Patents by Inventor Puneet Sharma

Puneet Sharma 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: 20210110135
    Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.
    Type: Application
    Filed: November 24, 2020
    Publication date: April 15, 2021
    Inventors: Shaohua Kevin Zhou, Mingqing Chen, Hui Ding, Bogdan Georgescu, Mehmet Akif Gulsun, Tae Soo Kim, Atilla Peter Kiraly, Xiaoguang Lu, Jin-hyeong Park, Puneet Sharma, Shanhui Sun, Daguang Xu, Zhoubing Xu, Yefeng Zheng
  • Patent number: 10973472
    Abstract: For material decomposition in medical imaging, a machine-learned model is trained to decompose. For example, spectral CT data for a plurality of locations is input, and the machine-learned model outputs the material composition. Using information from surrounding locations for the decomposition by the machine-learned model for a given location may allow for more accurate material decomposition and/or three or more material decomposition.
    Type: Grant
    Filed: March 5, 2019
    Date of Patent: April 13, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Pooyan Sahbaee Bagherzadeh, Puneet Sharma
  • Patent number: 10971271
    Abstract: A method and system for personalized blood flow modeling based on wearable sensor networks is disclosed. A personalized anatomical model of vessels of a patient is generated based on initial patient data. Continuous cardiovascular measurements of the patient are received from a wearable sensor network on the patient. A computational blood flow model for simulating blood flow in the patient-specific anatomical model of the vessels of the patient is personalized based on the continuous cardiovascular measurements from the wearable sensor network. Blood flow and pressure in the patient-specific anatomical model of the vessels of the patient are simulated using the personalized computational blood flow model. Hemodynamic measures of interest for the patient are computed based on the simulated blood flow and pressure.
    Type: Grant
    Filed: March 14, 2017
    Date of Patent: April 6, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Lucian Mihai Itu, Tiziano Passerini, Puneet Sharma
  • Patent number: 10965788
    Abstract: Various aspects of the subject technology relate to methods, systems, and machine-readable media for multi-path transmission control protocol (MP-TCP) proxy tunneling. The method includes reading a first multi-path transmission control protocol (MP-TCP) information from at least one first MP-TCP header, the at least one first MP-TCP header included in a first MP-TCP subflow, the first MP-TCP subflow included in a first MP-TCP session. The method also includes encapsulating the first MP-TCP information in a second MP-TCP session, the second MP-TCP session different from the first MP-TCP session. The method also includes sending the first MP-TCP information through the second MP-TCP session.
    Type: Grant
    Filed: March 18, 2019
    Date of Patent: March 30, 2021
    Assignee: Hewlett Packard Enterprise Development LP
    Inventors: Jean Tourrilhes, Puneet Sharma
  • Publication number: 20210085397
    Abstract: A method and system for non-invasive assessment and therapy planning for coronary artery disease from medical image data of a patient is disclosed. Geometric features representing at least a portion of a coronary artery tree of the patient are extracted from medical image data. Lesions are detected in coronary artery tree of the patient and a hemodynamic quantity of interest is computed at a plurality of points along the coronary artery tree including multiple points within the lesions based on the extracted geometric features using a machine learning model, resulting in an estimated pullback curve for the hemodynamic quantity of interest.
    Type: Application
    Filed: July 26, 2018
    Publication date: March 25, 2021
    Inventors: Tiziano Passerini, Thomas Redel, Paul Klein, Lucian Mihai Itu, Saikiran Rapaka, Puneet Sharma
  • Patent number: 10945613
    Abstract: An estimation of arterial wall properties is provided. A method for determining a wall property of an artery such as an aorta includes acquiring patient data and extracting physical data from the patient data. The physical data is applied to a blood flow model of the aorta to obtain an individual blood flow model. The wall property of the artery is directly or indirectly determined from the individual blood flow model.
    Type: Grant
    Filed: April 5, 2017
    Date of Patent: March 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Martin Kramer, Lucian Mihai Itu, Viorel Mihalef, Puneet Sharma
  • Publication number: 20210064936
    Abstract: Systems and methods for retraining a trained machine learning model are provided. One or more input medical images are received. Measures of interest for a primary task and a secondary task are predicted from the one or more input medical images using a trained machine learning model. The predicted measures of interest for the primary task and the secondary task are output. User feedback on the predicted measure of interest for the secondary task is received. The trained machine learning model is retrained for predicting the measures of interest for the primary task and the secondary task based on the user feedback on the output for the secondary task.
    Type: Application
    Filed: August 30, 2019
    Publication date: March 4, 2021
    Inventors: Lucian Mihai Itu, Tiziano Passerini, Thomas Redel, Puneet Sharma
  • Patent number: 10938667
    Abstract: An example method including identifying an intent-based stateful network having a first endpoint, a second endpoint, and one or more devices performing stateful network functions between the first endpoint and the second endpoint. Further, constructing a causality graph of the network, the causality graph having a plurality of nodes for each of the one or more devices performing stateful network functions, wherein the connecting comprises connecting the first endpoint, the second endpoint, and the one or more devices performing stateful network functions to show causal relationships between the first endpoint and the second endpoint and the one or more devices performing stateful network functions. Also, determining whether the connections between the first endpoint, the second endpoint, and the one or more devices performing stateful network functions provide a path from the first endpoint and the second endpoint, and updating, incrementally, the causality graph as a change to the network occurs.
