Patents by Inventor Brian Teixeira
Brian Teixeira 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: 11837352Abstract: For training a machine learning system for representing a patient body a plurality of stored medical imaging data sets each representing at least a part of a respective patient are obtained. A first one of the plurality of stored medical imaging data sets represents a different part of the patient body than a second one of the plurality of stored medical imaging data sets. A plurality of landmarks in the stored medical imaging data sets are estimated, and each of the stored medical imaging data sets are aligned to a predefined pose using the plurality of landmarks. A plurality of points in the aligned medical imaging data sets are sampled, and the machine learning system is trained based on at least the plurality of points. The learned parameters of the machine learning system are then stored and used in a method for inferring a body representation.Type: GrantFiled: April 15, 2021Date of Patent: December 5, 2023Assignee: Siemens Healthcare GmbHInventors: Birgi Tamersoy, Ankur Kapoor, Vivek Singh, Brian Teixeira
-
Patent number: 11810291Abstract: Systems and methods for generating a synthesized medical image are provided. An input medical image is received. A synthesized segmentation mask is generated. The input medical image is masked based on the synthesized segmentation mask. The masked input medical image has an unmasked portion and a masked portion. An initial synthesized medical image is generated using a trained machine learning based generator network. The initial synthesized medical image includes a synthesized version of the unmasked portion of the masked input medical image and synthesized patterns in the masked portion of the masked input medical image. The synthesized patterns is fused with the input medical image to generate a final synthesized medical image.Type: GrantFiled: May 1, 2020Date of Patent: November 7, 2023Assignee: Siemens Healthcare GmbHInventors: Siqi Liu, Bogdan Georgescu, Zhoubing Xu, Youngjin Yoo, Guillaume Chabin, Shikha Chaganti, Sasa Grbic, Sebastien Piat, Brian Teixeira, Thomas Re, Dorin Comaniciu
-
Publication number: 20220346742Abstract: CT scan parameters for performing a CT scan of an anatomical target region of a patient are determined and/or adjusted. An initial set of the CT scan parameters for starting to perform the CT scan is determined based on an initial set of attenuation curves associated with the anatomical target region of the patient. The initial set of attenuation curves are determined based on optical imaging data depicting the patient.Type: ApplicationFiled: March 30, 2022Publication date: November 3, 2022Inventors: Brian Teixeira, Vivek Singh, Ankur Kapoor, Andreas Prokein, Dorin Comaniciu
-
Patent number: 11430121Abstract: Systems and methods for assessing a disease are provided. Medical imaging data of lungs of a patient is received. The lungs are segmented from the medical imaging data and abnormality regions associated with a disease are segmented from the medical imaging data. An assessment of the disease is determined based on the segmented lungs and the segmented abnormality regions. The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia.Type: GrantFiled: April 1, 2020Date of Patent: August 30, 2022Assignee: Siemens Healthcare GmbHInventors: Shikha Chaganti, Sasa Grbic, Bogdan Georgescu, Zhoubing Xu, Siqi Liu, Youngjin Yoo, Thomas Re, Guillaume Chabin, Thomas Flohr, Valentin Ziebandt, Dorin Comaniciu, Brian Teixeira, Sebastien Piat
-
Patent number: 11410374Abstract: Synthetic CT is estimated for planning or other purposes from surface data (e.g., depth camera information). The estimation uses parameterization, such as landmark and/or segmentation information, in addition to the surface data. In training and/or application, the parameterization may be used to correct the predicted CT volume. The CT volume may be predicted as a sub-part of the patient, such as estimating the CT volume for scanning one system, organ, or type of tissue separately from other system, organ, or type of tissue.Type: GrantFiled: October 9, 2019Date of Patent: August 9, 2022Assignee: Siemens Healthcare GmbHInventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy, Andreas Krauß, Yifan Wu
-
Publication number: 20220130524Abstract: A stream of virtual topograms, in particular live virtual topograms, is predicted. Sets of surface data of an outer surface of a subject are continuously received. Based on each received set of surface data a (live) virtual topogram is continuously generated by a trained machine learning algorithm (MLA). Thereto, a representation of body landmarks is updated based on each received set of surface data by a trained body marker detector (BMD), of the trained MLA, and the (live) virtual topogram is predicted based on the updated spatial marker map and on the corresponding set of surface data by a trained topogram generator (TG) of the trained MLA.Type: ApplicationFiled: September 30, 2021Publication date: April 28, 2022Inventors: Brian Teixeira, Vivek Singh, Ankur Kapoor, Yao-jen Chang, Birgi Tamersoy
-
Patent number: 11257259Abstract: For topogram predication from surface data, a sensor captures the outside surface of a patient. A generative adversarial network (GAN) generates the topogram representing an interior organ based on the outside surface of the patient. To further adapt to specific patients, internal landmarks are used in the topogram prediction. The topogram generated by one generator of the GAN may be altered based on landmarks generated by another generator.Type: GrantFiled: July 20, 2018Date of Patent: February 22, 2022Assignee: Siemens Healthcare GmbHInventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy, Terrence Chen, Kai Ma, Andreas Krauss
