Patents by Inventor KERRY HALUPKA
KERRY HALUPKA 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: 11847764Abstract: A generative adversarial network including a generator portion and a discriminator portion is constructed. The network is configured such that the network operates to enhance intensity images, wherein an intensity image is obtained by illuminating an object with an energy pulse and measuring the return strength of the energy pulse, and wherein a pixel of the intensity image corresponds to the return strength. As a part of the configuring, a loss function of the generative adversarial network is minimized, the loss function comprising a mean square error loss measurement of a noisy intensity image relative to a mean square error loss measurement of a corresponding clean intensity image. An enhanced intensity image is generated by applying the minimized loss function of the network to an original intensity image, the applying improving an image quality measurement of the enhanced intensity image relative to the original intensity image.Type: GrantFiled: December 21, 2020Date of Patent: December 19, 2023Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Kerry Halupka, Bhavna Josephine Antony, Suman Sedai, Rahil Garnavi, Hiroshi Ishikawa
-
Patent number: 11712301Abstract: A method of generating a 4D model includes capturing imagery of a catheter and a vessel as the catheter is directed through the vessel to a location of interest, wherein the catheter is disposed on a guidewire, constructing a 3D time varying reference curve describing a trajectory of the guidewire, and constructing a time varying 3D model of the artery using the reference curve.Type: GrantFiled: April 8, 2019Date of Patent: August 1, 2023Assignee: International Business Machines CorporationInventors: Julia S. Baldauf, Darcy J. Beurle, Matthew Downton, Kerry Halupka, Stephen M. Moore, Christine Schieber
-
Patent number: 11357573Abstract: A technique relates to coronary reconstruction. Angiogram data associated with cardiac catheterization of an artery for a subject is received, where a contrasting agent is used during the cardiac catheterization. Frames that match from the angiogram data are selected, the frames being from different views. Two-dimensional ordered point clouds for the frames are formed. A three-dimensional ordered point cloud of a reconstructed coronary artery for the subject from the two-dimensional ordered point clouds of the frames is formed. Observed contrast motion caused by the contrasting agent onto the reconstructed coronary artery is mapped, the reconstructed coronary artery thereby providing a three-dimensional model of the artery of the subject during the cardiac catheterization.Type: GrantFiled: April 25, 2019Date of Patent: June 14, 2022Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Andrew Rawlinson, Kerry Halupka, Stephen Michael Moore, Sergiy Zhuk
-
Patent number: 11026583Abstract: A catheter including a monitoring body and a pair of markers disposed on the monitoring body, each marker of the pair of markers encircling the monitoring body, wherein the pair of markers are configured to indicate, through their appearance from a given point of view, an orientation of the monitoring body.Type: GrantFiled: April 26, 2017Date of Patent: June 8, 2021Assignee: International Business Machines CorporationInventors: Julia S. Baldauf, Darcy J. Beurle, Matthew Downton, Kerry Halupka, Stephen M. Moore, Christine Schieber
-
Patent number: 11024013Abstract: A generative adversarial network including a generator portion and a discriminator portion is constructed. The network is configured such that the network operates to enhance intensity images, wherein an intensity image is obtained by illuminating an object with an energy pulse and measuring the return strength of the energy pulse, and wherein a pixel of the intensity image corresponds to the return strength. As a part of the configuring, a loss function of the generative adversarial network is minimized, the loss function comprising a mean square error loss measurement of a noisy intensity image relative to a mean square error loss measurement of a corresponding clean intensity image. An enhanced intensity image is generated by applying the minimized loss function of the network to an original intensity image, the applying improving an image quality measurement of the enhanced intensity image relative to the original intensity image.Type: GrantFiled: March 8, 2019Date of Patent: June 1, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Kerry Halupka, Bhavna Josephine Antony, Suman Sedai, Rahil Garnavi, Hiroshi Ishikawa
