Three-dimensional Integrated Functional, Structural, and Computational Mapping to Define the Structural "Fingerprints" of Heart-Specific Atrial Fibrillation Drivers in Human Heart Ex Vivo.

TL;DR: A novel CNN with skip connections is demonstrated to perform efficient, automatic ECG signal classification that could potentially aid robust patient diagnosis in real time.

TL;DR: Song et al. as mentioned in this paper used a 21-layer 1D convolutional recurrent neural network (RNN) to classify ECGs of different rhythms including atrial fibrillation (AF).

TL;DR: This work has developed AtriaNet, a 16-layer convolutional neural network (CNN) that was tested on the largest known data set for LA segmentation, and to the best of the knowledge, it is the most robust approach that has ever been developed for segmenting LGE-MRIs.

TL;DR: This work provides a unified framework, based on LDRBMs, for generating full heart muscle fibers and proposes, for the first time, a LDRBM to be used for generating atrial fibers.

TL;DR: Analysis of historical data and more recent experimental evidence behind the hypothesis that AF may be organized by one, or a small number of high-frequency reentrant sources localized in the left atrium discusses the potential implications and evidence supporting such a hypothesis for human AF.

TL;DR: Electric dissociation of neighboring atrial muscle bundles is a key element in the development of the substrate of human fibrillatory process in patients with normal sinus rhythm and long-standing persistent AF.

TL;DR: This review of anatomy revisits the left atrium, inside as well as outside, for a better understanding of the atrial component parts and the spatial relationships of specific structures.

TL;DR: Patient-derived models demonstrate that AF in fibrotic substrates is perpetuated by RDs persisting in fibrosis boundary zones characterized by specific regional fibrosis metrics (high FE and FD).