Patents by Inventor Dorin Comaniciu

Dorin Comaniciu 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: 20190172207
    Abstract: A method of reviewing neural scans includes receiving at least one landmark corresponding to an anatomical region. A plurality of images of tissue including the anatomical region is received and a neural network configured to differentiate between healthy tissue and unhealthy tissue within the anatomical region is generated. The neural network is generated by a machine learning process configured to receive the plurality of images of tissue and generate a plurality of weighting factors configured to differentiate between healthy tissue and unhealthy tissue. At least one patient image of tissue including the anatomical region is received and a determination is made by the neural network whether the at least one patient image of tissue includes healthy or unhealthy tissue.
    Type: Application
    Filed: December 5, 2017
    Publication date: June 6, 2019
    Inventors: Benjamin L. Odry, Hasan Ertan Cetingul, Mariappan S. Nadar, Puneet Sharma, Shaohua Kevin Zhou, Dorin Comaniciu
  • Patent number: 10311978
    Abstract: A method and system for patient-specific planning of cardiac therapy, such as cardiac resynchronization therapy (CRT), based on preoperative clinical data and medical images, such as ECG data, magnetic resonance imaging (MRI) data, and ultrasound data, is disclosed. A patient-specific anatomical model of the left and right ventricles is generated from medical image data of a patient. A patient-specific computational heart model, which comprises cardiac electrophysiology, biomechanics and hemodynamics, is generated based on the patient-specific anatomical model of the left and right ventricles and clinical data. Simulations of cardiac therapies, such as CRT at one or more anatomical locations are performed using the patient-specific computational heart model. Changes in clinical cardiac parameters are then computed from the patient-specific model, constituting predictors of therapy outcome useful for therapy planning and optimization.
    Type: Grant
    Filed: January 30, 2013
    Date of Patent: June 4, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Tommaso Mansi, Bogdan Georgescu, Xudong Zheng, Ali Kamen, Dorin Comaniciu
  • Patent number: 10311373
    Abstract: A method for subject-specific assessment of neurological disorders, the method includes receiving 3D image data representative of a subject's brain and identifying subject-specific anatomical structures in the 3D image data. A subject-specific model for electrical dynamics is created based on the 3D image data and the subject-specific anatomical structures and one or more functional indicators of neurological disorder are computed using the subject-specific model for electrical dynamics.
    Type: Grant
    Filed: April 16, 2015
    Date of Patent: June 4, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Saikiran Rapaka, Hasan Ertan Cetingul, Francisco Pereira, Dorin Comaniciu, Alma Gregory Sorensen
  • Patent number: 10296809
    Abstract: A method and system for patient-specific cardiac electrophysiology is disclosed. Particularly, a patient-specific anatomical model of a heart is generated from medical image data of a patient, a level-set representation of the patient-specific anatomical model is generated of the heart on a Cartesian grid; and a transmembrane action potential at each node of the level-set representation of the of the patient-specific anatomical model of the heart is computed on a Cartesian grid.
    Type: Grant
    Filed: February 28, 2013
    Date of Patent: May 21, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Saikiran Rapaka, Tommaso Mansi, Bogdan Georgescu, Ali Kamen, Dorin Comaniciu
  • Patent number: 10297341
    Abstract: A method for modeling a blood vessel includes: (a) modeling a first segment of the blood vessel based on medical imaging data acquired from a subject; (b) computing a first modeling parameter at an interior point of the first segment; and (c) computing a second modeling parameter at a boundary point of the first segment using a viscoelastic wall model. Systems for modeling a blood vessel are described.
    Type: Grant
    Filed: September 12, 2013
    Date of Patent: May 21, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Lucian Mihai Itu, Puneet Sharma, Ali Kamen, Dorin Comaniciu
  • Patent number: 10297027
    Abstract: Anatomy, such as papillary muscle, is automatically detected (34) and/or detected in real-time. For automatic detection (34) of small anatomy, machine-learnt classification with spatial (32) and temporal (e.g., Markov) (34) constraints is used. For real-time detection, sparse machine-learnt detection (34) interleaved with optical flow tracking (38) is used.
    Type: Grant
    Filed: June 8, 2015
    Date of Patent: May 21, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Mihai Scutaru, Ingmar Voigt, Tommaso Mansi, Razvan Ionasec, Helene C. Houle, Anand Vinod Tatpati, Dorin Comaniciu, Bogdan Georgescu, Noha Youssry El-Zehiry
  • Patent number: 10296707
    Abstract: A method and system for image-based patient-specific guidance of cardiac arrhythmia therapies is disclosed. A patient-specific anatomical heart model is generated from medical image data of a patient. A patient-specific cardiac electrophysiology model is generated based on the patient-specific anatomical heart model and electrophysiology measurements of the patient. One or more virtual electrophysiological interventions are performed using the patient-specific cardiac electrophysiology model. One or more pacing targets or ablation targets based on the one or more virtual electrophysiological interventions are displayed.
