Abstract: In some embodiments, there are provided systems, devices, components, and corresponding methods configured to permit navigation and/or positioning of an intra-cardiac electrophysiological (EP) mapping basket or other EP mapping structure of an EP mapping catheter inside or near an atrium or other heart chamber of a patient's heart using biosignals or intra-cardiac signals. In one embodiment, QRS complexes are extracted or isolated from intra-cardiac signals sensed by electrodes mounted on the EP mapping basket. Using the QRS complexes and a statistical shape or other model of the EP mapping basket or other type of EP mapping structure, one or more computing devices then determine the locations of the electrodes inside or near the patient's atrium that are associated with each isolated or extracted QRS complex, and thereby permit accurate navigation within the heart and/or processing of data acquired using the EP mapping basket or other EP mapping structure.

Abstract: Electrographic flow mapping (EGF mapping) is a technique used for aiding catheter ablation when treating atrial fibrillation. Visualizing EGF fields during a cardiac catherization and ablation procedure is an important and necessary part of conducting the procedure. Several different visualization methods are described and disclosed herein that may be employed to visualize EGF fields and maps, including quiver plots, streamline plots, particle plots, particle trail plots, moving particle plots, and moving and fading particle plots.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to extract atrial signals from electrical signals acquired from a patient suffering from atrial fibrillation. The electrical signals acquired from the patient may be intra-cardiac signals or body surface electrode signals, or both. At least portions of QRS or QRS-T complexes corresponding to determined initial synchronization times are used to generate Fast Fourier Transforms (FFTs) corresponding to the extracted QRS complexes. A series of steps follow to generate isolated atrial signals corresponding to each electrical signal by subtracting generated reconstructed signals corresponding to each such electrical signal therefrom.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to estimate the action potential wave propagation in a patient's heart, and subsequently to detect at least one location or type of at least one source of, or rotational phenomenon associated with, at least one cardiac rhythm disorder using intracardiac electrodes and a modified multi-frame Horn-Schunck algorithm to generate a map corresponding to a spatial map, the map being configured to reveal on a monitor or display to a user the at least one location of the at least one source of the at least one cardiac rhythm disorder.

Abstract: In some embodiments, there are provided systems, devices, components, and corresponding methods configured to permit navigation and or positioning of an intra-cardiac electrophysiological (EP) mapping basket of an EP mapping catheter inside or near an atrium or other heart chamber of a patient's heart using biosignals or intra-cardiac signals. In one embodiment, QRS complexes are extracted or isolated from intra-cardiac signals sensed by electrodes mounted on the EP mapping basket. Using the QRS complexes, one or more computing devices then determine the locations of the electrodes inside or near the patient's atrium that are associated with each isolated or extracted QRS complex. The one or more computing devices can also be used to determine changes in the three-dimensional locations and orientations of the basket and the electrodes thereof as the basket is moved around, in, or near the patient's atrium, heart chamber, or other portion of the patient's heart.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to detect a location of a source of at least one cardiac rhythm disorder in a patient's heart.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining a batch of labeled training items and a batch of unlabeled training items; processing the labeled training items and the unlabeled training items using the neural network and in accordance with current values of the network parameters to generate respective embeddings; determining a plurality of similarity values, each similarity value measuring a similarity between the embedding for a respective labeled training item and the embedding for a respective unlabeled training item; determining a respective roundtrip path probability for each of a plurality of roundtrip paths; and performing an iteration of a neural network training procedure to determine a first value update to the current values of the network parameters that decreases roundtrip path probabilities for incorrect roundtrip paths.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to classify, and to detect at least one location or type of at least one source of, at least one cardiac rhythm disorder in a patient's heart using one or more body surface electrodes, and/or intracardiac electrodes. Body surface electrogram data, and optionally intracardiac electrode data, representative of cardiac signals acquired from the patient are provided to a computing device, which in turn determines the location and type of the at least one source of the at least one cardiac rhythm disorder in the patient's heart using electrographic flow (EGF) methods, and then classifies same using electrographic volatility index (EVI) methods.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to detect a location of a source of at least one cardiac rhythm disorder in a patient's heart. In some embodiments, electrogram signals are acquired from a patient's body surface, and subsequently normalized, adjusted and/or filtered, followed by generating a two-dimensional spatial map, grid or representation of the electrode positions, processing the amplitude-adjusted and filtered electrogram signals to generate a plurality of three-dimensional electrogram surfaces corresponding at least partially to the 2D map, one surface being generated for each or selected discrete times, and processing the plurality of three-dimensional electrogram surfaces through time to generate a velocity vector map corresponding at least partially to the 2D map.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to detect the locations of sources of cardiac rhythm disorders in a patient's heart, and then to generate an estimate or probability of the patient being free from atrial fibrillation. The various embodiments employ at least one computing device to process a plurality of electrogram surfaces through time to generate at least one electrographical flow (EGF) map, representation, pattern, or data set, and then process the at least one EGF map, representation, pattern, or data set to determine at least two of source activity levels, flow angle variability (FAV) levels, and active fractionation (AFR) levels corresponding thereto. On the basis of a combination of the determined at least two of source activity levels, FAV levels, and AFR levels, an electrographical volatility index (EVI) score or metric representative of the estimate or probability of the patient being free from AF is generated.

Abstract: Electrographic flow mapping (EGF mapping) is a technique used for aiding catheter ablation when treating atrial fibrillation. Visualizing EGF fields during a cardiac catherization and ablation procedure is an important and necessary part of conducting the procedure. Several different visualization methods are described and disclosed herein that may be employed to visualize EGF fields and maps, including quiver plots, streamline plots, particle plots, particle trail plots, moving particle plots, and moving and fading particle plots.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to detect a location of a source of at least one cardiac rhythm disorder in a patient's heart.

Abstract: Disclosed are various examples and embodiments of systems, devices, components and methods configured to detect a location of a source of at least one cardiac rhythm disorder in a patient's heart. In some embodiments, electrogram signals are acquired from a patient's body surface, and subsequently normalized, adjusted and/or filtered, followed by generating a two-dimensional spatial map, grid or representation of the electrode positions, processing the amplitude-adjusted and filtered electrogram signals to generate a plurality of three-dimensional electrogram surfaces corresponding at least partially to the 2D map, one surface being generated for each or selected discrete times, and processing the plurality of three-dimensional electrogram surfaces through time to generate a velocity vector map corresponding at least partially to the 2D map.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes obtaining a batch of labeled training items and a batch of unlabeled training items; processing the labeled training items and the unlabeled training items using the neural network and in accordance with current values of the network parameters to generate respective embeddings; determining a plurality of similarity values, each similarity value measuring a similarity between the embedding for a respective labeled training item and the embedding for a respective unlabeled training item; determining a respective roundtrip path probability for each of a plurality of roundtrip paths; and performing an iteration of a neural network training procedure to determine a first value update to the current values of the network parameters that decreases roundtrip path probabilities for incorrect roundtrip paths.