公开(公告)号：US07616792B2

公开(公告)日：2009-11-10

申请号：US10990888

申请日：2004-11-17

申请人： Kazunori Okada ,  Dorin Comaniciu ,  Arun Krishnan

发明人： Kazunori Okada ,  Dorin Comaniciu ,  Arun Krishnan

IPC分类号： G06K9/00 ,  H03F1/26

CPC分类号： G06K9/527 ,  G06T7/0012 ,  G06T7/11 ,  G06T2207/10081 ,  G06T2207/30064

摘要： A method for determining a structure in volumetric data includes determining an anisotropic scale-space for a local region around a given spatial local maximum, determining L-normalized scale-space derivatives in the anisotropic scale-space, and determining the presence of noise in the volumetric data and upon determining noise in the volumetric data, determining the structure by a most-stable-over-scales determination, and upon determining noise below a desirable level, determining the structure by one of the most-stable-over-scales determination and a maximum-over-scales determination.

摘要翻译： 一种用于确定体积数据中的结构的方法包括确定围绕给定空间局部最大值的局部区域的各向异性尺度空间，确定各向异性尺度空间中的L归一化尺度空间导数，以及确定在 体积数据和确定体积数据中的噪声，通过最稳定的超标度确定来确定结构，并且在将噪声确定在理想水平之下时，通过最稳定的超尺度确定之一来确定结构;以及 最大超尺度测定。

公开(公告)号：US20080267483A1

公开(公告)日：2008-10-30

申请号：US12110643

申请日：2008-04-28

申请人： Yiqiang Zhan ,  Xiang Zhou ,  Arun Krishnan

发明人： Yiqiang Zhan ,  Xiang Zhou ,  Arun Krishnan

IPC分类号： G06K9/00

CPC分类号： G06K9/32 ,  G06K2209/05 ,  G06T7/33

摘要： A method for registering a medical image includes acquiring a first medical image of a subject. One or more simulated medical images are synthesized based on the acquired first medical image. One or more matching functions are trained using the first medical image and the simulated medical images. A second medical image of the subject is acquired. The first medical image and the second medical image are registered using the one or more trained matching functions.

摘要翻译： 用于登记医学图像的方法包括获取对象的第一医学图像。 基于获取的第一医学图像合成一个或多个模拟医学图像。 使用第一医学图像和模拟医学图像训练一个或多个匹配函数。 获取受试者的第二个医学图像。 第一医用图像和第二医用图像使用一个或多个经过训练的匹配功能进行登记。

公开(公告)号：US20060050958A1

公开(公告)日：2006-03-09

申请号：US11184590

申请日：2005-07-19

申请人： Kazunori Okada ,  Umut Akdemir ,  Arun Krishnan

发明人： Kazunori Okada ,  Umut Akdemir ,  Arun Krishnan

IPC分类号： G06K9/34

CPC分类号： G06T7/143 ,  G06T7/11 ,  G06T7/194 ,  G06T2207/10072 ,  G06T2207/30096

摘要： A method for segmenting a digitized image includes providing a digitized volumetric image comprising a plurality of intensities corresponding to a domain of points in an N-dimensional space, identifying a target structure in said image, forming a window about said target structure whose size is a function of the target scale, and performing a joint space-intensity-likelihood ratio test at each point within said window to determine whether each said point is within said target structure.

摘要翻译： 用于分割数字化图像的方法包括提供数字化的体积图像，其包括对应于N维空间中的点的域的多个强度，识别所述图像中的目标结构，形成关于所述目标结构的窗口，其大小为 功能，并且在所述窗口内的每个点处执行联合空间 - 强度 - 似然比测试，以确定每个所述点是否在所述目标结构内。

公开(公告)号：US20060030769A1

公开(公告)日：2006-02-09

申请号：US11146961

申请日：2005-06-07

申请人： Venkat Ramamurthy ,  Arun Krishnan ,  Christian Beldinger ,  Juergen Soldner ,  Maxim Mamin ,  Axel Barth ,  Stefan Käpplinger ,  Michael Gluth ,  Peggy Hawman ,  Darrell Burckhardt ,  Axel Platz

发明人： Venkat Ramamurthy ,  Arun Krishnan ,  Christian Beldinger ,  Juergen Soldner ,  Maxim Mamin ,  Axel Barth ,  Stefan Käpplinger ,  Michael Gluth ,  Peggy Hawman ,  Darrell Burckhardt ,  Axel Platz

IPC分类号： A61B5/05

CPC分类号： G06T7/0012 ,  G06F19/321 ,  G06T7/38 ,  G06T2207/30004 ,  G16H10/60

摘要： A system and method for loading a timepoint for comparison with a previously loaded timepoint are provided. The method comprises: selecting an image dataset of the timepoint; validating the image dataset of the timepoint against a validated image dataset of the previously loaded timepoint; and constructing a volume based on the image dataset of the timepoint.