    Type: Grant
    Filed: April 10, 2015
    Date of Patent: May 21, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Tiziano Passerini, Tommaso Mansi, Ali Kamen, Bogdan Georgescu, Dorin Comaniciu
  • Publication number: 20190142358
    Abstract: A method for generating a nuclear image includes obtaining, via a camera, a surface image of a patient. A synthetic computed-tomography (CT) image of the patient is generated based on the surface image. First time-of-flight (TOF) data for the patient is obtained via a nuclear imaging modality. Attenuation correction is applied to the first TOF data. The synthetic image is applied as a density map during the attenuation correction. A nuclear image is generated from the attenuation corrected first TOF data.
    Type: Application
    Filed: November 13, 2017
    Publication date: May 16, 2019
    Inventors: Terrence Chen, Vivek Kumar Singh, Klaus J. Kirchberg, Vladimir Y. Panin, Dorin Comaniciu
  • Publication number: 20190139216
    Abstract: For object detection, deep learning is applied with an architecture designed for low contrast objects, such as lymph nodes. The architecture uses a combination of dense deep learning or features, which employs feed-forward connections between convolutions layers, and a pyramidal arrangement of the dense deep learning using different resolutions.
    Type: Application
    Filed: November 3, 2017
    Publication date: May 9, 2019
    Inventors: Bogdan Georgescu, Eric Wengrowski, Siqi Liu, Daguang Xu, Dorin Comaniciu, Shaohua Kevin Zhou
  • Patent number: 10282588
    Abstract: Machine training and application of machine-trained classifier are used for image-based tumor phenotyping in a medical system. To create a training database with known phenotype information, synthetic medical images are created. A computational tumor model creates various examples of tumors in tissue. Using the computational tumor model allows one to create examples not available from actual patients, increasing the number and variance of examples used for machine-learning to predict tumor phenotype. A model of an imaging system generates synthetic images from the examples. The machine-trained classifier is applied to images from actual patients to predict tumor phenotype for that patient based on the knowledge learned from the synthetic images.
    Type: Grant
    Filed: May 2, 2017
    Date of Patent: May 7, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Dorin Comaniciu, Ali Kamen, David Liu, Boris Mailhe, Tommaso Mansi
  • Publication number: 20190130067
    Abstract: A computer-implemented method for executing patient management workflows includes acquiring a pre-test dataset of clinically relevant information related to a patient and using a first intelligent agent to identify a diagnostic test for the patient based on the pre-test dataset. Following performance of the diagnostic test, a second intelligent agent is used to select a processing technique to be applied to data collected from the diagnostic test to obtain a diagnostic marker. Following application of the processing technique to the data collected from the diagnostic test, a third intelligent agent is used to generate an optimal patient management plan based on the pre-test dataset, the data collected from the diagnostic test, and the diagnostic marker.
    Type: Application
    Filed: October 27, 2017
    Publication date: May 2, 2019
    Inventors: Tiziano Passerini, Puneet Sharma, Dorin Comaniciu
  • Publication number: 20190125295
    Abstract: For cardiac flow detection in echocardiography, by detecting one or more valves, sampling planes or flow regions spaced from the valve and/or based on multiple valves are identified. A confidence of the detection may be used to indicate confidence of calculated quantities and/or to place the sampling planes.
    Type: Application
    Filed: October 30, 2017
    Publication date: May 2, 2019
    Inventors: Huseyin Tek, Bogdan Georgescu, Tommaso Mansi, Frank Sauer, Dorin Comaniciu, Helene C. Houle, Ingmar Voigt
  • Publication number: 20190130562
    Abstract: A computer-implemented method for identifying features in 3D image volumes includes dividing a 3D volume into a plurality of 2D slices and applying a pre-trained 2D multi-channel global convolutional network (MC-GCN) to the plurality of 2D slices until convergence. Following convergence of the 2D MC-GCN, a plurality of parameters are extracted from a first feature encoder network in the 2D MC-GCN. The plurality of parameters are transferred to a second feature encoder network in a 3D Anisotropic Hybrid Network (AH-Net). The 3D AH-Net is applied to the 3D volume to yield a probability map;. Then, using the probability map, one or more of (a) coordinates of the objects with non-maximum suppression or (b) a label map of objects of interest in the 3D volume are generated.
    Type: Application
    Filed: June 4, 2018
    Publication date: May 2, 2019
    Inventors: Siqi Liu, Daguang Xu, Shaohua Kevin Zhou, Thomas Mertelmeier, Julia Wicklein, Anna Jerebko, Sasa Grbic, Olivier Pauly, Dorin Comaniciu
  • Patent number: 10271817
    Abstract: A regurgitant orifice of a valve is detected. The valve is detected from ultrasound data. An anatomical model of the valve is fit to the ultrasound data. This anatomical model may be used in various ways to assist in valvular assessment. The model may define anatomical locations about which data is sampled for quantification. The model may assist in detection of the regurgitant orifice using both B-mode and color Doppler flow data with visualization without the jet. Segmentation of a regurgitant jet for the orifice may be constrained by the model. Dynamic information may be determined based on the modeling of the valve over time.
