Patents by Inventor Belma Dogdas

Belma Dogdas 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).

  • Patent number: 11107573
    Abstract: Systems and methods are disclosed for generating a specialized machine learning model by receiving a generalized machine learning model generated by processing a plurality of first training images to predict at least one cancer characteristic, receiving a plurality of second training images, the first training images and the second training images include images of tissue specimens and/or images algorithmically generated to replicate tissue specimens, receiving a plurality of target specialized attributes related to a respective second training image of the plurality of second training images, generating a specialized machine learning model by modifying the generalized machine learning model based on the plurality of second training images and the target specialized attributes, receiving a target image corresponding to a target specimen, applying the specialized machine learning model to the target image to determine at least one characteristic of the target image, and outputting the characteristic of the tar
    Type: Grant
    Filed: December 18, 2020
    Date of Patent: August 31, 2021
    Assignee: PAIGE.AI, INC.
    Inventors: Belma Dogdas, Christopher Kanan, Thomas Fuchs, Leo Grady
  • Publication number: 20210233236
    Abstract: Systems and methods are disclosed for receiving digital images of a pathology specimen from a patient, the pathology specimen comprising tumor tissue, the one or more digital images being associated with data about a plurality of biomarkers in the tumor tissue and data about a surrounding invasive margin around the tumor tissue; identifying the tumor tissue and the surrounding invasive margin region to be analyzed for each of the one or more digital images; generating, using a machine learning model on the one or more digital images, at least one inference of a presence of the plurality of biomarkers in the tumor tissue and the surrounding invasive margin region; determining a spatial relationship of each of the plurality of biomarkers identified in the tumor tissue and the surrounding invasive margin region to themselves and to other cell types; and determining a prediction for a treatment outcome and/or at least one treatment recommendation for the patient.
    Type: Application
    Filed: January 27, 2021
    Publication date: July 29, 2021
    Inventors: Belma DOGDAS, Christopher KANAN, Thomas FUCHS, Leo GRADY
  • Publication number: 20210210195
    Abstract: Systems and methods are disclosed for generating a specialized machine learning model by receiving a generalized machine learning model generated by processing a plurality of first training images to predict at least one cancer characteristic, receiving a plurality of second training images, the first training images and the second training images include images of tissue specimens and/or images algorithmically generated to replicate tissue specimens, receiving a plurality of target specialized attributes related to a respective second training image of the plurality of second training images, generating a specialized machine learning model by modifying the generalized machine learning model based on the plurality of second training images and the target specialized attributes, receiving a target image corresponding to a target specimen, applying the specialized machine learning model to the target image to determine at least one characteristic of the target image, and outputting the characteristic of the tar
    Type: Application
    Filed: December 18, 2020
    Publication date: July 8, 2021
    Inventors: Belma Dogdas, Christopher Kanan, Thomas Fuchs, Leo Grady
  • Publication number: 20210209753
    Abstract: Systems and methods are disclosed for receiving a digital image corresponding to a target specimen associated with a pathology category, wherein the digital image is an image of tissue specimen, determining a detection machine learning model, the detection machine learning model being generated by processing a plurality of training images to output a cancer qualification and further a cancer quantification if the cancer qualification is an confirmed cancer qualification, providing the digital image as an input to the detection machine learning model, receiving one of a pathological complete response (pCR) cancer qualification or a confirmed cancer quantification as an output from the detection machine learning model, and outputting the pCR cancer qualification or the confirmed cancer quantification.
    Type: Application
    Filed: December 16, 2020
    Publication date: July 8, 2021
    Inventors: Belma DOGDAS, Christopher KANAN, Thomas FUCHS, Leo GRADY, Kenan TURNACIOGLU
  • Patent number: 11030750
    Abstract: Approaches for the automatic segmentation of magnetic resonance (MR) images. Machine learning models segment images to identify image features in consecutive frames at different levels of resolution. A neural network block is applied to groups of MR images to produce primary feature maps at two or more levels of resolution. The images in a given group of MR images may correspond to a cycle and have a temporal order. A second RNN block is applied to the primary feature maps to produce two or more output tensors at corresponding levels of resolution. A segmentation block is applied to the two or more output tensors to produce a probability map for the MR images. The first neural network block may be a convolutional neural network (CNN) block. The second neural network block may be a convolutional long short-term (LSTM) block.
