公开(公告)号：US07792342B2

公开(公告)日：2010-09-07

申请号：US11675678

申请日：2007-02-16

申请人： Adrian Barbu ,  Vassilis Athitsos ,  Bogdan Georgescu ,  Peter Durlak ,  Stefan Boehm ,  Dorin Comaniciu

发明人： Adrian Barbu ,  Vassilis Athitsos ,  Bogdan Georgescu ,  Peter Durlak ,  Stefan Boehm ,  Dorin Comaniciu

IPC分类号： G06K9/00

CPC分类号： A61B6/12 ,  G06K9/48 ,  G06K2209/057

摘要： A system and method for populating a database with a set of image sequences of an object is disclosed. The database is used to detect localization of a guidewire in the object. A set of images of anatomical structures is received in which each image is annotated to show a guidewire, catheter, wire tip and stent. For each given image a Probabilistic Boosting Tree (PBT) is used to detect short line segments of constant length in the image. Two segment curves are constructed from the short line segments. A discriminative joint shape and appearance model is used to classify each two segment curve. A shape of an n-segment curve is constructed by concatenating all the two segment curves. A guidewire curve model is identified that includes a start point, end point and the n-segment curve. The guidewire curve model is stored in the database.

摘要翻译： 公开了一种使用一组对象的图像序列填充数据库的系统和方法。 数据库用于检测对象中导丝的定位。 接收一组解剖结构的图像，其中每个图像被注释以示出导丝，导管，线尖和支架。 对于每个给定的图像，使用概率增强树（PBT）来检测图像中恒定长度的短线段。 从短线段构建两段曲线。 使用歧视关节形状和外观模型对每个两段曲线进行分类。 通过连接所有两个段曲线构建n段曲线的形状。 识别出导线曲线模型，其包括起始点，终点和n段曲线。 导丝曲线模型存储在数据库中。

公开(公告)号：US20070270692A1

公开(公告)日：2007-11-22

申请号：US11675678

申请日：2007-02-16

申请人： Adrian Barbu ,  Vassilis Athitsos ,  Bogdan Georgescu ,  Stefan Boehm ,  Peter Durlak ,  Dorin Comaniciu

发明人： Adrian Barbu ,  Vassilis Athitsos ,  Bogdan Georgescu ,  Stefan Boehm ,  Peter Durlak ,  Dorin Comaniciu

IPC分类号： A61B6/00

CPC分类号： A61B6/12 ,  G06K9/48 ,  G06K2209/057

摘要： A system and method for populating a database with a set of image sequences of an object is disclosed. The database is used to detect localization of a guidewire in the object. A set of images of anatomical structures is received in which each image is annotated to show a guidewire, catheter, wire tip and stent. For each given image a Probabilistic Boosting Tree (PBT) is used to detect short line segments of constant length in the image. Two segment curves are constructed from the short line segments. A discriminative joint shape and appearance model is used to classify each two segment curve. A shape of an n-segment curve is constructed by concatenating all the two segment curves. A guidewire curve model is identified that includes a start point, end point and the n-segment curve. The guidewire curve model is stored in the database.

摘要翻译： 公开了一种使用一组对象的图像序列填充数据库的系统和方法。 数据库用于检测对象中导丝的定位。 接收一组解剖结构的图像，其中每个图像被注释以示出导丝，导管，线尖和支架。 对于每个给定的图像，使用概率增强树（PBT）来检测图像中恒定长度的短线段。 从短线段构建两段曲线。 使用歧视关节形状和外观模型对每个两段曲线进行分类。 通过连接所有两个段曲线构建n段曲线的形状。 识别出导线曲线模型，其包括起始点，终点和n段曲线。 导丝曲线模型存储在数据库中。

公开(公告)号：US20090116713A1

公开(公告)日：2009-05-07

申请号：US12286970

申请日：2008-10-03

申请人： Michelle Xiao-Hong Yan ,  Ti-Chiun Chang ,  Markus Lendl ,  Stefan Boehm ,  Tong Fang ,  Peter Durlak

发明人： Michelle Xiao-Hong Yan ,  Ti-Chiun Chang ,  Markus Lendl ,  Stefan Boehm ,  Tong Fang ,  Peter Durlak

