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

US08265390B2 Probabilistic segmentation in computer-aided detection 有权
标题翻译：计算机辅助检测中的概率分割
公开(公告)号：US08265390B2
公开(公告)日：2012-09-11
申请号：US12555799
申请日：2009-09-08
申请人： Shishir Dube , Sarang Lakare , Gerardo Hermosillo Valadez , Yoshihisa Shinagawa
发明人： Shishir Dube , Sarang Lakare , Gerardo Hermosillo Valadez , Yoshihisa Shinagawa
IPC分类号： G06K9/00
CPC分类号： G06K9/342 , G06T5/002 , G06T5/40 , G06T7/11 , G06T7/187 , G06T2207/30068
摘要： Described herein is a method and system for facilitating segmentation of images. A difference image is received and processed to extract at least one histogram (402). A noise component is determined by fitting a symmetric Gaussian distribution to the extracted histogram such that the negative portion of the Gaussian distribution coincides with the negative portion of the histogram (403). The noise component is then subtracted from the histogram to generate a probability distribution function (404), which may be converted to a cumulative distribution function (406) and applied to the difference image to generate a probabilistic representation of contrast enhancement (408).
摘要翻译：这里描述了一种便于图像分割的方法和系统。差分图像被接收和处理以提取至少一个直方图（402）。通过将对称高斯分布拟合到所提取的直方图来确定噪声分量，使得高斯分布的负部分与直方图（403）的负部分重合。然后从直方图中减去噪声分量以产生概率分布函数（404），该概率分布函数可被转换为累积分布函数（406）并应用于差分图像以生成对比度增强的概率表示（408）。

2. 发明授权

US08121366B2 Alignment of fat-sat and non-fat-sat T1 weighted images in MRI applications 失效
标题翻译：脂肪饱和和非脂肪饱和T1加权图像在MRI应用中的比对
公开(公告)号：US08121366B2
公开(公告)日：2012-02-21
申请号：US12204935
申请日：2008-09-05
申请人： Gerardo Hermosillo Valadez , Yoshihisa Shinagawa
发明人： Gerardo Hermosillo Valadez , Yoshihisa Shinagawa
IPC分类号： G06K9/00 , G06K9/62
CPC分类号： G01R33/56 , G01R33/4828 , G01R33/5607 , G01R33/5608 , G06T7/35 , G06T2207/10088 , G06T2207/30004
摘要： A method for aligning medical images, including: generating a learned joint distribution of intensities of corresponding voxels of images acquired by a first modality and a second modality, wherein the first and second modalities are different from each other; acquiring a first image of a patient using the first modality; acquiring a second image of the patient using the second modality; and aligning the first and second images based on the learned joint distribution.
摘要翻译：一种用于对准医学图像的方法，包括：产生通过第一模态和第二模态获取的图像的相应体素的强度的学习关联分布，其中所述第一和第二模态彼此不同; 使用所述第一模态获取患者的第一图像; 使用所述第二模式获取所述患者的第二图像; 以及基于所学习的联合分布来对准所述第一和第二图像。

3. 发明申请

US20100061609A1 Quotient Appearance Manifold Mapping For Image Classification 有权
标题翻译：商品外观图像分类图
公开(公告)号：US20100061609A1
公开(公告)日：2010-03-11
申请号：US12502510
申请日：2009-07-14
申请人： Yoshihisa Shinagawa , Yuping Lin , Gerardo Hermosillo Valadez , Bing Jian
发明人： Yoshihisa Shinagawa , Yuping Lin , Gerardo Hermosillo Valadez , Bing Jian
IPC分类号： G06K9/62 , G06K9/00
CPC分类号： G06K9/6252 , G06K9/6212 , G06T7/0012 , G06T2207/10072 , G06T2207/20081 , G06T2207/30032 , G06T2207/30064 , G06T2207/30068
摘要： Described herein is a technology for facilitating classification of an object. In one implementation, at least one quotient appearance manifold mapping is constructed from a sample image to untangle appearance fiber bundles. A feature characteristic of the sample image may then be extracted based on the quotient appearance manifold mapping. A classifier may further be trained based on the extracted feature, and adapted for associating the object with an object class.
摘要翻译：这里描述了一种便于对象分类的技术。在一个实施方式中，从样本图像到外观纤维束的解交织构造至少一个商显示歧管映射。然后可以基于商出口歧管映射来提取样本图像的特征。还可以基于提取的特征进一步训练分类器，并且适于将对象与对象类相关联。

