Patents by Inventor Roshni Bhagalia

Roshni Bhagalia has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20220172825
    Abstract: Medical scanner application platforms and associated components (e.g., using a computerized tool) is enabled. For example, a system, can comprise: a processor, and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising: determining, based on package schema data representative of a package schema of an application received via a network, one or more attributes of the application, based on the one or more attributes of the application, determining one or more constraints of the application applicable to a medical scanner communicatively coupled to the system via an agent of the medical scanner, and storing the application in an application database accessible to the agent of the medical scanner.
    Type: Application
    Filed: November 22, 2021
    Publication date: June 2, 2022
    Inventors: Roshni Bhagalia, David Erik Chevalier, Fausto Espinal, Bradley J. Gabrielse, Kenji Okabe, David Alexander Polyak, Nikhil Jones Tomy
  • Publication number: 20220164230
    Abstract: Intelligent, distributed medical software management (e.g., using a computerized tool) is enabled. A system can comprise a processor, and a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising determining requirement information representative of one or more requirements of a medical application off a group of medical applications, wherein the medical application is associated with a medical device, based on the requirement information, allocating elements of a cluster employable to host and run the medical application in a medical application container, wherein the elements of the cluster are determined to satisfy the requirement information, and in response to allocating the elements of the cluster, hosting the medical application in the medical application container, wherein hosting the medical application comprises communicatively coupling the medical application to the medical device.
    Type: Application
    Filed: October 21, 2021
    Publication date: May 26, 2022
    Inventors: Michael Braunstein, Aparna Nittala, Fausto Espinal, Roshni Bhagalia, Murali Kumaran Kariathungal
  • Patent number: 10573028
    Abstract: As set forth herein low energy signal data and high energy signal data can be acquired. A first material decomposed (MD) image of a first material basis and a second material decomposed (MD) image of a second material basis can be obtained using the low energy signal data and the high energy signal data. At least one of the first or second MD image can be input into a guide filter for output of at least one noise reduced and cross-contamination reduced image. A computed tomography (CT) imaging system can be provided that includes an X-ray source and a detector having a plurality of detector elements that detect X-ray beams emitted from the X-ray source. Low energy signal data and high energy signal data can be acquired using the detector.
    Type: Grant
    Filed: July 15, 2019
    Date of Patent: February 25, 2020
    Assignee: GENERAL ELECTRIC COMPANY
    Inventors: Roshni Bhagalia, Debashish Pal
  • Publication number: 20190340792
    Abstract: As set forth herein low energy signal data and high energy signal data can be acquired. A first material decomposed (MD) image of a first material basis and a second material decomposed (MD) image of a second material basis can be obtained using the low energy signal data and the high energy signal data. At least one of the first or second MD image can be input into a guide filter for output of at least one noise reduced and cross-contamination reduced image. A computed tomography (CT) imaging system can be provided that includes an X-ray source and a detector having a plurality of detector elements that detect X-ray beams emitted from the X-ray source. Low energy signal data and high energy signal data can be acquired using the detector.
    Type: Application
    Filed: July 15, 2019
    Publication date: November 7, 2019
    Inventors: Roshni Bhagalia, Debashish Pal
  • Patent number: 10453200
    Abstract: Embodiments described herein provide a hybrid technique which incorporates learned pulmonary nodule features in a model based energy minimization segmentation using graph cuts. Features are extracted from training samples using a convolutional neural network, and the segmentation cost function is augmented via the deep learned energy. The system and method improves segmentation performance and more robust initialization.
    Type: Grant
    Filed: December 2, 2016
    Date of Patent: October 22, 2019
    Assignee: GENERAL ELECTRIC COMPANY
    Inventors: Suvadip Mukherjee, Roshni Bhagalia, Xiaojie Huang
  • Patent number: 10403006
    Abstract: As set forth herein low energy signal data and high energy signal data can be acquired. A first material decomposed (MD) image of a first material basis and a second material decomposed (MD) image of a second material basis can be obtained using the low energy signal data and the high energy signal data. At least one of the first or second MD image can be input into a guide filter for output of at least one noise reduced and cross-contamination reduced image. A computed tomography (CT) imaging system can be provided that includes an X-ray source and a detector having a plurality of detector elements that detect X-ray beams emitted from the X-ray source. Low energy signal data and high energy signal data can be acquired using the detector.
    Type: Grant
    Filed: August 26, 2016
    Date of Patent: September 3, 2019
    Assignee: GENERAL ELECTRIC COMPANY
    Inventors: Roshni Bhagalia, Debashish Pal
  • Publication number: 20180122082
    Abstract: Embodiments described herein provide a hybrid technique which incorporates learned pulmonary nodule features in a model based energy minimization segmentation using graph cuts. Features are extracted from training samples using a convolutional neural network, and the segmentation cost function is augmented via the deep learned energy. The system and method improves segmentation performance and more robust initialization.
