中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

32 records (took 0.018 seconds)

    MODEL SUITABILITY COEFFICIENTS BASED ON GENERATIVE ADVERSARIAL NETWORKS AND ACTIVATION MAPS
    3.
    发明申请
    MODEL SUITABILITY COEFFICIENTS BASED ON GENERATIVE ADVERSARIAL NETWORKS AND ACTIVATION MAPS 有权

    公开(公告)号：US20220237467A1

    公开(公告)日：2022-07-28

    申请号：US17155997

    申请日：2021-01-22

    Applicant: GE Precision Healthcare LLC

    Inventor： Hariharan Ravishankar ,  Rahul Venkataramani ,  Prasad Sudhakara Murthy ,  Annangi P. Pavan Kumar

    IPC: G06N3/08

    Abstract: Systems and techniques that facilitate generation of model suitability coefficients based on generative adversarial networks and activation maps are provided. In various embodiments, a system can access a deep learning model that is trained on a training dataset. In various instances, the system can compute a model suitability coefficient that indicates whether the deep learning model is suitable for deployment on a target dataset, based on analyzing activation maps associated with the deep learning model. In various aspects, the system can train a generative adversarial network (GAN) to model a distribution of training activation maps of the deep learning model, based on samples from the training dataset. In various cases, the system can generate a set of target activation maps of the deep learning model, by feeding a set of samples from the target dataset to the deep learning model. In various instances, the system can cause a generator of the GAN to generate a set of synthetic training activation maps from the distribution of training activation maps of the deep learning model. In various aspects, the system can iteratively perturb inputs of the generator until distances between the set of synthetic training activation maps and the set of target activation maps are minimized. In various cases, the system can aggregate the minimized distances, wherein the model suitability coefficient is based on the aggregated minimized distances.

    SYSTEMS AND METHODS FOR GENERATING ULTRASOUND PROBE GUIDANCE INSTRUCTIONS
    4.
    发明申请
    SYSTEMS AND METHODS FOR GENERATING ULTRASOUND PROBE GUIDANCE INSTRUCTIONS 有权

    公开(公告)号：US20220061803A1

    公开(公告)日：2022-03-03

    申请号：US17143586

    申请日：2021-01-07

    Applicant: GE Precision Healthcare LLC

    Inventor： Rahul Venkataramani ,  Vikram Melapudi ,  Pavan Annangi

    IPC: A61B8/00 ,  A61B8/08 ,  A61B34/20

    Abstract: Systems, machine-readable media, and methods for ultrasound imaging can include acquiring three-dimensional data for one or more patient data sets and generating a three-dimensional environment based on one or more transition areas identified between a plurality of volumes of the three-dimensional data. A method can also include generating a set of probe guidance instructions based at least in part on the one or more transition areas and the plurality of volumes of the three-dimensional data, and acquiring, using an ultrasound probe, a first frame of two-dimensional data for a patient. The method can also include executing the set of probe guidance instructions to provide probe feedback for acquiring at least a second frame of two-dimensional data.

    FAILURE MODE ANALYSIS USING NATURAL LANGUAGE DESCRIPTORS
    5.
    发明申请
    FAILURE MODE ANALYSIS USING NATURAL LANGUAGE DESCRIPTORS 有权

    公开(公告)号：US20250124695A1

    公开(公告)日：2025-04-17

    申请号：US18485923

    申请日：2023-10-12

    Applicant: GE Precision Healthcare LLC

    Inventor： Rahul Venkataramani

    IPC: G06V10/776 ,  G06F40/279 ,  G06F40/40 ,  G06V10/778 ,  G06V10/94 ,  G06V20/50

    Abstract: In one embodiment, a method is provided for determining one or more failure modes of a machine learning model. In accordance with certain such embodiments, one or more images are accessed or acquired from a first source. The one or more images are processed using a machine learning model. The machine learning model outputs one or more processed images. One or more failure cases of the machine learning model are detected in the one or more processed images. One or more respective images corresponding to the one or more failure cases are processed using a text description generating framework configured to generate one or more text descriptors for each image corresponding to a failure case. One or more failure modes of the machine learning model are determined based on the text descriptors generated for the images corresponding to the failure cases.

