Automatic pose initialization for accurate 2-D/3-D registration applied to abdominal aortic aneurysm endovascular repair
    3.
    发明授权
    Automatic pose initialization for accurate 2-D/3-D registration applied to abdominal aortic aneurysm endovascular repair 有权
    自动姿态初始化用于准确的2-D / 3-D记录应用于腹主动脉瘤血管内修复

    公开(公告)号:US08588501B2

    公开(公告)日:2013-11-19

    申请号:US13473049

    申请日:2012-05-16

    IPC分类号: G06K9/00

    CPC分类号: G06K9/00214 G06K9/6203

    摘要: A method for automatically initializing pose for registration of 2D fluoroscopic abdominal aortic images with a 3D model of an abdominal aorta includes detecting a 2D iliac bifurcation and a 2D renal artery bifurcation from a sequence of 2D fluoroscopic abdominal aortic images, detecting a spinal centerline in a 2D fluoroscopic spine image, providing a 3D iliac bifurcation and a 3D renal artery bifurcation from a 3D image volume of the patient's abdomen, and a 3D spinal centerline from the 3D image volume of the patient's abdomen, and determining pose parameters {x, y, z, θ}, where (x, y) denotes the translation on a table plane, z denotes a depth of the table, and θ is a rotation about the z axis, by minimizing a cost function of the 2D and 3D iliac bifurcations, the 2D and 3D renal artery bifurcation, and the 2D and 3D spinal centerlines.

    摘要翻译: 用于自动初始化用于腹部主动脉3D模型的2D荧光透视腹主动脉图像配准的姿势的方法包括从2D荧光透视腹主动脉图像序列检测2D髂骨分叉和2D肾动脉分叉,检测脊髓中心线 2D透视脊柱图像,从患者腹部的3D图像体积提供3D髂骨分叉和3D肾动脉分叉,以及来自患者腹部的3D图像体积的3D脊柱中心线,以及确定姿势参数{x,y, z,theta},其中(x,y)表示平台上的平移,z表示桌子的深度,θ是围绕z轴的旋转,通过最小化2D和3D髂骨分叉的成本函数, 2D和3D肾动脉分叉,以及2D和3D脊髓中心线。

    Image Registration Using Interventional Devices
    4.
    发明申请
    Image Registration Using Interventional Devices 审中-公开
    使用介入设备的图像配准

    公开(公告)号:US20120150025A1

    公开(公告)日:2012-06-14

    申请号:US13236761

    申请日:2011-09-20

    IPC分类号: A61B5/05

    摘要: A system receives an image volume of a patient. A catheter applied to the patient contains at least one sensor, which may be a microcoil and which is detectable in the image volume. A size and a shape of a region of interest are pre-defined. A processor determines a location of the at least one sensor in the image volume. The image volume is generated by a medical imaging device. The processor defines the shape and size of the region of interest relative to the location of the at least one sensor to determine the region of interest in the image volume. Image data of the region of interest in the image volume and of the region of interest in a previous image volume are registered. The region of interest is determined during an interventional procedure on the patient.

    摘要翻译: 系统接收患者的图像体积。 应用于患者的导管包含至少一个传感器,其可以是微型线圈,并且可以在图像体积中检测。 预先确定感兴趣区域的大小和形状。 处理器确定图像体积中的至少一个传感器的位置。 图像体积由医学成像装置产生。 处理器相对于至少一个传感器的位置定义感兴趣区域的形状和尺寸,以确定图像体积中的感兴趣区域。 记录图像体积中的感兴趣区域和先前图像体积中的感兴趣区域的图像数据。 感兴趣区域是在患者的介入手术过程中确定的。

    AUTOMATIC DETECTION OF CONTRAST INJECTION
    5.
    发明申请
    AUTOMATIC DETECTION OF CONTRAST INJECTION 有权
    自动检测对比度注射

    公开(公告)号:US20120128226A1

    公开(公告)日:2012-05-24

    申请号:US13211716

    申请日:2011-08-17

    IPC分类号: G06K9/00

    摘要: A method for automatically detecting the presence of contrast in an x-ray image includes acquiring an x-ray image prior to administration of contrast. A background image is estimated based on the x-ray image. The contrast is administered. A set of x-ray images is acquired. The background image is subtracted from the set of images. Image intensity is determined for each of the subtracted images. The subtracted images having highest image intensity are selected. A predefined shape model is fitted to the selected subtracted images. The fitting of the predefined shape model is used to fit the shape model to each of the subtracted images. A feature value is calculated for each image frame based on pixel intensities of each pixel fitted to the shape model for the corresponding subtracted image. An image frame of peak contrast is determined by selecting the image frame with the greatest feature value.

    摘要翻译: 用于自动检测x射线图像中的对比度的存在的方法包括在施加对比度之前获取X射线图像。 基于x射线图像估计背景图像。 对比度被管理。 获取一组X射线图像。 从图像集中减去背景图像。 确定每个减影图像的图像强度。 选择具有最高图像强度的减影图像。 预定义的形状模型适合于所选择的减影图像。 使用预定义形状模型的拟合来将形状模型拟合到每个相减图像。 基于适合于相应减法图像的形状模型的每个像素的像素强度,针对每个图像帧计算特征值。 通过选择具有最大特征值的图像帧来确定峰值对比度的图像帧。