知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

20 records (took 0.015 seconds)

    RIB ENHANCEMENT IN RADIOGRAPHIC IMAGES
    4.
    发明申请
    RIB ENHANCEMENT IN RADIOGRAPHIC IMAGES 有权
    RIB增强放射影像

    公开(公告)号：US20140376798A1

    公开(公告)日：2014-12-25

    申请号：US14246455

    申请日：2014-04-07

    Applicant: Carestream Health, Inc.

    Inventor： Lynn M. La Pietra ,  Zhimin Huo ,  Mary E. Couwenhoven

    IPC: G06T11/60 ,  G06T7/00

    CPC classification number: G06T11/00 ,  G06T5/001 ,  G06T5/50 ,  G06T2207/10016 ,  G06T2207/10116 ,  G06T2207/30008 ,  G06T2207/30012 ,  G06T2207/30064

    Abstract: A method for radiographic imaging obtains a radiographic image of a patient's chest and processes the obtained image to generate a default radiographic image and a bone-enhanced image. At least a portion of one or more ribs within the default radiographic image is detected and a rib mask generated according to the at least the detected portion of the one or more ribs. The rib mask is applied to the bone-enhanced image to define masked enhanced image content that includes the detected at least the portion of one or more ribs. A composite image that combines the masked enhanced image content with the default radiographic image is generated and displayed.

    Abstract translation: 用于放射线照相成像的方法获得患者胸部的放射照相图像，并处理所获得的图像以生成默认放射照相图像和骨骼增强图像。 检测默认放射线照相图像内的一个或多个肋的至少一部分，以及根据至少所述一个或多个肋的所检测部分产生的肋掩模。 肋骨掩模被施加到骨增强图像以定义掩蔽的增强图像内容，其包括检测到一个或多个肋的至少一部分。 生成并显示将掩蔽的增强图像内容与默认放射照相图像组合的合成图像。

    CLAVICLE SUPPRESSION IN RADIOGRAPHIC IMAGES
    5.
    发明申请
    CLAVICLE SUPPRESSION IN RADIOGRAPHIC IMAGES 有权
    RADIOGRAPHIC IMAGES中的CLAVICLE抑制

    公开(公告)号：US20140140603A1

    公开(公告)日：2014-05-22

    申请号：US14082464

    申请日：2013-11-18

    Applicant: Carestream Health, Inc.

    Inventor： Zhimin Huo ,  Hui Zhao

    IPC: G06T7/00

    CPC classification number: G06T5/005 ,  G06T5/20 ,  G06T7/12 ,  G06T2207/10116 ,  G06T2207/20036 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30008 ,  G06T2207/30061

    Abstract: A method for clavicle suppression in a chest x-ray image. The method identifies the lung fields in the x-ray image and detects at least one portion of a clavicle ridge that lies outside the lung fields. Edges of a clavicle on each side of the detected clavicle ridge are detected, edge detection extended for the clavicle edges into the lung fields, and the clavicle defined within the x-ray image according to the edge detection. The clavicle is suppressed within the x-ray image to generate a clavicle-suppressed x-ray image and the clavicle-suppressed x-ray image is displayed, stored, or transmitted.

    Abstract translation: 一种胸部X线片抑制锁骨的方法。 该方法识别x射线图像中的肺域，并且检测位于肺区外的锁骨脊的至少一部分。 检测到锁骨脊的两侧的锁骨边缘，根据边缘检测将锁骨边缘扩展到锁骨边缘，并将锁骨定义在X射线图像内。 锁骨被抑制在X射线图像内以产生锁骨抑制的X射线图像，锁骨抑制的X射线图像被显示，存储或传输。

    Bone suppression for chest radiographs using deep learning
    6.
    发明授权
    Bone suppression for chest radiographs using deep learning 有权

    公开(公告)号：US11158050B2

    公开(公告)日：2021-10-26

    申请号：US16535124

    申请日：2019-08-08

    Applicant: CARESTREAM HEALTH, INC.

    Inventor： Zhimin Huo ,  Hui Zhao

    IPC: G06T7/00 ,  A61B6/00

    Abstract: A system and method for generating a rib suppressed radiographic image using deep learning computation. The method includes using a convolutional neural network module trained with pairs of a chest x-ray image and its counterpart bone suppressed image. The bone suppressed image is obtained using a bone suppression algorithm applied to the chest x-ray image. The convolutional neural network module is then applied to a chest x-ray image or the bone suppressed image to generate an enhanced bone suppressed image.