-
Publication number: 20210358595Abstract: For training a machine learning system for representing a patient body a plurality of stored medical imaging data sets each representing at least a part of a respective patient are obtained. A first one of the plurality of stored medical imaging data sets represents a different part of the patient body than a second one of the plurality of stored medical imaging data sets. A plurality of landmarks in the stored medical imaging data sets are estimated, and each of the stored medical imaging data sets are aligned to a predefined pose using the plurality of landmarks. A plurality of points in the aligned medical imaging data sets are sampled, and the machine learning system is trained based on at least the plurality of points. The learned parameters of the machine learning system are then stored and used in a method for inferring a body representation.Type: ApplicationFiled: April 15, 2021Publication date: November 18, 2021Inventors: Birgi Tamersoy, Ankur Kapoor, Vivek Singh, Brian Teixeira
-
Publication number: 20210327054Abstract: Systems and methods for generating a synthesized medical image are provided. An input medical image is received. A synthesized segmentation mask is generated. The input medical image is masked based on the synthesized segmentation mask. The masked input medical image has an unmasked portion and a masked portion. An initial synthesized medical image is generated using a trained machine learning based generator network. The initial synthesized medical image includes a synthesized version of the unmasked portion of the masked input medical image and synthesized patterns in the masked portion of the masked input medical image. The synthesized patterns is fused with the input medical image to generate a final synthesized medical image.Type: ApplicationFiled: May 1, 2020Publication date: October 21, 2021Inventors: Siqi Liu, Bogdan Georgescu, Zhoubing Xu, Youngjin Yoo, Guillaume Chabin, Shikha Chaganti, Sasa Grbic, Sebastien Piat, Brian Teixeira, Thomas Re, Dorin Comaniciu
-
Publication number: 20210304408Abstract: Systems and methods for assessing a disease are provided. Medical imaging data of lungs of a patient is received. The lungs are segmented from the medical imaging data and abnormality regions associated with a disease are segmented from the medical imaging data. An assessment of the disease is determined based on the segmented lungs and the segmented abnormality regions. The disease may be COVID-19 (coronavirus disease 2019) or diseases, such as, e.g., SARS (severe acute respiratory syndrome), MERS (Middle East respiratory syndrome), or other types of viral and non-viral pneumonia.Type: ApplicationFiled: April 1, 2020Publication date: September 30, 2021Inventors: Shikha Chaganti, Sasa Grbic, Bogdan Georgescu, Zhoubing Xu, Siqi Liu, Youngjin Yoo, Thomas Re, Guillaume Chabin, Thomas Flohr, Valentin Ziebandt, Dorin Comaniciu, Brian Teixeira, Sebastien Piat
-
Publication number: 20210110594Abstract: Synthetic CT is estimated for planning or other purposes from surface data (e.g., depth camera information). The estimation uses parameterization, such as landmark and/or segmentation information, in addition to the surface data. In training and/or application, the parameterization may be used to correct the predicted CT volume. The CT volume may be predicted as a sub-part of the patient, such as estimating the CT volume for scanning one system, organ, or type of tissue separately from other system, organ, or type of tissue.Type: ApplicationFiled: October 9, 2019Publication date: April 15, 2021Inventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy, Andreas Krauss, Yifan Wu
-
Patent number: 10849585Abstract: For anomaly detection based on topogram predication from surface data, a sensor captures the outside surface of a patient. A generative adversarial network (GAN) generates a topogram representing an interior anatomy based on the outside surface of the patient. An X-ray image of the patient is acquired and compared to the generated topogram. By quantifying the difference between the real X-ray image and the predicted one, anatomical anomalies may be detected.Type: GrantFiled: August 14, 2019Date of Patent: December 1, 2020Assignee: Siemens Healthcare GmbHInventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy
-
Patent number: 10521927Abstract: Machine learning is used to train a network to predict the location of an internal body marker from surface data. A depth image or other image of the surface of the patient is used to determine the locations of anatomical landmarks. The training may use a loss function that includes a term to limit failure to predict a landmark and/or off-centering of the landmark. The landmarks may then be used to configure medical scanning and/or for diagnosis.Type: GrantFiled: August 7, 2018Date of Patent: December 31, 2019Assignee: Siemens Healthcare GmbHInventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy, Terrence Chen, Kai Ma, Andreas Krauss, Andreas Wimmer
-
