公开(公告)号：US10595803B2

公开(公告)日：2020-03-24

申请号：US15263565

申请日：2016-09-13

Applicant: General Electric Company

Inventor： Xue Rui ,  Mingye Wu ,  Yannan Jin ,  Peter Michael Edic ,  Bruno Kristiaan Bernard De Man

IPC: A61B6/00 ,  A61B6/03

Abstract: A signal processing method is disclosed, which includes detecting a total intensity of X-rays passing through an object comprising multiple materials; obtaining at least one set of basis information of basis material information of the multiple materials and basis component information of photon-electric absorption basis component and Compton scattering basis component of the object; estimating a scatter intensity component of the detected X-rays based on the at least one set of basis information and the detected total intensity; and obtaining an intensity estimate of primary X-rays incident on a detector based on the detected total intensity and the estimated scatter intensity component. An imaging system adopting the above signal processing method is also disclosed.

公开(公告)号：US10475214B2

公开(公告)日：2019-11-12

申请号：US15480172

申请日：2017-04-05

Applicant: General Electric Company

Inventor： Lin Fu ,  Sathish Ramani ,  Bruno Kristiaan Bernard De Man ,  Xue Rui ,  Sangtae Ahn

IPC: G06K9/66 ,  G06T11/00

Abstract: The present approach relates to the use of machine learning and deep learning systems suitable for solving large-scale, space-variant tomographic reconstruction and/or correction problems. In certain embodiments, a tomographic transform of measured data obtained from a tomography scanner is used as an input to a neural network. In accordance with certain aspects of the present approach, the tomographic transform operation(s) is performed separate from or outside the neural network such that the result of the tomographic transform operation is instead provided as an input to the neural network. In addition, in certain embodiments, one or more layers of the neural network may be provided as wavelet filter banks.

公开(公告)号：US10222489B2

公开(公告)日：2019-03-05

申请号：US15457558

申请日：2017-03-13

Applicant: General Electric Company

Inventor： Geng Fu ,  Xue Rui ,  Yannan Jin ,  Jianjun Guo ,  Peter Michael Edic ,  Brian David Yanoff

IPC: G01T1/24 ,  G01T1/36 ,  G01T7/00

Abstract: The present approach relates to the use of reference pixels provided between the primary pixels of a detector panel. Coincidence circuitry or logic may be employed so that the measured signal arising from the same X-ray event may be properly, that is the signal measured at both a reference and primary pixel may be combined so as to provide an accurate estimate of the measured signal, at an appropriate location on the detector panel.

公开(公告)号：US20180330233A1

公开(公告)日：2018-11-15

申请号：US15593157

申请日：2017-05-11

Applicant: General Electric Company

Inventor： Xue Rui ,  Hua Qian ,  Hao Lai ,  Bruno Kristiaan Bernard De Man ,  John Eric Tkaczyk

IPC: G06N3/08 ,  G06F17/50 ,  G06F19/00 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F17/5009 ,  G06F19/321 ,  G06F2217/16 ,  G06N3/04 ,  G06T5/00

Abstract: The present approach relates to the use of machine-learning in convolution kernel design for scatter correction. In one aspect, a neural network is trained to replace or improve the convolution kernel used for scatter correction. The training data set may be generated probabilistically so that actual measurements are not employed.

公开(公告)号：US20180328863A1

公开(公告)日：2018-11-15

申请号：US15591926

申请日：2017-05-10

Applicant: General Electric Company

Inventor： Xue Rui ,  Yannan Jin ,  Biju Jacob ,  Brian David Yanoff ,  Uwe Wiedmann

IPC: G01N23/04 ,  G21K1/02 ,  A61B6/03 ,  A61B6/00

CPC classification number: G01N23/046 ,  A61B6/032 ,  A61B6/4291 ,  G01T1/242 ,  G21K1/025

Abstract: The present approach relates to scatter correction of signals acquired using radiation detectors on a pixel-by-pixel basis. In certain implementations, the systems and methods disclosed herein facilitate scatter correction for signals generated using a detector having segmented detector elements, such as may be present in an energy-resolving, photon-counting CT imaging system.

