Abstract: Apparatuses, systems, and techniques to perform registration among images. In at least one embodiment, one or more neural networks are trained to indicate registration of features in common among at least two images by generating a first correspondence by simulating a registration process of registering an image and applying the at least two images and the first correspondence to a neural network to derive a second correspondence of the features in common among the at least two images.

Abstract: Apparatuses, systems, and techniques to select a neural network architecture from a plurality of neural networks in a federated learning (FL) setting. In at least one embodiment, a neural network is trained by combining training results from different FL computing systems, where each of the different FL computing systems, for example, trains different portions of the neural network.

Abstract: Apparatuses, systems, and techniques estimate parameters to train one or more neural networks based on uniqueuss of training data. In at least one embodiment, a subset of training data is selected and used to estimate parameters to train one or more neural networks, based on, for example, uniqueness of training data.

Abstract: Apparatuses, systems, and techniques are presented to train neural networks. In at least one embodiment, one or more hyperparameters are adjusted in conjunction with one or more weight parameters corresponding to one or more neural networks.

Abstract: A segmentation model is trained with an image reconstruction model that shares an encoding. During application of the segmentation model, the segmentation model may use the encoding and network layers trained for the segmentation without the image reconstruction model. The image reconstruction model may include a probabilistic representation of the image that represents the image based on a probability distribution. When training the model, the encoding layers of the model use a loss function including an error term from the segmentation model and from the autoencoder model. The image reconstruction model thus regularizes the encoding layers and improves modeling results and prevents overfitting, particularly for small training sizes.

Abstract: Apparatuses, systems, and techniques estimate parameters to train one or more neural networks based on uniqueuss of training data. In at least one embodiment, a subset of training data is selected and used to estimate parameters to train one or more neural networks, based on, for example, uniqueness of training data.

Abstract: A method of image-guided radiation treatment is described. The method includes processing a first and second sets of image data to generate an enhanced image, wherein the enhanced image comprises a combination of the first and second sets of image data, wherein part or all of the image data comprises a target of a patient. The method also includes registering the enhanced image with another image to obtain a registration result and tracking the target using the registration result to generate tracking information. The method also includes directing treatment delivery to the target based on the tracking information obtained from the enhanced image.

Abstract: Apparatuses, systems, and techniques estimate parameters to train one or more neural networks based on uniqueuss of training data. In at least one embodiment, a subset of training data is selected and used to estimate parameters to train one or more neural networks, based on, for example, uniqueness of training data.

Abstract: Apparatuses, systems, and techniques to generate one or more neural networks. In at least one embodiment, one or more neural networks are generated, based on, for example, one or more convolutional neural network operations and one or more transformer neural network operations.

Abstract: Apparatuses, systems, and techniques to perform registration among images. In at least one embodiment, one or more neural networks are trained to indicate registration of features in common among at least two images by generating a first correspondence by simulating a registration process of registering an image and applying the at least two images and the first correspondence to a neural network to derive a second correspondence of the features in common among the at least two images.

Abstract: Apparatuses, systems, and techniques to perform registration among images. In at least one embodiment, one or more neural networks are trained to indicate registration of features in common among at least two images by generating a first correspondence by simulating a registration process of registering an image and applying the at least two images and the first correspondence to a neural network to derive a second correspondence of the features in common among the at least two images.

Abstract: Apparatuses, systems, and techniques are presented to generate images representing realistic motion or activity. In at least one embodiment, one or more neural networks are used to select a first neural network to perform a first task based, at least in part, upon a performance estimated by a second neural network.

Abstract: A method of operating a radiation apparatus is described. The method includes selecting at least a first angle and a second angle from a set of angles for a first rotation of a gantry of a radiation apparatus. The method also includes generating, using an imaging device mounted to the gantry, a first tracking image of a target from the first angle during the first rotation of the gantry. The method further includes generating, using the imaging device, a second tracking image of the target from the second angle during the first rotation of the gantry.

Abstract: A method of operating imaging and tracking. The method includes determining, for each angle of a plurality of angles from which tracking images can be generated by an imaging device, a value of a tracking quality metric for tracking a target based on an analysis of a projection generated at that angle. The method also includes selecting, by a processing device, a subset of the plurality of angles that have a tracking quality metric value that satisfies a tracking quality metric criterion, one or more angles of the subset to be used to generate a tracking image of the target during a treatment stage, wherein the subset comprises at least a first angle and a second angle that is at least separated by a minimum threshold from the first angle.

Abstract: Apparatuses, systems, and techniques are presented to select neural networks. In at least one embodiment, one or more first neural networks can be used to select one or more second neural networks, as may be based at least in part upon an inference to be generated by the one or more second neural networks.

Abstract: Apparatuses, systems, and techniques are presented to classify objects in images. In at least one embodiment, one or more neural networks are used to identify one or more objects in one or more full images based, at least in part, on the one or more neural networks having been trained using the one or more full images and one or more portions of the one or more full images.

Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, one or more neural networks are used to help generate one or more segmentation boundaries of one or more objects within one or more digital images, wherein the one or more neural networks are to transform one or more representations of one or more portions of the one or more objects into one or more lower-dimensional representations of the one or more portions of the one or more objects.

Abstract: Apparatuses, systems, and techniques are presented to predict annotations for objects in images. In at least one embodiment, boundaries of an object within an image can be identified based, at least in part, on a user-generated outline of only a portion of this object or information about a size of this object provided by a user.

Abstract: Apparatuses, systems, and techniques to generate one or more images of an object. In at least one embodiment, a technique includes training one or more neural networks to generate one or more images of an object from at least a first image of the object and a second lower-resolution image of the object, where the training includes a comparison of the one or more generated images of the object with the second lower-resolution image of the object.

Abstract: Apparatuses, systems, and techniques to improve federated learning for neural networks. In at least one embodiment, a federated server dynamically selects neural network weights according to one or more learnable aggregation weights indicating a contribution from each of one or more edge devices or clients during federated training according to various characteristics of each edge device or client model and training data.