Abstract: Provided herein are methods of generating models to predict prospective pathology scores of test subjects having a pathology in certain embodiments. Related systems and computer program products are also provided.

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

Abstract: Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

Abstract: A method for enriching a historical learning base. Training of a first neural network to transform first photos of first dental scenes into first hyper-realistic images to simulate the effect of a dental event on the first dental scenes. Submission, to the trained first neural network, of a source photo representing a source dental scene in a dental context, so as to obtain a final image representing, hyper-realistically, the source dental scene after simulation of the dental event. Creation of a descriptor of the final image, or “final descriptor.” Creation of a historical record consisting of the final image and the final descriptor, and addition of the historical record in the historical learning base.

Abstract: Devices and methods for nasal administration of a pharmaceutical composition. In certain embodiments, the devices comprises a reservoir, a conduit in fluid communication with the reservoir, and an anatomic positioning device configured to position the conduit in a nasal cavity of a user. Particular embodiments include an actuator configured to transfer the pharmaceutical composition from the reservoir to the conduit and emit the pharmaceutical composition from the conduit.

Abstract: An apparatus for generating a three-dimensional (3D) model of cardiac anatomy via machine-learning, wherein the apparatus includes a process and a memory containing instructions configuring the processor to receive a set of images of a cardiac anatomy pertaining to a subject, generate an 3D data structure representing the cardiac anatomy as a function of the set of images using a cardiac anatomy modeling model, generate an initial 3D model of the cardiac anatomy, refine the generated initial 3D model of the cardiac anatomy as a function of the 3D data structure representing the cardiac anatomy, and generate a subsequent 3D model of the cardiac anatomy as a function of the refinement.

Abstract: Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

Abstract: Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

Abstract: An apparatus for scaling images includes one or more processors and one or more computer-readable storage media on which computer-executable instructions are stored. The computer-executable instructions, upon being executed by the one or more processors, provide for execution of the following steps: capturing one or more first images by an imaging and/or image recording system, wherein the one or more captured first images are related to a first resolution; and generating, by a neural network, one or more corresponding second images based on one or more captured first images, wherein the one or more second images are related to a second resolution, the first resolution differing from the second resolution.

Abstract: The present application provides an AI-based system for evaluating an individual's mindfulness (e.g., during prayer) based on video captured of the individual. In one example, the video may be captured via a smart phone. The individual's mindfulness may be continually evaluated from the captured video by observing the individual's body pose and movements. For instance, turning the individual's head to one side or moving the individual's eyes around rapidly can be signs of losing focus. Body pose and movement information of an individual may be derived from the video through AI-based video analytics. The user's body pose and movements may be checked against a set of predefined criteria for mindfulness, and an objective evaluation may be provided. Such evaluation can then be fed back to the individual, for example, to remind the individual whenever they lose focus during prayer.

Abstract: Apparatus and methods related to applying lighting models to images of objects are provided. A neural network can be trained to apply a lighting model to an input image. The training of the neural network can utilize confidence learning that is based on light predictions and prediction confidence values associated with lighting of the input image. A computing device can receive an input image of an object and data about a particular lighting model to be applied to the input image. The computing device can determine an output image of the object by using the trained neural network to apply the particular lighting model to the input image of the object.

Abstract: Disclosed is a method and a device for coding a sequence including first and second digital holograms representing respective scenes, the digital holograms being represented by a set of wavelets each defined by a multiplet of coordinates in multidimensional space. The first and second holograms are represented by first and second coefficients respectively associated with wavelets. The coding method includes the following steps: for each second coefficient, determining a remainder by a difference between the second coefficient concerned, associated with a first wavelet defined by a given multiplet, and the first coefficient) associated with a second wavelet defined by a multiplet having as its image the multiplet by a transform in the multidimenisonal space; coding the determined remainders. The transform is determined by analysis of variation between the first scene represented by the first digital hologram and the second scene represented by the second digital hologram.

Abstract: Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

Abstract: Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

Abstract: A plurality of images can be acquired from a plurality of sensors and a plurality of flattened patches can be extracted from the plurality of images. An image location in the plurality of images and a sensor type token identifying a type of sensor used to acquire an image in the plurality of images from which the respective flattened patch was acquired can be added to each of the plurality of flattened patches. The flattened patches can be concatenated into a flat tensor and add a task token indicating a processing task to the flat tensor, wherein the flat tensor is a one-dimensional array that includes two or more types of data. The flat tensor can be input to a first deep neural network that includes a plurality of encoder layers and a plurality of decoder layers and outputs transformer output. The transformer output can be input to a second deep neural network that determines an object prediction indicated by the token and the object predictions can be output.

Abstract: A method of operation of a compute system includes: verifying a patient image as an acceptable image; detecting a body part from the acceptable image; generating a skin segmentation for the body part including a non-skin region and a skin region based on the acceptable image; and generating a local Hidradenitis Suppurativa (HS) severity score based on the patient image for displaying on a device to assist in diagnosis.

Abstract: Systems and methods for analyzing pathologies utilizing quantitative imaging are presented herein. Advantageously, the systems and methods of the present disclosure utilize a hierarchical analytics framework that identifies and quantify biological properties/analytes from imaging data and then identifies and characterizes one or more pathologies based on the quantified biological properties/analytes. This hierarchical approach of using imaging to examine underlying biology as an intermediary to assessing pathology provides many analytic and processing advantages over systems and methods that are configured to directly determine and characterize pathology from underlying imaging data.

Abstract: The disclosure belongs to the field of image segmentation in medical image processing and discloses a three-dimensional medical image segmentation method and system based on short-term and long-term memory self-attention models, in which the method can segment a target area image in the medical image, which includes the following. (1) A training set sample is established. (2) Processing is performed on the original three-dimensional medical image to be segmented to obtain a sample to be segmented. (3) A three-dimensional medical image segmentation network based on short-term and long-term memory self-attention is established and trained. (4) The sample to be segmented is input to the network, and then a segmentation result of the target area in the sample to be segmented is output. By combining CNN and Transformer, a new model for accurate real-time segmentation of the target area (such as a tumor) in the three-dimensional medical image is obtained.

Abstract: The method, apparatus and computer program product estimate the depth to objects within a scene that is captured by first and second cameras of a mobile terminal. A method includes determining, based upon an image including an eye of a user captured by a first camera of a mobile terminal and an image of a scene captured by a second camera of the mobile terminal, two or more angles of a geometric shape defined by the eye, the mobile terminal and an object of the scene. Based upon the image captured by the first camera, the method also determines a first distance from the first camera to the eye. The method further estimates the depth to the object in the scene relative to the mobile terminal based upon the first distance and one or more angles of the geometric shape defined by the eye, the mobile terminal and the object.

Abstract: Techniques for detecting key points associated with objects in an environment are described herein. The techniques may include receiving sensor data representing a portion of an environment in which the vehicle is operating and inputting the sensor data into a machine-learned model. Based on the input sensor data, the machine-learned model may detect one or more key points corresponding to physical features (e.g., hands, feet, eyes, etc.) of a pedestrian who is in the environment. Based on the one or more key points, a bounding box associated with the pedestrian may be generated and the vehicle may be controlled based on at least one of the key points or the bounding box. The techniques may also include training the machine-learned model to detect key points associated with pedestrians.