    Type: Grant
    Filed: December 20, 2018
    Date of Patent: March 2, 2021
    Assignee: Hewlett Packard Enterprise Development LP
    Inventors: Puneet Sharma, Huazhe Wang
  • Patent number: 10937205
    Abstract: A system and method includes acquisition of a first plurality of images, determination, for each of the first plurality of images, of whether an infarct is depicted in the image and generating a label associated with the image based on the determination, acquisition of a second plurality of non-contrast-enhanced computed tomography images, determination, for each of the second plurality of non-contrast-enhanced computed tomography images, of a corresponding one of the first plurality of images, association of each of the second plurality of non-contrast-enhanced computed tomography images with the label associated with its corresponding one of the first plurality of images, and training of a neural network to output a network-generated label, the training based on the second plurality of non-contrast-enhanced computed tomography images and associated labels.
    Type: Grant
    Filed: November 6, 2018
    Date of Patent: March 2, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Pooyan Sahbaee Bagherzadeh, Saikiran Rapaka, Puneet Sharma
  • Patent number: 10929973
    Abstract: A method and system for medical image pre-processing at the medical image scanner that facilitates joint interpretation of the medical images by radiologists and artificial intelligence algorithms is disclosed. Raw medical image data is acquired by performing a medical image scan of a patient using a medical image scanner. Input data associated with the medical image scan of the patient and available downstream automated image analysis algorithms is acquired. A set of pre-processing algorithms to apply to the raw medical image data is selected based on the input data associated with the medical image scan of the patient and the available downstream automated image analysis algorithms using a trained machine learning based model. One or more medical images are generated from the raw medical image data by applying the selected set of pre-processing algorithms to the raw medical image data.
    Type: Grant
    Filed: October 2, 2018
    Date of Patent: February 23, 2021
    Assignee: Siemens Healtcare GmbH
    Inventor: Puneet Sharma
  • Patent number: 10929420
    Abstract: Structured report data is generated from a medical text report. A medical text report including one or more natural language statements is acquired. A computer implemented text analysis process analyses the medical text report to determine, for each natural language statement, one or more labels for the natural language statement. Structured report data including the determined one or more labels each in association with natural language data from the natural language statement to which the label corresponds is generated. The computer implemented text analysis process includes, for each natural language statement: determining, for each of the one or more words of the natural language statement, and, using word embeddings, a vector representing the word; and determining, based on the determined one or more vectors, and using a text classification model, the one or more labels associated with the natural language statement.
    Type: Grant
    Filed: April 12, 2019
    Date of Patent: February 23, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Juan Xu, Puneet Sharma
  • Patent number: 10918309
    Abstract: For COPD assessment in medical imaging, imaging data is used to model airways and to extract values for features representative of COPD. The airway model provides values for anatomy of the airways and/or airflow. The values of anatomy, airflow, and/or extracted image features in combination indicate COPD information A machine-learned model may be used to relate the anatomy, airflow, and/or extracted image features to the COPD information. Additional information may be used, such as spirometry results and/or questionnaire answers. The combination of information, including airway modeling, as input to a COPD model may provide a more comprehensive understanding of COPD for assistance in therapy and/or diagnosis of a particular patient.
    Type: Grant
    Filed: April 11, 2019
    Date of Patent: February 16, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Saikiran Rapaka, Justin Hodges, Puneet Sharma
  • Publication number: 20210042771
    Abstract: Methods, systems and computer program products for facilitating use of select hyper-local data sets for improved modeling are provided. Aspects include receiving customer data associated with a customer by a workbench platform and determining an accuracy of a customer model using the customer data. For each of a plurality of hyper-local data sets, aspects also include determining an increase in model accuracy based on use of the hyper-local data set and the customer data. Aspects include identifying at least one group of hyper-local data sets of the plurality of hyper-local data sets that result in similar increases in model accuracy. Aspects also include facilitating use of a selected one or more of the hyper-local data sets of the at least one group of hyper-local data sets in generating an improved accuracy customer model.
    Type: Application
    Filed: August 9, 2019
    Publication date: February 11, 2021
    Inventors: PUNEET SHARMA, RAJESH PHILLIPS, RAJENDRA RAO, MANISHA SHARMA KOHLI, VIJAY EKAMBARAM
  • Patent number: 10909676
    Abstract: A method and system for non-invasive medical image based assessment of coronary artery disease (CAD) for clinical decision support using on-site and off-site processing is disclosed. Medical image data of a patient is received. A processing strategy for assessing CAD of the patient using one of on-site processing, off-site processing, or joint on-site and off-site processing is automatically selected based on clinical requirements for a current clinical scenario. Non-invasive assessment of CAD of the patient is performed based on the medical image data of the patient using one of on-site processing, off-site-processing, or joint on-site and off-site processing according to the selected processing strategy. A final assessment of CAD of the patient is output based on the non-invasive assessment of CAD.
