Patents by Inventor Fabien Gaire

Fabien Gaire 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: 20240079138
    Abstract: Systems and methods relate to predicting disease progression by processing digital pathology images using neural networks. A digital pathology image that depicts a specimen stained with one or more stains is accessed. The specimen may have been collected from a subject. A set of patches are defined for the digital pathology image. Each patch of the set of patches depicts a portion of the digital pathology image. For each patch of the set of patches and using an attention-score neural network, an attention score is generated. The attention-score neural network may have been trained using a loss function that penalized attention-score variability across patches in training digital pathology images labeled to indicate no or low subsequent disease progression. Using a result-prediction neural network and the attention scores, a result is generated that represents a prediction of whether or an extent to which a disease of the subject will progress.
    Type: Application
    Filed: April 26, 2023
    Publication date: March 7, 2024
    Inventors: Yao NIE, Xiao LI, Trung Kien NGUYEN, Fabien GAIRE, Eldad KLAIMAN, Ido BEN-SHAUL, Jacob GILDENBLAT, Ofir Etz HADAR
  • Publication number: 20230143860
    Abstract: Systems and methods relate to processing digital pathology mages. More specifically, depictions of objects of a first class (e.g., lymphocytes) and depictions of objects of a second class (e.g., tumor cells) are detected. Locations of each biological object depiction are identified, which are used to generate multiple spatial-distribution metrics that characterize where depictions of objects of a first class are located relative to objects of a second class. The spatial-distribution metrics are used to generate a result corresponding to a predicted biological state of or a potential treatment of a subject. For example, the result may predict whether and/or an extent to which lymphocytes have infiltrated a tumor, whether checkpoint blockade therapy would be an effective treatment for the subject, and/or whether a subject is eligible for a clinical trial.
    Type: Application
    Filed: November 14, 2022
    Publication date: May 11, 2023
    Inventors: Xiao LI, Jian DAI, Fabien GAIRE
  • Patent number: 11315240
    Abstract: At least one embodiment relates to an image analysis system for tumor classification. The system is configured for receiving at least one digital image of a tissue sample; analyzing the at least one received image for identifying immune cells and tumor cells in the at least one received image; for each of the identified tumor cells, determining the distance of the tumor cell to the nearest immune cell; computing a proximity measure as a function of the determined distances; in dependence on the proximity measure, classifying the identified tumor cells into tumor cells of an inflammatory tumor or as tumor cells of a non-inflammatory tumor; and storing the classification result on a storage medium and/or displaying the classification result on a display device.
    Type: Grant
    Filed: May 18, 2017
    Date of Patent: April 26, 2022
    Assignee: HOFFMANN-LA ROCHE INC.
    Inventors: Fabien Gaire, Eldad Klaiman, Konstanty Korski
  • Publication number: 20210343009
    Abstract: The invention relates to an image analysis method for determining the biomedical state of a tissue sample. The method comprises: receiving a digital image of a tissue sample; identifying the number and location of A-type cells and B-type cells; obtaining an observed relative distribution; obtaining a reference relative distribution of expected distances between reference A-type cells and reference B-type cells; computing a proximity score as a difference of the reference relative distribution and the observed relative distribution; computing a combined score comprising the proximity score and the density of the A-type cells and/or the density of the B-type cells; using the combined score for determining the biomedical state of the tissue sample and/or outputting the combined score.
    Type: Application
    Filed: October 23, 2019
    Publication date: November 4, 2021
    Applicant: HOFFMANN-LA ROCHE INC.
    Inventors: Fabien GAIRE, Karin Emilia ANDERSSON, Franziska BRAUN, Konstanty KORSKI, Fabian SCHMICH
  • Patent number: 11017533
    Abstract: The system is configured to receive at least one digital image of a tissue sample of a patient; analyze the at least one received image for identifying tumor cells in a region of the at least one received image; analyze the at least one received image for identifying FAP+ areas in the region, each FAP+ area being a pixel blob representing one or more cells express the fibroblast activation protein—“FAP”; analyze the at least one received image for identifying distances between the identified tumor cells and their respective nearest FAP+ area; computing a proximity measure as a function of the identified distances; process the proximity measure by a classifier for generating a classification result, the classification result indicating if the tumor of the patient can be treated by a drug or drug-component that binds to FAP; and output the classification result.
    Type: Grant
    Filed: November 2, 2017
    Date of Patent: May 25, 2021
    Assignee: HOFFMANN-LA ROCHE INC.
    Inventors: Fabien Gaire, Oliver Grimm, Hadassah Sumum Sade, Suzana Vega Harring
  • Publication number: 20190287240
    Abstract: At least one embodiment relates to an image analysis system for tumor classification. The system is configured for receiving at least one digital image of a tissue sample; analyzing the at least one received image for identifying immune cells and tumor cells in the at least one received image; for each of the identified tumor cells, determining the distance of the tumor cell to the nearest immune cell; computing a proximity measure as a function of the determined distances; in dependence on the proximity measure, classifying the identified tumor cells into tumor cells of an inflammatory tumor or as tumor cells of a non-inflammatory tumor; and storing the classification result on a storage medium and/or displaying the classification result on a display device.
