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

US08265367B2 Identifying blood vessels in lung x-ray radiographs 有权
标题翻译：识别肺X线片中的血管
公开(公告)号：US08265367B2
公开(公告)日：2012-09-11
申请号：US12132381
申请日：2008-06-03
申请人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel , Sandesh Gupta
发明人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel , Sandesh Gupta
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G06T7/13 , G06T2207/10116 , G06T2207/30061 , G06T2207/30064
摘要： A method of detecting blood vessel shadows in an anterior posterior x-ray radiograph comprising the steps of: generating candidate sub areas of the radiograph showing changes in contrast above a threshold level; supressing rib shadow edges; eliminating lung tissue shadow edges, and categorizing and eliminating nodule shadows.
摘要翻译：一种检测前后X线放射照片中的血管阴影的方法，包括以下步骤：产生放射照片的候选子区域，其显示高于阈值水平的对比度的变化; 抵抗肋阴影边缘; 消除肺组织阴影边缘，并分类和消除结节阴影。

2. 发明申请

US20080298666A1 Identifying blood vessels in lung x-ray radiographs 有权
标题翻译：识别肺X线片中的血管
公开(公告)号：US20080298666A1
公开(公告)日：2008-12-04
申请号：US12132381
申请日：2008-06-03
申请人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel , Sandesh Gupta
发明人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel , Sandesh Gupta
IPC分类号： G06K9/78
CPC分类号： G06T7/0012 , G06T7/13 , G06T2207/10116 , G06T2207/30061 , G06T2207/30064
摘要： A method of detecting blood vessel shadows in an anterior posterior x-ray radiograph comprising the steps of: generating candidate sub areas of the radiograph showing changes in contrast above a threshold level; supressing rib shadow edges; eliminating lung tissue shadow edges, and categorizing and eliminating nodule shadows.
摘要翻译：一种检测前后X线放射照片中的血管阴影的方法，包括以下步骤：产生放射照片的候选子区域，其显示高于阈值水平的对比度的变化; 抵抗肋阴影边缘; 消除肺组织阴影边缘，并分类和消除结节阴影。

3. 发明申请

US20080317322A1 Identifying Ribs in Lung X-Rays 失效
标题翻译：识别龙X射线的肋骨
公开(公告)号：US20080317322A1
公开(公告)日：2008-12-25
申请号：US12132339
申请日：2008-06-03
申请人： Mausumi Acharyya , Sumit Chakravarty , Dinesh Mysore Siddu , Eliahu Ratner , Alexandra Manevitch , Jonathan Stoeckel
发明人： Mausumi Acharyya , Sumit Chakravarty , Dinesh Mysore Siddu , Eliahu Ratner , Alexandra Manevitch , Jonathan Stoeckel
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G06T7/13 , G06T2207/10116 , G06T2207/30061 , G06T2207/30064
摘要： A method of detecting lung nodules in an anterior posterior x-ray radiograph comprising the steps of: generating candidate regions in image showing changes in contrast above a threshold level, and eliminating false positives by eliminating edges assignable to organs by: identifying edges; categorizing and eliminating rib edges; categorizing and eliminating lung tissue edges, and categorizing and eliminating blood vessels.
摘要翻译：一种检测前后X线放射照片中的肺结节的方法，包括以下步骤：产生图像中的候选区域，所述候选区域显示对比度高于阈值水平的变化，以及通过以下方式消除假阳性：通过以下方式识别边缘; 分类和消除肋边缘; 分类和消除肺组织边缘，分类和消除血管。

4. 发明授权

US08150135B2 Identifying ribs in lung X-rays 失效
标题翻译：识别肺X线片中的肋骨
公开(公告)号：US08150135B2
公开(公告)日：2012-04-03
申请号：US12132339
申请日：2008-06-03
申请人： Mausumi Acharyya , Sumit Chakravarty , Dinesh Mysore Siddu , Eliahu Ratner , Alexandra Manevitch , Jonathan Stoeckel
发明人： Mausumi Acharyya , Sumit Chakravarty , Dinesh Mysore Siddu , Eliahu Ratner , Alexandra Manevitch , Jonathan Stoeckel
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G06T7/13 , G06T2207/10116 , G06T2207/30061 , G06T2207/30064
摘要： A method of detecting lung nodules in an anterior posterior x-ray radiograph comprising the steps of: generating candidate regions in image showing changes in contrast above a threshold level, and eliminating false positives by eliminating edges assignable to organs by: identifying edges; categorizing and eliminating rib edges; categorizing and eliminating lung tissue edges, and categorizing and eliminating blood vessels.
摘要翻译：一种检测前后X线放射照片中的肺结节的方法，包括以下步骤：产生图像中的候选区域，所述候选区域显示对比度高于阈值水平的变化，以及通过以下方式消除假阳性：通过以下方式识别边缘; 分类和消除肋边缘; 分类和消除肺组织边缘，分类和消除血管。

