公开(公告)号：US06181811B2

公开(公告)日：2001-01-30

申请号：US09006457

申请日：1998-01-13

申请人： Chih-Chau L. Kuan ,  Shih-Jong J. Lee ,  Seho Oh ,  Larry A. Nelson ,  Dayle G. Ellison ,  Florence W. Patten

发明人： Chih-Chau L. Kuan ,  Shih-Jong J. Lee ,  Seho Oh ,  Larry A. Nelson ,  Dayle G. Ellison ,  Florence W. Patten

IPC分类号： G06K900

CPC分类号： G06K9/00127

摘要： A method and apparatus for optimizing biological and cytological specimen screening and diagnosis. A slide review process is recommended for cytological specimen screening to identify abnormal sub-populations for further review and also diagnosis by a human expert. An automated screener processes a cytological specimen. Using a slide score generated by the automated screener, a slide review process using a slide score classification is determined. The recommendation of slide review processes improves overall performance of the screening process as measured by sensitivity to abnormal specimens, and at the same time reduces the work load of a human reviewer. The system also effectively and smoothly integrates the process of initial screening of the specimen with the process of further review of the specimen and final diagnosis of the specimen.

摘要翻译： 用于优化生物学和细胞学标本筛选和诊断的方法和装置。 推荐用于细胞学标本筛选的幻灯片审查过程，以识别异常亚群以供进一步审查，并由人类专家进行诊断。 自动筛选器处理细胞学标本。 使用由自动筛选器生成的幻灯片得分，确定使用幻灯片分数分类的幻灯片审阅过程。 幻灯片审查过程的推荐通过对异常标本的敏感度测量，提高了筛选过程的整体性能，同时降低了人类审阅者的工作量。 该系统还将样品初始筛选过程与样品进一步检查和样品的最终诊断过程进行了有效平滑的整合。

公开(公告)号：US6134354A

公开(公告)日：2000-10-17

申请号：US121012

申请日：1998-07-22

申请人： Shih-Jong J. Lee ,  Paul S. Wilhelm ,  Wendy R. Bannister ,  Chih-Chau L. Kuan ,  Seho Oh ,  Michael G. Meyer

发明人： Shih-Jong J. Lee ,  Paul S. Wilhelm ,  Wendy R. Bannister ,  Chih-Chau L. Kuan ,  Seho Oh ,  Michael G. Meyer

IPC分类号： G01N15/14 ,  G06K9/00 ,  G06K9/38

CPC分类号： G06K9/00127 ,  G01N15/1475 ,  G01N2015/1497

摘要： A free-lying cell classifier. An automated microscope system comprising a computer and high speed processing field of view processors identifies free-lying cells. An image of a biological specimen is obtained and the image is segmented to create a set of binary masks. The binary masks are used by a feature calculator to compute the features that characterize objects of interest including free-lying cells, artifacts and other biological objects. The objects are classified to identify their type, their normality or abnormality or their identification as an artifact. The results are summarized and reported. A stain evaluation of the slide is performed as well as a typicality evaluation. The robustness of the measurement is also quantified as a classification confidence value. The free-lying cell evaluation is used by an automated cytology system to classify a biological specimen slide.

公开(公告)号：US20120106809A1

公开(公告)日：2012-05-03

申请号：US12925874

申请日：2010-11-01

申请人： Shih-Jong J. Lee ,  Seho Oh

发明人： Shih-Jong J. Lee ,  Seho Oh

IPC分类号： G06K9/00

CPC分类号： G06K9/342 ,  G06K9/0014

摘要： A teachable object contour mapping method for region partition receives an object boundary and a teaching image. An object contour mapping recipe creation is performed using the object boundary and the teaching image to generate object contour mapping recipe output. An object contour mapping is applied to an application image using the object contour mapping recipe and the application image to generate object contour map output. An object region partition using the object contour map to generate object region partition output An updateable object contour mapping method receives a contour mapping recipe and a validation image. An object contour mapping is performed using the object contour mapping recipe and the validation image to generate validation contour map output. An object region partition receives a region mask to generate validation object region partition output. A boundary correction is performed using the validation object region partition to generate corrected object boundary output. An update contour mapping is performed using the corrected object boundary, the validation image and the contour mapping recipe to generate updated contour mapping recipe output.