    SYSTEM AND METHODS FOR ELECTROCARDIOGRAM BEAT SIMILARITY ANALYSIS
    7.
    发明公开
    SYSTEM AND METHODS FOR ELECTROCARDIOGRAM BEAT SIMILARITY ANALYSIS 审中-公开

    公开(公告)号：US20230181082A1

    公开(公告)日：2023-06-15

    申请号：US18167693

    申请日：2023-02-10

    Applicant: GE Precision Healthcare LLC

    Inventor： Hariharan Ravishankar ,  Rahul Venkataramani

    IPC: A61B5/335 ,  A61B5/00

    CPC classification number: A61B5/335 ,  A61B5/7246 ,  A61B5/7267

    Abstract: Methods and systems are provided for determining a phase shift and noise insensitive similarity metric for electrocardiogram (ECG) beats in a Holter monitor recording. In one embodiment, a method includes selecting a first beat and a second beat recorded via one or more Holter monitors, determining a dynamic time warping (DTW) distance between the first beat and the second beat, setting a similarity label for the first beat and the second beat based on the DTW distance, and storing the first beat, the second beat, and the similarity label, in a location of non-transitory memory as an ECG training data triad, and training a machine learning model with the ECG training data triad.

    System and methods for electrocardiogram beat similarity analysis using deep neural networks
    8.
    发明授权
    System and methods for electrocardiogram beat similarity analysis using deep neural networks 有权

    公开(公告)号：US11589828B2

    公开(公告)日：2023-02-28

    申请号：US16733797

    申请日：2020-01-03

    Applicant: GE Precision Healthcare LLC

    Inventor： Hariharan Ravishankar ,  Rahul Venkataramani

    IPC: G06N3/084 ,  G16H50/20 ,  G16H40/63 ,  G16H10/60 ,  A61B5/316 ,  A61B5/00 ,  G06N3/04

    Abstract: Methods and systems are provided for automatically determining a phase shift and noise insensitive similarity metric for electrocardiogram (ECG) beats in a Holter monitor recording. In one embodiment, a deep neural network may be trained to map an ECG beat to a phase shift insensitive and noise insensitive feature space embedding using a training data triad, wherein the training data triad may be produced by a method comprising: selecting a first beat and a second beat recorded via one or more Holter monitors, determining a dynamic time warping (DTW) distance between the first beat and the second beat, setting a similarity label for the first beat and the second beat based on the DTW distance, and storing the first beat, the second beat, and the similarity label, in a location of non-transitory memory as an ECG training data triad.

    TISSUE SPECIFIC TIME GAIN COMPENSATION METHODS AND SYSTEMS
    9.
    发明申请
    TISSUE SPECIFIC TIME GAIN COMPENSATION METHODS AND SYSTEMS 有权

    公开(公告)号：US20220101544A1

    公开(公告)日：2022-03-31

    申请号：US17488750

    申请日：2021-09-29

    Applicant: GE Precision Healthcare LLC

    Inventor： Rahul Venkataramani ,  Krishna Seetharam Shriram ,  Aditi Garg

    IPC: G06T7/40 ,  G06T7/11

    Abstract: Systems and methods for tissue specific time gain compensation of an ultrasound image are provided. The method comprises acquiring an ultrasound image of a subject and displaying the ultrasound image over a console. The method further comprises selecting by a user a region within the ultrasound image that requires time gain compensation. The method further comprises carrying out time gain compensation of the user selected region of the ultrasound image. The method further comprises identifying a region having a similar texture to the user selected region and carrying out time gain compensation of the user selected region by an artificial intelligence (AI) based deep learning module.

Patent Agency Ranking