    Type: Application
    Filed: May 18, 2017
    Publication date: September 19, 2019
    Applicant: HOFFMANN-LA ROCHE INC.
    Inventors: Fabien GAIRE, Eldad KLAIMAN, Konstanty KORSKI
  • Publication number: 20190287249
    Abstract: The system is configured to receive at least one digital image of a tissue sample of a patient; analyze the at least one received image for identifying tumor cells in a region of the at least one received image; analyze the at least one received image for identifying FAP+ areas in the region, each FAP+ area being a pixel blob representing one or more cells express the fibroblast activation protein—“FAP”; analyze the at least one received image for identifying distances between the identified tumor cells and their respective nearest FAP+ area; computing a proximity measure as a function of the identified distances; process the proximity measure by a classifier for generating a classification result, the classification result indicating if the tumor of the patient can be treated by a drug or drug-component that binds to FAP; and output the classification result.
    Type: Application
    Filed: November 2, 2017
    Publication date: September 19, 2019
    Applicant: HOFFMANN-LA ROCHE INC.
    Inventors: Fabien GAIRE, Oliver GRIMM, Hadassah Sumum SADE, Suzana VEGA HARRING
  • Publication number: 20160130666
    Abstract: The present invention provides compositions and methods for simultaneously detecting mutational status and gene copy number. In particular, the present invention provides simultaneous measurement of gene copy number and detection of the L858R and Exon 19 del mutations in a tissue sample.
    Type: Application
    Filed: January 17, 2016
    Publication date: May 12, 2016
    Inventors: SHALINI SINGH, Hiro NITTA, Fabien GAIRE, Edmundo David DEL VALLE
  • Patent number: 9127028
    Abstract: Embodiments of substrates and processes for chromogenic detection, and in particular pyrazolyl dihydrogen phosphate compounds, are disclosed.
    Type: Grant
    Filed: August 12, 2011
    Date of Patent: September 8, 2015
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Brian Daniel Kelly, Christopher Bieniarz, Hiro Nitta, Fabien Gaire
  • Publication number: 20130273540
    Abstract: The present invention provides a method and kit for detection of two or more target molecules in a single tissue sample, such as for gene and protein dual detection in a single tissue sample. Methods comprise treating a tissue sample with a first binding moiety that specifically binds a first target molecule. Methods further comprise treating the tissue sample with a solution containing a soluble electron-rich aromatic compound prior to or concomitantly with contacting the tissue sample with a hapten-labeled binding moiety and detecting a second target molecule. In one example, the first target molecule is a protein and the second is a nucleic acid sequence, the first target molecule being detected by immunohistochemistry and the second by in situ hybridization. The disclosed method reduces background due to non-specific binding of the hapten-labeled specific binding moiety to an insoluble electron rich compound deposited near the first target molecule.
    Type: Application
    Filed: June 7, 2013
    Publication date: October 17, 2013
    Inventors: Richard Gniewek, Michael Farrell, Hiro Nitta, Megan Lehrkamp, Jerome II W. Kosmeder, Christopher A. Bieniarz, Brian Daniel Kelly, Thomas Grogan, Fabien Gaire, Mary Padilla
  • Patent number: 8481270
    Abstract: The present invention provides a method and kit for detection of two or more target molecules in a single tissue sample, such as for gene and protein dual detection in a single tissue sample. Methods comprise treating a tissue sample with a first binding moiety that specifically binds a first target molecule. Methods further comprise treating the tissue sample with a solution containing a soluble electron-rich aromatic compound prior to or concomitantly with contacting the tissue sample with a hapten-labeled binding moiety and detecting a second target molecule. In one example, the first target molecule is a protein and the second is a nucleic acid sequence, the first target molecule being detected by immunohistochemistry and the second by in situ hybridization. The disclosed method reduces background due to non-specific binding of the hapten-labeled specific binding moiety to an insoluble electron rich compound deposited near the first target molecule.
    Type: Grant
    Filed: August 21, 2009
    Date of Patent: July 9, 2013
    Assignee: Ventana Medical Systems, Inc.
    Inventors: Richard Gniewek, Michael Farrell, Hiroaki Nitta, Megan Lehrkamp, Jerome Kosmeder, Brian Daniel Kelly, Thomas Grogan, Fabien Gaire, Mary Padilla, Christopher Bieniarz
  • Publication number: 20130115593
    Abstract: Embodiments of substrates and processes for chromogenic detection, and in particular pyrazolyl dihydrogen phosphate compounds, are disclosed.
    Type: Application
    Filed: August 12, 2011
    Publication date: May 9, 2013
    Applicant: Ventana Medical Systems, Inc.