IPC分类号： G06K9/00

CPC分类号： G06K9/4619 ,  G06K2209/05 ,  G06T7/0012

摘要： A method and system for image quality assessment is disclosed. The image quality assessment method is a no-reference method for objectively assessing the quality of medical images. This method is guided by the human vision model in order to accurately reflect human perception. A region of interest (ROI) of medical image is divided into non-overlapping blocks of equal size. Each of the blocks is categorized as a smooth block, a texture block, or an edge block. A perceptual sharpness measure, which is weighted by local contrast, is calculated for each of the edge blocks. A perceptual noise level measure, which is weighted by background luminance, is calculated for each of the smooth blocks. A sharpness quality index is determined based on the perceptual sharpness measures of all of the edge blocks, and a noise level quality index is determined based on the perceptual noise level measures of all of the smooth blocks. An overall image quality index can be determined by using task specific machine learning of samples of annotated images. The image quality assessment method can be used in applications, such as video/image compression and storage in healthcare and homeland security, and band-width limited wireless communication.

摘要翻译： 公开了一种用于图像质量评估的方法和系统。 图像质量评估方法是客观评估医学图像质量的非参考方法。 这种方法是以人类视觉模型为指导，以准确反映人类的感知。 医学图像的感兴趣区域（ROI）被划分成相等大小的不重叠块。 每个块被分类为平滑块，纹理块或边缘块。 针对每个边缘块计算出由局部对比度加权的感知锐度度量。 为每个平滑块计算感知噪声水平测量，其由背景亮度加权。 基于所有边缘块的感知锐度测量来确定锐度质量指标，并且基于所有平滑块的感知噪声水平测量来确定噪声水平质量指数。 可以通过使用注释图像的样本的任务特定机器学习来确定整体图像质量指数。 图像质量评估方法可用于医疗保健和国土安全中的视频/图像压缩和存储等应用，以及带宽有限的无线通信。

公开(公告)号：US08244020B2

公开(公告)日：2012-08-14

申请号：US12286992

申请日：2008-10-03

申请人： Yunqiang Chen ,  Tong Fang ,  Sandra Martin ,  Stefan Boehm ,  Peter Durlak

发明人： Yunqiang Chen ,  Tong Fang ,  Sandra Martin ,  Stefan Boehm ,  Peter Durlak

IPC分类号： G06K9/40 ,  G06K9/60 ,  G06T5/50 ,  G01N23/083

CPC分类号： A61B6/504 ,  A61B6/481 ,  A61B6/482 ,  G06K2009/00932

摘要： A method and system for intelligent digital subtraction is disclosed. The method and system for intelligent digital subtraction can be used in a roadmap application for a coronary intervention. A mask image is obtained with vessels highlighted by contrast media. A guide wire is inserted into the vessels, and a guide wire image is obtained. A direct subtraction image is generated from the guide wire image and the mask image. A reduced noise subtraction image is generated based on mutual image information between the subtraction image and the guide wire image and mutual image information between the subtraction image and the mask image.

摘要翻译： 公开了一种智能数字减法的方法和系统。 用于智能数字减法的方法和系统可用于冠状动脉干预的路线图应用。 用造影剂强调的血管获得掩模图像。 将引导线插入容器中，并获得导丝图像。 从引导线图像和掩模图像生成直接减法图像。 基于减法图像和引导线图像之间的相互图像信息以及减法图像和掩模图像之间的相互图像信息，生成降噪噪声减影图像。

公开(公告)号：US08086007B2

公开(公告)日：2011-12-27

申请号：US12286970

申请日：2008-10-03

申请人： Michelle Xiao-Hong Yan ,  Ti-chiun Chang ,  Markus Lendl ,  Stefan Boehm ,  Tong Fang ,  Peter Durlak

发明人： Michelle Xiao-Hong Yan ,  Ti-chiun Chang ,  Markus Lendl ,  Stefan Boehm ,  Tong Fang ,  Peter Durlak

IPC分类号： G06K9/00

CPC分类号： G06K9/4619 ,  G06K2209/05 ,  G06T7/0012

摘要： A method and system for image quality assessment is disclosed. The image quality assessment method is a no-reference method for objectively assessing the quality of medical images. This method is guided by the human vision model in order to accurately reflect human perception. A region of interest (ROI) of medical image is divided into non-overlapping blocks of equal size. Each of the blocks is categorized as a smooth block, a texture block, or an edge block. A perceptual sharpness measure, which is weighted by local contrast, is calculated for each of the edge blocks. A perceptual noise level measure, which is weighted by background luminance, is calculated for each of the smooth blocks. A sharpness quality index is determined based on the perceptual sharpness measures of all of the edge blocks, and a noise level quality index is determined based on the perceptual noise level measures of all of the smooth blocks. An overall image quality index can be determined by using task specific machine learning of samples of annotated images. The image quality assessment method can be used in applications, such as video/image compression and storage in healthcare and homeland security, and band-width limited wireless communication.