    Type: Grant
    Filed: July 12, 2017
    Date of Patent: February 2, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Tiziano Passerini, Lucian Mihai Itu, Dorin Comaniciu, Puneet Sharma
  • Publication number: 20210027466
    Abstract: Systems and methods for determining a quantity of interest of a patient comprise receiving patient data of the patient at a first physiological state. A value of a quantity of interest of the patient at the first physiological state is determined based on the patient data. The quantity of interest represents a medical characteristic of the patient. Features are extracted from the patient data, wherein the features which are extracted are based on the quantity of interest to be determined for the patient at a second physiological state. The value of the quantity of interest of the patient at the first physiological state is mapped to a value of the quantity of interest of the patient at the second physiological state based on the extracted features.
    Type: Application
    Filed: October 15, 2020
    Publication date: January 28, 2021
    Inventors: Puneet Sharma, Lucian Mihai Itu, Saikiran Rapaka, Frank Sauer
  • Publication number: 20210015438
    Abstract: For decision support based on perfusion in medical imaging, a machine-learned model, such as a model trained with deep learning, generates perfusion examination information from CT scans of the patient. Other information, such as patient-specific information, may be used with the CT scans to generate the perfusion examination information. Since a machine-learned model is used, the perfusion examination information may be estimated from a spatial and/or temporally sparse number of scan shots or amount of CT dose. The results of perfusion imaging may be provided with less than the current, standard, or typical radiation dose.
    Type: Application
    Filed: July 16, 2019
    Publication date: January 21, 2021
    Inventors: Pooyan Sahbaee Bagherzadeh, Puneet Sharma
  • Patent number: 10897470
    Abstract: An example system may comprise a first computing device comprising instructions executable by a hardware processor to: create, responsive to detecting a second computing device initially attempting to connect to a network, an unpopulated baseline profile for the second computing device; populate the baseline profile with initial processes running on the second computing device and initial system calls made by the initial processes during an initial operation time period of the second computing device; monitor, during a subsequent operation time period of the second computing device, subsequent processes running on the second computing device and subsequent system calls made by the subsequent processes; and detect an attack on the second computing device based on a comparison of the subsequent processes and the subsequent system calls to the populated baseline profile.
    Type: Grant
    Filed: January 31, 2018
    Date of Patent: January 19, 2021
    Assignee: Hewlett Packard Enterprise Development LP
    Inventors: Puneet Sharma, Anand Mudgerikar
  • Patent number: 10888234
    Abstract: A method and system for determining fractional flow reserve (FFR) for a coronary artery stenosis of a patient is disclosed. In one embodiment, medical image data of the patient including the stenosis is received, a set of features for the stenosis is extracted from the medical image data of the patient, and an FFR value for the stenosis is determined based on the extracted set of features using a trained machine-learning based mapping. In another embodiment, a medical image of the patient including the stenosis of interest is received, image patches corresponding to the stenosis of interest and a coronary tree of the patient are detected, an FFR value for the stenosis of interest is determined using a trained deep neural network regressor applied directly to the detected image patches.
    Type: Grant
    Filed: March 4, 2019
    Date of Patent: January 12, 2021
    Assignee: Siemens Healthcare GmbH
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • Publication number: 20200412763
    Abstract: Systems and methods are provided for managing network devices using policy graph representations. In some embodiments, the method includes receiving configurations for a plurality of network devices; extracting one or more policies from the configurations; extracting a label hierarchy from the configurations, the label hierarchy describing an organization of nodes in a network comprising the network devices; generating a connectivity of a network comprising the network devices based on the one or more policies and the label hierarchy; generating a policy graph representation of the connectivity of the network; and displaying the policy graph representation of the connectivity to a user.
    Type: Application
    Filed: June 25, 2019
    Publication date: December 31, 2020
    Inventors: ANU MERCIAN, PUNEET SHARMA, CHARLES F. CLARK
  • Patent number: 10878219
    Abstract: Methods and systems for artificial intelligence based medical image segmentation are disclosed. In a method for autonomous artificial intelligence based medical image segmentation, a medical image of a patient is received. A current segmentation context is automatically determined based on the medical image and at least one segmentation algorithm is automatically selected from a plurality of segmentation algorithms based on the current segmentation context. A target anatomical structure is segmented in the medical image using the selected at least one segmentation algorithm.
    Type: Grant
    Filed: July 19, 2017
    Date of Patent: December 29, 2020
    Assignee: Siemens Healthcare GmbH
    Inventors: Shaohua Kevin Zhou, Mingqing Chen, Hui Ding, Bogdan Georgescu, Mehmet Akif Gulsun, Tae Soo Kim, Atilla Peter Kiraly, Xiaoguang Lu, Jin-hyeong Park, Puneet Sharma, Shanhui Sun, Daguang Xu, Zhoubing Xu, Yefeng Zheng