5. 发明申请

US20070248254A1 System and Method for Automatic Detection of Internal Structures in Medical Images 有权
标题翻译：医学图像内部结构自动检测系统与方法
公开(公告)号：US20070248254A1
公开(公告)日：2007-10-25
申请号：US11694050
申请日：2007-03-30
申请人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel
发明人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K2209/05 , G06T7/11 , G06T2207/10072 , G06T2207/20012 , G06T2207/30032 , G06T2207/30048 , G06T2207/30064
摘要： A medical imaging system is used to recognize an internal structure from a three-dimensional image. The image includes image sub-volumes. An image sub-volume is selected using a non-linear search pattern. The selected image sub-volume is analyzed for the presence of the internal structure. The steps of selecting an image sub-volume using the non-linear search pattern and analyzing the selected sub-volume for the presence of the internal structure are repeated until the internal structure is found in an image sub-volume. Bounds of the internal structure are identified based on the location of the image sub-volume within which the internal structure is found.
摘要翻译：医学成像系统用于从三维图像识别内部结构。图像包括图像子卷。使用非线性搜索模式选择图像子卷。分析所选图像子体积是否存在内部结构。重复使用非线性搜索模式选择图像子体积并分析所选择的子体积以存在内部结构的步骤，直到在图像子体积中找到内部结构。内部结构的界限是根据找到内部结构的图像子体积的位置进行识别的。

6. 发明授权

US08090178B2 System and method for automatic detection of internal structures in medical images 有权
标题翻译：医学图像内部结构的自动检测系统及方法
公开(公告)号：US08090178B2
公开(公告)日：2012-01-03
申请号：US11694050
申请日：2007-03-30
申请人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel
发明人： Dinesh Mysore Siddu , Mausumi Acharyya , Jonathan Stoeckel
IPC分类号： G06K9/00
CPC分类号： G06K9/4638 , G06K2209/05 , G06T7/11 , G06T2207/10072 , G06T2207/20012 , G06T2207/30032 , G06T2207/30048 , G06T2207/30064
摘要： A medical imaging system is used to recognize an internal structure from a three-dimensional image. The image includes image sub-volumes. An image sub-volume is selected using a non-linear search pattern. The selected image sub-volume is analyzed for the presence of the internal structure. The steps of selecting an image sub-volume using the non-linear search pattern and analyzing the selected sub-volume for the presence of the internal structure are repeated until the internal structure is found in an image sub-volume. Bounds of the internal structure are identified based on the location of the image sub-volume within which the internal structure is found.
摘要翻译：医学成像系统用于从三维图像识别内部结构。图像包括图像子卷。使用非线性搜索模式选择图像子卷。分析所选图像子体积是否存在内部结构。重复使用非线性搜索模式选择图像子体积并分析所选择的子体积以存在内部结构的步骤，直到在图像子体积中找到内部结构。内部结构的界限是根据找到内部结构的图像子体积的位置进行识别的。

7. 发明申请

US20090052763A1 Characterization of lung nodules 审中-公开
公开(公告)号：US20090052763A1
公开(公告)日：2009-02-26
申请号：US12132365
申请日：2008-06-03
申请人： Mausumi Acharyya , Sumit Chakravarty , Jonathan Stoeckel
发明人： Mausumi Acharyya , Sumit Chakravarty , Jonathan Stoeckel
IPC分类号： G06K9/00
CPC分类号： G06T7/0012 , G06T7/13 , G06T2207/10116 , G06T2207/20012 , G06T2207/30061 , G06T2207/30064 , G06T2207/30196
摘要： A method of identifying nodules in radiological images, said method comprising: (a) obtaining a radiological image; (b) selecting a sub-image centered around a candidate location; (c) dividing the sub-image into a rectangular array of cells; (d) calculating absolute values of Intensity Differences id(k) according to a Fractional Brownian Motion (FBM) calculation equation: id ( k ) = [ ∑ x = 0 N - 1  ∑ y = 0 N - k - 1   I  ( x , y ) - I  ( x , y + k )  4  N  ( N - k ) + ∑ y = 0 N - 1  ∑ x = 0 N - k - 1   I  ( x , y ) - I  ( x + k , y )  4  N  ( N - k ) + ∑ x = 0 N - 1 - k  ∑ y = 0 N - k - 1   I  ( x , y ) - I  ( x + k , y + k )  4  ( N - k ) 2 + ∑ x = 0 N - 1 - k  ∑ y = 0 N - k - 1   I  ( x , N - y ) - I  ( x + k , N - ( y + k ) )  4  ( N - k ) 2 ] , for k=1 to s; (e) calculating a NFBM feature, f(k), for each id(k): f(k)=log(id(k))−log(id(1); (f) integrating f(k), over k=1 to s; (i) classifying the cells into intensity contrast classes, according to intensity contrast between each cell and its neighbors, and the integration result; (k) remapping each cell of the sub-image according to its contrast class, and (m) determining the shape of the region of high-contrast cells in the sub-image, wherein an annular shape identifies a nodule.

