More Like this

1. Cardiac endocardial left atrial substrate and lesion depth mapping using near-infrared spectroscopy

   https://doi.org/10.1364/BOE.451547  

   Park, Soo Young ; Yang, Haiqiu ; Marboe, Charles ; Ziv, Ohad ; Laurita, Kenneth ; Rollins, Andrew ; Saluja, Deepak ; Hendon, Christine P. ( March 2022 , Biomedical Optics Express)

   Atrial fibrillation (AF) is a rapid irregular electrical activity in the upper chamber and the most common sustained cardiac arrhythmia. Many patients require radiofrequency ablation (RFA) therapy to restore sinus rhythm. Pulmonary vein isolation requires distinguishing normal atrial wall from the pulmonary vein tissue, and atrial substrate ablation requires differentiating scar tissue, fibrosis, and adipose tissue. However, current anatomical mapping methods for strategically locating ablation sites by identifying structural substrates in real-time are limited. An intraoperative tool that accurately provides detailed structural information and classifies endocardial substrates could help improve RF guidance during RF ablation therapy. In this work, we propose a 7F NIRS integrated ablation catheter and demonstrate endocardial mapping onex vivoswine (n = 12) and human (n = 5) left atrium (LA). First, pulmonary vein (PV) sleeve, fibrosis and ablation lesions were identified with NIRS-derived contrast indices. Based on these key spectral features, classification algorithms identified endocardial substrates with high accuracy (<11% error). Then, a predictive model for lesion depth was evaluated on classified lesions. Model predictions correlated well with histological measurements of lesion dimensions (R = 0.984). Classified endocardial substrates and lesion depth were represented in 2D spatial maps. These results suggest NIRS integrated mapping catheters can serve as a complementary tool to the current electroanatomical mapping system to improve treatment efficacy.

    

   more » « less
2. Imaging of subendocardial adipose tissue and fiber orientation distributions in the human left atrium using optical coherence tomography

   https://doi.org/10.1111/jce.14255  

   Lye, Theresa H. ; Marboe, Charles C. ; Hendon, Christine P. ( November 2019 , Journal of Cardiovascular Electrophysiology)

   Optical coherence tomography (OCT) has the potential to provide real‐time imaging guidance for atrial fibrillation ablation, with promising results for lesion monitoring. OCT can also offer high‐resolution imaging of tissue composition, but there is insufficient cardiac OCT data to inform the use of OCT to reveal important tissue architecture of the human left atrium. Thus, the objective of this study was to define OCT imaging data throughout the human left atrium, focusing on the distribution of adipose tissue and fiber orientation as seen from the endocardium.

   Human hearts (n = 7) were acquired for imaging the left atrium with OCT. A spectral‐domain OCT system with 1325 nm center wavelength, 6.5 μm axial resolution, 15 μm lateral resolution, and a maximum imaging depth of 2.51 mm in the air was used. Large‐scale OCT image maps of human left atrial tissue were developed, with adipose thickness and fiber orientation extracted from the imaging data. OCT imaging showed scattered distributions of adipose tissue around the septal and pulmonary vein regions, up to a depth of about 0.43 mm from the endocardial surface. The total volume of adipose tissue detected by OCT over one left atrium ranged from 1.42 to 28.74 mm³. Limited fiber orientation information primarily around the pulmonary veins and the septum could be identified.

   OCT imaging could provide adjunctive information on the distribution of subendocardial adipose tissue, particularly around thin areas around the pulmonary veins and septal regions. Variations in OCT‐detected tissue composition could potentially assist ablation guidance.

    

   more » « less
3. Arrhythmogenic Effects of Genetic Mutations Affecting Potassium Channels in Human Atrial Fibrillation: A Simulation Study

   https://doi.org/10.3389/fphys.2021.681943  

   Belletti, Rebecca ; Romero, Lucia ; Martinez-Mateu, Laura ; Cherry, Elizabeth M. ; Fenton, Flavio H. ; Saiz, Javier ( May 2021 , Frontiers in Physiology)

   null (Ed.)

