BRAIN IMAGE PROCESSING
    2.
    发明公开

    公开(公告)号:US20240346657A1

    公开(公告)日:2024-10-17

    申请号:US18291522

    申请日:2022-07-21

    Inventor: Ian HARDINGHAM

    Abstract: Systems, methods (300), computer program products, and computer readable media for processing images of brains are described. Techniques are described for transforming, into a common space, reference points obtained from at least one image of a reference brain in a first space (302), transforming, into the common space, test points obtained from at least one image of a test brain in a second space (304), determining a position of each of the transformed reference points and each of the transformed test points in the common space (306), calculating a displacement of each of the transformed test points relative to each of the transformed reference points based on the determined positions (308), determining a correspondence between one of the transformed test points and a given transformed reference point based on the calculated displacements (310), and determining a corresponding test point in the second space to a reference point in the first space based on the determined correspondence (312).

    PREDICTING CLASSIFICATION LABELS FOR BIOELECTRIC SIGNALS USING A NEURAL NETWORK

    公开(公告)号:US20240341695A1

    公开(公告)日:2024-10-17

    申请号:US18609211

    申请日:2024-03-19

    Applicant: Tiposi, Inc.

    Abstract: Embodiments of a system for training a classification neural network are provided. The system is configured to receive a first set of simulated bioelectric signals and patient bioelectric signals from a first computing device and a second set of simulated bioelectric signals from a second computing device, generate a compensation factor for the second computing device based on the first set of simulated bioelectric signals and the second set of simulated bioelectric signals, generate compensated patient bioelectric signals based on the compensation factor and the patient bioelectric signals, and train the classification neural network based on the compensated patient bioelectric signals, the second set of simulated bioelectric signals and the compensation factor. The classification neural network is trained to predict a classification label for each of one or more bioelectric signals.

    Systems and methods for finger-to-thumb crease testing

    公开(公告)号:US12089946B1

    公开(公告)日:2024-09-17

    申请号:US16358793

    申请日:2019-03-20

    Abstract: In one embodiment, a system for finger-to-thumb crease testing includes a patient interface configured to attach to a thumb of a patient, the patient interface including a touch sensor configured to sense contact between a finger of the patient and the touch sensor, the touch sensor being positioned on the patient interface in a location at which it overlies a distalmost thumb crease of the thumb when the patient interface is attached, and a control module in electrical communication with the patient interface, the control module being configured to count a number of times the patient successfully taps the touch sensor with the finger.

Patent Agency Ranking