Segmentation and identification of layered structures in images
    74.
    发明授权
    Segmentation and identification of layered structures in images 有权
    图像中分层结构的分割和识别

    公开(公告)号:US09589346B2

    公开(公告)日:2017-03-07

    申请号:US15049103

    申请日:2016-02-21

    申请人: Duke University

    摘要: Disclosed herein are systems and method for segmentation and identification of structured features in images. According to an aspect, a method may include representing an image as a graph of nodes connected together by edges. For example, the image may be an ocular image showing layered structures or other features of the retina. The method may also include adding, to the graph, nodes adjacent to nodes along first and second sides of the graph. The added nodes may have edge weights less than the nodes along the first and second sides of the graph. Further, the method may include assigning start and end points to any of the added nodes along the first and second sides, respectively. The method may also include graph cutting between the start and end points for identifying a feature in the image.

    摘要翻译: 这里公开了用于分割和识别图像中的结构化特征的系统和方法。 根据一个方面,一种方法可以包括将图像表示为由边缘连接在一起的节点的图形。 例如,图像可以是显示视网膜的分层结构或其他特征的眼睛图像。 该方法还可以包括向图中添加与图的第一和第二侧相邻的节点相邻的节点。 添加的节点可以具有小于沿图的第一和第二侧的节点的边权重。 此外,该方法可以包括分别将起点和终点分配给沿着第一和第二侧的任何添加的节点。 该方法还可以包括用于识别图像中的特征的开始点和结束点之间的图形切割。

    GENERATING A RESPIRATION GATING SIGNAL FROM A VIDEO
    75.
    发明申请
    GENERATING A RESPIRATION GATING SIGNAL FROM A VIDEO 审中-公开
    从视频生成呼叫评估信号

    公开(公告)号:US20170055920A1

    公开(公告)日:2017-03-02

    申请号:US14837898

    申请日:2015-08-27

    申请人: Xerox Corporation

    IPC分类号: A61B5/00 A61B5/113 A61B5/11

    摘要: What is disclosed is a system and method for generating a respiration gating signal from a video of a subject for gating diagnostic imaging and therapeutic delivery applications which require respiration phase and/or respiration amplitude gating. One embodiment involves receiving a video of a subject and generating a plurality of time-series signals from the video image frames. A set of features are extracted from the time-series signals and multi-dimensional feature vectors are formed. The feature vectors are clustered. Time-series signals corresponding in each of the clusters are averaged in a temporal direction to obtain a representative signal for each cluster. One cluster is selected and a respiration gating signal is generated from that cluster's representative signal. Thereafter, the respiration gating signal is used to gate diagnostic imaging and therapeutic delivery applications which requires gating based on a threshold set with respect to either respiration phase or respiration amplitude.

    摘要翻译: 公开的是用于从需要呼吸相位和/或呼吸振幅选通的门诊诊断成像和治疗递送应用的对象视频产生呼吸门控信号的系统和方法。 一个实施例涉及接收对象的视频并从视频图像帧产生多个时间序列信号。 从时间序列信号中提取一组特征,形成多维特征向量。 特征向量是聚类的。 在每个簇中对应的时间序列信号在时间方向上被平均以获得每个簇的代表信号。 选择一个群集,并从该群集的代表信号中生成呼吸门控信号。 此后,呼吸门控信号用于门诊诊断成像和治疗递送应用,其需要基于相对于呼吸相位或呼吸振幅设定的阈值进行门控。

    METHOD, APPARATUS, AND COMPUTER-READABLE MEDIUM FOR GENERATING A SET OF RECOMMENDED ORTHOTIC PRODUCTS
    76.
    发明申请
    METHOD, APPARATUS, AND COMPUTER-READABLE MEDIUM FOR GENERATING A SET OF RECOMMENDED ORTHOTIC PRODUCTS 审中-公开
    用于产生一组推荐的产品的方法,装置和计算机可读介质

    公开(公告)号:US20170027477A1

    公开(公告)日:2017-02-02

    申请号:US15303031

    申请日:2015-04-09

    IPC分类号: A61B5/107 A61B5/103 A61B5/00

    摘要: In an embodiment, the present invention is an apparatus, comprising: a foot mat; a depth sensing camera; an elevated foot platform that reduces or prevents rotational movement of a foot; a processor in communication with the depth sensing camera, the processor further configured to calculate the circumference of a user's leg based on data from the depth sensing camera while the user has one foot on the foot mat and one foot on the elevated foot platform, the processor further configured to select a recommended product for the user's knee or ankle from among a set of pre-manufactured candidate products for knees or ankles based at least in part upon the leg circumference of the user; and an output device to display information received from the processor, the information identifying the recommended product to the user.

    摘要翻译: 在一个实施例中,本发明是一种装置,包括:脚垫; 深度感应摄像机; 一个可以降低或防止足部旋转运动的升高的脚踏平台; 所述处理器与所述深度感测摄像机通信,所述处理器还被配置为基于来自所述深度感测摄像机的数据来计算用户腿部的周长,同时所述用户在所述脚踏板上具有一只脚并且在所述升高的脚踏板上具有一只脚, 处理器还被配置为至少部分地基于用户的腿部周长从用于膝盖或脚踝的一组预制的候选产品中为用户的膝盖或脚踝选择推荐的产品; 以及输出装置,用于显示从所述处理器接收的信息,所述信息将所述推荐产品标识给所述用户。

    METHOD OF QUANTITATIVE MAGNETIC RESONANCE LUNG IMAGING
    80.
    发明申请
    METHOD OF QUANTITATIVE MAGNETIC RESONANCE LUNG IMAGING 有权
    定量磁共振成像方法

    公开(公告)号:US20160367200A1

    公开(公告)日:2016-12-22

    申请号:US15178894

    申请日:2016-06-10

    摘要: A method of processing magnetic resonance (MR) lung images creates a quantitative ventilation map of the lung, which is calculated from ventilation images. A step of determining ventilation frequency includes a frequency analysis of a time series of a quantitative lung dimension parameter which is characteristic for the dimension of the lung at the time of collecting the corresponding MR lung image. Creation of the quantitative ventilation map includes selecting a first group of ventilation images, which consists of expiration ventilation images collected at regular expiration phases of multiple ventilation periods, and a second group of ventilation images, which consists of inspiration ventilation images collected at regular inspiration phases of the multiple ventilation periods, and calculating the quantitative ventilation map from the first and second groups of ventilation images, wherein the quantitative ventilation map is adjusted with reference to the tidal volume of the lung.

    摘要翻译: 一种处理磁共振(MR)肺图像的方法产生肺的定量通气图,其由通气图像计算。 确定通气频率的步骤包括定量肺尺寸参数的时间序列的频率分析,其是在收集相应的MR肺图像时肺的尺寸的特征。 定量通气图的创建包括选择第一组通气图像,其包括在多个通气期的常规呼气阶段收集的呼气透气图像和第二组通气图像,其包括在常规吸气阶段收集的吸气透气图像 并计算来自第一组和第二组通气图像的定量通气图,其中参照肺的潮气量调整定量通气图。