    Bone segmentation and display for 3D extremity imaging
    7.
    发明授权
    Bone segmentation and display for 3D extremity imaging 有权

    公开(公告)号：US10796475B2

    公开(公告)日：2020-10-06

    申请号：US16108184

    申请日：2018-08-22

    Applicant: CARESTREAM HEALTH, INC.

    Inventor： Zhimin Huo ,  Jing Zhang ,  Hui Zhao

    IPC: G06K9/00 ,  G06T15/08 ,  G06T7/00 ,  A61B6/00 ,  A61B6/03 ,  G06T5/00 ,  G06T17/00

    Abstract: A method acquires a reconstructed tomographic volume image of anatomy of a patient and constructs a primary axis for a bone of interest in the imaged anatomy. The method forms a sectioned image of the bone in the volume image according to a first plane that is defined to extend along the bone and to extend through two or more articular surfaces. A primary axis for the bone is estimated, wherein the primary axis is midway between outer edges of the bone image that intersect the first sectioning plane. The bone is sectioned in the volume image by a second plane that is orthogonal to the first plane and that extends through the estimated primary axis. The method recalculates the position of the constructed primary axis according to the sectioning of the bone by the second plane. The recalculated constructed primary axis for the bone of interest is displayed.

    Metal artifacts reduction for cone beam CT
    8.
    发明授权
    Metal artifacts reduction for cone beam CT 有权

    公开(公告)号：US10395397B2

    公开(公告)日：2019-08-27

    申请号：US15810863

    申请日：2017-11-13

    Applicant: Carestream Health, Inc.

    Inventor： Jing Zhang ,  Zhimin Huo ,  Frank Zhao

    IPC: G06K9/00 ,  G06T11/00 ,  G06T7/11 ,  G06T7/187 ,  G06T7/174 ,  G06T7/13

    Abstract: A method for processing volume image data obtains two-dimensional projection images of a subject on an image detector, wherein each of the images has the detector and a radiation source at a different scan angles. The image data is arranged as an image stack with corresponding pixel data from the detector in register for each of the images in the stack. A partial subset of projection images showing a metal object is identified. Information relative to the metal object propagates from the partial subject of projection images to the remaining images of the stack. For each of one or more stacked projection images, region growing defines a metal mask and adjusts image data values defined by the mask. The volume image data is reconstructed using region growing results. A 2D image is rendered and displayed from the reconstructed volume image data.

    QUANTITATIVE METHOD FOR 3-D JOINT CHARACTERIZATION
    10.
    发明申请
    QUANTITATIVE METHOD FOR 3-D JOINT CHARACTERIZATION 审中-公开
    3-D接头特征的量化方法

    公开(公告)号：US20160180520A1

    公开(公告)日：2016-06-23

    申请号：US14969332

    申请日：2015-12-15

    Applicant: Carestream Health, Inc.

    Inventor： Zhimin Huo ,  William J. Sehnert ,  Mingming Kong ,  Andre Souza

    IPC: G06T7/00 ,  G06T15/08 ,  G06T19/20 ,  G06T11/20

    CPC classification number: G06T7/0012 ,  G06T7/11 ,  G06T7/194 ,  G06T11/206 ,  G06T2207/10081 ,  G06T2207/10088 ,  G06T2207/30008

    Abstract: A method for characterizing a bone joint of a patient, the method executed at least in part by a computer, accesses 3-D volume image content that includes the bone joint and automatically segments the bone joint volume image content from background content to define at least a first bone surface and a second bone surface that is spaced apart from and faces the first bone surface. One or more distances between at least a first point on the first bone surface and one or more points on the second bone surfaces are computed. The method displays at least the first and second bone surfaces, wherein the display appearance is conditioned by the one or more computed distances. The method displays, stores, or transmits data relating to the one or more computed distances.

    Abstract translation: 用于表征患者的骨关节的方法至少部分地由计算机执行的方法访问包括骨关节的3-D体积图像内容，并且从背景内容自动分割骨关节体积图像内容以限定至少 第一骨表面和与第一骨表面间隔开并面向第一骨表面的第二骨表面。 计算第一骨表面上的至少第一点与第二骨表面上的一个或多个点之间的一个或多个距离。 该方法至少显示第一和第二骨表面，其中显示外观由一个或多个计算的距离调节。 该方法显示，存储或发送与一个或多个计算距离有关的数据。

Patent Agency Ranking