Patents by Inventor Thomas Matthews
Thomas Matthews 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: 20260320987Abstract: Disclosed herein is a method for monitoring, surveillance, and/or operation of a machine-learning medical imaging screening classifier, comprising: obtaining the classifier, which is trained to process medical image data of a subject to determine a classification output indicative of a presence or absence of a health state in the subject; obtaining medical image data of clinical subjects of a medical imaging clinical site; applying the classifier to the medical image data to determine classification outputs indicative of a health state in the clinical subjects; determining performance metrics of the classifier, based at least in part on the classification outputs and an actual presence or absence of the health state for the clinical subjects; and operating the classifier in (i) an autonomous operating mode when the classifier is validated based on the performance metrics meeting pre-determined criteria, or (ii) an semi-autonomous or non-autonomous operating mode when the classifier is not validated.Type: ApplicationFiled: February 19, 2026Publication date: October 15, 2026Inventors: Thomas Matthews, Maguerite Thomlinson, Siddhartha Chattopadhyay, Jason Su
-
Publication number: 20260298941Abstract: The present technology comprises methods for detecting a neutralizing antibody (NAb) against a target antibody. In some embodiments, the target antibody comprises an anti-Tumor Necrosis Factor-alpha (TNF?) antibody. In some embodiments, the target antibody comprises SEQ ID NO: 9-11 or 15-17 and SEQ ID NOs: 12-14 or 18-20. The present technology further comprises kits for performing the methods of the present technology.Type: ApplicationFiled: June 7, 2024Publication date: October 1, 2026Inventors: Thomas Matthews, Kenneth Swart
-
Publication number: 20260298940Abstract: The present technology includes methods for detecting an anti-drug antibody (ADA) that binds an anti-TNF? antibody (target antibody) in a sample comprising incubating the sample with a composition comprising an affinity antibody and a detection antibody, and isolating and detecting the ADAs that form a complex with the affinity antibody and the detection antibody. The technology also includes methods for determining the ADA concentration in a sample and confirming that a sample comprises ADAs. The technology also includes a kit for performing any of the methods of the present technology.Type: ApplicationFiled: April 19, 2024Publication date: October 1, 2026Inventor: Thomas Matthews
-
Publication number: 20260112028Abstract: The present disclosure provides methods and systems directed to performing real-time and/or AI-assisted radiology. A method for processing an image of a location of a body of a subject may comprise (a) obtaining the image of the location of a body of the subject; (b) using a trained algorithm to classify the image or a derivative thereof to a category among a plurality of categories, wherein the classifying comprises applying an image processing algorithm; (c) directing the image to a first radiologist for radiological assessment if the image is classified to a first category among the plurality of categories, or (ii) directing the image to a second radiologist for radiological assessment, if the image is classified to a second category among the plurality of categories; and (d) receiving a recommendation from the first or second radiologist to examine the subject based at least in part on the radiological assessment.Type: ApplicationFiled: May 27, 2025Publication date: April 23, 2026Inventors: Jason Su, Rakesh Mathur, Brent Mombourquette, Thomas Matthews
-
Patent number: 12586360Abstract: Disclosed herein is a method for monitoring, surveillance, and/or operation of a machine-learning medical imaging screening classifier, comprising: obtaining the classifier, which is trained to process medical image data of a subject to determine a classification output indicative of a presence or absence of a health state in the subject; obtaining medical image data of clinical subjects of a medical imaging clinical site; applying the classifier to the medical image data to determine classification outputs indicative of a health state in the clinical subjects; determining performance metrics of the classifier, based at least in part on the classification outputs and an actual presence or absence of the health state for the clinical subjects; and operating the classifier in (i) an autonomous operating mode when the classifier is validated based on the performance metrics meeting pre-determined criteria, or (ii) an semi-autonomous or non-autonomous operating mode when the classifier is not validated.Type: GrantFiled: December 19, 2023Date of Patent: March 24, 2026Assignee: Whiterabbit.ai Inc.Inventors: Thomas Matthews, Marguerite Thomlinson, Siddhartha Chattopadhyay, Jason Su