-
Publication number: 20210150675Abstract: A generative adversarial network including a generator portion and a discriminator portion is constructed. The network is configured such that the network operates to enhance intensity images, wherein an intensity image is obtained by illuminating an object with an energy pulse and measuring the return strength of the energy pulse, and wherein a pixel of the intensity image corresponds to the return strength. As a part of the configuring, a loss function of the generative adversarial network is minimized, the loss function comprising a mean square error loss measurement of a noisy intensity image relative to a mean square error loss measurement of a corresponding clean intensity image. An enhanced intensity image is generated by applying the minimized loss function of the network to an original intensity image, the applying improving an image quality measurement of the enhanced intensity image relative to the original intensity image.Type: ApplicationFiled: December 21, 2020Publication date: May 20, 2021Applicants: International Business Machines Corporation, New York UniversityInventors: Kerry Halupka, Bhavna Josephine Antony, Suman Sedai, Rahil Gamavi, Hiroshi Ishikawa
-
Patent number: 10832074Abstract: From a first image using a model, a first uncertainty map is generated. An uncertainty level of a location in the first uncertainty map corresponds to a detection of a known structure in a portion of the first image. A first weighted image corresponding to the first uncertainty map is generated, the generating including assigning a first weight to a pixel of the first image, the first weight corresponding to the uncertainty level of a location in the first uncertainty map corresponding to the pixel. From a second image using a model, a second uncertainty map is generated. A second weighted image corresponding to the second uncertainty map is generated. The first image and the second image are combined to form a composite image, each image participating in the composite image according to the corresponding weighted image.Type: GrantFiled: March 8, 2019Date of Patent: November 10, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Suman Sedai, Bhavna Josephine Antony, Kerry Halupka, Dwarikanath Mahapatra, Rahil Garnavi
-
Publication number: 20200337773Abstract: A technique relates to coronary reconstruction. Angiogram data associated with cardiac catheterization of an artery for a subject is received, where a contrasting agent is used during the cardiac catheterization. Frames that match from the angiogram data are selected, the frames being from different views. Two-dimensional ordered point clouds for the frames are formed. A three-dimensional ordered point cloud of a reconstructed coronary artery for the subject from the two-dimensional ordered point clouds of the frames is formed. Observed contrast motion caused by the contrasting agent onto the reconstructed coronary artery is mapped, the reconstructed coronary artery thereby providing a three-dimensional model of the artery of the subject during the cardiac catheterization.Type: ApplicationFiled: April 25, 2019Publication date: October 29, 2020Inventors: Andrew Rawlinson, Kerry Halupka, Stephen Michael Moore, Sergiy Zhuk
-
Publication number: 20200286208Abstract: A generative adversarial network including a generator portion and a discriminator portion is constructed. The network is configured such that the network operates to enhance intensity images, wherein an intensity image is obtained by illuminating an object with an energy pulse and measuring the return strength of the energy pulse, and wherein a pixel of the intensity image corresponds to the return strength. As a part of the configuring, a loss function of the generative adversarial network is minimized, the loss function comprising a mean square error loss measurement of a noisy intensity image relative to a mean square error loss measurement of a corresponding clean intensity image. An enhanced intensity image is generated by applying the minimized loss function of the network to an original intensity image, the applying improving an image quality measurement of the enhanced intensity image relative to the original intensity image.Type: ApplicationFiled: March 8, 2019Publication date: September 10, 2020Applicants: International Business Machines Corporation, New York UniversityInventors: Kerry Halupka, Bhavna Josephine Antony, Suman Sedai, Rahil Garnavi, Hiroshi Ishikawa
-