4. 发明申请

US20090034814A1 Expanded Pharmacokinetic Model for Population Studies in Breast Magnetic Resonance Imaging (MRI) 有权
标题翻译：乳腺磁共振成像（MRI）人口研究的扩展药代动力学模型
公开(公告)号：US20090034814A1
公开(公告)日：2009-02-05
申请号：US12181396
申请日：2008-07-29
申请人： Yoshihisa Shinagawa , Vandana Mohan , Gerardo Hermosillo Valadez
发明人： Yoshihisa Shinagawa , Vandana Mohan , Gerardo Hermosillo Valadez
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G01R33/5601 , G01R33/56366 , G06T2207/30068
摘要： A method for pharmacokinetic analysis, including: receiving time-series medical image data of a patient introduced with a contrast agent; identifying a reference region in the medical image data; identifying a plurality of points of interest in the medical image data; measuring an intensity of voxels in the reference region; and for each point of interest, measure an intensity of voxels therein, use the measured reference region and point of interest intensities to obtain an expression relating the point of interest's voxel concentration to that of the reference region, wherein the expression is a five-parameter nonlinear model with no reference to an arterial input function; and obtain values for each of the five-parameters by solving the expression and use the obtained values to determine whether the point of interest is malignant.
摘要翻译：一种用于药代动力学分析的方法，包括：接收引入了造影剂的患者的时间序列医学图像数据; 识别所述医学图像数据中的参考区域; 识别所述医学图像数据中的多个兴趣点; 测量参考区域中体素的强度; 并且对于每个感兴趣点，测量其中体素的强度，使用测量的参考区域和兴趣点强度来获得将兴趣点的体素浓度与参考区域的浓度相关联的表达式，其中表达式是五参数无参考动脉输入功能的非线性模型; 并通过求解表达式获得每个五个参数的值，并使用获得的值来确定兴趣点是否是恶性的。

5. 发明授权

US08160343B2 Efficient features for computer-aided detection 有权
标题翻译：高效的计算机辅助检测功能
公开(公告)号：US08160343B2
公开(公告)日：2012-04-17
申请号：US12423963
申请日：2009-04-15
申请人： Yoshihisa Shinagawa , Gerardo Hermosillo Valadez , Bing Jian
发明人： Yoshihisa Shinagawa , Gerardo Hermosillo Valadez , Bing Jian
IPC分类号： G06K9/00
CPC分类号： G06T7/0016 , G06T2207/10096 , G06T2207/20012 , G06T2207/30068 , G06T2207/30096
摘要： A technology for facilitating computer-aided detection (CAD) includes in one implementation, receiving an enhancement pattern (602) generated from image data. The enhancement pattern is pre-processed to produce an alert level (604, 606, 608). Computationally-intensive analysis may be performed on a region of interest if it corresponds to an enhancement pattern with a high alert level.
摘要翻译：一种用于促进计算机辅助检测（CAD）的技术包括在一个实现中，接收从图像数据生成的增强图案（602）。增强模式被预处理以产生警报级别（604,606,608）。如果对应于具有高警报级别的增强模式，则可以在感兴趣的区域上执行计算密集型分析。