摘要翻译： 公开了一种用于图像质量评估的方法和系统。 图像质量评估方法是客观评估医学图像质量的非参考方法。 这种方法是以人类视觉模型为指导，以准确反映人类的感知。 医学图像的感兴趣区域（ROI）被划分成相等大小的不重叠块。 每个块被分类为平滑块，纹理块或边缘块。 针对每个边缘块计算出由局部对比度加权的感知锐度度量。 为每个平滑块计算感知噪声水平测量，其由背景亮度加权。 基于所有边缘块的感知锐度测量来确定锐度质量指标，并且基于所有平滑块的感知噪声水平测量来确定噪声水平质量指数。 可以通过使用注释图像的样本的任务特定机器学习来确定整体图像质量指数。 图像质量评估方法可用于医疗保健和国土安全中的视频/图像压缩和存储等应用，以及带宽有限的无线通信。

公开(公告)号：US20090103682A1

公开(公告)日：2009-04-23

申请号：US12286992

申请日：2008-10-03

申请人： Yungiang Chen ,  Tong Fang ,  Sandra Martin ,  Stefan Boehm ,  Peter Durlak

发明人： Yungiang Chen ,  Tong Fang ,  Sandra Martin ,  Stefan Boehm ,  Peter Durlak

IPC分类号： H05G1/64 ,  G06K9/00

CPC分类号： A61B6/504 ,  A61B6/481 ,  A61B6/482 ,  G06K2009/00932

摘要： A method and system for intelligent digital subtraction is disclosed. The method and system for intelligent digital subtraction can be used in a roadmap application for a coronary intervention. A mask image is obtained with vessels highlighted by contrast media. A guide wire is inserted into the vessels, and a guide wire image is obtained. A direct subtraction image is generated from the guide wire image and the mask image. A reduced noise subtraction image is generated based on mutual image information between the subtraction image and the guide wire image and mutual image information between the subtraction image and the mask image.

摘要翻译： 公开了一种智能数字减法的方法和系统。 用于智能数字减法的方法和系统可用于冠状动脉干预的路线图应用。 用造影剂强调的血管获得掩模图像。 将引导线插入容器中，并获得导丝图像。 从引导线图像和掩模图像生成直接减法图像。 基于减法图像和引导线图像之间的相互图像信息以及减法图像和掩模图像之间的相互图像信息，生成降噪噪声减影图像。

公开(公告)号：US06763084B2

公开(公告)日：2004-07-13

申请号：US09990346

申请日：2001-11-23

申请人： Stefan Boehm ,  Martin Spahn

发明人： Stefan Boehm ,  Martin Spahn

IPC分类号： G01N2324

CPC分类号： G09G3/006 ,  A61B6/583 ,  A61B6/585 ,  G06T7/0004 ,  G06T2207/10116 ,  G06T2207/30004 ,  G06T2207/30121 ,  G09G2330/08 ,  G09G2330/10 ,  H04N5/2176 ,  H04N5/325

摘要： In a method for operating an imaging medical examination device (1), an event of the undisturbed operation of the medical examination device (1) automatically triggers a defect determination (63) for determining a defective pixel possibly present in the image. The event is derived for example from a switch-on process, a calibration process and/or an examination process. Preferably, after the defect determination (63), a correction process (67) is automatically triggered if a defective pixel was detected. A medical examination device (1) has a detection device (31) for automatically determining a defective pixel possibly present in the image, in which case the detection device (31) can be activated by an event of the undisturbed operation of the medical examination device. A correction device (41) for automatically eliminating a defective pixel that has possibly been detected is preferably present.