   Genetic mutations in genes encoding for potassium channel protein structures have been recently associated with episodes of atrial fibrillation in asymptomatic patients. The aim of this study is to investigate the potential arrhythmogenicity of three gain-of-function mutations related to atrial fibrillation—namely, KCNH2 T895M, KCNH2 T436M, and KCNE3-V17M—using modeling and simulation of the electrophysiological activity of the heart. A genetic algorithm was used to tune the parameters’ value of the original ionic currents to reproduce the alterations experimentally observed caused by the mutations. The effects on action potentials, ionic currents, and restitution properties were analyzed using versions of the Courtemanche human atrial myocyte model in different tissues: pulmonary vein, right, and left atrium. Atrial susceptibility of the tissues to spiral wave generation was also investigated studying the temporal vulnerability. The presence of the three mutations resulted in an overall more arrhythmogenic substrate. Higher current density, action potential duration shortening, and flattening of the restitution curves were the major effects of the three mutations at the single-cell level. The genetic mutations at the tissue level induced a higher temporal vulnerability to the rotor’s initiation and progression, by sustaining spiral waves that perpetuate until the end of the simulation. The mutation with the highest pro-arrhythmic effects, exhibiting the widest sustained VW and the smallest meandering rotor’s tip areas, was KCNE3-V17M. Moreover, the increased susceptibility to arrhythmias and rotor’s stability was tissue-dependent. Pulmonary vein tissues were more prone to rotor’s initiation, while in left atrium tissues rotors were more easily sustained. Re-entries were also progressively more stable in pulmonary vein tissue, followed by the left atrium, and finally the right atrium. The presence of the genetic mutations increased the susceptibility to arrhythmias by promoting the rotor’s initiation and maintenance. The study provides useful insights into the mechanisms underlying fibrillatory events caused by KCNH2 T895M, KCNH2 T436M, and KCNE3-V17M and might aid the planning of patient-specific targeted therapies. 

   more » « less
4. The Deep Learning Epilepsy Detection Challenge: Design, Implementation, and Test of a New Crowd-Sourced AI Challenge Ecosystem

   Kiral, Isabell ; Roy, Subhrajit ; Mummert, Todd ; Braz, Alan ; Tsay, Jason ; Tang, Jianbin ; Asif, Umar ; Schaffter, Thomas ; Mehmet, Eren ; Picone, Joseph ; et al ( April 2019 , Challenges in Machine Learning Competitions for All (CiML))

   null (Ed.)

