Patents by Inventor Yefeng Zheng

Yefeng Zheng 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).

  • Method and System for Extracting Centerline Representation of Vascular Structures in Medical Images Via Optimal Paths in Computational Flow Fields
    Publication number: 20170258433
    Abstract: A method and apparatus for extracting centerline representations of vascular structures in medical images is disclosed. A vessel orientation tensor for each of a plurality of voxels associated with the target vessel, such as a coronary artery, in a medical image, such as a coronary tomography angiography (CTA) image, using a trained vessel orientation tensor classifier. A flow field is estimated for the plurality of voxels associated with the target vessel in the medical image based on the vessel orientation tensor estimated for each of the plurality of voxels. A centerline of the target vessel is extracted based on the estimated flow field for the plurality of vessels associated with the target vessel in the medical image by detecting a path that carries maximum flow.
    Type: Application
    Filed: March 8, 2017
    Publication date: September 14, 2017
    Inventors: Mehmet Akif Gulsun, Yefeng Zheng, Saikiran Rapaka, Viorel Mihalef, Puneet Sharma, Gareth Funka-Lea
  • Method and System for Machine Learning Based Estimation of Anisotropic Vessel Orientation Tensor
    Publication number: 20170262981
    Abstract: A method and apparatus for machine learning based detection of vessel orientation tensors of a target vessel from a medical image is disclosed. For each of a plurality of voxels in a medical image, such as a computed tomography angiography (CTA), features are extracted from sampling patches oriented to each of a plurality of discrete orientations in the medical image. A classification score is calculated for each of the plurality of discrete orientations at each voxel based on the features extracted from the sampling patches oriented to each of the plurality of discrete orientations using a trained vessel orientation tensor classifier. A vessel orientation tensor at each voxel is calculated based on the classification scores of the plurality of discrete orientations at that voxel.
    Type: Application
    Filed: March 1, 2017
    Publication date: September 14, 2017
    Inventors: Mehmet Akif Gulsun, Yefeng Zheng, Saikiran Rapaka, Gareth Funka-Lea
  • Method and System for Machine Learning Based Classification of Vascular Branches
    Publication number: 20170262733
    Abstract: A method and apparatus for learning based classification of vascular branches to distinguish falsely detected branches from true branches is disclosed. A plurality of overlapping fixed size branch segments are sampled from branches of a detected centerline tree of a target vessel extracted from a medical image of a patient. A plurality of 1D profiles are extracted along each of the overlapping fixed size branch segments. A probability score for each of the overlapping fixed size branch segments is calculated based on the plurality of 1D profiles extracted for each branch segment using a trained deep neural network classifier. The trained deep neural network classifier may be a convolutional neural network (CNN) trained to predict a probability of a branch segment being fully part of a target vessel based on multi-channel 1D input.
    Type: Application
    Filed: March 1, 2017
    Publication date: September 14, 2017
    Inventors: Mehmet Akif Gulsun, Yefeng Zheng, Gareth Funka-Lea, Mingqing Chen
  • Method and system for automatic detection of coronary stenosis in cardiac computed tomography data
    Patent number: 9761004
    Abstract: A method and system for automatic coronary stenosis detection in computed tomography (CT) data is disclosed. Coronary artery centerlines are obtained in an input cardiac CT volume. A trained classifier, such as a probabilistic boosting tree (PBT) classifier, is used to detect stenosis regions along the centerlines in the input cardiac CT volume. The classifier classifies each of the control points that define the coronary artery centerlines as a stenosis point or a non-stenosis point.
    Type: Grant
    Filed: June 18, 2009
    Date of Patent: September 12, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Sushil Mittal, Yefeng Zheng, Bogdan Georgescu, Fernando Vega-Higuera, Dorin Comaniciu
  • Deep image-to-image network learning for medical image analysis
    Patent number: 9760807
    Abstract: A method and apparatus for automatically performing medical image analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image of a patient is received. An output image that provides a result of a target medical image analysis task on the input medical image is automatically generated using a trained deep image-to-image network (DI2IN). The trained DI2IN uses a conditional random field (CRF) energy function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary and pairwise terms of the CRF energy function. The DI2IN may be trained on an image with multiple resolutions. The input image may be split into multiple parts and a separate DI2IN may be trained for each part. Furthermore, the multi-scale and multi-part schemes can be combined to train a multi-scale multi-part DI2IN.
    Type: Grant
    Filed: December 16, 2016
    Date of Patent: September 12, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: S. Kevin Zhou, Dorin Comaniciu, Bogdan Georgescu, Yefeng Zheng, David Liu, Daguang Xu
  • Method and system for improved hemodynamic computation in coronary arteries
    Patent number: 9747525
    Abstract: Systems and methods for non-invasive assessment of an arterial stenosis, comprising include segmenting a plurality of mesh candidates for an anatomical model of an artery including a stenosis region of a patient from medical imaging data. A hemodynamic index for the stenosis region is computed in each of the plurality of mesh candidates. It is determined whether a variation among values of the hemodynamic index for the stenosis region in each of the plurality of mesh candidates is significant with respect to a threshold associated with a clinical decision regarding the stenosis region.