-
Publication number: 20260042831Abstract: Provided are compositions comprising an anti-TNF? antibody sialylated with one or more N-acetylneuraminic acid molecules, and associated methods. In some embodiments, provided are methods for treating or preventing sarcoidosis and/or granuloma size or formation in patients in need thereof.Type: ApplicationFiled: December 8, 2023Publication date: February 12, 2026Inventors: Kirsten ANDERSON, Thomas MATTHEWS, Tom SHEA, Noopur SINGH
-
Patent number: 12347104Abstract: The present disclosure provides methods and systems directed to performing real-time and/or AI-assisted radiology. A method for processing an image of a location of a body of a subject may comprise (a) obtaining the image of the location of a body of the subject; (b) using a trained algorithm to classify the image or a derivative thereof to a category among a plurality of categories, wherein the classifying comprises applying an image processing algorithm; (c) directing the image to a first radiologist for radiological assessment if the image is classified to a first category among the plurality of categories, or (ii) directing the image to a second radiologist for radiological assessment, if the image is classified to a second category among the plurality of categories; and (d) receiving a recommendation from the first or second radiologist to examine the subject based at least in part on the radiological assessment.Type: GrantFiled: July 8, 2022Date of Patent: July 1, 2025Assignee: Whiterabbit.ai Inc.Inventors: Jason Su, Rakesh Mathur, Brent Mombourquette, Thomas Matthews
-
Publication number: 20250084074Abstract: The invention relates to substituted heterocycles of the general formula I, and the use of the compounds of the present invention for the treatment and/or prevention of hyperproliferative diseases and disorders in mammals, especially humans, and pharmaceutical compositions containing such compound.Type: ApplicationFiled: January 9, 2023Publication date: March 13, 2025Applicants: MERCK PATENT GMBH, THE INSTITUTE OF CANCER RESEARCH, CANCER RESEARCH HORIZONSInventors: Hans-Peter BUCHSTALLER, Daniel KUHN, Ian COLLINS, Thomas MATTHEWS, Jan LANZ, John CALDWELL, Giampiero COLOMBANO
-
Patent number: 12220895Abstract: A glass facer for a constructions board includes a first non-woven layer of coarse fibers and a second non-woven layer of coarse fibers and microfibers. The glass facer also includes a binder that simultaneously binds or adheres the coarse fibers of the first non-woven layer together, the coarse fibers and the microfibers of the second non-woven layer together, and the first non-woven layer to the second non-woven layer. The first non-woven layer has a porosity and air permeability that enables the first non-woven layer to absorb a material of the construction board when the glass facer is positioned atop the construction board during manufacture of the construction board. The second non-woven layer is configured to block the material of the construction board from passing through the glass facer to an exterior surface of the second non-woven layer so that the material is not externally visible.Type: GrantFiled: March 22, 2024Date of Patent: February 11, 2025Assignee: Johns ManvilleInventors: Souvik Nandi, Glenda B Bennett, Thomas Matthews
-
Publication number: 20250014719Abstract: Disclosed herein is computer-implemented method for processing at least one image of a location of a body of a subject. The method may comprise obtaining the at least one image, and using a trained algorithm to classify the at least one image or a derivative thereof to a category among a plurality of categories comprising a first category and a second category. The classifying may comprise applying a image processing algorithm. The method may comprise, based at least in part on the classifying, designating the at least one image or derivative thereof as having a first or second priority (e.g., lower priority or urgency than the first priority) for radiological assessment if the at least one image is classified to the first or second category, respectively. The method may comprise generating an electronic assessment of the subject, such as a negative report indicative of the subject not having a health condition.Type: ApplicationFiled: January 8, 2024Publication date: January 9, 2025Inventors: Jason Su, Rakesh Mathur, Brent Mombourquette, Thomas Matthews, Stefano Pedemonte, Marguerite Thomlinson, Siddhartha Chattopadhyay, Trevor Tsue, Hugo Vergnes
-
