Abstract: A device may receive images of a patient, and may perform segmentation of surfaces on the images to create a 3D model. The device may identify normal tissue regions and atrial fibrosis (AF) regions in the 3D model, and may divide the 3D model into the normal tissue regions and the AF regions. The device may assign first cell and tissue properties to the normal tissue regions, and may assign second cell and tissue properties to the AF regions. The device may perform simulations on the normal tissue regions and the AD regions, based on the first and second cell and tissue properties, to generate simulation results, and may extract first features from the simulation results. The device may extract second features from the images, and may process the first and second features, with a model, to select a feature that is predictive of atrial fibrillation recurrence.

Abstract: A device may receive images of a patient, and may perform segmentation of surfaces on the images to create a 3D model. The device may identify normal tissue regions and atrial fibrosis (AF) regions in the 3D model, and may divide the 3D model into the normal tissue regions and the AF regions. The device may assign first cell and tissue properties to the normal tissue regions, and may assign second cell and tissue properties to the AF regions. The device may perform simulations on the normal tissue regions and the AD regions, based on the first and second cell and tissue properties, to generate simulation results, and may extract first features from the simulation results. The device may extract second features from the images, and may process the first and second features, with a model, to select a feature that is predictive of atrial fibrillation recurrence.

Abstract: A device may receive images of a patient, and may perform segmentation of surfaces on the images to create a 3D model. The device may identify normal tissue regions and atrial fibrosis (AF) regions in the 3D model, and may divide the 3D model into the normal tissue regions and the AF regions. The device may assign first cell and tissue properties to the normal tissue regions, and may assign second cell and tissue properties to the AF regions. The device may perform simulations on the normal tissue regions and the AD regions, based on the first and second cell and tissue properties, to generate simulation results, and may extract first features from the simulation results. The device may extract second features from the images, and may process the first and second features, with a model, to select a feature that is predictive of atrial fibrillation recurrence.

Abstract: Methods and systems for machine-learning-based prediction of a dose-volume histogram for radiotherapy treatment planning. The method includes receiving prescription information and a plan geometry. The plan geometry includes a planning target volume and an organ at risk. The method also includes extracting a plurality of input features using the plan geometry and a machine-learning model. The method further includes determining the dose-volume histogram by combining the plurality of input features using the machine-learning model.

Abstract: A device may receive images of a patient, and may perform segmentation of surfaces on the images to create a 3D model. The device may identify normal tissue regions and atrial fibrosis (AF) regions in the 3D model, and may divide the 3D model into the normal tissue regions and the AF regions. The device may assign first cell and tissue properties to the normal tissue regions, and may assign second cell and tissue properties to the AF regions. The device may perform simulations on the normal tissue regions and the AD regions, based on the first and second cell and tissue properties, to generate simulation results, and may extract first features from the simulation results. The device may extract second features from the images, and may process the first and second features, with a model, to select a feature that is predictive of atrial fibrillation recurrence.