-
公开(公告)号：US11017269B2
公开(公告)日：2021-05-25
申请号：US16334091
申请日：2017-06-21
Applicant: General Electric Company
Inventor： Sheshadri Thiruvenkadam , Sohan Rashmi Ranjan , Vivek Prabhakar Vaidya , Hariharan Ravishankar , Rahul Venkataramani , Prasad Sudhakar
Abstract: A method for determining optimized deep learning architecture includes receiving a plurality of training images and a plurality of real time images corresponding to a subject. The method further includes receiving, by a medical practitioner, a plurality of learning parameters comprising a plurality of filter classes and a plurality of architecture parameters. The method also includes determining a deep learning model based on the plurality of learning parameters and the plurality of training images, wherein the deep learning model comprises a plurality of reusable filters. The method further includes determining a health condition of the subject based on the plurality of real time images and the deep learning model. The method also includes providing the health condition of the subject to the medical practitioner.
-
公开(公告)号：US20200069285A1
公开(公告)日：2020-03-05
申请号：US16118466
申请日：2018-08-31
Applicant: GENERAL ELECTRIC COMPANY
Inventor： Pavan Kumar Annangi , Chandan Kumar Aladahalli , Krishna Seetharam Shriram , Prasad Sudhakar
Abstract: A method for ultrasound imaging is presented. The method includes acquiring at least one image of a subject, determining a current position of an ultrasound probe on a body surface of the subject based on the image, identifying anatomical regions of interest in the image, quantifying the image to determine suitability of the image to one or more scan planes corresponding to a clinical protocol, generating a personalized anatomical model of the subject based on a current position of the ultrasound probe, the identified anatomical regions of interest, and the quantification of the image, computing a desired trajectory of the ultrasound probe from the current location to a target location based on the clinical protocol, communicating a desired movement of the ultrasound probe based on the computed trajectory, moving the ultrasound probe along the computed trajectory based on the communicated desired movement to acquire images of the subject.
-
公开(公告)号：US11810301B2
公开(公告)日：2023-11-07
申请号：US17227093
申请日：2021-04-09
Applicant: General Electric Company
Inventor： Harihan Ravishankar , Vivek Vaidya , Sheshadri Thiruvenkadam , Rahul Venkataramani , Prasad Sudhakar
CPC classification number: G06T7/10 , G06F17/15 , G06N3/045 , G06T2207/20084
Abstract: A method for image segmentation includes receiving an input image. The method further includes obtaining a deep learning model having a triad of predictors. Furthermore, the method includes processing the input image by a shape model in the triad of predictors to generate a segmented shape image. Moreover, the method includes presenting the segmented shape image via a display unit.
-
公开(公告)号：US11232344B2
公开(公告)日：2022-01-25
申请号：US15799698
申请日：2017-10-31
Applicant: General Electric Company
Inventor： Hariharan Ravishankar , Bharath Ram Sundar , Prasad Sudhakar , Rahul Venkataramani , Vivek Vaidya
Abstract: The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.
-
5.发明申请公开(公告)号：US20190200964A1
公开(公告)日：2019-07-04
申请号：US15860771
申请日：2018-01-03
Applicant: GENERAL ELECTRIC COMPANY
Inventor： Prasad Sudhakar , Justin Daniel Lanning , Pavan Kumar Annangi , Michael Washburn
CPC classification number: A61B8/5246 , A61B8/4245 , A61B8/461 , A61B8/5207 , A61B8/5223 , G06T7/0014 , G06T2207/10028 , G06T2207/10136 , G06T2207/20081 , G06T2207/20101 , G06T2207/30096 , G06T2207/30204
Abstract: A system and method for generating a patient-specific organ model is provided. The method may include receiving ultrasound images of an organ and probe position data corresponding with each of the ultrasound images. The method may include receiving identification of landmarks in the ultrasound images corresponding with pre-defined landmarks of a generic geometric organ model. The method may include automatically identifying surface points of the organ in the ultrasound images. The method may include generating a patient-specific ultrasound point cloud of the organ based on the received identification of the landmarks, the automatically identified surface points of the organ, and the probe position data. The method may include registering a point cloud of the generic geometric model to the patient-specific ultrasound point cloud to create a patient-specific organ model. The method may include presenting the patient-specific organ model at a display system.