摘要翻译： 提供了用于加载用于与先前加载的时间点进行比较的时间点的系统和方法。 该方法包括：选择时间点的图像数据集; 根据先前加载的时间点的经过验证的图像数据集验证时间点的图像数据集; 并基于时间点的图像数据集构建卷。

公开(公告)号：US06389104B1

公开(公告)日：2002-05-14

申请号：US09607906

申请日：2000-06-30

申请人： Ali Bani-Hashemi ,  Arun Krishnan ,  James Williams

发明人： Ali Bani-Hashemi ,  Arun Krishnan ,  James Williams

IPC分类号： A61B603

CPC分类号： A61B6/504 ,  A61B6/12 ,  A61B6/4441 ,  A61B6/463 ,  A61B6/466 ,  A61B6/481 ,  A61B6/5235 ,  A61B6/5247 ,  A61B90/36 ,  G06T11/006 ,  G06T2211/404 ,  G06T2211/412 ,  G06T2211/428

摘要： A method and apparatus for providing a high-quality representation of a volume having a real-time 3-D reconstruction therein of movement of an object, wherein the real-time movement of the object is determined using a lower-quality representation of only a portion of the volume. Movement of the object is detected in a 2-D X-ray fluoroscopy image and is reconstructed in a 3-D angiography (X-ray) reconstruction. Using a common C-arm and X-ray geometry advantageously, the 2-D and 3-D data representative of vascular structures of a patient is acquired, thereby facilitating the merger of the real-time 2-D fluoroscopic images with the 3-D reconstructed vascular structures in a common 3-D-visualization framework. Also described is a technique for 3-D reconstruction of a catheter from real-time 2-D fluoroscopic images and stored 3-D angiography data, so as to present the 3-D reconstructed catheter in the common coordinate frame. The merger of 3-D angiography image representations acquired with other modalities, such as MR or CT, is also disclosed.

摘要翻译： 一种用于提供其中具有物体的移动的实时3维重建的体积的高质量表示的方法和装置，其中使用较低质量的仅仅一个 部分音量。 在2-D X射线荧光透视图像中检测物体的移动，并在3-D血管造影（X射线）重建中重建。 有利地使用常见的C形臂和X射线几何形状，代表患者的血管结构的2-D和3-D数据，从而有助于将实时2-D透视图像与3- D重建血管结构在一个共同的3-D可视化框架。 还描述了一种用于从实时二维透视图像和存储的三维血管造影数据进行导管三维重建的技术，以将3-D重建的导管呈现在共同的坐标系中。 还公开了与其他方式（例如MR或CT）获得的3-D血管造影图像表示的合并。

公开(公告)号：US08260833B2

公开(公告)日：2012-09-04

申请号：US13015076

申请日：2011-01-27

申请人： Alain Dazzi ,  Arun Krishnan

发明人： Alain Dazzi ,  Arun Krishnan

IPC分类号： G06F12/00 ,  G06F17/30

CPC分类号： G06F17/30

摘要： A method allowing for fast mapping between a content identifier (ID) for a media content file and the file path of said media content file includes: dividing a plurality of characters making up the contend ID into a plurality of ordered subsections separated by a separator character, correlating at least one of the subsections with a directory in an electronic file system, and correlating the last of the subsections with a name of the media content file, the media content file being located within a directory correlated with a preceding subsection.

摘要翻译： 允许在媒体内容文件的内容标识符（ID）和所述媒体内容文件的文件路径之间进行快速映射的方法包括：将构成竞争ID的多个字符分成由分隔符分隔的多个有序子部分 将至少一个子部分与电子文件系统中的目录相关联，并且将最后的子部分与媒体内容文件的名称相关联，所述媒体内容文件位于与前一小节相关的目录内。

公开(公告)号：US20110191447A1

公开(公告)日：2011-08-04

申请号：US13015122

申请日：2011-01-27

申请人： Alain Dazzi ,  Arun Krishnan

发明人： Alain Dazzi ,  Arun Krishnan

IPC分类号： G06F15/16

CPC分类号： G06F15/16

摘要： A system for storing content available for streaming includes a storage tier with a plurality of storage clusters, each of the storage clusters having at least one server, the storage clusters collectively storing multiple media content files; a streaming tier coupled to the storage tier, the streaming tier having multiple streaming servers, the streaming tier being configured to stream data over a network faster than the storage tier is able to stream the data over the network; and a computer-implemented synchronization module configured to analyze traffic statistics associated with a media content file stored on the storage tier and selectively replicate the media content file on the streaming tier based on the traffic statistics.

摘要翻译： 用于存储可用于流传输的内容的系统包括具有多个存储集群的存储层，每个存储集群具有至少一个服务器，所述存储集群共同存储多个媒体内容文件; 耦合到所述存储层的流层，所述流层具有多个流服务器，所述流层被配置为比所述存储层能够通过所述网络流式传输所述数据更快地流过网络上的数据; 以及计算机实现的同步模块，被配置为分析与存储在存储层上的媒体内容文件相关联的流量统计，并且基于流量统计选择性地在流层上复制媒体内容文件。

公开(公告)号：US20110191446A1

公开(公告)日：2011-08-04

申请号：US13014881

申请日：2011-01-27

申请人： Alain Dazzi ,  Arun Krishnan

发明人： Alain Dazzi ,  Arun Krishnan

IPC分类号： G06F15/16

CPC分类号： G06F15/16

摘要： Providing media content includes storing a plurality of media files on a storage tier having at least one storage cluster, each storage cluster having at least one server, replicating at least some of the media files stored on the storage tier on at least one streaming server of a streaming tier configured to stream data over a network faster than the storage tier is able to stream the data over the network; receiving a request from a client over the network for a portion of a selected media file; streaming the requested portion of the selected media file to the client from the streaming tier if the selected media file is stored on the streaming tier; and streaming the requested portion of the selected media file to the client from the storage tier if the media file is not stored on the streaming tier.

