Method for determining an optimally weighted wavelet transform based on
supervised training for detection of microcalcifications in digital
mammograms
    1.
    发明授权
    Method for determining an optimally weighted wavelet transform based on supervised training for detection of microcalcifications in digital mammograms 失效
    基于用于检测数字乳腺X线照片中微钙化的监督训练来确定最佳加权小波变换的方法

    公开(公告)号:US6075878A

    公开(公告)日:2000-06-13

    申请号:US979623

    申请日:1997-11-28

    IPC分类号: G06F17/14 G06T7/00 G06K9/00

    CPC分类号: G06F17/148 G06T7/0012

    摘要: A computer-aided diagnosis (CAD) method for detection of clustered microcalcifications in digital mammograms based on an image reconstruction using a substantially optimally weighted wavelet transform. Weights at individual scales of the wavelet transform are optimized based on a supervised learning method. In the learning method, an error function represents a difference between a desired output and a reconstructed image obtained from weighted wavelet coefficients of the wavelet transform for a given mammogram. The error function is then minimized by modifying the weights by means of a conjugate gradient algorithm. Performance of the optimally weighted wavelets was evaluated by means of receiver-operating characteristic (ROC) analysis which indicated that the present invention outperformed both a difference-image technique and partial reconstruction method currently used in CAD methods.

    摘要翻译: 一种用于基于使用基本上最佳加权的小波变换的图像重建来检测数字乳腺X线照片中的聚类微钙化的计算机辅助诊断(CAD)方法。 基于监督学习方法优化小波变换的个体尺度权重。 在学习方法中,误差函数表示对于给定的乳腺X线照片,从小波变换的加权小波系数获得的期望输出和重建图像之间的差。 然后通过使用共轭梯度算法修改权重来最小化误差函数。 通过接收机操作特性(ROC)分析评估了最佳加权小波的性能,表明本发明优于当前在CAD方法中使用的差分图像技术和部分重建方法。

    Shift-invariant artificial neural network for computerized detection of
clustered microcalcifications in mammography
    2.
    发明授权
    Shift-invariant artificial neural network for computerized detection of clustered microcalcifications in mammography 失效
    用于乳腺摄影中聚类微钙化计算机检测的移位不变人工神经网络

    公开(公告)号:US5732697A

    公开(公告)日:1998-03-31

    申请号:US562188

    申请日:1995-11-22

    申请人: Wei Zhang Kunio Doi

    发明人: Wei Zhang Kunio Doi

    CPC分类号: G06T7/0012

    摘要: A computerized method and system using a shift-invariant artificial neural network (SIANN) for the quantitative analysis of image data. A series of digitized medical images are used to train an artificial neural network to differentiate between diseased and normal tissue. The sum of the weights in groups between layers is constrained to be substantially zero so as to avoid saturation of layers which would otherwise be saturated by low frequency background noise. The method and system also include utilizing training-free zones to exclude from training the center portions of microcalcifications in the digitized images. The method and system further include rule-based selection criteria for providing a more accurate diagnosis.

    摘要翻译: 一种使用移位不变人工神经网络(SIANN)进行图像数据定量分析的计算机化方法和系统。 使用一系列数字化医学图像来训练人造神经网络来区分患病和正常组织。 层之间的组中的权重之和被约束为基本为零,以避免否则将被低频背景噪声饱和的层的饱和。 该方法和系统还包括利用无训练区域来排除在数字化图像中训练微钙化的中心部分。 该方法和系统还包括用于提供更准确的诊断的基于规则的选择标准。

    Method and system for the detection of microcalcifications in digital
mammograms
    3.
    发明授权
    Method and system for the detection of microcalcifications in digital mammograms 失效
    用于检测数字乳腺X线照片中微钙化的方法和系统

    公开(公告)号:US5491627A

    公开(公告)日:1996-02-13

    申请号:US060531

    申请日:1993-05-13

    申请人: Wei Zhang Kunio Doi

    发明人: Wei Zhang Kunio Doi

    IPC分类号: A61B6/00 G06F19/00 G06T7/00

    摘要: A method and system for the detection of microcalcifications in digital mammograms. Digital mammograms are obtained and regions-of-interest (ROIs) are selected therefrom which contain suspected microcalcifications, either individual or clustered microcalcifications. The suspect ROIs are background-trend corrected, followed by Fourier transformation and power spectrum calculation to perform detection in the frequency domain. Detection can also be carried out in the spatial domain by omitting the Fourier transformation and power spectrum calculation. The ROI is then scaled for input into a neural network trained to detect microcalcifications. The neural network outputs ROIs with detected microcalcifications. The method and system can also include normalizing the background-trend corrected ROIs and imputing the normalized ROI to a shift-invariant neural network trained to detect microcalcifications. The output ROI of the shift-invariant neural network is thresholded to remove additional false positive detections, and then the thresholded ROI undergoes a cluster detection to detect clustered microcalcifications. Feature extraction techniques can be applied to the remaining ROI to remove additional false positive detections.