   The DeepLearningEpilepsyDetectionChallenge: design, implementation, andtestofanewcrowd-sourced AIchallengeecosystem Isabell Kiral*, Subhrajit Roy*, Todd Mummert*, Alan Braz*, Jason Tsay, Jianbin Tang, Umar Asif, Thomas Schaffter, Eren Mehmet, The IBM Epilepsy Consortium◊ , Joseph Picone, Iyad Obeid, Bruno De Assis Marques, Stefan Maetschke, Rania Khalaf†, Michal Rosen-Zvi† , Gustavo Stolovitzky† , Mahtab Mirmomeni† , Stefan Harrer† * These authors contributed equally to this work † Corresponding authors: rkhalaf@us.ibm.com, rosen@il.ibm.com, gustavo@us.ibm.com, mahtabm@au1.ibm.com, sharrer@au.ibm.com ◊ Members of the IBM Epilepsy Consortium are listed in the Acknowledgements section J. Picone and I. Obeid are with Temple University, USA. T. Schaffter is with Sage Bionetworks, USA. E. Mehmet is with the University of Illinois at Urbana-Champaign, USA. All other authors are with IBM Research in USA, Israel and Australia. Introduction This decade has seen an ever-growing number of scientific fields benefitting from the advances in machine learning technology and tooling. More recently, this trend reached the medical domain, with applications reaching from cancer diagnosis [1] to the development of brain-machine-interfaces [2]. While Kaggle has pioneered the crowd-sourcing of machine learning challenges to incentivise data scientists from around the world to advance algorithm and model design, the increasing complexity of problem statements demands of participants to be expert data scientists, deeply knowledgeable in at least one other scientific domain, and competent software engineers with access to large compute resources. People who match this description are few and far between, unfortunately leading to a shrinking pool of possible participants and a loss of experts dedicating their time to solving important problems. Participation is even further restricted in the context of any challenge run on confidential use cases or with sensitive data. Recently, we designed and ran a deep learning challenge to crowd-source the development of an automated labelling system for brain recordings, aiming to advance epilepsy research. A focus of this challenge, run internally in IBM, was the development of a platform that lowers the barrier of entry and therefore mitigates the risk of excluding interested parties from participating. The challenge: enabling wide participation With the goal to run a challenge that mobilises the largest possible pool of participants from IBM (global), we designed a use case around previous work in epileptic seizure prediction [3]. In this “Deep Learning Epilepsy Detection Challenge”, participants were asked to develop an automatic labelling system to reduce the time a clinician would need to diagnose patients with epilepsy. Labelled training and blind validation data for the challenge were generously provided by Temple University Hospital (TUH) [4]. TUH also devised a novel scoring metric for the detection of seizures that was used as basis for algorithm evaluation [5]. In order to provide an experience with a low barrier of entry, we designed a generalisable challenge platform under the following principles: 1. No participant should need to have in-depth knowledge of the specific domain. (i.e. no participant should need to be a neuroscientist or epileptologist.) 2. No participant should need to be an expert data scientist. 3. No participant should need more than basic programming knowledge. (i.e. no participant should need to learn how to process fringe data formats and stream data efficiently.) 4. No participant should need to provide their own computing resources. In addition to the above, our platform should further • guide participants through the entire process from sign-up to model submission, • facilitate collaboration, and • provide instant feedback to the participants through data visualisation and intermediate online leaderboards. The platform The architecture of the platform that was designed and developed is shown in Figure 1. The entire system consists of a number of interacting components. (1) A web portal serves as the entry point to challenge participation, providing challenge information, such as timelines and challenge rules, and scientific background. The portal also facilitated the formation of teams and provided participants with an intermediate leaderboard of submitted results and a final leaderboard at the end of the challenge. (2) IBM Watson Studio [6] is the umbrella term for a number of services offered by IBM. Upon creation of a user account through the web portal, an IBM Watson Studio account was automatically created for each participant that allowed users access to IBM's Data Science Experience (DSX), the analytics engine Watson Machine Learning (WML), and IBM's Cloud Object Storage (COS) [7], all of which will be described in more detail in further sections. (3) The user interface and starter kit were hosted on IBM's Data Science Experience platform (DSX) and formed the main component for designing and testing models during the challenge. DSX allows for real-time collaboration on shared notebooks between team members. A starter kit in the form of a Python notebook, supporting the popular deep learning libraries TensorFLow [8] and PyTorch [9], was provided to all teams to guide them through the challenge process. Upon instantiation, the starter kit loaded necessary python libraries and custom functions for the invisible integration with COS and WML. In dedicated spots in the notebook, participants could write custom pre-processing code, machine learning models, and post-processing algorithms. The starter kit provided instant feedback about participants' custom routines through data visualisations. Using the notebook only, teams were able to run the code on WML, making use of a compute cluster of IBM's resources. The starter kit also enabled submission of the final code to a data storage to which only the challenge team had access. (4) Watson Machine Learning provided access to shared compute resources (GPUs). Code was bundled up automatically in the starter kit and deployed to and run on WML. WML in turn had access to shared storage from which it requested recorded data and to which it stored the participant's code and trained models. (5) IBM's Cloud Object Storage held the data for this challenge. Using the starter kit, participants could investigate their results as well as data samples in order to better design custom algorithms. (6) Utility Functions were loaded into the starter kit at instantiation. This set of functions included code to pre-process data into a more common format, to optimise streaming through the use of the NutsFlow and NutsML libraries [10], and to provide seamless access to the all IBM services used. Not captured in the diagram is the final code evaluation, which was conducted in an automated way as soon as code was submitted though the starter kit, minimising the burden on the challenge organising team. Figure 1: High-level architecture of the challenge platform Measuring success The competitive phase of the "Deep Learning Epilepsy Detection Challenge" ran for 6 months. Twenty-five teams, with a total number of 87 scientists and software engineers from 14 global locations participated. All participants made use of the starter kit we provided and ran algorithms on IBM's infrastructure WML. Seven teams persisted until the end of the challenge and submitted final solutions. The best performing solutions reached seizure detection performances which allow to reduce hundred-fold the time eliptologists need to annotate continuous EEG recordings. Thus, we expect the developed algorithms to aid in the diagnosis of epilepsy by significantly shortening manual labelling time. Detailed results are currently in preparation for publication. Equally important to solving the scientific challenge, however, was to understand whether we managed to encourage participation from non-expert data scientists. Figure 2: Primary occupation as reported by challenge participants Out of the 40 participants for whom we have occupational information, 23 reported Data Science or AI as their main job description, 11 reported being a Software Engineer, and 2 people had expertise in Neuroscience. Figure 2 shows that participants had a variety of specialisations, including some that are in no way related to data science, software engineering, or neuroscience. No participant had deep knowledge and experience in data science, software engineering and neuroscience. Conclusion Given the growing complexity of data science problems and increasing dataset sizes, in order to solve these problems, it is imperative to enable collaboration between people with differences in expertise with a focus on inclusiveness and having a low barrier of entry. We designed, implemented, and tested a challenge platform to address exactly this. Using our platform, we ran a deep-learning challenge for epileptic seizure detection. 87 IBM employees from several business units including but not limited to IBM Research with a variety of skills, including sales and design, participated in this highly technical challenge. 