公开(公告)号：US20180293762A1

公开(公告)日：2018-10-11

申请号：US15480172

申请日：2017-04-05

Applicant: General Electric Company

Inventor： Lin Fu ,  Sathish Ramani ,  Bruno Kristiaan Bernard De Man ,  Xue Rui ,  Sangtae Ahn

IPC: G06T11/00 ,  G06K9/66

CPC classification number: G06T11/003 ,  G06K9/66 ,  G06T11/006 ,  G06T2210/41 ,  G06T2211/416

Abstract: The present approach relates to the use of machine learning and deep learning systems suitable for solving large-scale, space-variant tomographic reconstruction and/or correction problems. In certain embodiments, a tomographic transform of measured data obtained from a tomography scanner is used as an input to a neural network. In accordance with certain aspects of the present approach, the tomographic transform operation(s) is performed separate from or outside the neural network such that the result of the tomographic transform operation is instead provided as an input to the neural network. In addition, in certain embodiments, one or more layers of the neural network may be provided as wavelet filter banks.

公开(公告)号：US20170285188A1

公开(公告)日：2017-10-05

申请号：US15087560

申请日：2016-03-31

Applicant: General Electric Company

Inventor： Xue Rui ,  Geng Fu ,  Jianjun Guo ,  Bruno Kristiaan Bernard De Man ,  Brian David Yanoff

IPC: G01T1/24 ,  G01N23/04 ,  G01T1/20

CPC classification number: G01N23/046 ,  G01N23/083 ,  G01N2223/505 ,  G01T1/17 ,  G01T1/2985

Abstract: The present approach relates to a detector design that allows detector-based wobble using an electronic control scheme. In one implementation, each detector pixel is divided into sub-pixels. The readout of the sub-pixels can be binned with minimal noise penalty to enable the detector wobble without physically shifting the detector or alternating the physical focal spot location, though, as discussed herein alternation of the focal spot location may be used in conjunction with the present approach to further improve radial and longitudinal imaging resolution as well as suppressing artifacts resulted by limited spatial sampling.

公开(公告)号：US20160242712A1

公开(公告)日：2016-08-25

申请号：US15044787

申请日：2016-02-16

Applicant: GENERAL ELECTRIC COMPANY

Inventor： Yannan Jin ,  Bruno Kristiaan Bernard De Man ,  Peter Michael Edic ,  Paul Francis Fitzgerald ,  Xue Rui ,  Yangyang Yao ,  Zhye Yin ,  Uwe Wiedmann

IPC: A61B6/00 ,  A61B6/03

CPC classification number: A61B6/405 ,  A61B6/032 ,  A61B6/4233 ,  A61B6/488 ,  A61B6/5205 ,  A61B6/542

Abstract: An imaging method includes executing a low-dose preparatory scan to an object by applying tube voltages and tube currents in an x-ray source, and generating a first image of the object corresponding to the low-dose preparatory scan. The method further includes generating image quality estimates and dose estimates view by view at least based on the first image. The method includes optimizing the tube voltages and the tube currents to generate optimal profiles for the tube voltage and the tube current. At least one of the optimal profiles for the tube voltage and the tube current is generated based on the image quality estimates and the dose estimates. The method includes executing an acquisition scan by applying the tube voltages and the tube currents based on the optimal profiles and generating a second image of the object corresponding to the acquisition scan. An imaging system is also provided.

Abstract translation: 成像方法包括通过在x射线源中施加管电压和管电流来对对象执行低剂量预备扫描，以及生成对应于低剂量预备扫描的对象的第一图像。 该方法还包括至少基于第一图像通过视图生成图像质量估计和剂量估计视图。 该方法包括优化管电压和管电流以产生管电压和管电流的最佳轮廓。 基于图像质量估计和剂量估计，产生管电压和管电流的最佳曲线中的至少一个。 该方法包括通过基于最佳轮廓施加管电压和管电流来执行采集扫描，并且生成对应于采集扫描的对象的第二图像。 还提供了一种成像系统。