    Type: Grant
    Filed: June 10, 2015
    Date of Patent: April 30, 2019
    Assignee: Siemens Medical Solutions USA, Inc.
    Inventors: Ingmar Voigt, Tommaso Mansi, Bogdan Georgescu, Helene C Houle, Dorin Comaniciu, Codruta-Xenia Ene, Mihai Scutaru
  • Publication number: 20190120918
    Abstract: A computer-implemented method for decoding brain imaging data of individual subjects by using additional imaging data from other subjects includes receiving a plurality of functional Magnetic Resonance Imaging (fMRI) datasets corresponding to a plurality of subjects. Each fMRI dataset corresponds to a distinct subject and comprises brain activation patterns resulting from presentation of a plurality of stimuli to the distinct subject. A group dimensionality reduction (GDR) technique is applied to the example fMRI datasets to yield a low-dimensional space of response variables shared by the plurality of subjects. A model is trained to predict a set of target variables based on the low-dimensional space of response variables shared by all subjects, wherein the set of target variables comprise one or more characteristics of the plurality of stimuli.
    Type: Application
    Filed: October 25, 2017
    Publication date: April 25, 2019
    Inventors: Francisco Pereira, Ahmet Tuysuzoglu, Bin Lou, Tommaso Mansi, Dorin Comaniciu
  • Publication number: 20190117072
    Abstract: A computer-implemented method for decoding patient characteristics and brain state from multi-modality brain imaging data includes receiving a plurality of brain imaging datasets comprising brain imaging data corresponding to plurality of subjects. The brain imaging datasets are aligned to a common reference space and quantitative measures are extracted from each brain imaging dataset. Non-imaging characteristics corresponding to each subject are received and a forward model is trained to map the plurality of characteristics to the quantitative measures.
    Type: Application
    Filed: October 24, 2017
    Publication date: April 25, 2019
    Inventors: Francisco Pereira, Bin Lou, Ahmet Tuysuzoglu, Tommaso Mansi, Dorin Comaniciu
  • Patent number: 10268915
    Abstract: A method for real-time collimation and ROI-filter positioning in X-ray imaging in interventional procedures includes acquiring an image of a region-of-interest (ROI) at a beginning of a medical intervention procedure on a subject, classifying the image based on low-level features in the image to determine a type of procedure being performed, determining a list of landmarks in the image from the type of procedure being performed, and loading a pre-trained landmark model for each landmark in the list of landmarks, where landmarks include anatomical structures of the subject and medical devices being used in the medical intervention procedure, and computing collimator settings of an X-ray imaging device from ROI filter margins and bounding boxes of the landmarks calculated using the landmark models.
    Type: Grant
    Filed: June 9, 2015
    Date of Patent: April 23, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Wen Wu, Terrence Chen, Anton Nekovar, Martin Ostermeier, Dorin Comaniciu
  • Patent number: 10258244
    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: April 20, 2018
    Date of Patent: April 16, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • Patent number: 10241968
    Abstract: A method and system for simulating patient-specific cardiac electrophysiology including the effect of the electrical conduction system of the heart is disclosed. A patient-specific anatomical heart model is generated from cardiac image data of a patient. The electrical conduction system of the heart of the patient is modeled by determining electrical diffusivity values of cardiac tissue based on a distance of the cardiac tissue from the endocardium. A distance field from the endocardium surface is calculated with sub-grid accuracy using a nested-level set approach. Cardiac electrophysiology for the patient is simulated using a cardiac electrophysiology model with the electrical diffusivity values determined to model the Purkinje network of the patient.
    Type: Grant
    Filed: February 17, 2015
    Date of Patent: March 26, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Tiziano Passerini, Tommaso Mansi, Ali Kamen, Bogdan Georgescu, Saikiran Rapaka, Dorin Comaniciu
  • Patent number: 10210613
    Abstract: The present embodiments relate to detecting multiple landmarks in medical images. By way of introduction, the present embodiments described below include apparatuses and methods for detecting landmarks using hierarchical feature learning with end-to-end training. Multiple neural networks are provided with convolutional layers for extracting features from medical images and with a convolutional layer for learning spatial relationships between the extracted features. Each neural network is trained to detect different landmarks using a different resolution of the medical images, and the convolutional layers of each neural network are trained together with end-to-end training to learn appearance and spatial configuration simultaneously. The trained neural networks detect multiple landmarks in a test image iteratively by detecting landmarks at different resolutions, using landmarks detected a lesser resolutions to detect additional landmarks at higher resolutions.
    Type: Grant
    Filed: May 10, 2017
    Date of Patent: February 19, 2019
    Assignee: Siemens Healthcare GmbH
    Inventors: Daguang Xu, Tao Xiong, David Liu, Shaohua Kevin Zhou, Mingqing Chen, Dorin Comaniciu