8. 发明申请

US20100303358A1 METHOD FOR THE AUTOMATIC ANALYSIS OF IMAGE DATA OF A STRUCTURE 审中-公开
标题翻译：一种结构图像数据自动分析方法
公开(公告)号：US20100303358A1
公开(公告)日：2010-12-02
申请号：US12786853
申请日：2010-05-25
申请人： Mausumi Acharyya
发明人： Mausumi Acharyya
IPC分类号： G06K9/46 , G06T15/00
CPC分类号： A61B6/466 , A61B5/055 , A61B5/7264 , A61B5/7267 , A61B6/505 , G06T7/0014 , G06T7/41 , G06T2207/10081 , G06T2207/10088 , G06T2207/20021 , G06T2207/30008 , G16H50/50
摘要： A method is described for the automatic analysis of image data of a structure. in at least one embodiment, the method includes: providing image data in the form of a three-dimensional voxel array, performing segmentation of the voxel array in order to determine a voxel subset, performing feature extraction at least for particular voxels of the voxel subset in order to generate a feature map, generating a scalar difference map on the basis of the feature map, performing classification with the aid of the difference map and identifying a structural anomaly in the image data on the basis of a classification result. A method for driving an image display device, an image processing system and an imaging system are furthermore described.
摘要翻译：描述了用于结构的图像数据的自动分析的方法。在至少一个实施例中，该方法包括：以三维体素阵列的形式提供图像数据，执行体素阵列的分割以确定体素子集，至少对体素子集的特定体素进行特征提取为了生成特征图，基于特征图生成标量差图，借助差分图进行分类，基于分类结果来识别图像数据中的结构异常。进一步描述用于驱动图像显示装置，图像处理系统和成像系统的方法。

9. 发明授权

US08229195B2 Method and system for verifying detection of a lung nodule 有权
标题翻译：检测肺结节的方法和系统
公开(公告)号：US08229195B2
公开(公告)日：2012-07-24
申请号：US12540121
申请日：2009-08-12
申请人： Mausumi Acharyya
发明人： Mausumi Acharyya
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/6212 , G06T7/0012 , G06T7/136 , G06T7/44 , G06T2207/10116 , G06T2207/30064
摘要： Detected lung nodules are presented in a chest radiographic sub-image. A curve is matched to pixels in the sub-image and confidence values for individual pixels is determined. A confidence image is generated consisting of the confidence values at the position of the respective pixel. Separated regions of pixels within the confidence image are identified which have a confidence value greater than a threshold confidence value. A filtered confidence image is generated consisting of the separated regions of the confidence image which are larger than a threshold area. A histogram of values characteristic for the matching of the curve is determined, wherein the filtered confidence image is used as a mask, such that only values are considered for the histogram which correspond to the separated regions of the filtered confidence image. A statistical measure of the histogram is determined and the lung nodules are verified based on the statistical measure.
摘要翻译：检测到的肺结节呈现在胸部X光照相子图像中。曲线与子图像中的像素匹配，并确定各个像素的置信度值。产生由相应像素的位置处的置信度值组成的置信图像。识别置信图像内的像素的分离区域，其具有大于阈值置信度值的置信度值。生成由置信图像的分离区域大于阈值区域的经滤波的置信图像。确定曲线匹配特征值的直方图，其中滤波的置信图像用作掩模，使得对于对应于滤波的置信图像的分离区域的直方图仅考虑值。确定直方图的统计量度，并根据统计学方法验证肺结节。

10. 发明申请

US20100040269A1 METHOD AND SYSTEM FOR VERIFYING DETECTION OF A LUNG NODULE 有权
标题翻译：一种用于验证肺功能检测的方法和系统
公开(公告)号：US20100040269A1
公开(公告)日：2010-02-18
申请号：US12540121
申请日：2009-08-12
申请人： Mausumi Acharyya
发明人： Mausumi Acharyya
IPC分类号： G06K9/00
CPC分类号： G06K9/4604 , G06K9/6212 , G06T7/0012 , G06T7/136 , G06T7/44 , G06T2207/10116 , G06T2207/30064
摘要： Detected lung nodules are presented in a chest radiographic sub-image. A curve is matched to pixels in the sub-image and confidence values for individual pixels is determined. A confidence image is generated consisting of the confidence values at the position of the respective pixel. Separated regions of pixels within the confidence image are identified which have a confidence value greater than a threshold confidence value. A filtered confidence image is generated consisting of the separated regions of the confidence image which are larger than a threshold area. A histogram of values characteristic for the matching of the curve is determined, wherein the filtered confidence image is used as a mask, such that only values are considered for the histogram which correspond to the separated regions of the filtered confidence image. A statistical measure of the histogram is determined and the lung nodules are verified based on the statistical measure.
摘要翻译：检测到的肺结节呈现在胸部X光照相子图像中。曲线与子图像中的像素匹配，并确定各个像素的置信度值。产生由相应像素的位置处的置信度值组成的置信图像。识别置信图像内的像素的分离区域，其具有大于阈值置信度值的置信度值。生成由置信图像的分离区域大于阈值区域的经滤波的置信图像。确定曲线匹配特征值的直方图，其中滤波的置信图像用作掩模，使得对于对应于滤波的置信图像的分离区域的直方图仅考虑值。确定直方图的统计量度，并根据统计学方法验证肺结节。

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