公开(公告)号：US20070092121A1

公开(公告)日：2007-04-26

申请号：US11516211

申请日：2006-09-06

申请人： Senthil Periaswamy ,  Yangming Ou ,  Anna Jerebko

发明人： Senthil Periaswamy ,  Yangming Ou ,  Anna Jerebko

IPC分类号： G06K9/00 ,  G06K9/68

CPC分类号： G06T7/0012 ,  G06T7/12 ,  G06T7/143 ,  G06T2207/10088 ,  G06T2207/30012

摘要： A method of extracting a spinal cord from a digitized medical image includes providing a digitized medical image, selecting a set of points from said image as candidates for belonging to the spine, initializing a probability for each candidate point to belong to said spine, minimizing a weighted sum of square differences of image intensities of said candidate points and intensities determined by a mathematical model of said spine to estimate parameter values for said model, calculating a residual error for each point from the differences at each point between an estimated image intensity calculated from said estimated model parameters and an actual image intensity, updating the candidate point probabilities from said residual errors, and eliminating candidate points whose probability falls below a predetermined value.

摘要翻译： 从数字化医学图像提取脊髓的方法包括提供数字化的医学图像，从所述图像中选择一组点作为属于脊柱的候选，初始化每个候选点属于所述脊柱的概率，最小化 所述候选点的图像强度的平方差的加权和和由所述脊柱的数学模型确定的强度估计用于估计所述模型的参数值，根据从每个点处的差值计算每个点的残差， 所述估计模型参数和实际图像强度，从所述残差错误中更新候选点概率，以及消除概率低于预定值的候选点。

公开(公告)号：US08805122B1

公开(公告)日：2014-08-12

申请号：US13020138

申请日：2011-02-03

申请人： Senthil Periaswamy

发明人： Senthil Periaswamy

IPC分类号： G06K9/00

CPC分类号： G06T3/4007

摘要： Disclosed herein are a computer system, an image processing method, and a computer-readable medium for interpolating volumetric medical image data. There is disclosed a hybrid interpolation procedure performed on the volumetric medical image data in accordance with spatial transforms. In the hybrid interpolation procedure, a different order of interpolation, respectively, is performed for at least two different dimensions of the volumetric medical image data. The different orders of interpolation can include bicubic interpolation and linear interpolation. Applications include registration of source volumetric medical images to target volumetric medical images and operations (e.g., rotation, re-scaling) invoking a transformation for medical image data visualization/display purposes.

摘要翻译： 本文公开了一种用于内插体积医学图像数据的计算机系统，图像处理方法和计算机可读介质。 公开了根据空间变换对体积医学图像数据执行的混合插值程序。 在混合插值程序中，针对容积医学图像数据的至少两个不同维度分别执行不同的插值次序。 插值的不同顺序可以包括双三次插值和线性插值。 应用包括将源体积医学图像登记到目标体积医学图像和调用用于医学图像数据可视化/显示目的的变换的操作（例如，旋转，重新缩放）。

公开(公告)号：US08472684B1

公开(公告)日：2013-06-25

申请号：US12797231

申请日：2010-06-09

申请人： Senthil Periaswamy

发明人： Senthil Periaswamy

IPC分类号： G06K9/00 ,  G06K9/32

CPC分类号： G06K9/6289 ,  G06K2209/051 ,  G06T7/337 ,  G06T2207/10096 ,  G06T2207/20076 ,  G06T2207/20128 ,  G06T2207/30096

摘要： This invention provides a system and method for fusing and synthesizing a plurality of medical images defined by a plurality of imaging parameters that allow the visual enhancements of each image data set to be selectively combined with those of other image datasets. In this manner, a user-defined parameter set can be generated in the final response image dataset. This final response image dataset displays visual data represents a form particularly useful to the clinician. In an illustrative embodiment, the system for fusing and synthesizing the plurality of medical images provides an image fusion process/processor that fuses a plurality of magnetic resonance imaging (MRI) datasets. A first image dataset of the MRI datasets is defined by apparent diffusion coefficient (ADC) values. A second image dataset of the MRI datasets is defined by at least one parameter other than the ADC values. The image fusion processor generates a fused response image that visually displays a combination of image features generated by the ADC values combined with image features generated by the at least one parameter other than the ADC values. The fused response image can illustratively include at least one of color-enhanced regions of interest and intensity-enhanced regions of interest.