-
Patent Agency Ranking
公开(公告)号：US20190130247A1
公开(公告)日：2019-05-02
申请号：US15799698
申请日：2017-10-31
Applicant: General Electric Company
Inventor： Hariharan Ravishankar , Bharath Ram Sundar , Prasad Sudhakar , Rahul Venkataramani , Vivek Vaidya
Abstract: The present approach relates to feature ranking within deep neural networks in a multi-task and/or multi-label setting. Approaches are described to identify features that are task-specific as well as features that are shared across multiple tasks. In addition to facilitating interpretability, the selected subset of features can be used to make efficient models leading to better stability & regularization along with reduced compute and memory.
-
公开(公告)号：US20210233244A1
公开(公告)日：2021-07-29
申请号：US17227093
申请日：2021-04-09
Applicant: General Electric Company
Inventor： Harihan Ravishankar , Vivek Vaidya , Sheshadri Thiruvenkadam , Rahul Venkataramani , Prasad Sudhakar
Abstract: A method for image segmentation includes receiving an input image. The method further includes obtaining a deep learning model having a triad of predictors. Furthermore, the method includes processing the input image by a shape model in the triad of predictors to generate a segmented shape image. Moreover, the method includes presenting the segmented shape image via a display unit.
-
公开(公告)号：US10997724B2
公开(公告)日：2021-05-04
申请号：US16469373
申请日：2017-12-14
Applicant: General Electric Company
Inventor： Hariharan Ravishankar , Vivek Prabhakar Vaidya , Sheshadri Thiruvenkadam , Rahul Venkataramani , Prasad Sudhakar
Abstract: A method for image segmentation includes receiving an input image (102). The method further includes obtaining a deep learning model (104) having a triad of predictors (116, 118, 120). Furthermore, the method includes processing the input image by a shape model in the triad of predictors (116, 118, 120) to generate a segmented shape image (110). Moreover, the method includes presenting the segmented shape image via a display unit (128).
-
公开(公告)号：US10952705B2
公开(公告)日：2021-03-23
申请号：US15860771
申请日：2018-01-03
Applicant: GENERAL ELECTRIC COMPANY
Inventor： Prasad Sudhakar , Justin Daniel Lanning , Pavan Kumar Annangi , Michael Washburn
Abstract: A system and method for generating a patient-specific organ model is provided. The method may include receiving ultrasound images of an organ and probe position data corresponding with each of the ultrasound images. The method may include receiving identification of landmarks in the ultrasound images corresponding with pre-defined landmarks of a generic geometric organ model. The method may include automatically identifying surface points of the organ in the ultrasound images. The method may include generating a patient-specific ultrasound point cloud of the organ based on the received identification of the landmarks, the automatically identified surface points of the organ, and the probe position data. The method may include registering a point cloud of the generic geometric model to the patient-specific ultrasound point cloud to create a patient-specific organ model. The method may include presenting the patient-specific organ model at a display system.
-
公开(公告)号：US20190266448A1
公开(公告)日：2019-08-29
申请号：US16334091
申请日：2017-06-21
Applicant: General Electric Company
Inventor： Sheshadri Thiruvenkadam , Sohan Rashmi Ranjan , Vivek Prabhakar Vaidya , Hariharan Ravishankar , Rahul Venkataramani , Prasad Sudhakar
Abstract: A method for determining optimized deep learning architecture includes receiving a plurality of training images and a plurality of real time images corresponding to a subject. The method further includes receiving, by a medical practitioner, a plurality of learning parameters comprising a plurality of filter classes and a plurality of architecture parameters. The method also includes determining a deep learning model based on the plurality of learning parameters and the plurality of training images, wherein the deep learning model comprises a plurality of reusable filters. The method further includes determining a health condition of the subject based on the plurality of real time images and the deep learning model. The method also includes providing the health condition of the subject to the medical practitioner.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.017 seconds)