   more » « less
5. Predicting atrial fibrillation recurrence after ablation in patients with heart failure: Validity of the APPLE and CAAP‐AF risk scoring systems

   https://doi.org/10.1111/pace.13805  

   Black‐Maier, Eric ; Parish, Alice ; Steinberg, Benjamin A. ; Green, Cynthia L. ; Loring, Zak ; Barnett, Adam S. ; Al‐Khatib, Sana M. ; Atwater, Brett D. ; Daubert, James P. ; Frazier‐Mills, Camille ; et al ( October 2019 , Pacing and Clinical Electrophysiology)

   Compared with medical therapy, catheter ablation of atrial fibrillation (AF) in patients with heart failure (HF) improves cardiovascular outcomes. Risk scores (CAAP‐AF and APPLE) have been developed to predict the likelihood of AF recurrence after ablation, have not been validated specifically in patients with AF and HF.

   We analyzed baseline characteristics, risk scores, and rates of AF recurrence 12 months postablation in a cohort of 230 consecutive patients with AF and HF undergoing PVI in the Duke Center for Atrial Fibrillation registry from 2009‐2013.

   During a follow‐up period of 12 months, 76 of 230 (33%) patients with HF experienced recurrent AF after ablation. The median APPLE and CAAP‐AF scores were 1.5 ([Q1, Q3]: [1.0, 2.0]) and 4.0 ([Q1, Q3]: [3.0, 5.0]), respectively and were not different from those patients with and without recurrent AF. Freedom from AF was not different according to APPLE and CAAP‐AF scores. Discrimination for recurrent AF with the CAAP‐AF score was modest with a C‐statistic of 0.60 (95% CI 0.52‐0.67). Discrimination with the APPLE score was similarly modest, with a C‐statistic of 0.54 (95% CI: 0.47‐0.62).

   Validated predictive risk scores for recurrent AF after catheter ablation exhibit limited predictive ability in cohorts of AF and HF. Additional tools are needed to facilitate risk stratification and patient selection for AF ablation in patients with concomitant HF.

    

   more » « less