Patent number: 12039639Abstract: Systems and methods reconstruct an image of a subject or object by performing an iterative reconstruction method to produce a plurality of intermediate images and the image of the subject, and transforming at least one selected intermediate image from the plurality of intermediate images using a quasi-projection operator. The quasi-projection operator includes a deep-learning model configured to map the at least one selected intermediate image to at least one regularized intermediate image. In addition, systems and methods for training the deep-learning model using a training data set that includes a plurality of training images and a plurality of corresponding training object images is disclosed.Type: GrantFiled: June 27, 2022Date of Patent: July 16, 2024Assignee: Washington UniversityInventors: Mark Anastasio, Thomas Matthews, Brendan Kelly
-
Publication number: 20240227362Abstract: A glass facer for a constructions board includes a first non-woven layer of coarse fibers and a second non-woven layer of coarse fibers and microfibers. The glass facer also includes a binder that simultaneously binds or adheres the coarse fibers of the first non-woven layer together, the coarse fibers and the microfibers of the second non-woven layer together, and the first non-woven layer to the second non-woven layer. The first non-woven layer has a porosity and air permeability that enables the first non-woven layer to absorb a material of the construction board when the glass facer is positioned atop the construction board during manufacture of the construction board. The second non-woven layer is configured to block the material of the construction board from passing through the glass facer to an exterior surface of the second non-woven layer so that the material is not externally visible.Type: ApplicationFiled: March 22, 2024Publication date: July 11, 2024Inventors: Souvik Nandi, Glenda B Bennett, Thomas Matthews
-
Patent number: 11951712Abstract: A glass facer for a constructions board includes a first non-woven layer of coarse fibers and a second non-woven layer of coarse fibers and microfibers. The glass facer also includes a binder that simultaneously binds or adheres the coarse fibers of the first non-woven layer together, the coarse fibers and the microfibers of the second non-woven layer together, and the first non-woven layer to the second non-woven layer. The first non-woven layer has a porosity and air permeability that enables the first non-woven layer to absorb a material of the construction board when the glass facer is positioned atop the construction board during manufacture of the construction board. The second non-woven layer is configured to block the material of the construction board from passing through the glass facer to an exterior surface of the second non-woven layer so that the material is not externally visible.Type: GrantFiled: January 14, 2020Date of Patent: April 9, 2024Assignee: Johns ManvilleInventors: Souvik Nandi, Glenda B Bennett, Thomas Matthews
-
Publication number: 20230346454Abstract: An electrosurgical generator arranged to supply radio frequency (RF) energy to fuse tissue is provided. The generator is arranged to supply RF energy through a removably coupled electrosurgical instrument to fuse tissue grasped by the instrument. The generator monitors a phase angle of the supplied RF energy and adjusts or terminates the supplied RF energy based on the monitored phase angle in comparison to predetermined thresholds and conditions to optimally fuse the tissue. The electrosurgical instrument conducts radio frequency energy to fuse tissue captured between the jaws and a blade to mechanically cut tissue between the jaws. A conductive post positioned on the jaw adjacent to the blade.Type: ApplicationFiled: June 7, 2023Publication date: November 2, 2023Inventors: Patrick Elliott, Gary Johnson, Duy Nguyen, Daniel McFarland, Jagdish Sabarad, Benjamin Linville-Engler, Jeremy Albrecht, Dan Durant, Gerald Kowalski, Lou Tiberia, Michael Whitlock, Michael Logan, Igor Gorin, Kevin Hudson, Hank Jacobs, Thomas Matthews
-
Patent number: 11672589Abstract: An electrosurgical generator arranged to supply radio frequency (RF) energy to fuse tissue is provided. The generator is arranged to supply RF energy through a removably coupled electrosurgical instrument to fuse tissue grasped by the instrument. The generator monitors a phase angle of the supplied RF energy and adjusts or terminates the supplied RF energy based on the monitored phase angle in comparison to predetermined thresholds and conditions to optimally fuse the tissue. The electrosurgical instrument conducts radio frequency energy to fuse tissue captured between the jaws and a blade to mechanically cut tissue between the jaws. A conductive post positioned on the jaw adjacent to the blade.Type: GrantFiled: December 4, 2018Date of Patent: June 13, 2023Assignee: Applied Medical Resources CorporationInventors: Patrick Elliott, Gary Johnson, Duy Nguyen, Daniel McFarland, Jagdish Sabarad, Benjamin Linville-Engler, Jeremy Albrecht, Dan Durant, Gerald Kowalski, Lou Tiberia, Michael Whitlock, Michael Logan, Igor Gorin, Kevin Hudson, Hank Jacobs, Thomas Matthews
