivers (RDs) and investigates the role of RR in AF recurrence. Methods: Left atrial (LA) models were reconstructed from LGE-MRI scans of AF patients (n = 15) and coupled with the Courtemanche-Ramirez-Nattel (CRN) electrophysiology model. RDs were induced via pacing, identified using DGM analysis, and targeted ablation was performed in-silico. Pulmonary vein isolation (PVI) was applied as a reference. Following termination, AF recurrence was tested under three levels of electrical reverse remodelling (ERR: 0%, 50%, and 100%), with and without structural reverse remodelling (SRR). Results: Targeted ablation acutely terminated AF in all patient-specific models. After the first procedure, AF recurrence decreased progressively from 55% at 0% ERR to 36.7% at 50% ERR and 5% at 100% ERR; with additional SRR, recurrence was further reduced to 46.7%, 26.7%, and 0%, respectively. After the second CA procedure, AF recurrence rate was 42.9%, 17.9%, and 0% without SRR and 25%, 14.3%, and 0% with SRR. Conclusion: This study highlights the importance of RR for therapy success, with a novel targeted CA technique ensuring <5% AF recurrence in patient-specific simulations. After clinical validation, this approach can help improve long-term patient outcomes.

  • Effects of Fibrotic Border Zone on Drivers for Atrial Fibrillation: An In-Silico Mechanistic Investigation

    by Shaheim Ogbomo-Harmitt, George Obada, Nele Vandersickel, Andrew P. King, Oleg Aslanidi

  • TESSLA: Two-Stage Ensemble Scar Segmentation for the Left Atrium

    by Shaheim Ogbomo-Harmitt, Jakub Grzelak, Ahmed Qureshi, Andrew P. King, Oleg Aslanidi


  • Open Access

    Exploring interpretability in deep learning prediction of successful ablation therapy for atrial fibrillation

    by Shaheim Ogbomo-Harmitt, Marica Muffoletto, Aya Zeidan, Ahmed Qureshi, Andrew P. King, Oleg Aslanidi

    Background: Radiofrequency catheter ablation (RFCA) therapy is the first-line treatment for atrial fibrillation (AF), the most common type of cardiac arrhythmia globally. However, the procedure currently has low success rates in dealing with persistent AF, with a reoccurrence rate of ∼50% post-ablation. Therefore, deep learning (DL) has increasingly been applied to improve RFCA treatment for AF. However, for a clinician to trust the prediction of a DL model, its decision process needs to be interpretable and have biomedical relevance.Aim: This study explores interpretability in DL prediction of successful RFCA therapy for AF and evaluates if pro-arrhythmogenic regions in the left atrium (LA) were used in its decision process.Methods: AF and its termination by RFCA have been simulated in MRI-derived 2D LA tissue models with segmented fibrotic regions (n = 187). Three ablation strategies were applied for each LA model: pulmonary vein isolation (PVI), fibrosis-based ablation (FIBRO) and a rotor-based ablation (ROTOR). The DL model was trained to predict the success of each RFCA strategy for each LA model. Three feature attribution (FA) map methods were then used to investigate interpretability of the DL model: GradCAM, Occlusions and LIME.Results: The developed DL model had an AUC (area under the receiver operating characteristic curve) of 0.78 ± 0.04 for predicting the success of the PVI strategy, 0.92 ± 0.02 for FIBRO and 0.77 ± 0.02 for ROTOR. GradCAM had the highest percentage of informative regions in the FA maps (62% for FIBRO and 71% for ROTOR) that coincided with the successful RFCA lesions known from the 2D LA simulations, but unseen by the DL model. Moreover, GradCAM had the smallest coincidence of informative regions of the FA maps with non-arrhythmogenic regions (25% for FIBRO and 27% for ROTOR).Conclusion: The most informative regions of the FA maps coincided with pro-arrhythmogenic regions, suggesting that the DL model leveraged structural features of MRI images to identify such regions and make its prediction. In the future, this technique could provide a clinician with a trustworthy decision support tool.


  • Open Access

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

    by Laila Muizniece, Adrian Bertagnoli, Ahmed Qureshi, Aya Zeidan, Aditi Roy, Marica Muffoletto, Oleg Aslanidi

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


  • Open Access

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

    by Laila Muizniece, Adrian Bertagnoli, Ahmed Qureshi, Aya Zeidan, Aditi Roy, Marica Muffoletto, Oleg Aslanidi

    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.