    Type: Grant
    Filed: May 7, 2015
    Date of Patent: August 29, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Frank Sauer, Yefeng Zheng, Puneet Sharma, Bogdan Georgescu
  • Method and system for anatomical object detection using marginal space deep neural networks
    Patent number: 9730643
    Abstract: A method and system for anatomical object detection using marginal space deep neural networks is disclosed. The pose parameter space for an anatomical object is divided into a series of marginal search spaces with increasing dimensionality. A respective sparse deep neural network is trained for each of the marginal search spaces, resulting in a series of trained sparse deep neural networks. Each of the trained sparse deep neural networks is trained by injecting sparsity into a deep neural network by removing filter weights of the deep neural network.
    Type: Grant
    Filed: February 26, 2016
    Date of Patent: August 15, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Bogdan Georgescu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh, Dorin Comaniciu, David Liu
  • Method and system for automatic aorta segmentation
    Patent number: 9715637
    Abstract: A method and system for aorta segmentation in a 3D volume, such as a C-arm CT volume is disclosed. The aortic root is detected in the 3D volume using marginal space learning (MSL) based segmentation. The aortic arch is detected in the 3D volume using MSL based segmentation. The ascending aorta is tracked from the aortic root to the aortic arch in the 3D volume, and the descending aorta is tracked from the aortic arch in the 3D volume.
    Type: Grant
    Filed: March 17, 2010
    Date of Patent: July 25, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Yefeng Zheng, Bogdan Georgescu, Matthias John, Jan Boese, Dorin Comaniciu
  • Deep Image-to-Image Network Learning for Medical Image Analysis
    Publication number: 20170200067
    Abstract: A method and apparatus for automatically performing medical image analysis tasks using deep image-to-image network (DI2IN) learning. An input medical image of a patient is received. An output image that provides a result of a target medical image analysis task on the input medical image is automatically generated using a trained deep image-to-image network (DI2IN). The trained DI2IN uses a conditional random field (CRF) energy function to estimate the output image based on the input medical image and uses a trained deep learning network to model unary and pairwise terms of the CRF energy function. The DI2IN may be trained on an image with multiple resolutions. The input image may be split into multiple parts and a separate DI2IN may be trained for each part. Furthermore, the multi-scale and multi-part schemes can be combined to train a multi-scale multi-part DI2IN.
    Type: Application
    Filed: December 16, 2016
    Publication date: July 13, 2017
    Inventors: S. Kevin Zhou, Dorin Comaniciu, Bogdan Georgescu, Yefeng Zheng, David Liu, Daguang Xu
  • Method and system for machine learning based assessment of fractional flow reserve
    Patent number: 9700219
    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: October 16, 2014
    Date of Patent: July 11, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • System and Method For Learning Based Magnetic Resonance Fingerprinting
    Publication number: 20170160363
    Abstract: A learning-based magnetic resonance fingerprinting (MRF) reconstruction method for reconstructing an MR image of a tissue space in an MR scan subject for a particular MR sequence is disclosed. The method involves using a machine-learning algorithm that has been trained to generate a set of tissue parameters from acquired MR signal evolution without using a dictionary or dictionary matching.
    Type: Application
    Filed: December 8, 2016
    Publication date: June 8, 2017
    Inventors: Xiao Chen, Boris Mailhe, Qiu Wang, Shaohua Kevin Zhou, Yefeng Zheng, Xiaoguang Lu, Puneet Sharma, Benjamin L. Odry, Bogdan Georgescu, Mariappan S. Nadar
  • Method and system for anatomical object detection using marginal space deep neural networks
    Patent number: 9668699
    Abstract: A method and system for anatomical object detection using marginal space deep neural networks is disclosed. The pose parameter space for an anatomical object is divided into a series of marginal search spaces with increasing dimensionality. A respective deep neural network is trained for each of the marginal search spaces, resulting in a series of trained deep neural networks. Each of the trained deep neural networks can evaluate hypotheses in a current parameter space using discriminative classification or a regression function. An anatomical object is detected in a medical image by sequentially applying the series of trained deep neural networks to the medical image.
    Type: Grant
    Filed: May 12, 2015
    Date of Patent: June 6, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Bogdan Georgescu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh, Dorin Comaniciu, David Liu
  • Computer-aided analysis of medical images
    Patent number: 9642586
    Abstract: A pair of medical images is analyzed, the pair including a first image, which is a contrasted scan of a part in a human or animal body, and a second image, which is a native scan of the same part of the human or animal body. Anatomic structures are identified within both the first image and the second image. By using those anatomic structures, centerlines of vessels in the first image are mapped to the second image. Candidate calcified plaques are extracted in the second image, and calcified plaques out of the candidate calcified plaques are identified by a machine learning classifier. The positional information of the centerlines in the second image is used for extracting the candidate calcified plaques in the second image and/or for identifying the calcified plaques out of the candidate calcified plaques by the machine learning classifier.