摘要翻译： 在用于操作成像医疗检查装置（1）的方法中，医疗检查装置（1）的未受干扰的操作的事件自动触发用于确定可能存在于图像中的缺陷像素的缺陷确定（63）。 该事件例如来自接通过程，校准过程和/或检查过程。 优选地，在缺陷确定（63）之后，如果检测到缺陷像素，则自动触发校正处理（67）。 医疗检查装置（1）具有用于自动确定图像中可能存在的缺陷像素的检测装置（31），在这种情况下，检测装置（31）可以由医疗检查装置的未受干扰的操作的事件激活 。 优选地存在用于自动消除可能被检测到的缺陷像素的校正装置（41）。

公开(公告)号：US08199316B2

公开(公告)日：2012-06-12

申请号：US12161227

申请日：2007-02-08

申请人： Stefan Boehm ,  Mark Hellmanns ,  Klaus Dilger ,  Karl-Heinz Brakhage

发明人： Stefan Boehm ,  Mark Hellmanns ,  Klaus Dilger ,  Karl-Heinz Brakhage

IPC分类号： G01B3/08

CPC分类号： G01B11/002 ,  B25J9/1697 ,  G05B19/404 ,  G05B2219/37388 ,  G05B2219/39178 ,  G05B2219/40623

摘要： A description is given of a device (1) for tracking the movement of a tool of a handling unit (2), having at least one directional radiator (5) that can be aligned with the tool and be tracked, and a signal evaluation unit (4) for determining the movement.The directional radiators (5) have actuators for aligning the directional beam (6) at adjustable angles with reference to a fixed spatial plane, and angle sensors for determining the current directional beam angle with reference to the spatial plane, the angle sensors being connected to the signal evaluation unit (4). Directional beam sensors (7) for detecting the directional beam (6) are arranged with a fixed reference to the tool and movably therewith, the directional beam sensors (7) being connected to the signal evaluation unit (4). The signal evaluation unit (4) is set up for tracking the directional beams (6) of the at least one directional radiator (5) onto an assigned, moving directional beam sensor (7), and for determining the arbitrary movement of the tool in three-dimensional space as a function of the directional beam angles.

摘要翻译： 给出了用于跟踪处理单元（2）的工具的移动的装置（1），其具有可与工具对准的并被跟踪的至少一个定向辐射器（5）和信号评估单元 （4）用于确定运动。 定向辐射器（5）具有用于相对于固定空间平面以可调节的角度对准定向光束（6）的致动器，以及用于相对于空间平面确定当前定向光束角度的角度传感器，角度传感器连接到 信号评估单元（4）。 用于检测方向光束（6）的定向光束传感器（7）以固定的参考方式布置并与之一起移动，定向光束传感器（7）连接到信号评估单元（4）。 信号评估单元（4）被设置用于将至少一个定向辐射器（5）的定向波束（6）跟踪到分配的移动定向波束传感器（7）上，并且用于确定工具的任意移动 作为定向光束角度的函数的三维空间。

公开(公告)号：US20070163671A1

公开(公告)日：2007-07-19

申请号：US11622550

申请日：2007-01-12

申请人： Stefan Boehm ,  Ludwig Danzer ,  Sven Rathmann ,  Jan Wrege

发明人： Stefan Boehm ,  Ludwig Danzer ,  Sven Rathmann ,  Jan Wrege

IPC分类号： B65B1/04 ,  B65B3/04 ,  G01B11/02 ,  B65B31/00

CPC分类号： G01F23/2928

摘要： In a method and a device for non-contacting monitoring of the fill state of liquids in an unpressurized liquid container, the fill state and/or the fill state change is determined by radiating light onto the boundary region of the liquid at which a fill state-dependent curvature arises due to adhesion forces of the liquid at the reservoir wall and surface tension, and the intensity of the reflected light or the reflection angle is measured at a predetermined location.

摘要翻译： 在非接触式监测非加压液体容器中的液体填充状态的方法和装置中，填充状态和/或填充状态变化通过将光照射到液体的填充状态的边界区域 由于储存器壁处的液体的粘附力和表面张力而产生依赖的曲率，并且在预定位置处测量反射光的强度或反射角。

公开(公告)号：US5132101A

公开(公告)日：1992-07-21

申请号：US578346

申请日：1990-09-06

申请人： Emanuel Vogel ,  Alexander D. Cross ,  Norbert Jux ,  Eduardo Rodriguez-Val ,  Stefan Boehm ,  Wolfgang Hennig

发明人： Emanuel Vogel ,  Alexander D. Cross ,  Norbert Jux ,  Eduardo Rodriguez-Val ,  Stefan Boehm ,  Wolfgang Hennig

IPC分类号： A61K41/00 ,  C07D487/22

CPC分类号： C07D487/22 ,  A61K41/0076

摘要： Dihydro- and tetrahydro-acetylene-cumulene porphycene compounds having the structure shown below ##STR1## are useful as photogynamic therapy agents.

摘要翻译： 具有下述结构的二氢 - 和四氢 - 乙炔 - 枯烯卟吩化合物可用作光动力学治疗剂。