Publication number: 20200285880Abstract: From a first image using a model, a first uncertainty map is generated. An uncertainty level of a location in the first uncertainty map corresponds to a detection of a known structure in a portion of the first image. A first weighted image corresponding to the first uncertainty map is generated, the generating including assigning a first weight to a pixel of the first image, the first weight corresponding to the uncertainty level of a location in the first uncertainty map corresponding to the pixel. From a second image using a model, a second uncertainty map is generated. A second weighted image corresponding to the second uncertainty map is generated. The first image and the second image are combined to form a composite image, each image participating in the composite image according to the corresponding weighted image.Type: ApplicationFiled: March 8, 2019Publication date: September 10, 2020Applicant: International Business Machines CorporationInventors: Suman Sedai, Bhavna Josephine Antony, Kerry Halupka, Dwarikanath Mahapatra, Rahil Garnavi
-
Patent number: 10390888Abstract: A method of generating a 4D model includes capturing imagery of a catheter and a vessel as the catheter is directed through the vessel to a location of interest, wherein the catheter is disposed on a guidewire, constructing a 3D time varying reference curve describing a trajectory of the guidewire, and constructing a time varying 3D model of the artery using the reference curve.Type: GrantFiled: December 29, 2017Date of Patent: August 27, 2019Assignee: International Business Machines CorporationInventors: Julia S. Baldauf, Darcy J. Beurle, Matthew Downton, Kerry Halupka, Stephen M. Moore, Christine Schieber
-
Publication number: 20190231438Abstract: A method of generating a 4D model includes capturing imagery of a catheter and a vessel as the catheter is directed through the vessel to a location of interest, wherein the catheter is disposed on a guidewire, constructing a 3D time varying reference curve describing a trajectory of the guidewire, and constructing a time varying 3D model of the artery using the reference curve.Type: ApplicationFiled: April 8, 2019Publication date: August 1, 2019Inventors: JULIA S. BALDAUF, DARCY J. BEURLE, MATTHEW DOWNTON, KERRY HALUPKA, STEPHEN M. MOORE, CHRISTINE SCHIEBER
-
Patent number: 10251708Abstract: A method of generating a 4D model includes capturing imagery of a catheter and a vessel as the catheter is directed through the vessel to a location of interest, wherein the catheter is disposed on a guidewire, constructing a 3D time varying reference curve describing a trajectory of the guidewire, and constructing a time varying 3D model of the artery using the reference curve.Type: GrantFiled: April 26, 2017Date of Patent: April 9, 2019Assignee: International Business Machines CorporationInventors: Julia S. Baldauf, Darcy J. Beurle, Matthew Downton, Kerry Halupka, Stephen M. Moore, Christine Schieber
-
Publication number: 20180310830Abstract: A catheter including a monitoring body and a pair of markers disposed on the monitoring body, each marker of the pair of markers encircling the monitoring body, wherein the pair of markers are configured to indicate, through their appearance from a given point of view, an orientation of the monitoring body.Type: ApplicationFiled: April 26, 2017Publication date: November 1, 2018Inventors: JULIA S. BALDAUF, DARCY J. BEURLE, MATTHEW DOWNTON, KERRY HALUPKA, STEPHEN M. MOORE, CHRISTINE SCHIEBER
-
Publication number: 20180310992Abstract: A method of generating a 4D model includes capturing imagery of a catheter and a vessel as the catheter is directed through the vessel to a location of interest, wherein the catheter is disposed on a guidewire, constructing a 3D time varying reference curve describing a trajectory of the guidewire, and constructing a time varying 3D model of the artery using the reference curve.Type: ApplicationFiled: April 26, 2017Publication date: November 1, 2018Inventors: JULIA S. BALDAUF, DARCY J. BEURLE, MATTHEW DOWNTON, KERRY HALUPKA, STEPHEN M. MOORE, CHRISTINE SCHIEBER
-
Publication number: 20180310994Abstract: A method of generating a 4D model includes capturing imagery of a catheter and a vessel as the catheter is directed through the vessel to a location of interest, wherein the catheter is disposed on a guidewire, constructing a 3D time varying reference curve describing a trajectory of the guidewire, and constructing a time varying 3D model of the artery using the reference curve.Type: ApplicationFiled: December 29, 2017Publication date: November 1, 2018Inventors: JULIA S. BALDAUF, DARCY J. BEURLE, MATTHEW DOWNTON, KERRY HALUPKA, STEPHEN M. MOORE, CHRISTINE SCHIEBER