    Type: Grant
    Filed: August 18, 2014
    Date of Patent: May 9, 2017
    Assignee: Siemens Aktiengesellschaft
    Inventors: Michael Kelm, Yefeng Zheng
  • Intelligent Multi-scale Medical Image Landmark Detection
    Publication number: 20170116497
    Abstract: Intelligent multi-scale image parsing determines the optimal size of each observation by an artificial agent at a given point in time while searching for the anatomical landmark. The artificial agent begins searching image data with a coarse field-of-view and iteratively decreases the field-of-view to locate the anatomical landmark. After searching at a coarse field-of view, the artificial agent increases resolution to a finer field-of-view to analyze context and appearance factors to converge on the anatomical landmark. The artificial agent determines applicable context and appearance factors at each effective scale.
    Type: Application
    Filed: January 3, 2017
    Publication date: April 27, 2017
    Inventors: Bogdan Georgescu, Florin Cristian Ghesu, Yefeng Zheng, Dominik Neumann, Tommaso Mansi, Dorin Comaniciu, Wen Liu, Shaohua Kevin Zhou
  • Method and system for approximating deep neural networks for anatomical object detection
    Patent number: 9633306
    Abstract: A method and system for approximating a deep neural network for anatomical object detection is discloses. A deep neural network is trained to detect an anatomical object in medical images. An approximation of the trained deep neural network is calculated that reduces the computational complexity of the trained deep neural network. The anatomical object is detected in an input medical image of a patient using the approximation of the trained deep neural network.
    Type: Grant
    Filed: May 7, 2015
    Date of Patent: April 25, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: David Liu, Nathan Lay, Shaohua Kevin Zhou, Jan Kretschmer, Hien Nguyen, Vivek Kumar Singh, Yefeng Zheng, Bogdan Georgescu, Dorin Comaniciu
  • Sparse appearance learning-based segmentation
    Patent number: 9594976
    Abstract: The coronary sinus or other vessel is segmented by finding a centerline and then using the centerline to locate the boundary of the vessel. For finding the centerline, a refinement process uses multi-scale sparse appearance learning. For locating the boundary, the lumen is segmented as a graph cut problem.
    Type: Grant
    Filed: February 6, 2015
    Date of Patent: March 14, 2017
    Assignee: SIEMENS HEALTHCARE GMBH
    Inventors: Yefeng Zheng, Shiyang Lu, Xiaojie Huang
  • Method and system for efficient extraction of a silhouette of a 3D mesh
    Patent number: 9582934
    Abstract: A method and system for extracting a silhouette of a 3D mesh representing an anatomical structure is disclosed. The 3D mesh is projected to two dimensions. Silhouette candidate edges are generated in the projected mesh by pruning edges and mesh points based on topology analysis of the projected mesh. Each silhouette candidate edge that intersects with another edge in the projected mesh is split into two silhouette candidate edges. The silhouette is extracted using an edge following process on the silhouette candidate edges.
    Type: Grant
    Filed: September 19, 2011
    Date of Patent: February 28, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Yefeng Zheng, Yu Pang, Rui Liao, Matthias John, Jan Boese, Shaohua Kevin Zhou, Dorin Comaniciu
  • Method and system for physiological image registration and fusion
    Patent number: 9547902
    Abstract: A method and system for physiological image registration and fusion is disclosed. A physiological model of a target anatomical structure in estimated each of a first image and a second image. The physiological model is estimated using database-guided discriminative machine learning-based estimation. A fused image is then generated by registering the first and second images based on correspondences between the physiological model estimated in each of the first and second images.
    Type: Grant
    Filed: September 18, 2009
    Date of Patent: January 17, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Razvan Ionasec, Bogdan Georgescu, Yefeng Zheng, Dorin Comaniciu
  • Method and system for machine learning based assessment of fractional flow reserve
    Patent number: 9538925
    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 13, 2015
    Date of Patent: January 10, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • Method and System for Approximating Deep Neural Networks for Anatomical Object Detection
    Publication number: 20160328643
    Abstract: A method and system for approximating a deep neural network for anatomical object detection is discloses. A deep neural network is trained to detect an anatomical object in medical images. An approximation of the trained deep neural network is calculated that reduces the computational complexity of the trained deep neural network. The anatomical object is detected in an input medical image of a patient using the approximation of the trained deep neural network.
    Type: Application
    Filed: May 7, 2015
    Publication date: November 10, 2016
    Inventors: David Liu, Nathan Lay, Shaohua Kevin Zhou, Jan Kretschmer, Hien Nguyen, Vivek Kumar Singh, Yefeng Zheng, Bogdan Georgescu, Dorin Comaniciu