    Inventors: Brian Daniel Kelly, Christopher Bieniarz, Hiro Nitta, Fabien Gaire
  • Patent number: 8329421
    Abstract: Disclosed herein are antigen-binding molecules, such as antibodies, that specifically recognize a portion of the EGFR C-terminal (intracellular) regulatory domain that interacts with one or more regulatory molecules (such as Suppressor of Cytokine Signaling (“SOCS”) proteins). In certain normal or neoplastic cells and/or tissues, this region is inaccessible to the disclosed antigen-binding molecules. Thus, such antigen-binding molecules are useful at least to interrogate the regulated state of EGFR, predict the response of a cancer patient to EGFR inhibitor therapies, and/or predict the aggressiveness of neoplasms.
    Type: Grant
    Filed: July 11, 2008
    Date of Patent: December 11, 2012
    Assignee: Ventana Medical Systems, Inc.
    Inventors: William C. Powell, Linda Willoughby Kivi, Patrick C. Roche, Gary Gooch, Fabien Gaire
  • Publication number: 20120264127
    Abstract: The present invention provides compositions and methods for simultaneously detecting mutational status and gene copy number. In particular, the present invention provides simultaneous measurement of gene copy number and detection of the L858R and Exon 19 del mutations in a tissue sample.
    Type: Application
    Filed: December 30, 2010
    Publication date: October 18, 2012
    Inventors: Shalini Singh, Hiro Nitta, Fabien Gaire, Edmundo David Del Valle
  • Publication number: 20120141472
    Abstract: Disclosed herein are methods of predicting prognosis of a neoplastic disease (such as lung cancer, for example NSCLC), including determining the IGF1R gene copy number in a biological sample from a patient having a neoplastic disease; wherein an increase in IGF1R copy number predicts a good prognosis of the neoplastic disease in the patient. Also disclosed herein are methods of scoring copy number of a gene of interest in a biological sample. The method includes identifying individual cells in the sample having highest number of signals for the gene of interest detected by in situ hybridization, counting the number of signals for the gene of interest in the identified individual cells and determining an average number of signals per cell.
    Type: Application
    Filed: May 28, 2010
    Publication date: June 7, 2012
    Inventors: Shalini Singh, Fabien Gaire, James Ranger-Moore
  • Publication number: 20110136130
    Abstract: The present invention provides a method and kit for detection of two or more target molecules in a single tissue sample, such as for gene and protein dual detection in a single tissue sample. Methods comprise treating a tissue sample with a first binding moiety that specifically binds a first target molecule. Methods further comprise treating the tissue sample with a solution containing a soluble electron-rich aromatic compound prior to or concomitantly with contacting the tissue sample with a hapten-labeled binding moiety and detecting a second target molecule. In one example, the first target molecule is a protein and the second is a nucleic acid sequence, the first target molecule being detected by immunohistochemistry and the second by in situ hybridization. The disclosed method reduces background due to non-specific binding of the hapten-labeled specific binding moiety to an insoluble electron rich compound deposited near the first target molecule.
    Type: Application
    Filed: August 21, 2009
    Publication date: June 9, 2011
    Inventors: Richard Gniewek, Michael Farrell, Hiroaki Nitta, Megan Lehrkamp, Jerome Kosmeder, Brian Daniel Kelly, Fabien Gaire, Mary Padilla, Thomas Grogan, Christopher Bieniarz
  • Publication number: 20100285025
    Abstract: Disclosed herein are antigen-binding molecules, such as antibodies, that specifically recognize a portion of the EGFR C-terminal (intracellular) regulatory domain that interacts with one or more regulatory molecules (such as Suppressor of Cytokine Signaling (“SOCS”) proteins). In certain normal or neoplastic cells and/or tissues, this region is inaccessible to the disclosed antigen-binding molecules. Thus, such antigen-binding molecules are useful at least to interrogate the regulated state of EGFR, predict the response of a cancer patient to EGFR inhibitor therapies, and/or predict the aggressiveness of neoplasms.
    Type: Application
    Filed: July 11, 2008
    Publication date: November 11, 2010
    Inventors: William C. Powell, Linda Willoughby Kivi, Patrick C. Roche, Gary Gooch, Fabien Gaire
  • Publication number: 20090017050
    Abstract: Disclosed herein are antigen-binding molecules, such as antibodies, that specifically recognize a portion of the EGFR C-terminal (intracellular) regulatory domain that interacts with one or more regulatory molecules (such as Suppressor of Cytokine Signaling (“SOCS”) proteins). In certain normal or neoplastic cells and/or tissues, this region is inaccessible to the disclosed antigen-binding molecules. Thus, such antigen-binding molecules are useful at least to interrogate the regulated state of EGFR, predict the response of a cancer patient to EGFR inhibitor therapies, and/or predict the aggressiveness of neoplasms.
    Type: Application
    Filed: July 11, 2008
    Publication date: January 15, 2009
    Inventors: William C. Powell, Linda Willoughby Kivi, Patrick C. Roche, Gary Gooch, Fabien Gaire