  • Open Access

    Toward Patient-Specific Prediction of Ablation Strategies for Atrial Fibrillation Using Deep Learning

    by Marica Muffoletto, Ahmed Qureshi, Aya Zeidan, Laila Muizniece, Xiao Fu, Jichao Zhao, Aditi Roy, Paul A. Bates, Oleg Aslanidi

    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.


  • Open Access

    Investigating Strain as a Biomarker for Atrial Fibrosis Quantified by Patient Cine MRI Data

    by Ahmed Qureshi, Aditi Roy, Henry Chubb, Adelaide de Vecchi, Oleg Aslanidi


  • Open Access

    Identifying locations of re-entrant drivers from patient-specific distribution of fibrosis in the left atrium

    by Aditi Roy, Marta Varela, Henry Chubb, Robert MacLeod, Jules C. Hancox, Tobias Schaeffter, Oleg Aslanidi

    Clinical evidence suggests a link between fibrosis in the left atrium (LA) and atrial fibrillation (AF), the most common sustained arrhythmia. Image-derived fibrosis is increasingly used for patient stratification and therapy guidance. However, locations of re-entrant drivers (RDs) sustaining AF are unknown and therapy success rates remain suboptimal. This study used image-derived LA models to explore the dynamics of RD stabilization in fibrotic regions and generate maps of RD locations. LA models with patient-specific geometry and fibrosis distribution were derived from late gadolinium enhanced magnetic resonance imaging of 6 AF patients. In each model, RDs were initiated at multiple locations, and their trajectories were tracked and overlaid on the LA fibrosis distributions to identify the most likely regions where the RDs stabilized. The simulations showed that the RD dynamics were strongly influenced by the amount and spatial distribution of fibrosis. In patients with fibrosis burden greater than 25%, RDs anchored to specific locations near large fibrotic patches. In patients with fibrosis burden below 25%, RDs either moved near small fibrotic patches or anchored to anatomical features. The patient-specific maps of RD locations showed that areas that harboured the RDs were much smaller than the entire fibrotic areas, indicating potential targets for ablation therapy. Ablating the predicted locations and connecting them to the existing pulmonary vein ablation lesions was the most effective in-silico ablation strategy. Atrial fibrillation (AF) is the most common cardiac arrhythmia and a huge healthcare problem, but its mechanisms are incompletely understood, and clinical therapies such as catheter ablation (CA) have poor long-term outcomes. This is due to the empirical nature of the procedure and lack of mechanistic knowledge of optimal ablation sites and strategies in patients whose atria is altered by AF-induced structural remodelling. In this study, we developed 3D atrial models with patient-specific geometry and distribution of fibrosis obtained from AF patient imaging and applied the models to explore the mechanisms of re-entrant drivers (RD) sustaining AF. Moreover, we used the novel mechanistic knowledge to simulate CA based on the model predictions and compared its success with existing clinical CA strategies. We discovered that the RD dynamics were strongly influenced by the spatial distribution of fibrosis, and RDs typically anchored to specific locations near large fibrotic patches. Virtual ablations of such anchoring locations by connecting them with linear lesions to the nearest pulmonary veins (PV) had superior efficacy compared to clinically used strategies such as the PV isolation. After incorporating further patient-specific information and careful validation, the proposed in-silico approach can help evaluate and potentially guide CA therapy in the clinic.


  • Open Access

    Editorial: Recent Advances in Understanding the Basic Mechanisms of Atrial Fibrillation Using Novel Computational Approaches

    by Jichao Zhao, Oleg Aslanidi, Pawel Kuklik, Geoffrey Lee, Gary Tse, Steven Niederer, Edward J. Vigmond