Publication number: 20190057521Abstract: For topogram predication from surface data, a sensor captures the outside surface of a patient. A generative adversarial network (GAN) generates the topogram representing an interior organ based on the outside surface of the patient. To further adapt to specific patients, internal landmarks are used in the topogram prediction. The topogram generated by one generator of the GAN may be altered based on landmarks generated by another generator.Type: ApplicationFiled: July 20, 2018Publication date: February 21, 2019Inventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy, Terrence Chen, Kai Ma, Andreas Krauss
-
Publication number: 20190057515Abstract: Machine learning is used to train a network to predict the location of an internal body marker from surface data. A depth image or other image of the surface of the patient is used to determine the locations of anatomical landmarks. The training may use a loss function that includes a term to limit failure to predict a landmark and/or off-centering of the landmark. The landmarks may then be used to configure medical scanning and/or for diagnosis.Type: ApplicationFiled: August 7, 2018Publication date: February 21, 2019Inventors: Brian Teixeira, Vivek Kumar Singh, Birgi Tamersoy, Terrence Chen, Kai Ma, Andreas Krauss, Andreas Wimmer
-
Patent number: 7850152Abstract: Methods and devices for moisturizing hyperpolarized noble gas and associated hyperpolarized noble gas products which are formulated for inhalation or ventilation delivery include adding moisture content to (dry) hyperpolarized gas.Type: GrantFiled: April 23, 2002Date of Patent: December 14, 2010Assignee: Medi Physics, Inc.Inventors: Ken Bolam, Patrick Cella, John Nouls, Brian Teixeira
-
Publication number: 20080004747Abstract: Methods, systems and computer program products for dispensing hyperpolarized gas include or operate a plurality of spaced apart individually operable valves positioned in fluid communication with and located along a gas flow path. The gas flow path that is intermediate the spaced apart valves defines at least one meted holding space with an associated volume that can be selectively isolated from the remainder of the gas flow path. The system and methods include a pressure sensor operably associated with the gas flow path and a control module operably associated with the plurality of spaced apart valves and the pressure sensor, the control module being configured to direct the operational sequence of the opening and closing of the valves, wherein, in operation, the control module directs a plurality of capture and release cycles, the cycles being successively carried out so to temporally isolate a predetermined portion of the gas flow path to capture and then release discrete amounts of gas therein.Type: ApplicationFiled: September 6, 2007Publication date: January 3, 2008Inventor: Brian Teixeira
-
Patent number: 7277775Abstract: Methods, systems and computer program products for dispensing hyperpolarized gas include or operate a plurality of spaced apart individually operable valves positioned in fluid communication with and located along a gas flow path. The gas flow path that is intermediate the spaced apart valves defines at least one meted holding space with an associated volume that can be selectively isolated from the remainder of the gas flow path. The system and methods include a pressure sensor operably associated with the gas flow path and a control module operably associated with the plurality of spaced apart valves and the pressure sensor, the control module being configured to direct the operational sequence of the opening and closing of the valves, wherein, in operation, the control module directs a plurality of capture and release cycles, the cycles being successively carried out so to temporally isolate a predetermined portion of the gas flow path to capture and then release discrete amounts of gas therein.Type: GrantFiled: July 22, 2003Date of Patent: October 2, 2007Assignee: Medi-Physics, Inc.Inventor: Brian Teixeira
-
Publication number: 20040016768Abstract: Methods, systems and computer program products for dispensing hyperpolarized gas include or operate a plurality of spaced apart individually operable valves positioned in fluid communication with and located along a gas flow path. The gas flow path that is intermediate the spaced apart valves defines at least one meted holding space with an associated volume that can be selectively isolated from the remainder of the gas flow path. The system and methods include a pressure sensor operably associated with the gas flow path and a control module operably associated with the plurality of spaced apart valves and the pressure sensor, the control module being configured to direct the operational sequence of the opening and closing of the valves, wherein, in operation, the control module directs a plurality of capture and release cycles, the cycles being successively carried out so to temporally isolate a predetermined portion of the gas flow path to capture and then release discrete amounts of gas therein.Type: ApplicationFiled: July 22, 2003Publication date: January 29, 2004Inventor: Brian Teixeira
-
Publication number: 20020168419Abstract: Methods and devices for moisturizing hyperpolarized noble gas and associated hyperpolarized noble gas products which are formulated for inhalation or ventilation delivery include adding moisture content to (dry) hyperpolarized gas.Type: ApplicationFiled: April 23, 2002Publication date: November 14, 2002Inventors: Ken Bolam, Patrick Cella, John Nouls, Brian Teixeira