摘要翻译： 区域分区的可教对象轮廓映射方法接收对象边界和教学图像。 使用对象边界和教学图像执行对象轮廓映射配方创建，以生成对象轮廓映射配方输出。 使用对象轮廓映射配方和应用图像将对象轮廓映射应用于应用图像以生成对象轮廓图输出。 使用对象轮廓图生成对象区域分区输出的对象区域分区可更新对象轮廓映射方法接收轮廓映射配方和验证图像。 使用对象轮廓映射配方和验证图像执行对象轮廓映射以生成验证轮廓图输出。 对象区域分区接收区域掩码以生成验证对象区域分区输出。 使用验证对象区域分区执行边界校正，以生成校正对象边界输出。 使用校正的对象边界，验证图像和轮廓映射配方来执行更新轮廓映射以生成更新的轮廓映射配方输出。

公开(公告)号：US20110274339A1

公开(公告)日：2011-11-10

申请号：US13135711

申请日：2011-07-13

申请人： Shih-Jong J. Lee ,  Seho Oh ,  Samuel V. Alworth

发明人： Shih-Jong J. Lee ,  Seho Oh ,  Samuel V. Alworth

IPC分类号： G06K9/00

CPC分类号： G06K9/00127 ,  G06K2009/3291

摘要： A computerized derivable kinetic characterization measurement method for live cell kinetic characterization inputs kinetic recognition data for a plurality of time frames. A single cell measurement step is performed using the kinetic recognition data for a plurality of time frames to generate single cell feature for a plurality of time frames output. The single cell feature includes cell morphological profiling feature. A kinetic measurement step uses the single cell feature for a plurality of time frames to generate kinetic feature output. A trajectory measurement step uses the single cell feature for a plurality of time frames and the kinetic feature to generate trajectory feature output. An interval measurement step uses the kinetic feature to generate interval feature output. A cell state classifier step uses the interval feature to generate cell state output. A state based measurement uses the single cell feature, the kinetic feature and the cell state to generate state based feature output.

摘要翻译： 用于活细胞动力学特征的计算机可推导动力学表征测量方法输入多个时间帧的动力学识别数据。 使用多个时间帧的动力学识别数据来执行单个小区测量步骤，以生成多个时间帧输出的单个小区特征。 单细胞特征包括细胞形态分析特征。 动力学测量步骤使用多个时间帧的单细胞特征来产生动力特征输出。 轨迹测量步骤使用单个小区特征用于多个时间帧，并且所述动力特征生成轨迹特征输出。 间隔测量步骤使用动力学特征来产生间隔特征输出。 单元状态分类器步骤使用间隔特征来生成单元格状态输出。 基于状态的测量使用单细胞特征，动力学特征和细胞状态来产生基于状态的特征输出。

公开(公告)号：US07463773B2

公开(公告)日：2008-12-09

申请号：US10723397

申请日：2003-11-26

申请人： Shih-Jong J. Lee ,  Seho Oh

发明人： Shih-Jong J. Lee ,  Seho Oh

IPC分类号： G06K9/68 ,  G06K9/62 ,  G06K9/00

CPC分类号： G06F17/30256 ,  G06F17/30277 ,  G06K9/6857 ,  G06T7/74 ,  Y10S707/99933

摘要： An initial search method uses the input image and the template to create an initial search result output. A high precision match uses the initial search result, the input image, and the template to create a high precision match result output. The high precision match method estimates high precision parameters by image interpolation and interpolation parameter optimization. The method also performs robust matching by limiting pixel contribution or pixel weighting. An invariant high precision match method estimates subpixel position and subsampling scale and rotation parameters by image interpolation and interpolation parameter optimization on the log-converted radial-angular transformation domain.