    Where we are at regarding atrial fibrillation Atrial fibrillation (AF) is the most common sustained heart rhythm disturbance, associated with substantial morbidity and mortality (Andrade et al., 2014). The current prevalence of AF is ~2% of the general population worldwide and is projected to more than double in the following decades, becoming a global epidemic due to the aging population and the increasing incidence of heart failure and other comorbidities such as hypertension and diabetes (Colilla et al., 2013;Krijthe et al., 2013). Current clinical treatment for AF is suboptimal. Ablation treatment for persistent and permanent AF and AF with concurrent cardiac diseases is disappointing with long term success rates being < 30% for single ablation procedures (Brooks et al., 2010;Nishida and Nattel, 2014). Furthermore, anti-arrhythmic drugs (AADs) often lose their efficacy and have side effects (Woods and Olgin, 2014). The poor clinical outcomes are primarily due to a lack of basic understanding of the AF mechanism and quantitative tools to optimize treatment strategies in a clinical setting (Haissaguerre et al., 2007;Hansen et al., 2015). Novel computational approaches and techniques are playing an important role in our understanding and treatment of AF. Multi-scale computer models of the human atria have been used to investigate the important role of fibrosis in AF and consistently demonstrated that AF is perpetuated by the re-entrant circuits persisting in the fibrotic boundary zones (Bayer et al., 2016;Morgan et al., 2016;Vigmond et al., 2016;Zahid et al., 2016;Zhao et al., 2017). Moreover, models have been applied to propose efficient ablation (Bayer et al., 2016) and AAD (Varela et al., 2016) treatments for AF. To improve patients outcomes, novel computational analysis-aided ablation strategies have also been proposed. Narayan and co-workers have identified stable AF re-entrant drivers in patients using phase singularity analysis and atrial cellular restitution properties and demonstrated that it was possible to reverse AF in 80.3% of patients by directly targeting these regions in their Focal Impulse and Rotor Modulation (FIRM) trial (Narayan et al., 2014). In addition to the FIRM trial study, Haissaguerre et al. studied 103 patients with persistent AF using a noninvasive ECG imaging (ECGI) approach (Haissaguerre et al., 2014) and concluded that AF is sustained by localized spatially stable drivers where targeted ablation led to 85% of patients being freed from AF at 12-months post ablation. These high success rates are yet to be confirmed in a multi-center randomized clinical trial and the recent REAFFIRM clinical trial presented during a late-breaking session at Heart Rhythm 2019, however, failed to provide evidence of the superiority of the FIRM approach over pulmonary vein isolation. Meanwhile, machine learning is proving to be a promising tool for helping us to understand AF. For example, deep convolutional neural networks have been used to classify AF from single-lead ECGs (Hannun et al., 2019) and to reconstruct 3D left atrial chambers from gadolinium-enhanced MRIs (Xiong et al., 2019) with superior performance. The aim of this research topic was to collect a series of reviews and original research articles presenting recent advances towards a better understanding and treatment of AF through the development or use of: 1) structure-detailed computer modeling; 2) biophysics-based atrial cellular modeling; 3) signal processing and clinical mapping; and 4) meta-analysis and clinical studies. A total of 27 accepted articles were published under this research topic. Here in this editorial, we will summarize the new knowledge and approaches generated, and discuss how these can contribute to an improved understanding of AF mechanisms and clinical treatment, as well as how they may shape future research directions. Critical insights learned from structure-detailed computer modeling Improvements in clinical imaging and mapping allow detailed characterization of atrial anatomy, structure and electrophysiology. Computer models of atrial electrical activation provide a powerful computational framework for understanding the structure-function relationship that underlies atrial re-entrant arrhythmias. Atrial structure, including wall thickness, fibrosis, and myofiber orientation, have been suggested to dictate the locations of AF re-entrant drivers in explanted human heart studies (Zhao et al., 2015; Bishop et al., 2015; Zhao et al., 2017). Of all atrial structures, fibrosis, the hallmark of structural remodeling, has been investigated extensively in this Research Topic. Clayton studied the effect of the spatial scale of simulated fibrosis on electrical propagations by smoothly varying the diffusion coefficient in 2D atrial tissue models. His study concludes that the spatial scale of fibrosis has important effects on both dispersion of recovery and vulnerability to re-entry. The Aslanidi group evaluated the effects of both atrial wall thickness and fibrosis on AF re-entrant drivers using two sets of computer models, a simple model of an atrial tissue slab with a step change in wall thickness and a synthetic fibrosis patch, and a set of 3D patient-specific computer models based on MRI (Roy et al.). In the slab model, they observed that an AF re-entrant driver drifted towards and along the regions with changes/gradients in wall thickness. Furthermore, they discovered that additional patchy fibrosis would pull the AF re-entrant driver towards it, and that the locations of AF re-entrant drivers were determined by both fibrosis and wall thickness gradients. On the other hand, results from the patient-specific computer models suggested that the interaction between wall thickness and fibrosis plays a very important role in the right atrium due to extensive trabecular structure, whilst fibrosis performs a more decisive role in the left atrium due to a comparably smaller trabecular...