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.

Abstract: A method of the present disclosure includes performing, by a processing device, a first image registration between a reference image of a patient and a motion image of the patient to perform alignment between the reference image and the motion image, wherein the reference image and the motion image include a target position of the patient. The method further includes performing, by the processing device, a second image registration between the reference image and a motion x-ray image of the patient, via a first digitally reconstructed radiograph (DRR) for the reference image of the patient. The method further includes tracking at least a translational change in the target position based on the first registration and the second registration.

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: 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 processing device determines a plurality of angles from which tracking images can be generated by an imaging device. The processing device generates a plurality of projections of a treatment planning image of a patient, the treatment planning image comprising a delineated target, wherein each projection of the plurality of projections has an angle that corresponds to one of the plurality of angles from which the tracking images can be taken. The processing device determines, for each angle of the plurality of angles, a value of a tracking quality metric for tracking the target based on an analysis of a projection generated at that angle. The processing device selects a subset of the plurality of angles that have a tracking quality metric value that satisfies a tracking quality metric criterion.

Abstract: A method of operating a radiation apparatus is described that selects at least a first angle and a second angle from the set of angles for a first rotation of the gantry. The method generates, using an imaging device mounted to the gantry, a first tracking image of the target from the first angle during the first rotation of the gantry. The method generates, using the imaging device, a second tracking image of the target from the second angle during the first rotation of the gantry. The method performs targeting tracking based on the first tracking image and the second tracking image.

Abstract: Apparatuses, systems, and techniques to facilitate global semi-supervised training of neural networks to perform image segmentation related to diagnosis and management of emerging diseases, such as COVID-19. In at least one embodiment, distributed client training frameworks train one or more client neural networks to perform image segmentation according to a local training data set as well as global neural network data aggregated, by one or more central servers, from each of one or more globally distributed client neural networks.

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 to select a nueral network architecture from a plurality of neural networs in a federated learning (FL) settng. In at least one embodiment, a neural network is trained by combining training resutls from different FL computing systesms, where each of the different FL computing systems, for example, trains different portions of the nerual network.

Abstract: A method of image-guided radiation treatment is described. The method may include acquiring a pre-treatment image of a patient and generating a first set of image data of part or all of the patient using imaging radiation at a first energy level and a second set of image data of part or all of the patient using imaging radiation at a second energy level. The method may also include processing the 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, and wherein part or all of the image data comprises the target. The method may also include registering the enhanced image with the pre-treatment image to obtain a registration result and tracking movement and position of the target using the registration result to generate tracking information.

Abstract: Apparatuses, systems, and techniques are presented to predict segmentations for objects in images. In at least one embodiment, a neural network is trained to determine one or more segmentation masks corresponding to one or more objects of one or more digital images based, at least in part, on one or more boundary regions of the one or more objects.

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.