Abstract: The present disclosure relates to methods, apparatuses, and computer programs for processing computed tomography images. Precise segmentation of the left atrium (LA) in computed tomography (CT) images constitutes a crucial preparatory step for catheter ablation in atrial fibrillation (AF). We aim to apply deep convolutional neural networks (DCNNs) to automate the LA detection/segmentation procedure and create a three-dimensional (3D) geometries. The deep learning provides an efficient and accurate way for automatic contouring and LA volume calculation based on the construction of the 3D LA geometry. Non-pulmonary vein (NPV) trigger has been reported as an important predictor of recurrence post atrial fibrillation (AF) ablation. Elimination of NPV triggers can reduce the post-ablation AF recurrence. The deep learning was applied in pre-ablation pulmonary vein computed tomography (PVCT) geometric slices to create a prediction model for NPV triggers in patients with paroxysmal atrial fibrillation (PAF).

Abstract: The present disclosure relates to methods, apparatuses, and computer programs for processing computed tomography images. Precise segmentation of the left atrium (LA) in computed tomography (CT) images constitutes a crucial preparatory step for catheter ablation in atrial fibrillation (AF). We aim to apply deep convolutional neural networks (DCNNs) to automate the LA detection/segmentation procedure and create a three-dimensional (3D) geometries. The deep learning provides an efficient and accurate way for automatic contouring and LA volume calculation based on the construction of the 3D LA geometry. Non-pulmonary vein (NPV) trigger has been reported as an important predictor of recurrence post atrial fibrillation (AF) ablation. Elimination of NPV triggers can reduce the post-ablation AF recurrence. The deep learning was applied in pre-ablation pulmonary vein computed tomography (PVCT) geometric slices to create a prediction model for NPV triggers in patients with paroxysmal atrial fibrillation (PAF).

Abstract: A computer-assisted method for quantitatively characterizing atrial fibrillation in a patient includes recording time series of bipolar atrial fibrillation signals at multiple sites in a patient's atria using two or more electrodes, calculating a similarity index vector by a computer system based on the bipolar atrial fibrillation signal between a first site and its neighboring sites, constructing an similarity-index vector field based on similarity-index vectors at different sites, calculating Curl and Divergence of the similarity-index vector field, calculating Rotor Identification using Curl and Divergence, calculating Focal Identification using Divergence, and determining one or more critical regions in the patient's atria if Rotor Identification is above a first predetermined threshold and Focal Identification is above a second predetermined threshold.

Abstract: A computer-assisted method for quantitative characterizing atrial fibrillation (AF) in a patient includes recording unipolar atrial fibrillation signals from multiple sites in a patient's atria, calculating bipolar electrograms using unipolar AF signals recorded at adjacent sites by a computer system, applying Empirical Mode Decomposition to remove a background from the bipolar electrogram signal to obtain a filtered bipolar electrogram signal, applying Hilbert transform to an envelope function of the filtered bipolar electrogram signal to obtain a time series of instantaneous phases of the filtered bipolar electrogram signal, and identifying a rotor region in patient's atria using the instantaneous phases in the filtered bipolar electrogram signal.

Abstract: A computer-assisted method for quantitatively characterizing atrial fibrillation in a patient includes recording time series of bipolar atrial fibrillation signals at multiple sites in a patient's atria using two or more electrodes, calculating a similarity index vector by a computer system based on the bipolar atrial fibrillation signal between a first site and its neighboring sites, constructing an similarity-index vector field based on similarity-index vectors at different sites, calculating Curl and Divergence of the similarity-index vector field, calculating Rotor Identification using Curl and Divergence, calculating Focal Identification using Divergence, and determining one or more critical regions in the patient's atria if Rotor Identification is above a first predetermined threshold and Focal Identification is above a second predetermined threshold.

Abstract: A computer-assisted method for quantitative characterization and treatment of ventricular fibrillation includes preprocessing a time series of an atrial fibrillation signal obtained from a patient, segmenting the time series of the AF signal into activation segments by the computer system, obtaining local activation waveforms (LAW) from the activation segments, determining degrees of similarity between the LAWs, and identifying one or more critical regions in the patient's atria if the LAWs have degrees of similarity exceeding a first threshold value.

Abstract: A computer-assisted method for quantitative characterization and treatment of ventricular fibrillation includes preprocessing a time series of an atrial fibrillation signal obtained from a patient, segmenting the time series of the AF signal into activation segments by the computer system, obtaining local activation waveforms (LAW) from the activation segments, determining degrees of similarity between the LAWs, and identifying one or more critical regions in the patient's atria if the LAWs have degrees of similarity exceeding a first threshold value.