Abstract: A system may access a source image of the subject. A system may execute an image segmentation model that uses the source image to distinguish the target object from among other objects in the source image. A system may generate a binary image of the target object based on execution of the image segmentation model. A system may generate, based on the binary image, a size estimate of the target object. A system may execute a machine learning-based model that uses the size estimate and one or more covariates to predict a future size of the target object. A system may determine a risk classification for the subject based on the predicted growth rate, the risk classification being based on a probability that the target object of the subject will result in a disease state, the risk classification to be used to determine a treatment regimen to treat or prevent the disease state.

Abstract: A camera includes a fixed pattern aperture with a pattern that has a transmittance that is different in different portions of the fixed pattern aperture. The camera also includes an array of sensors that generate signals based on an intensity of light received by the sensors through the fixed pattern aperture. In some cases, the camera includes a processor to generate measurement vectors based on values of signals received from the sensors in the sensor array when exposed to a scene. The processor is also configured to determine values of voxels that represent a 3D image of the scene based on the measurement vectors. A transformed sensing matrix associated with the fixed pattern aperture and the sensor array is generated based on measurement vectors captured by the camera when exposed to basis images at different separations from the camera. Volumetric images of objects are determined from the transformed sensing matrix.

Abstract: The present disclosure generally discloses single-aperture multi-sensor lensless compressive image acquisition capabilities. The present disclosure generally discloses a single-aperture multi-sensor lensless camera including a programmable aperture and a set of sensors. The programmable aperture is configured to modulate an amount of light permitted to pass through the programmable aperture and has a shape defined based on a set of vertices of the programmable aperture. The sensors are arranged, with respect to each other, based on the vertices of the programmable aperture. The sensors may be arranged such that respective reference lines, between the respective vertices of the programmable aperture and the respective sensors, are parallel or substantially parallel.

Abstract: The present disclosure provides systems and methods that are configured for feature extraction or object recognition using compressive measurements that represent a compressed image of a scene. In various aspects, a compressive sensing matrix is constructed and used to acquire the compressive measurements, such that in the extraction phase, the compressive measurements can be processed to detect feature points and determine their feature vectors in the scene without using a pixel representation of the scene. The determined feature vectors are used to detect objects based on comparison with one or more predetermined feature vectors.

Abstract: The present disclosure generally discloses single-aperture multi-sensor lensless compressive image acquisition capabilities. The present disclosure generally discloses a single-aperture multi-sensor lensless camera including a programmable aperture and a set of sensors. The programmable aperture is configured to modulate an amount of light permitted to pass through the programmable aperture and has a shape defined based on a set of vertices of the programmable aperture. The sensors are arranged, with respect to each other, based on the vertices of the programmable aperture. The sensors may be arranged such that respective reference lines, between the respective vertices of the programmable aperture and the respective sensors, are parallel or substantially parallel.

Abstract: A method for locating mobile terminals is provided. First, information of a home Public Land Mobile Network (PLMN) of a target mobile terminal, the location of which is to be determined, is checked in response to a location service request from a client. Then, information of a visited PLMN, where the target mobile terminal is currently located, is checked based on the checked information of the home PLMN. The home PLMN calculates location assistance information of the visited PLMN using specific location information of the visited PLMN. The location assistance information is transferred to the target mobile terminal. This allows location information of a mobile terminal to be obtained irrespective of the area or communication network where the mobile terminal is located. It is thus possible to locate a mobile terminal in an area where no location assistance information is provided.