6. 发明授权

US08144952B2 Expanded pharmacokinetic model for population studies in breast magnetic resonance imaging (MRI) 有权
标题翻译：乳腺磁共振成像（MRI）中群体研究的扩展药代动力学模型
公开(公告)号：US08144952B2
公开(公告)日：2012-03-27
申请号：US12181396
申请日：2008-07-29
申请人： Yoshihisa Shinagawa , Vandana Mohan , Gerardo Hermosillo Valadez
发明人： Yoshihisa Shinagawa , Vandana Mohan , Gerardo Hermosillo Valadez
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G01R33/5601 , G01R33/56366 , G06T2207/30068
摘要： A method for pharmacokinetic analysis, including: receiving time-series medical image data of a patient introduced with a contrast agent; identifying a reference region in the medical image data; identifying a plurality of points of interest in the medical image data; measuring an intensity of voxels in the reference region; and for each point of interest, measure an intensity of voxels therein, use the measured reference region and point of interest intensities to obtain an expression relating the point of interest's voxel concentration to that of the reference region, wherein the expression is a five-parameter nonlinear model with no reference to an arterial input function; and obtain values for each of the five-parameters by solving the expression and use the obtained values to determine whether the point of interest is malignant.
摘要翻译：一种用于药代动力学分析的方法，包括：接收引入了造影剂的患者的时间序列医学图像数据; 识别所述医学图像数据中的参考区域; 识别所述医学图像数据中的多个兴趣点; 测量参考区域中体素的强度; 并且对于每个感兴趣点，测量其中体素的强度，使用测量的参考区域和兴趣点强度来获得将兴趣点的体素浓度与参考区域的浓度相关联的表达式，其中表达式是五参数无参考动脉输入功能的非线性模型; 并通过求解表达式获得每个五个参数的值，并使用获得的值来确定兴趣点是否是恶性的。

7. 发明申请

US20090080741A1 Multi-Scale Analysis of Signal Enhancement in Breast MRI 有权
标题翻译：乳腺MRI信号增强多尺度分析
公开(公告)号：US20090080741A1
公开(公告)日：2009-03-26
申请号：US12206804
申请日：2008-09-09
申请人： Yoshihisa Shinagawa , Gerardo Hermosillo Valadez
发明人： Yoshihisa Shinagawa , Gerardo Hermosillo Valadez
IPC分类号： G06K9/00 , A61B5/055
CPC分类号： G01R33/5601 , G01R33/5608 , G06K9/4609 , G06K2209/05 , G06T5/50 , G06T7/0012 , G06T7/11 , G06T7/174 , G06T2207/10088 , G06T2207/20224 , G06T2207/30068 , G06T2207/30096
摘要： A method for computer assisted lesion detection in magnetic resonance (MR) images includes acquiring dynamic contrast enhanced (DCE) MR images. The images are processed to produce a subtraction image illustrating change in voxel enhancement between the images. A Gaussian low-pass filter is applied to the subtraction image. An elimination mask is created from the filtered subtraction image by removing voxels with enhancement values below a threshold value. The elimination mask is used to remove noise from the subtraction image. One or more regions of suspicion are automatically detected from the noise-removed subtraction image. To produce the subtraction image, DCE-MR images are divided into first and second sub-sets. Positive-signed enhancement values of voxels of the MR images from the first sub-set are added to a combined subtraction image along with absolute values of all enhancement values of voxels of the MR images from the second sub-set.
摘要翻译：用于磁共振（MR）图像中计算机辅助病变检测的方法包括采集动态对比度增强（DCE）MR图像。图像被处理以产生减影图像，说明图像之间的体素增强的变化。将高斯低通滤波器应用于减法图像。通过去除具有低于阈值的增强值的体素，从滤波的减法图像创建消除掩模。消除掩模用于从减影图像中去除噪声。从噪声消除的减影图像中自动检测一个或多个怀疑区域。为了产生减法图像，DCE-MR图像被分成第一和第二子集。来自第一子集的MR图像的体素的正号增强值与来自第二子集的MR图像的体素的所有增强值的绝对值相加到组合减影图像。

