专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US08340372B2 Image analysis 有权
标题翻译：图像分析
公开(公告)号：US08340372B2
公开(公告)日：2012-12-25
申请号：US10538150
申请日：2003-12-12
申请人： Sharon Katrina Watson , Graham Howard Watson
发明人： Sharon Katrina Watson , Graham Howard Watson
IPC分类号： G06K9/00
CPC分类号： G06K9/0014 , G06T7/0012 , G06T7/64
摘要： A method for the automated analysis of digital images, particularly for the purpose of assessing mitotic activity from images of histological slides for prognostication of breast cancer. The method includes the steps of identifying the locations of objects within the image which have intensity and size characteristics consistent with mitotic epithelial cell nuclei, taking the darkest 10% of those objects, deriving contours indicating their boundary shape, and smoothing and measuring the curvature around the boundaries using a Probability Density Association Filter (PDAF). The PDAF output is used to compute a measure of any concavity of the boundary—a good indicator of mitosis. Objects are finally classified as representing mitotic nuclei or not, as a function of boundary concavity and mean intensity, by use of a Fisher classifier trained on known examples.
摘要翻译：一种用于数字图像的自动分析的方法，特别是为了从用于预测乳腺癌的组织学载玻片的图像评估有丝分裂活性的目的。该方法包括以下步骤：识别图像中具有与有丝分裂上皮细胞核一致的强度和尺寸特征的物体的位置，获取那些物体中最暗的10％，导出指示它们的边界形状的轮廓，以及平滑和测量周围的曲率边界使用概率密度关联过滤器（PDAF）。 PDAF输出用于计算边界任何凹度的量度 - 有丝分裂的良好指标。通过使用根据已知实例训练的Fisher分类器，物体最终分类为代表有丝分裂核或不是边界凹面和平均强度的函数。

2. 发明授权

US07684596B2 Image analysis 有权
标题翻译：图像分析
公开(公告)号：US07684596B2
公开(公告)日：2010-03-23
申请号：US10543911
申请日：2004-02-05
申请人： Sharon Katrina Watson , Graham Howard Watson
发明人： Sharon Katrina Watson , Graham Howard Watson
IPC分类号： G06K9/00
CPC分类号： G06K9/00127 , G06F19/00 , G06T7/0012 , G06T7/12 , G06T7/62 , G06T2207/10056 , G06T2207/30024
摘要： A method for the automated analysis of digital images, particularly for the purpose of assessing nuclear pleomorphism from images of histological slides for prognostication of breast cancer. The method includes the steps of identifying the locations of objects within the image which have intensity and size characteristics consistent with epithelial cell nuclei and deriving boundaries for those objects. Statistics concerning at least the shapes of the derived boundaries are calculated and clutter is rejected on the basis of those statistics and/or they are used to assign probabilities that the respective objects are epithelial cell nuclei, and a measure of the variability of at least the areas enclosed by such boundaries is then calculated.
摘要翻译：一种用于自动分析数字图像的方法，特别是用于从用于预测乳腺癌的组织学载玻片的图像评估核多形性的目的。该方法包括以下步骤：识别图像中具有与上皮细胞核一致的强度和尺寸特征的图像中的物体的位置，以及为这些物体导出边界。计算关于衍生边界的至少形状的统计量，并且基于这些统计量来排除杂波，和/或它们用于分配各个对象是上皮细胞核的概率，以及至少然后计算由这种边界包围的区域。

3. 发明申请

US20100002942A1 TARGET ORIENTATION 有权
标题翻译：目标方位
公开(公告)号：US20100002942A1
公开(公告)日：2010-01-07
申请号：US12375992
申请日：2007-08-14
申请人： Graham Howard Watson
发明人： Graham Howard Watson
IPC分类号： G06K9/68
CPC分类号： G06K9/00214 , G06K9/522 , G06K9/6203 , G06T7/35 , G06T7/37 , G06T7/74
摘要： A method of target recognition performs a 3D comparison of target and reference data. Translation invariant signatures are derived from the two data sets, and an estimate of the orientation of the target with respect to the reference is obtained. Rotational alignment and comparison can then be achieved. The 3D data sets can be represented on an axi-symmetric surface such as a sphere and rotational convolution, over a discrete set of selected rotation angles can be performed. Optic flow can be used to derive the estimate of orientation or the target relative to the reference, in terms of a displacement field.
摘要翻译：目标识别的方法执行目标和参考数据的3D比较。从两个数据集导出翻译不变签名，并且获得目标相对于参考的取向的估计。然后可以实现旋转对准和比较。可以在诸如球体和旋转卷积之类的轴对称表面上，在可选择的旋转角度的离散组上执行3D数据集。光学流量可以用于根据位移场来导出相对于参考的取向或目标的估计。

