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 machine learning based classification of vascular branches
    Patent number: 10115039
    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: Grant
    Filed: March 1, 2017
    Date of Patent: October 30, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Mehmet Akif Gulsun, Yefeng Zheng, Gareth Funka-Lea, Mingqing Chen
  • METHOD AND SYSTEM FOR MACHINE LEARNING BASED ASSESSMENT OF FRACTIONAL FLOW RESERVE
    Publication number: 20180242857
    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: Application
    Filed: April 20, 2018
    Publication date: August 30, 2018
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • Deep image-to-image network learning for medical image analysis
    Patent number: 10062014
    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: June 9, 2017
    Date of Patent: August 28, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: S. Kevin Zhou, Dorin Comaniciu, Bogdan Georgescu, Yefeng Zheng, David Liu, Daguang Xu
  • Method and system for pigtail catheter motion prediction
    Patent number: 9999399
    Abstract: A method and system for autoregressive model based pigtail catheter motion prediction in a fluoroscopic image sequence is disclosed. Parameters of an autoregressive model are estimated based on observed pigtail catheter tip positions in a plurality of previous frames of a fluoroscopic image sequence. A pigtail catheter tip position in a current frame of the fluoroscopic image sequence is predicted using the fitted autoregressive model. The predicted pigtail catheter tip position can be used to constrain pigtail catheter tip detection in the current frame. The predicted pigtail catheter tip position may also be used to predict abnormal motion in the fluoroscopic image sequence.
    Type: Grant
    Filed: November 16, 2011
    Date of Patent: June 19, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Yu Pang, Yefeng Zheng, Matthias John, Jan Boese, Dorin Comaniciu
  • Method and system for machine learning based assessment of fractional flow reserve
    Patent number: 9974454
    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: June 7, 2017
    Date of Patent: May 22, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • ATLAS-BASED CONTOURING OF ORGANS AT RISK FOR RADIATION THERAPY
    Publication number: 20180096478
    Abstract: Embodiments can provide a method for atlas-based contouring, comprising constructing a relevant atlas database; selecting one or more optimal atlases from the relevant atlas database; propagating one or more atlases; fusing the one or more atlases; and assessing the quality of one or more propagated contours.
    Type: Application
    Filed: June 16, 2017
    Publication date: April 5, 2018
    Inventors: Li Zhang, Shanhui Sun, Shaohua Kevin Zhou, Daguang Xu, Zhoubing Xu, Tommaso Mansi, Ying Chi, Yefeng Zheng, Pavlo Dyban, Nora Hünemohr, Julian Krebs, David Liu
  • METHOD AND SYSTEM FOR LANDMARK DETECTION IN MEDICAL IMAGES USING DEEP NEURAL NETWORKS
    Publication number: 20180089530
    Abstract: A method and system for anatomical landmark detection in medical images using deep neural networks is disclosed. For each of a plurality of image patches centered at a respective one of a plurality of voxels in the medical image, a subset of voxels within the image patch is input to a trained deep neural network based on a predetermined sampling pattern. A location of a target landmark in the medical image is detected using the trained deep neural network based on the subset of voxels input to the trained deep neural network from each of the plurality of image patches.
    Type: Application
    Filed: May 11, 2015
    Publication date: March 29, 2018
    Inventors: David Liu, Bogdan Georgescu, Yefeng Zheng, Hien Nguyen, Shaohua Kevin Zhou, Vivek Kumar Singh, Dorin Comaniciu
  • Deep similarity learning for multimodal medical images
    Patent number: 9922272
    Abstract: The present embodiments relate to machine learning for multimodal image data. By way of introduction, the present embodiments described below include apparatuses and methods for learning a similarity metric using deep learning based techniques for multimodal medical images. A novel similarity metric for multi-modal images is provided using the corresponding states of pairs of image patches to generate a classification setting for each pair. The classification settings are used to train a deep neural network via supervised learning. A multi-modal stacked denoising auto encoder (SDAE) is used to pre-train the neural network. A continuous and smooth similarity metric is constructed based on the output of the neural network before activation in the last layer. The trained similarity metric may be used to improve the results of image fusion.
    Type: Grant
    Filed: September 25, 2015
    Date of Patent: March 20, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Xi Cheng, Li Zhang, Yefeng Zheng
  • Unsupervised Deep Representation Learning for Fine-grained Body Part Recognition
    Publication number: 20180060652
    Abstract: A method and apparatus for deep learning based fine-grained body part recognition in medical imaging data is disclosed. A paired convolutional neural network (P-CNN) for slice ordering is trained based on unlabeled training medical image volumes. A convolutional neural network (CNN) for fine-grained body part recognition is trained by fine-tuning learned weights of the trained P-CNN for slice ordering. The CNN for fine-grained body part recognition is trained to calculate, for an input transversal slice of a medical imaging volume, a normalized height score indicating a normalized height of the input transversal slice in the human body.
    Type: Application
    Filed: August 29, 2017
    Publication date: March 1, 2018
    Inventors: Pengyue Zhang, Yefeng Zheng
  • Method and system for vascular disease detection using recurrent neural networks
    Patent number: 9881372
    Abstract: A method and apparatus for vascular disease detection and characterization using a recurrent neural network (RNN) is disclosed. A plurality of 2D cross-section image patches are extracted from a 3D computed tomography angiography (CTA) image, each extracted at a respective sampling point along a vessel centerline of a vessel of interest in the 3D CTA image. Vascular abnormalities in the vessel of interest are detected and characterized by classifying each of the sampling points along the vessel centerline based on the plurality of 2D cross-section image patches using a trained RNN.