摘要翻译： 本发明提供了一种用于融合和合成由多个成像参数定义的多个医学图像的系统和方法，其允许每个图像数据集的视觉增强与其他图像数据集的视觉增强有选择地组合。 以这种方式，可以在最终响应图像数据集中生成用户定义的参数集。 该最终响应图像数据集显示视觉数据表示对临床医生特别有用的形式。 在说明性实施例中，用于融合和合成多个医学图像的系统提供融合多个磁共振成像（MRI）数据集的图像融合处理/处理器。 MRI数据集的第一个图像数据集由表观扩散系数（ADC）值定义。 MRI数据集的第二个图像数据集由除ADC值以外的至少一个参数定义。 图像融合处理器产生融合的响应图像，其在视觉上显示由与由ADC值以外的至少一个参数产生的图像特征组合的ADC值所生成的图像特征的组合。 融合响应图像可以说明性地包括感兴趣的增强色彩区域和强度增强区域中的至少一个。

公开(公告)号：US07756313B2

公开(公告)日：2010-07-13

申请号：US11592869

申请日：2006-11-03

申请人： Jinbo Bi ,  Senthil Periaswamy ,  Kazunori Okada ,  Toshiro Kubota ,  Glenn Fung ,  Marcos Salganicoff ,  R. Bharat Rao

发明人： Jinbo Bi ,  Senthil Periaswamy ,  Kazunori Okada ,  Toshiro Kubota ,  Glenn Fung ,  Marcos Salganicoff ,  R. Bharat Rao

IPC分类号： G06K9/00

CPC分类号： G06K9/6256 ,  G06K9/6282

摘要： A method for computer aided detection of anatomical abnormalities in medical images includes providing a plurality of abnormality candidates and features of said abnormality candidates, and classifying said abnormality candidates as true positives or false positives using a hierarchical cascade of linear classifiers of the form sign(wTx+b), wherein x is a feature vector, w is a weighting vector and b is a model parameter, wherein different weights are used to penalize false negatives and false positives, and wherein more complex features are used for each successive stage of said cascade of classifiers.

摘要翻译： 一种用于计算机辅助检测医学图像中的解剖异常的方法，包括提供所述异常候选的多个异常候选和特征，并且使用形式符号的线性分类器（wTx）的分级级联将所述异常候选分类为真正的肯定或假阳性 + b），其中x是特征向量，w是加权向量，b是模型参数，其中使用不同权重来惩罚假否定和假阳性，并且其中对于级联的每个连续阶段使用更复杂的特征 的分类器。

公开(公告)号：US20080050043A1

公开(公告)日：2008-02-28

申请号：US11841251

申请日：2007-08-20

申请人： Gerardo Hermosillo Valadez ,  Senthil Periaswamy

发明人： Gerardo Hermosillo Valadez ,  Senthil Periaswamy

IPC分类号： G06K9/32 ,  G06K9/00

CPC分类号： G06T7/0012 ,  G06K9/6206 ,  G06T7/32 ,  G06T7/38 ,  G06T2207/10072 ,  G06T2207/20221 ,  G06T2207/30004 ,  G06T2207/30096

摘要： A method for registering images, for example medical images, includes acquiring a first image. A second image is acquired. A deformation field for registering the second image to the first image is calculated. The deformation field includes a sum of a plurality of weighted distortion vectors each of which has a substantially Gaussian distribution. The calculated deformation field is applied to the second image to register it to the first image.

摘要翻译： 用于登记图像的方法，例如医学图像，包括获取第一图像。 获取第二张图像。 计算用于将第二图像登记到第一图像的变形场。 变形场包括多个加权失真矢量的和，每个加权失真矢量具有基本上高斯分布。 将计算的变形场应用于第二图像以将其注册到第一图像。

公开(公告)号：US20080050003A1

公开(公告)日：2008-02-28

申请号：US11841168

申请日：2007-08-20

申请人： Senthil Periaswamy ,  Marcos Salganicoff

发明人： Senthil Periaswamy ,  Marcos Salganicoff

IPC分类号： G06K9/00

CPC分类号： G06T7/0012 ,  G06K9/4609 ,  G06K2209/05 ,  G06T5/50 ,  G06T7/12 ,  G06T2207/10072 ,  G06T2207/10116 ,  G06T2207/30061 ,  G06T2207/30101

摘要： A method for detecting a substantially cylindrical internal structures and dark structures surrounded by bright intensity values (contrast) in a medical image includes acquiring a medical image. A gradient of the medical image is calculated. Local shape index information for the calculated gradient of the medical image is calculated. Gradient information having a local shape index not indicative of a ridge and rut shapes is removed. Diverging gradient field responses (DGFR) are calculated based on the remaining gradient information. The DGFR responses and relative amount of DGFR responses for the rut and ridge areas is used as a discriminative feature in detecting the substantially cylindrical internal structure as well as darker occluding structures within cylindrical structures such as Pulmonary Emboli.

摘要翻译： 用于检测医疗图像中由亮度值（对比度）包围的基本上圆柱形的内部结构和暗结构的方法包括获取医学图像。 计算医学图像的梯度。 计算医学图像的计算梯度的局部形状指数信息。 具有不表示脊和车辙形状的局部形状指标的梯度信息被去除。 基于剩余梯度信息计算发散梯度场响应（DGFR）。 用于车辙和脊部区域的DGFR响应和DGFR响应的相对量用作检测圆柱形结构（例如肺栓塞）中的基本上圆柱形的内部结构以及较暗的闭塞结构的鉴别特征。