    摘要翻译: 用于检测数字乳腺X线照片中微钙化的方法和系统。 获得数字乳腺X线照片,并从中选择感兴趣区域(ROI),其中包含怀疑的微钙化,单个或聚集的微钙化。 可疑ROI是背景趋势校正,随后进行傅里叶变换和功率谱计算,以在频域中进行检测。 也可以通过省略傅里叶变换和功率谱计算在空间域中进行检测。 然后,将ROI投影到经过训练以检测微钙化的神经网络中。 神经网络通过检测到的微钙化输出ROI。 该方法和系统还可以包括对背景趋势校正的ROI进行归一化,并将归一化的ROI估算为经过训练以检测微钙化的移位不变神经网络。 移位不变神经网络的输出ROI被阈值化以去除额外的假阳性检测,然后阈值ROI进行聚类检测以检测聚类微钙化。 特征提取技术可以应用于剩余的ROI以消除额外的假阳性检测。

    APPARATUS AND METHODS FOR EXPANDING AND COLLAPSING A ROD

    公开(公告)号:US20220110303A1

    公开(公告)日:2022-04-14

    申请号:US17067711

    申请日:2020-10-11

    申请人: Wei Zhang

    发明人: Wei Zhang

    IPC分类号: A01K87/02

    摘要: Methods and apparatus for expanding a rod from a collapsed position to a formed position are disclosed. One such apparatus includes a plurality of segments for forming the body of the collapsible rod including with each segment coupled to each immediately adjacent segment of the plurality of segments. The apparatus may include a coupler for coupling each segment of the plurality of segments to each immediately adjacent segment of the plurality of segments. The coupler may stretch from a base segment to the tip of the apparatus and may be biased to apply a force to hold the plurality of segments in a formed position and to urge the plurality of segments into a formed position from a collapsed position. In the formed position, the plurality of segments may be aligned end-to-end to form a rod and in the collapsed position, the plurality of segments may be folded against each other such that cylindrical walls of each of the plurality of segments are positioned adjacent each other.

    Convertible Bullet-proof Backpack
    5.
    发明申请

    公开(公告)号:US20180295974A1

    公开(公告)日:2018-10-18

    申请号:US15731045

    申请日:2017-04-12

    申请人: Wei Zhang

    发明人: Wei Zhang

    摘要: A convertible bullet-proof backpack and vest includes a body section divided into a front portion, a middle portion, and back portion. The middle portion has a head slot opening, and the front and back portions have respective sections of bullet-proof fabric integrated therein. A zipper runs around an outer perimeter of the front and back portions. In a backpack configuration, the front portion and the back portion fold toward each other and the zipper secures the outer perimeters of the front portion and the back portion together thereby forming a hollow backpack interior between them. In a bullet-proof vest configuration, the zipper is unzipped thereby allowing a user to insert their head through the head slot opening such that the front portion hangs in front of a torso of the user and the back portion hangs behind the torso of the user.

    APPARATUS AND METHOD FOR TREATING MALE IMPOTENCE

    公开(公告)号:US20180177625A1

    公开(公告)日:2018-06-28

    申请号:US15820401

    申请日:2017-11-21

    申请人: Wei Zhang

    发明人: Wei Zhang

    IPC分类号: A61F5/41

    CPC分类号: A61F5/41 A61F2005/411

    摘要: The present invention strategically utilizes the sturdiness of thin wires enwrapped inside a thick layer of soft material such as silicone rubber which is smoother and softer than human tissue. Therefore, the device doesn't cause any damage or side effect and feels comfortable to user. The exposure of skin is 90% or higher, therefore solves the lack of sensation issue faced by prior art devices. The device is hard and yet flexible, the side walls or double bars are positioned toward ventral side of the device so that it is pleasing to the eye during use in addition to feeling good by the user.

    Electron donor-fullerene conjugated molecules for organic photovoltaic cells
    8.
    发明授权
    Electron donor-fullerene conjugated molecules for organic photovoltaic cells 有权
    用于有机光伏电池的电子供体 - 富勒烯共轭分子

    公开(公告)号:US09478746B2

    公开(公告)日:2016-10-25

    申请号:US13911351

    申请日:2013-06-06

    IPC分类号: H01L51/00 H01L51/42

    摘要: A photovoltaic cell has an active area formed electron donor-fullerene conjugated molecules. The electron donor is formed of a polymer, which is conjugated with an electron acceptor, such as fullerene. By conjugating the fullerene, such as C60, with electron donor moieties, such as that of the polymer, double channels are formed therebetween, whereby one channel provides hole transport and the other channel provides electron transport. As a result, the electronic coupling between the fullerene and the electron donor moiety leads to increased short-circuit current density (Jsc) and increased open-circuit voltage (Voc), resulting in high power conversion efficacy (PCE) in the solar cell.

    摘要翻译: 光伏电池具有形成的电子供体 - 富勒烯共轭分子的有源区。 电子给体由与电子受体(例如富勒烯)共轭的聚合物形成。 通过将诸如C60的富勒烯与诸如聚合物的电子供体部分共轭,在其间形成双通道,由此一个通道提供空穴传输,另一个通道提供电子传输。 结果,富勒烯和电子给体部分之间的电子耦合导致短路电流密度(Jsc)增加和开路电压(Voc)增加,导致太阳能电池中的高功率转换效率(PCE)。