摘要翻译： 初始搜索方法使用输入图像和模板来创建初始搜索结果输出。 高精度匹配使用初始搜索结果，输入图像和模板来创建高精度匹配结果输出。 高精度匹配方法通过图像插值和插值参数优化来估计高精度参数。 该方法还通过限制像素贡献或像素加权来执行鲁棒匹配。 不变高精度匹配方法通过对数转换的径向角变换域的图像插值和插值参数优化来估计子像素位置和子采样比例尺和旋转参数。

公开(公告)号：US20080120077A1

公开(公告)日：2008-05-22

申请号：US11604590

申请日：2006-11-22

申请人： Shih-Jong J. Lee ,  Seho Oh ,  Yuhui Y.C. Cheng ,  Samuel V. Alworth

发明人： Shih-Jong J. Lee ,  Seho Oh ,  Yuhui Y.C. Cheng ,  Samuel V. Alworth

IPC分类号： G06G7/48

CPC分类号： G06K9/00127 ,  G06K2009/3291

摘要： A computerized derivable kinetic characterization measurement method for live cell kinetic characterization inputs kinetic recognition data for a plurality of time frames. A single cell measurement step is performed using the kinetic recognition data for a plurality of time frames to generate single cell feature for a plurality of time frames output. The single cell feature includes cell morphological profiling feature. A kinetic measurement step uses the single cell feature for a plurality of time frames to generate kinetic feature output. A trajectory measurement step uses the single cell feature for a plurality of time frames and the kinetic feature to generate trajectory feature output. An interval measurement step uses the kinetic feature to generate interval feature output. A cell state classifier step uses the interval feature to generate cell state output. A state based measurement uses the single cell feature, the kinetic feature and the cell state to generate state based feature output.

摘要翻译： 用于活细胞动力学特征的计算机可推导动力学表征测量方法输入多个时间帧的动力学识别数据。 使用多个时间帧的动力学识别数据来执行单个小区测量步骤，以生成多个时间帧输出的单个小区特征。 单细胞特征包括细胞形态分析特征。 动力学测量步骤使用多个时间帧的单细胞特征来产生动力特征输出。 轨迹测量步骤使用单个小区特征用于多个时间帧，并且所述动力特征生成轨迹特征输出。 间隔测量步骤使用动力学特征来产生间隔特征输出。 单元状态分类器步骤使用间隔特征来生成单元状态输出。 基于状态的测量使用单细胞特征，动力学特征和细胞状态来产生基于状态的特征输出。

公开(公告)号：US07142718B2

公开(公告)日：2006-11-28

申请号：US10283380

申请日：2002-10-28

申请人： Shih-Jong J. Lee ,  Seho Oh ,  Donglok Kim

发明人： Shih-Jong J. Lee ,  Seho Oh ,  Donglok Kim

IPC分类号： G06K9/62 ,  G06K9/54

CPC分类号： G06K9/4647 ,  G06K9/6203 ,  G06K9/6857

摘要： An accumulation transformation method for fast pattern search accurately locates general patterns of interest. The method can be used for fast invariant search to match patterns of interest in images where the searched pattern varies in size or orientation or aspect ratio, when pattern appearance is degraded, when the pattern is partially occluded, where the searched image is large, multidimensional, or very high resolution, or where the pattern size is large. The accumulation transformations of the input image are determined based upon the searched projection directions. Projection profile result images are derived from the accumulation transformed input image and used for fast matching with template pattern projection profiles.

摘要翻译： 用于快速图案搜索的积累变换方法准确地定位了感兴趣的一般模式。 该方法可用于快速不变搜索，以匹配图像中所关注的图案，其中搜索的图案在尺寸或取向或纵横比上变化，当图案外观劣化时，当图案被部分遮挡时，搜索图像大，多维度 ，或非常高的分辨率，或者图案尺寸大的地方。 基于搜索到的投影方向来确定输入图像的累积变换。 投影轮廓结果图像从积累变换的输入图像中导出，用于与模板图案投影轮廓的快速匹配。