    Type: Grant
    Filed: May 30, 2019
    Date of Patent: June 8, 2021
    Assignees: Merck Sharp & Dohme Corp., MSD International GmbH
    Inventors: Antong Chen, Dongqing Zhang, Ilknur Icke, Belma Dogdas, Sarayu Parimal
  • Patent number: 11010591
    Abstract: A protein crystallization trial is automatically analyzed by capturing images of the protein drops in the trial. A machine-learned model, such as a neural network, is applied to classify the images. The model generates a predicted classification from among a set of possible classifications which includes one or more crystal type classifications and one or more non-crystal type classifications. Users may be notified automatically of newly identified crystals (e.g., drops that are classified as a crystal type). The notification may include a link to a user interface that includes results of the trial.
    Type: Grant
    Filed: February 1, 2019
    Date of Patent: May 18, 2021
    Assignee: Merck Sharp & Dohme Corp.
    Inventors: Soheil Ghafurian, Ilknur Icke, Charles A. Lesburg, Belma Dogdas
  • Publication number: 20200250397
    Abstract: A protein crystallization trial is automatically analyzed by capturing images of the protein drops in the trial. A machine-learned model, such as a neural network, is applied to classify the images. The model generates a predicted classification from among a set of possible classifications which includes one or more crystal type classifications and one or more non-crystal type classifications. Users may be notified automatically of newly identified crystals (e.g., drops that are classified as a crystal type). The notification may include a link to a user interface that includes results of the trial.
    Type: Application
    Filed: February 1, 2019
    Publication date: August 6, 2020
    Inventors: Soheil Ghafurian, Ilknur Icke, Charles A. Lesburg, Belma Dogdas
  • Publication number: 20200111214
    Abstract: Approaches for the automatic segmentation of magnetic resonance (MR) images. Machine learning models segment images to identify image features in consecutive frames at different levels of resolution. A neural network block is applied to groups of MR images to produce primary feature maps at two or more levels of resolution. The images in a given group of MR images may correspond to a cycle and have a temporal order. A second RNN block is applied to the primary feature maps to produce two or more output tensors at corresponding levels of resolution. A segmentation block is applied to the two or more output tensors to produce a probability map for the MR images. The first neural network block may be a convolutional neural network (CNN) block. The second neural network block may be a convolutional long short-term (LSTM) block.
    Type: Application
    Filed: May 30, 2019
    Publication date: April 9, 2020
    Inventors: Antong Chen, Dongqing Zhang, Ilknur Icke, Belma Dogdas, Sarayu Parimal
  • Publication number: 20190219585
    Abstract: The present disclosure describes an IHC assay for detecting and quantifying spatially proximal pairs of PD-1-expressing cells (PD-1+ cells) and PD-Ligand-expressing cells (PD-L+ cells) in tumor tissue, and the use of the assay to generate proximity biomarkers that are predictive of which cancer patients are most likely to benefit from treatment with a PD-1 antagonist. The disclosure also provides methods for testing tumor samples for the proximity biomarkers, as well as methods for treating subjects with a PD-1 antagonist based on the test results.
    Type: Application
    Filed: January 17, 2019
    Publication date: July 18, 2019
    Applicant: Merck Sharp & Dohme Corp.
    Inventors: Robert H. Pierce, Jennifer H. Yearley, Scott P. Turner, Belma Dogdas, Ansuman Bagchi
  • Patent number: 10241115
    Abstract: The present disclosure describes an IHC assay for detecting and quantifying spatially proximal pairs of PD-1-expressing cells (PD-1+ cells) and PD-Ligand-expressing cells (PD-L+ cells) in tumor tissue, and the use of the assay to generate proximity biomarkers that are predictive of which cancer patients are most likely to benefit from treatment with a PD-1 antagonist. The disclosure also provides methods for testing tumor samples for the proximity biomarkers, as well as methods for treating subjects with a PD-1 antagonist based on the test results.
    Type: Grant
    Filed: December 8, 2014
    Date of Patent: March 26, 2019
    Assignee: Merck Sharp & Dohme Corp.
    Inventors: Robert H. Pierce, Jennifer H. Yearley, Scott P. Turner, Belma Dogdas, Ansuman Bagchi
  • Publication number: 20160305947
    Abstract: The present disclosure describes an IHC assay for detecting and quantifying spatially proximal pairs of PD-1-expressing cells (PD-1+ cells) and PD-Ligand-expressing cells (PD-L+ cells) in tumor tissue, and the use of the assay to generate proximity biomarkers that are predictive of which cancer patients are most likely to benefit from treatment with a PD-1 antagonist. The disclosure also provides methods for testing tumor samples for the proximity biomarkers, as well as methods for treating subjects with a PD-1 antagonist based on the test results.
    Type: Application
    Filed: December 8, 2014
    Publication date: October 20, 2016
    Applicant: Merck Sharp & Dohme Corp.
    Inventors: Robert H. Pierce, Jennifer H. Yearley, Scott P. Turner, Belma Dogdas, Ansuman Bagchi