8. 发明申请

US20090067751A1 Alignment of Fat-Sat and Non-Fat-Sat T1 Weighted Images in MRI Applications 失效
标题翻译：脂肪 - 星期六和非脂肪 - 星期六T1加权图像在MRI应用中的比对
公开(公告)号：US20090067751A1
公开(公告)日：2009-03-12
申请号：US12204935
申请日：2008-09-05
申请人： Gerardo Hermosillo Valadez , Yoshihisa Shinagawa
发明人： Gerardo Hermosillo Valadez , Yoshihisa Shinagawa
IPC分类号： G06K9/54
CPC分类号： G01R33/56 , G01R33/4828 , G01R33/5607 , G01R33/5608 , G06T7/35 , G06T2207/10088 , G06T2207/30004
摘要： A method for aligning medical images, including: generating a learned joint distribution of intensities of corresponding voxels of images acquired by a first modality and a second modality, wherein the first and second modalities are different from each other; acquiring a first image of a patient using the first modality; acquiring a second image of the patient using the second modality; and aligning the first and second images based on the learned joint distribution.
摘要翻译：一种用于对准医学图像的方法，包括：产生通过第一模态和第二模态获取的图像的相应体素的强度的学习关联分布，其中所述第一和第二模态彼此不同; 使用所述第一模态获取患者的第一图像; 使用所述第二模式获取所述患者的第二图像; 以及基于所学习的联合分布来对准所述第一和第二图像。

9. 发明申请

US20090067693A1 Automatic Calibration of Computer Aided Diagnosis Based on Retrospective Examination 有权
标题翻译：基于回顾性检查的计算机辅助诊断自动校准
公开(公告)号：US20090067693A1
公开(公告)日：2009-03-12
申请号：US12204870
申请日：2008-09-05
申请人： Yoshihisa Shinagawa , Gerardo Hermosillo Valadez
发明人： Yoshihisa Shinagawa , Gerardo Hermosillo Valadez
IPC分类号： A61B5/00
CPC分类号： G06T7/0012
摘要： A method for automatic detection of lesions within a medical image include acquiring medical image data. Regions of suspicion are automatically identified within the medical image data. It is automatically determined whether each identified region of suspicion is of a benign state, is of a suspicious state that requires a biopsy, or is of an indeterminate state that requires subsequent imaging after a particular length of time. When an identified region of suspicion is determined to be of an indeterminate state, the determination is automatically reconsidered in light of a calibration factor that biases the automatic determination towards either a benign state or a suspicious state. The calibration factor may be based on data collected from follow-up examinations that reveal whether a lesion previously characterized as indeterminate was actually a benign or malignant lesion or on additional diagnostic information including prior image data or non-image data.
摘要翻译：用于自动检测医学图像内的病变的方法包括获取医学图像数据。怀疑区域在医学图像数据内自动识别。自动确定每个识别的怀疑区域是否处于良性状态，是需要活组织检查的可疑状态，或者是在特定时间长度之后需要后续成像的不确定状态。当识别出的怀疑区域被确定为不确定状态时，根据将自动判定偏向良性状态或可疑状态的校准因素自动重新确定该确定。校准因子可以基于从随访检查中收集的数据，其揭示先前特征为不确定性的病变实际上是良性或恶性病变，还是包括先前图像数据或非图像数据的附加诊断信息。

10. 发明授权

US08331641B2 System and method for automatically classifying regions-of-interest 有权
标题翻译：自动分类感兴趣区域的系统和方法
公开(公告)号：US08331641B2
公开(公告)日：2012-12-11
申请号：US12549381
申请日：2009-08-28
申请人： Gerardo Hermosillo Valadez , Bing Jian , Yoshihisa Shinagawa
发明人： Gerardo Hermosillo Valadez , Bing Jian , Yoshihisa Shinagawa
IPC分类号： G06K9/00 , A61B6/04
CPC分类号： G06K9/3233 , G06T7/0012 , G06T2207/10096 , G06T2207/20104 , G06T2207/30068
摘要： Described herein is a method and system for facilitating automatic classification of regions-of-interest (ROIs). Contrast enhanced image data may be received (202) and processed to generate at least one texture value of at least one ROI in the image data (204). The ROI may be automatically classified as either a mass or a non-mass like enhancement (NMLE) based on the texture value (e.g., bumpiness) (208).
摘要翻译：这里描述的是用于促进兴趣区域（ROI）的自动分类的方法和系统。对象增强图像数据可以被接收（202）并被处理以在图像数据（204）中生成至少一个ROI的至少一个纹理值。基于纹理值（例如，颠簸），ROI可以被自动分类为质量或非质量像增强（NMLE）（208）。

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