公开(公告)号：US06941288B2

公开(公告)日：2005-09-06

申请号：US10118553

申请日：2002-04-08

申请人： Shih-Jong J. Lee ,  Owsley Lane ,  Seho Oh

发明人： Shih-Jong J. Lee ,  Owsley Lane ,  Seho Oh

IPC分类号： G06N5/02 ,  G06F15/18

CPC分类号： G06N5/025

摘要： A learning model is initiated during start-up learning to activate operation of a decision system. During operation of the decision system, data is qualified for use in online learning. Online learning allows a system to adapt or learn application dependent parameters to optimize or maintain its performance during normal operation. Methods for qualifying data for use in online learning include thresholding of features, restriction of score space for qualified objects, and using a different source of information than is used in the decision process. Clustering methods are used to improve the quality of the learning model. Using the cumulative distribution function to compare two distributions and produce a measure of similarity derives a metric for learning maturity.

摘要翻译： 在启动学习过程中启动学习模型以激活决策系统的运作。 在决策系统运行过程中，数据有资格用于在线学习。 在线学习允许系统适应或学习应用依赖参数，以在正常操作期间优化或维持其性能。 用于在线学习中使用资料的方法包括特征阈值，限定对象的分数空间限制，以及使用不同于决策过程中使用的信息源。 聚类方法用于提高学习模型的质量。 使用累积分布函数来比较两个分布并产生相似性度量来获得学习成熟度的度量。

公开(公告)号：US06829382B2

公开(公告)日：2004-12-07

申请号：US09882734

申请日：2001-06-13

申请人： Shih-Jong J. Lee ,  Seho Oh

发明人： Shih-Jong J. Lee ,  Seho Oh

IPC分类号： G06K900

CPC分类号： G06T7/0002 ,  G06T7/12 ,  G06T7/33 ,  G06T2207/30164

摘要： When application domain structure information is erroneously encoded into parameters for image processing and measurements the accuracy of the result can degrade. A structure-guided automatic alignment system for image processing receives an image input and application domain structure input and automatically creates an estimated structure output having improved alignment. Measurement and image processing robustness are improved.

摘要翻译： 当应用程序域结构信息被错误地编码为用于图像处理和测量的参数时，结果的精度可能降低。 用于图像处理的结构引导自动对准系统接收图像输入和应用域结构输入，并自动创建具有改进的对准的估计结构输出。 改善了测量和图像处理的鲁棒性。

公开(公告)号：US06456741B1

公开(公告)日：2002-09-24

申请号：US09739084

申请日：2000-12-15

申请人： Shih-Jong J. Lee ,  Seho Oh

发明人： Shih-Jong J. Lee ,  Seho Oh

IPC分类号： G06K946

CPC分类号： G06K9/4609 ,  G06T7/13

摘要： Structure-guided image estimation and measurement methods are described for computer vision applications. Results of the structure-guided estimation are symbolic representations of geometry entities such as lines, points, arcs and circles. The symbolic representation facilitates sub-pixel measurements by increasing the number of pixels used in the matching of image features to structural entities, improving the detection of structural entities within the image, weighting the contribution of each image sample to the measurement that is being made and optimizing that contribution. After the structure-guided estimation, geometric entities are represented by their symbolic representations. Structure-guided measurements can be conducted using the symbolic representation of the geometric entities. Measurements performed from the symbolic representation are not limited by image resolution or pixel quantization error and therefore can yield sub-pixel accuracy and repeatability.

摘要翻译： 针对计算机视觉应用描述了结构引导图像估计和测量方法。 结构指导估计的结果是几何实体的象征性表示，如线，点，弧和圆。 符号表示通过增加在图像特征与结构实体的匹配中使用的像素数量来促进子像素测量，改善图像内的结构实体的检测，对每个图像样本对正在进行的测量的贡献加权，以及 优化该贡献。在结构指导估计之后，几何实体由其符号表示来表示。 可以使用几何实体的符号表示来进行结构指导测量。 从符号表示进行的测量不受图像分辨率或像素量化误差的限制，因此可以产生子像素精度和重复性。