METHOD OF QUANTIFYING POSTERIOR CONFIDENCE

    公开(公告)号:US20250086485A1

    公开(公告)日:2025-03-13

    申请号:US18824972

    申请日:2024-09-05

    Inventor: Bo ZHANG

    Abstract: Examples of the disclosure relate to a computer-implemented method, the method including quantifying a posterior confidence of an output of a layer of an artificial intelligence (AI) model for a set of input data samples using a mixture model, the AI model being a classifier model, providing an assumed prevalence prior on a class distribution, and calibrating the quantified posterior confidence based on the prevalence prior.

    ULTRASONIC METHOD AND SYSTEM FOR ESTIMATING THE NONLINEAR SHEAR WAVE ELASTICITY OF A MEDIUM

    公开(公告)号:US20230044531A1

    公开(公告)日:2023-02-09

    申请号:US17875470

    申请日:2022-07-28

    Abstract: The invention relates to an ultrasonic method for estimating a nonlinear shear wave elasticity of a medium, the method comprising the following steps: A1. a first collection step in which a first set comprising one shear wave elasticity data point of the medium is collected at a first level of deformation applied to the medium, A2. a second collection step in which a second set comprising one shear wave elasticity data point of the medium is collected at a second level of deformation applied to the medium different to the first level, A3. a deformation estimation step in which the difference of deformation between the first and the second level of deformation is estimated, B1. a calculation step in which a gradient between at least two data points respectively belonging to the first and the second set is calculated as a function of the difference of deformation between the first and the second level of deformation, B2. an elasticity estimation step in which the nonlinear shear wave elasticity of the medium is estimated as a function of the gradient.

    METHOD AND DEVICE FOR DETERMINING LIVER CONDITION OF SUBJECT

    公开(公告)号:US20240428404A1

    公开(公告)日:2024-12-26

    申请号:US18665179

    申请日:2024-05-15

    Abstract: Examples of the disclosure relate to a method and a device for determining the condition of the liver of a subject. The method includes obtaining a first group of scan data from ultrasonic waves propagating according to a first scan configuration of the liver, obtaining a second group of scan data from ultrasonic waves propagating according to a second scan configuration of a group of tissues of the subject, and determining, by a combination of the first and second groups of scan data, an indicator representative of the condition of the liver.

    METHOD AND SYSTEM FOR PROCESSING MULTI-MODALITY AND/OR MULTI-SOURCE DATA OF A MEDIUM

    公开(公告)号:US20240054756A1

    公开(公告)日:2024-02-15

    申请号:US18550935

    申请日:2022-03-15

    Inventor: Bo ZHANG

    CPC classification number: G06V10/60 G06V10/48 G06T15/06 G06T15/08 G06V2201/03

    Abstract: The invention relates to for method for processing multi-modality and/or multi-source data of a medium, wherein said method may be implemented by a processing system, the method comprising the following steps:



    an optical determination step in which for at least one of a plurality of volume units of the medium an optical property is determined based on the data of a modality and/or source,
    a fluorescence determination step in which for at least one of the volume units a fluorescence property is determined based on the data of a second modality and/or source, and
    a rendering step in which a data representation of the medium is rendered based on the determined optical and fluorescence properties of the volume units. The invention also relates to a corresponding processing system.

    METHOD OF REFINING SEGMENTATION MASK

    公开(公告)号:US20250005762A1

    公开(公告)日:2025-01-02

    申请号:US18658697

    申请日:2024-05-08

    Inventor: Bo ZHANG

    Abstract: Examples of the disclosure relate to a method of refining a segmentation mask, the method including providing a first segmentation mask associated with a region of interest in an image, providing a user input comprising a user-defined area of the image, and obtaining a second segmentation mask by refining the first segmentation mask based on image data of the image using a computer-implemented algorithm, wherein the algorithm is configured to penalize a violation of the user input.

    METHOD AND SYSTEM FOR COMPSENSATING DEPTH-DEPENDENT ATTENUATION IN ULTRASONIC SIGNAL DATA

    公开(公告)号:US20220163646A1

    公开(公告)日:2022-05-26

    申请号:US17474650

    申请日:2021-09-14

    Abstract: A method for compensating a depth-dependent attenuation in ultrasonic signal data of a medium and a system for performing the method. The method is implemented by a processing system (8), the method comprising the following: processing (c), in which ultrasound signal data is processed by the processing unit for providing in-phase and quadrature phase (IQ) data of the medium, and attenuation compensation (f), in which a phase of the IQ data is compensated as a function of a respective frequency shift amount for each of a plurality of different depths (z1, z2, zn) in the medium, such that the IQ data spectrum is recentered across the plurality of different depths.

Patent Agency Ranking