-
Publication number: 20230005151Abstract: The present disclosure provides methods and systems directed to performing real-time and/or AI-assisted radiology. A method for processing an image of a location of a body of a subject may comprise (a) obtaining the image of the location of a body of the subject; (b) using a trained algorithm to classify the image or a derivative thereof to a category among a plurality of categories, wherein the classifying comprises applying an image processing algorithm; (c) directing the image to a first radiologist for radiological assessment if the image is classified to a first category among the plurality of categories, or (ii) directing the image to a second radiologist for radiological assessment, if the image is classified to a second category among the plurality of categories; and (d) receiving a recommendation from the first or second radiologist to examine the subject based at least in part on the radiological assessment.Type: ApplicationFiled: July 8, 2022Publication date: January 5, 2023Inventors: Jason Su, Rakesh Mathur, Brent Mombourquette, Thomas Matthews
-
Publication number: 20220327751Abstract: Systems and methods reconstruct an image of a subject or object by performing an iterative reconstruction method to produce a plurality of intermediate images and the image of the subject, and transforming at least one selected intermediate image from the plurality of intermediate images using a quasi-projection operator. The quasi-projection operator includes a deep-learning model configured to map the at least one selected intermediate image to at least one regularized intermediate image. In addition, systems and methods for training the deep-learning model using a training data set that includes a plurality of training images and a plurality of corresponding training object images is disclosed.Type: ApplicationFiled: June 27, 2022Publication date: October 13, 2022Inventors: Mark Anastasio, Thomas Matthews, Brendan Kelley
-
Publication number: 20220289338Abstract: A watercraft matting is described that includes a bottom surface configured to come into contact with a watercraft surface, a top surface having a plurality of recessed portions disposed between a plurality of protruding portions, where the protruding portions being formed of a non-skid material, and a phosphorescent material positioned within the plurality of recessed portions. The phosphorescent material is adapted to glow-in-the-dark when exposed to an ultraviolet light. The plurality of protruding portions may be formed of a cross-linked-closed-cell (CLCC) foam material.Type: ApplicationFiled: March 9, 2022Publication date: September 15, 2022Inventor: Thomas Matthews
-
Patent number: 11403792Abstract: Systems and methods for reconstructing an image of a subject or object based on a plurality of measured signals representing the subject or object obtained by an imaging device are disclosed. The systems and methods reconstruct the image of the subject or object by performing an iterative reconstruction method to produce a plurality of intermediate images and the image of the subject, and transforming at least one selected intermediate image from the plurality of intermediate images using a quasi-projection operator. The quasi-projection operator includes a deep-learning model configured to map the at least one selected intermediate image to at least one regularized intermediate image. In addition, systems and methods for training the deep-learning model using a training data set that includes a plurality of training images and a plurality of corresponding training object images is disclosed.Type: GrantFiled: June 18, 2018Date of Patent: August 2, 2022Assignee: Washington UniversityInventors: Mark Anastasio, Thomas Matthews, Brendan Kelly
-
Publication number: 20210150779Abstract: Systems and methods for reconstructing an image of a subject or object based on a plurality of measured signals representing the subject or object obtained by an imaging device are disclosed. The systems and methods reconstruct the image of the subject or object by performing an iterative reconstruction method to produce a plurality of intermediate images and the image of the subject, and transforming at least one selected intermediate image from the plurality of intermediate images using a quasi-projection operator. The quasi-projection operator includes a deep-learning model configured to map the at least one selected intermediate image to at least one regularized intermediate image. In addition, systems and methods for training the deep-learning model using a training data set that includes a plurality of training images and a plurality of corresponding training object images is disclosed.Type: ApplicationFiled: June 18, 2018Publication date: May 20, 2021Applicant: Washington UniversityInventors: Mark ANASTASIO, Thomas MATTHEWS, Brendan KELLY