4. 发明申请

US20060083418A1 Image analysis 有权
标题翻译：图像分析
公开(公告)号：US20060083418A1
公开(公告)日：2006-04-20
申请号：US10543911
申请日：2004-02-05
申请人： Sharon Watson , Graham Howard Watson
发明人： Sharon Watson , Graham Howard Watson
IPC分类号： G06K9/00 , G06K9/62 , G06K9/40
CPC分类号： G06K9/00127 , G06F19/00 , G06T7/0012 , G06T7/12 , G06T7/62 , G06T2207/10056 , G06T2207/30024
摘要： A method for the automated analysis of digital images, particularly for the purpose of assessing nuclear pleomorphism from images of histological slides for prognostication of breast cancer. The method includes the steps of identifying the locations of objects within the image which have intensity and size characteristics consistent with epithelial cell nuclei and deriving boundaries for those objects. Statistics concerning at least the shapes of the derived boundaries are calculated and clutter is rejected on the basis of those statistics and/or they are used to assign probabilities that the respective objects are epithelial cell nuclei, and a measure of the variability of at least the areas enclosed by such boundaries is then calculated. In one embodiment the boundaries are derived by seeking closed contours consisting of points of the same grey-level within regions centred on the locations of such objects. Another embodiment involves the deformation of a closed loop starting within the respective object, moving outward in stages in accordance with grey-level gradients around the loop, and selecting as the best fit to the real boundary the deformed loop which satisfies specified edge metrics.
摘要翻译：一种用于自动分析数字图像的方法，特别是用于从用于预测乳腺癌的组织学载玻片的图像评估核多形性的目的。该方法包括以下步骤：识别图像中具有与上皮细胞核一致的强度和尺寸特征的图像中的物体的位置，以及为这些物体导出边界。计算关于衍生边界的至少形状的统计量，并且基于这些统计量来排除杂波，和/或它们用于分配各个对象是上皮细胞核的概率，以及至少然后计算由这种边界包围的区域。在一个实施例中，通过在以这些对象的位置为中心的区域内寻找由相同灰度级的点组成的封闭轮廓来导出边界。另一个实施例涉及在相应物体内开始的闭合回路的变形，根据循环周围的灰度梯度逐级向外移动，并且选择满足特定边缘度量的变形回路对实际边界的最佳拟合。

5. 发明授权

US08270730B2 Target orientation 有权
标题翻译：目标方向
公开(公告)号：US08270730B2
公开(公告)日：2012-09-18
申请号：US12375992
申请日：2007-08-14
申请人： Graham Howard Watson
发明人： Graham Howard Watson
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/00214 , G06K9/522 , G06K9/6203 , G06T7/35 , G06T7/37 , G06T7/74
摘要： A method of target recognition performs a 3D comparison of target and reference data. Translation invariant signatures are derived from the two data sets, and an estimate of the orientation of the target with respect to the reference is obtained. Rotational alignment and comparison can then be achieved. The 3D data sets can be represented on an axi-symmetric surface such as a sphere and rotational convolution, over a discrete set of selected rotation angles can be performed. Optic flow can be used to derive the estimate of orientation or the target relative to the reference, in terms of a displacement field.
摘要翻译：目标识别的方法执行目标和参考数据的3D比较。从两个数据集导出翻译不变签名，并且获得目标相对于参考的取向的估计。然后可以实现旋转对准和比较。可以在诸如球体和旋转卷积之类的轴对称表面上，在可选择的旋转角度的离散组上执行3D数据集。光学流量可以用于根据位移场来导出相对于参考的取向或目标的估计。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式