公开(公告)号：US20060018555A1

公开(公告)日：2006-01-26

申请号：US11185602

申请日：2005-07-20

申请人： Pascal Cathier ,  Senthil Periaswamy

发明人： Pascal Cathier ,  Senthil Periaswamy

IPC分类号： G06K9/36

CPC分类号： G06T1/60

摘要： A method of storing a digital image in a computer memory includes providing a N-dimensional digital image, defining an offset for each image element (x1, . . . , xN) by the formula offset ⁡ ( x 1 , … ⁢   , x N ) = ∑ i ⁢   ⁢ ∑ n = 1 N ⁢   ⁢ K x n ⁡ ( i ) ⁢ x ni , where i is summed over all bits and n is summed over all dimensions. The coefficient K for the ith bit of the nth dimension is defined as K x n ⁡ ( i ) = ( ∏ j = 1 n - 1 ⁢   ⁢ f ⁡ ( x j , 2 i + 1 , sx j ) ) ⁢ 2 i ⁢ ( ∏ j = n + 1 N ⁢   ⁢ f ⁡ ( x j , 2 i , sx j ) ) , where xj is the jth dimension, f(x,G,sxj)=min(G,sxj−└x┘G) G is a power of 2, sxj represents the size associated with a given dimension, and └x┘G=x−x mod G. Image elements are stored in the computer memory in an order defined by the offset of each image element.

公开(公告)号：US09311705B1

公开(公告)日：2016-04-12

申请号：US13341528

申请日：2011-12-30

申请人： Sergey Fotin ,  Senthil Periaswamy

发明人： Sergey Fotin ,  Senthil Periaswamy

IPC分类号： G06K9/00 ,  G06T7/00

CPC分类号： G06T7/0014 ,  G06T7/74 ,  G06T2207/10088 ,  G06T2207/30081 ,  G06T7/0012 ,  A61B6/12

摘要： This invention provides a system, method and computer-readable medium for detecting and localizing organs and other regions of interest in medical image data provided by a medical imaging procedure using gradient template information with respect to an example of the imaged organ and cross-correlation techniques to generate object detection information. In an embodiment, the detection and localization process/processor receives a plurality of gradient templates and employers a template with the closest matching cross-correlation to the gradient of the organ in the medical image.

摘要翻译： 本发明提供了一种系统，方法和计算机可读介质，用于检测和定位由医学成像程序提供的医学图像数据中的器官和其他感兴趣区域，所述医学图像数据使用关于成像器官和互相关技术的示例的梯度模板信息 生成对象检测信息。 在一个实施例中，检测和定位处理/处理器接收多个梯度模板和雇主具有与医学图像中器官的梯度最接近的匹配互相关的模板。

公开(公告)号：US07912292B2

公开(公告)日：2011-03-22

申请号：US10985548

申请日：2004-11-10

申请人： Senthil Periaswamy ,  Luca Bogoni

发明人： Senthil Periaswamy ,  Luca Bogoni

IPC分类号： G06K9/00

CPC分类号： G06T7/0012 ,  G06K9/4609 ,  G06T7/64 ,  G06T2207/10081 ,  G06T2207/30028 ,  G06T2207/30032

摘要： A system and method for determining the presence or absence of candidate objects in a digital image by computing a gradient field of the digital image and then applying predetermined filters to the gradient field to obtain a response image which can be further processed to detect the objects. The application of these filters to the digital image can be performed by convolution and the filters can be adapted based on the shape of the object to be searched.

摘要翻译： 一种用于通过计算数字图像的梯度场然后将预定滤波器应用于梯度场来确定数字图像中候选对象的存在或不存在的系统和方法，以获得能够进一步处理以检测对象的响应图像。 可以通过卷积来执行这些滤波器到数字图像的应用，并且可以基于要搜索的对象的形状来适配滤波器。

公开(公告)号：US07657072B2

公开(公告)日：2010-02-02

申请号：US11516211

申请日：2006-09-06

申请人： Senthil Periaswamy ,  Yangming Ou ,  Anna Jerebko

发明人： Senthil Periaswamy ,  Yangming Ou ,  Anna Jerebko

IPC分类号： G06K9/00

CPC分类号： G06T7/0012 ,  G06T7/12 ,  G06T7/143 ,  G06T2207/10088 ,  G06T2207/30012

摘要： A method of extracting a spinal cord from a digitized medical image includes providing a digitized medical image, selecting a set of points from said image as candidates for belonging to the spine, initializing a probability for each candidate point to belong to said spine, minimizing a weighted sum of square differences of image intensities of said candidate points and intensities determined by a mathematical model of said spine to estimate parameter values for said model, calculating a residual error for each point from the differences at each point between an estimated image intensity calculated from said estimated model parameters and an actual image intensity, updating the candidate point probabilities from said residual errors, and eliminating candidate points whose probability falls below a predetermined value.

摘要翻译： 从数字化医学图像提取脊髓的方法包括提供数字化的医学图像，从所述图像中选择一组点作为属于脊柱的候选，初始化每个候选点属于所述脊柱的概率，最小化 所述候选点的图像强度的平方差的加权和和由所述脊柱的数学模型确定的强度估计用于估计所述模型的参数值，根据从每个点处的差值计算每个点的残差， 所述估计模型参数和实际图像强度，从所述残差错误中更新候选点概率，以及消除概率低于预定值的候选点。