摘要翻译： 提供媒体内容包括将多个媒体文件存储在具有至少一个存储集群的存储层上，每个存储集群具有至少一个服务器，在至少一个流媒体服务器上复制存储在存储层上的至少一些媒体文件 配置成通过网络流式传输数据流的流层比存储层能够通过网络流式传输数据; 通过所述网络从所述客户端接收针对所选择的媒体文件的一部分的请求; 如果所选择的媒体文件存储在流媒体层上，则将所选择的媒体文件的所请求部分从流层传送到客户端; 以及如果所述媒体文件未被存储在所述流层上，则将所选择的媒体文件的所请求部分从所述存储层流式传输到所述客户端。

公开(公告)号：US20100284590A1

公开(公告)日：2010-11-11

申请号：US12787916

申请日：2010-05-26

申请人： Zhigang Peng ,  Yimo Tao ,  Xiang Sean Zhou ,  Yiqiang Zhan ,  Arun Krishnan

发明人： Zhigang Peng ,  Yimo Tao ,  Xiang Sean Zhou ,  Yiqiang Zhan ,  Arun Krishnan

IPC分类号： G06K9/46 ,  G06K9/00

CPC分类号： A61B6/032 ,  A61B6/469 ,  A61B6/488 ,  G06K9/3233 ,  G06K9/6231 ,  G06K9/6267 ,  G06K2209/05 ,  G06T7/12 ,  G06T7/73 ,  G06T2207/10081 ,  G06T2207/20104 ,  G06T2207/20164 ,  G06T2207/30048

摘要： Systems and methods for performing a medical imaging study include acquiring a preliminary scan. A set of local feature candidates is automatically detected from the preliminary scan. The accuracy of each local feature candidate is assessed using multiple combinations of the other local feature candidates and removing a local feature candidate that is assessed to have the lowest accuracy. The assessing and removing steps are repeated until only a predetermined number of local feature candidates remain. A region of interest (ROI) is located from within the preliminary scan based on the remaining predetermined number of local feature candidates. A medical imaging study is performed based on the location of the ROI within the preliminary scan.

摘要翻译： 用于执行医学成像研究的系统和方法包括获取初步扫描。 从初步扫描中自动检测一组本地特征候选。 使用其他本地特征候选者的多个组合来评估每个本地特征候选者的准确性，并且去除被评估为具有最低精度的局部特征候选。 重复评估和去除步骤，直到仅保留预定数量的局部特征候选。 感兴趣区域（ROI）基于剩余的预定数量的局部特征候选位于初步扫描内。 基于初步扫描中ROI的位置执行医学成像研究。

公开(公告)号：US20090310836A1

公开(公告)日：2009-12-17

申请号：US12427974

申请日：2009-04-22

申请人： Arun Krishnan ,  Xiang Zhou ,  Martin Huber ,  Michael Kelm ,  Joerg Freund

发明人： Arun Krishnan ,  Xiang Zhou ,  Martin Huber ,  Michael Kelm ,  Joerg Freund

IPC分类号： G06K9/62 ,  G06K9/00

CPC分类号： G06T7/11 ,  G06F19/00 ,  G06T7/0012 ,  G06T2207/20081 ,  G16H50/70

摘要： A method for training a computer system for automatic detection of regions of interest includes receiving patient records. For each of the received patient records a text field and a medical image are identified from within the patient record and the medical image is automatically segmented to identify a structure of interest. The text field is searched for one or more keywords indicative of a particular abnormality associated with the structure of interest. The medical image is added to a grouping representing the particular abnormality when the text field indicates that the patient has the particular abnormality and the medical image is added to a grouping representing the absence of the particular abnormality when the text field does not indicate that the patient has the particular abnormality. The groupings of medical images are used to automatically train a computer system for the subsequent detection of the particular abnormality.

摘要翻译： 用于训练用于感兴趣区域的自动检测的计算机系统的方法包括接收患者记录。 对于每个接收到的患者记录，从患者记录中识别文本字段和医学图像，并且医疗图像被自动分段以识别感兴趣的结构。 搜索文本字段以查找指示与感兴趣结构相关联的特定异常的一个或多个关键字。 当文本字段指示患者具有特定异常并将医学图像添加到代表不存在特定异常的分组时，医疗图像被添加到表示特定异常的分组中，当文本字段没有指示患者 有特殊的异常。 医学图像的分组用于自动训练计算机系统以便随后检测特定的异常。