APPARATUS AND METHOD FOR COMPUTER AIDED DIAGNOSIS (CAD), AND APPARATUS FOR CONTROLLING ULTRASONIC TRANSMISSION PATTERN OF PROBE
    1.
    发明申请
    APPARATUS AND METHOD FOR COMPUTER AIDED DIAGNOSIS (CAD), AND APPARATUS FOR CONTROLLING ULTRASONIC TRANSMISSION PATTERN OF PROBE 审中-公开
    用于计算机辅助诊断(CAD)的装置和方法,以及用于控制探头超声波传播模式的装置

    公开(公告)号:US20160157832A1

    公开(公告)日:2016-06-09

    申请号:US14958144

    申请日:2015-12-03

    Abstract: An apparatus and a method for Computer Aided Diagnosis (CAD) and an apparatus for controlling an ultrasonic transmission pattern of a probe, are provided. The apparatus for controlling the ultrasonic transmission pattern is configured to transmit ultrasonic signals to an object in directions, and receive ultrasonic echo signals in response to the ultrasonic signals being reflected from the object. The apparatus for controlling the ultrasonic transmission pattern includes a determiner configured to determine, based on pressure that is applied on the probe, a number of transmission directions in which the ultrasonic signals are to be transmitted, and determine the transmission directions in which the ultrasonic signals are to be transmitted, based on the determined number of the transmission directions. The apparatus further includes an energy controller configured to control energy of each of the ultrasonic signals based on the determined number of the transmission directions.

    Abstract translation: 提供了一种用于计算机辅助诊断(CAD)的装置和方法以及用于控制探头的超声波传输模式的装置。 用于控制超声波传输模式的装置被配置为响应于超声信号从物体反射而在方向上向对象发送超声信号,并且接收超声波回波信号。 用于控制超声波发送模式的装置包括确定器,其被配置为基于施加在探头上的压力来确定要发送超声波信号的传输方向的数量,并且确定超声波信号的传输方向 将根据确定的传输方向的数量进行传输。 该装置还包括能量控制器,其被配置为基于确定的传输方向的数量来控制每个超声波信号的能量。

    CONVOLUTION NEURAL NETWORK TRAINING APPARATUS AND METHOD THEREOF
    4.
    发明申请
    CONVOLUTION NEURAL NETWORK TRAINING APPARATUS AND METHOD THEREOF 审中-公开
    解决神经网络训练装置及其方法

    公开(公告)号:US20160162782A1

    公开(公告)日:2016-06-09

    申请号:US14960942

    申请日:2015-12-07

    Inventor: Hyoung Min PARK

    CPC classification number: G06N3/082 G06N3/0454

    Abstract: An apparatus and method of training a convolutional neural network (CNN) are provided. A method of training a CNN including a plurality of convolution layers stored in a memory involves approximating, using a processor, a convolution layer among the plurality of convolution layers using a low-rank approximation; reducing the number of output reconstruction filters of the approximated convolution layer; and modifying a structure of the CNN based on an approximation result and the reduced number of output reconstruction filters.

    Abstract translation: 提供了一种训练卷积神经网络(CNN)的装置和方法。 训练包含存储在存储器中的多个卷积层的CNN的方法包括使用处理器近似使用低等级近似的多个卷积层中的卷积层; 减少近似卷积层的输出重建滤波器的数量; 以及基于近似结果和减少的输出重建滤波器数量来修改CNN的结构。

    APPARATUS AND METHOD FOR SAMPLING IMAGES
    6.
    发明申请
    APPARATUS AND METHOD FOR SAMPLING IMAGES 有权
    装置和采样图像的方法

    公开(公告)号:US20150365566A1

    公开(公告)日:2015-12-17

    申请号:US14661269

    申请日:2015-03-18

    Abstract: Disclosed are an image sampling apparatus and method. The image sampling apparatus includes a probe angular velocity detector configured to detect an angular velocity of a probe representing a change in an angle of the probe at a surface of an object, an image segmenter configured to receive the angular velocity and an image captured by the probe, and to segment the image into sub-regions based on the angular velocity, and a differential sampler configured to sample the sub-regions with a different sampling rate based on a position of a sub-region.

    Abstract translation: 公开了一种图像采样装置和方法。 图像取样装置包括探测器角速度检测器,被配置为检测表示探测器在物体表面处的角度变化的探测器的角速度,被配置为接收角速度的图像分割器和由 探测,并且基于角速度将图像分割成子区域;以及差分采样器,被配置为基于子区域的位置以不同的采样率对子区域进行采样。

Patent Agency Ranking