    Type: Application
    Filed: December 2, 2016
    Publication date: May 3, 2018
    Inventors: Suvadip Mukherjee, Roshni Bhagalia, Xiaojie Huang
  • Publication number: 20180061088
    Abstract: As set forth herein low energy signal data and high energy signal data can be acquired. A first material decomposed (MD) image of a first material basis and a second material decomposed (MD) image of a second material basis can be obtained using the low energy signal data and the high energy signal data. At least one of the first or second MD image can be input into a guide filter for output of at least one noise reduced and cross-contamination reduced image. A computed tomography (CT) imaging system can be provided that includes an X-ray source and a detector having a plurality of detector elements that detect X-ray beams emitted from the X-ray source. Low energy signal data and high energy signal data can be acquired using the detector.
    Type: Application
    Filed: August 26, 2016
    Publication date: March 1, 2018
    Applicant: GENERAL ELECTRIC COMPANY
    Inventors: Roshni BHAGALIA, Debashish PAL
  • Patent number: 9852501
    Abstract: A method of creating a diagnostic evaluation for usual interstitial pneumonia is provided, including obtaining a first plurality of series of HRCT lung slices indicating the presence of UIP, obtaining an identification of UIP and non-UIP voxels, extracting textural and localization features from the UIP and non-UIP voxels, selecting features that are more accurate in differentiating UIP voxels from non-UIP voxels than other features are, eliminating features highly correlated with a more accurate feature, and constructing a predictive model by performing a second classifier to provide a probability that a voxel signifies the presence of UIP. Also provided is a method of identifying UIP in a subject's lung by applying a diagnostic evaluation for UIP that was created with the foregoing method.
    Type: Grant
    Filed: May 23, 2016
    Date of Patent: December 26, 2017
    Assignee: General Electric Company
    Inventors: Mirabela Rusu, Roshni Bhagalia
  • Publication number: 20170337676
    Abstract: A method of creating a diagnostic evaluation for usual interstitial pneumonia is provided, including obtaining a first plurality of series of HRCT lung slices indicating the presence of UIP, obtaining an identification of UIP and non-UIP voxels, extracting textural and localization features from the UIP and non-UIP voxels, selecting features that are more accurate in differentiating UIP voxels from non-UIP voxels than other features are, eliminating features highly correlated with a more accurate feature, and constructing a predictive model by performing a second classifier to provide a probability that a voxel signifies the presence of UIP. Also provided is a method of identifying UIP in a subject's lung by applying a diagnostic evaluation for UIP that was created with the foregoing method.
    Type: Application
    Filed: May 23, 2016
    Publication date: November 23, 2017
    Applicant: GENERAL ELECTRIC COMPANY
    Inventors: Mirabela RUSU, Roshni BHAGALIA
  • Publication number: 20150086101
    Abstract: In some embodiments, a method for localizing organs in anatomical imaging may include: performing an anterior-posterior view scan and a lateral view scan to create an anterior-posterior view scan image and a lateral view scan image; creating a joint anatomical model based on the anterior-posterior scan image and the lateral view scan image; and refining the joint anatomical model.
    Type: Application
    Filed: September 25, 2014
    Publication date: March 26, 2015
    Inventors: Roshni Bhagalia, Qi Song, Albert Amos Montillo
  • Patent number: 8135187
    Abstract: Techniques for removing image autoflourescence from fluorescently stained biological images are provided herein. The techniques utilize non-negative matrix factorization that may constrain mixing coefficients to be non-negative. The probability of convergence to local minima is reduced by using smoothness constraints. The non-negative matrix factorization algorithm provides the advantage of removing both dark current and autofluorescence.
    Type: Grant
    Filed: March 26, 2008
    Date of Patent: March 13, 2012
    Assignee: General Electric Company
    Inventors: Ali Can, Michael John Gerdes, Musodiq Olatayo Bello, Xiaodong Tao, Francis Edward Pavan-Woolfe, Roshni Bhagalia
  • Publication number: 20090245611
    Abstract: Techniques for removing image autoflourescence from fluorescently stained biological images are provided herein. The techniques utilize non-negative matrix factorization that may constrain mixing coefficients to be non-negative. The probability of convergence to local minima is reduced by using smoothness constraints. The non-negative matrix factorization algorithm provides the advantage of removing both dark current and autofluorescence.
    Type: Application
    Filed: March 26, 2008
    Publication date: October 1, 2009
    Applicant: General Electric Company
    Inventors: Ali Can, Michael John Gerdes, Musodiq Olatayo Bello, Xiaodong Tao, Francis Edward Pavan-Woolfe, Roshni Bhagalia