    Type: Grant
    Filed: August 18, 2017
    Date of Patent: January 30, 2018
    Assignee: Siemens Healthcare GmbH
    Inventors: Mehmet A. Gulsun, Yefeng Zheng, Puneet Sharma, Bogdan Georgescu, Dorin Comaniciu
  • INTELLIGENT MULTI-SCALE MEDICAL IMAGE LANDMARK DETECTION
    Publication number: 20180005083
    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: August 29, 2017
    Publication date: January 4, 2018
    Inventors: Bogdan Georgescu, Florin Cristian Ghesu, Yefeng Zheng, Dominik Neumann, Tommaso Mansi, Dorin Comaniciu, Wen Liu, Shaohua Kevin Zhou
  • Method and System for Vascular Disease Detection Using Recurrent Neural Networks
    Publication number: 20170372475
    Abstract: A method and apparatus for vascular disease detection and characterization using a recurrent neural network (RNN) is disclosed. A plurality of 2D cross-section image patches are extracted from a 3D computed tomography angiography (CTA) image, each extracted at a respective sampling point along a vessel centerline of a vessel of interest in the 3D CTA image. Vascular abnormalities in the vessel of interest are detected and characterized by classifying each of the sampling points along the vessel centerline based on the plurality of 2D cross-section image patches using a trained RNN.
    Type: Application
    Filed: August 18, 2017
    Publication date: December 28, 2017
    Inventors: Mehmet A. Gulsun, Yefeng Zheng, Puneet Sharma, Bogdan Georgescu, Dorin Comaniciu
  • Method and system for model-based fusion of multi-modal volumetric images
    Patent number: 9824302
    Abstract: A method and system for fusion of multi-modal volumetric images is disclosed. A first image acquired using a first imaging modality is received. A second image acquired using a second imaging modality is received. A model and of a target anatomical structure and a transformation are jointly estimated from the first and second images. The model represents a model of the target anatomical structure in the first image and the transformation projects a model of the target anatomical structure in the second image to the model in the first image. The first and second images can be fused based on estimated transformation.
    Type: Grant
    Filed: March 6, 2012
    Date of Patent: November 21, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Sasa Grbic, Razvan Ioan Ionasec, Yang Wang, Bogdan Georgescu, Tommaso Mansi, Dorin Comaniciu, Yefeng Zheng, Shaohua Kevin Zhou, Matthias John, Jan Boese
  • Method and System for Improved Hemodynamic Computation in Coronary Arteries
    Publication number: 20170323177
    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: Application
    Filed: July 28, 2017
    Publication date: November 9, 2017
    Inventors: Frank Sauer, Yefeng Zheng, Puneet Sharma, Bogdan Georgescu
  • Method and system for segmentation of brain structures in 3D magnetic resonance images
    Patent number: 9805473
    Abstract: A method and system for segmenting multiple brain structures in 3D magnetic resonance (MR) images is disclosed. After intensity standardization of a 3D MR image, a meta-structure including center positions of multiple brain structures is detected in the 3D MR image. The brain structures are then individually segmented using marginal space learning (MSL) constrained by the detected meta-structure.
    Type: Grant
    Filed: September 14, 2009
    Date of Patent: October 31, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Michael Wels, Gustavo Henrique Monteiro de Barros Carneiro, Martin Huber, Dorin Comaniciu, Yefeng Zheng
  • Intelligent multi-scale medical image landmark detection
    Patent number: 9792531
    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: Grant
    Filed: January 3, 2017
    Date of Patent: October 17, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Bogdan Georgescu, Florin Cristian Ghesu, Yefeng Zheng, Dominik Neumann, Tommaso Mansi, Dorin Comaniciu, Wen Liu, Shaohua Kevin Zhou
  • Deep Image-to-Image Network Learning for Medical Image Analysis
    Publication number: 20170277981
    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: June 9, 2017
    Publication date: September 28, 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
    Publication number: 20170265754
    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: Application
    Filed: June 7, 2017
    Publication date: September 21, 2017
    Inventors: Puneet Sharma, Ali Kamen, Bogdan Georgescu, Frank Sauer, Dorin Comaniciu, Yefeng Zheng, Hien Nguyen, Vivek Kumar Singh
  • Multi-layer aggregation for object detection
    Patent number: 9767385
    Abstract: Object detection uses a deep or multiple layer network to learn features for detecting the object in the image. Multiple features from different layers are aggregated to train a classifier for the object. In addition or as an alternative to feature aggregation from different layers, an initial layer may have separate learnt nodes for different regions of the image to reduce the number of free parameters. The object detection is learned or a learned object detector is applied.
    Type: Grant
    Filed: August 12, 2014
    Date of Patent: September 19, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Hien Nguyen, Vivek Kumar Singh, Yefeng Zheng, Bogdan Georgescu, Dorin Comaniciu, Shaohua Kevin Zhou
  • Method and system for vascular disease detection using recurrent neural networks
    Patent number: 9767557
    Abstract: A method and apparatus for vascular disease detection and characterization using a recurrent neural network (RNN) is disclosed. A plurality of 2D cross-section image patches are extracted from a 3D computed tomography angiography (CTA) image, each extracted at a respective sampling point along a vessel centerline of a vessel of interest in the 3D CTA image. Vascular abnormalities in the vessel of interest are detected and characterized by classifying each of the sampling points along the vessel centerline based on the plurality of 2D cross-section image patches using a trained RNN.
    Type: Grant
    Filed: February 10, 2017
    Date of Patent: September 19, 2017
    Assignee: Siemens Healthcare GmbH
    Inventors: Mehmet A. Gulsun, Yefeng Zheng, Puneet Sharma, Bogdan Georgescu, Dorin Comaniciu