公开(公告)号：US07248728B2

公开(公告)日：2007-07-24

申请号：US10384737

申请日：2003-03-11

Applicant: Hideya Takeo

Inventor： Hideya Takeo

IPC: G06K9/00

CPC classification number: G06T7/0012

Abstract: In an abnormal shadow detecting system, a mammary gland distribution map generating system generates a mammary gland distribution map of each of left and right breasts by dividing an image of each of the left and right breasts into a plurality of ranges according to the density of the image on the basis of image data representing the image, and an extracting system extracts a bilaterally asymmetric range by comparing the ranges of the mammary gland distribution map for one of the left and right breasts with those of the mammary gland distribution map for the other breast.

Abstract translation: 在异常阴影检测系统中，乳腺分布图生成系统通过将左乳房和右乳房中的每一个的图像分成多个范围来生成左乳房和右乳房中的每一个的乳腺分布图， 基于表示图像的图像数据的图像，并且提取系统通过比较左乳房和右乳房之一的乳腺分布图与另一乳房的乳腺分布图的范围来提取双侧不对称范围 。

公开(公告)号：US07123773B2

公开(公告)日：2006-10-17

申请号：US09778908

申请日：2001-02-08

Applicant: Hideya Takeo

Inventor： Hideya Takeo

IPC: G06K9/36

CPC classification number: H04N19/63 ,  H04N19/124

Abstract: A multiresolution coding section includes a wavelet transformation section for performing a wavelet transformation process on an image signal to obtain coefficient signals, a coefficient transformation section for performing a coefficient transformation process, which corresponds to image processing, on the coefficient signals to obtain processed coefficient signals, and a coding section for performing a coding process on the processed coefficient signals to obtain processed coded data. A restoration section includes a decoding section for decoding the processed coded data to obtain the processed coefficient signals, and an inverse wavelet transformation section for performing an inverse wavelet transformation process on the processed coefficient signals to obtain a processed image signal subjected to the image processing. In the process of transforming an image signal to coded data, image processing is performed in parallel with a coding process so that a processed image can be quickly displayed only by performing a restoration process.

Abstract translation: 多分辨率编码部分包括用于对图像信号执行小波变换处理以获得系数信号的小波变换部分，用于对系数信号执行对应于图像处理的系数变换处理的系数变换部分，以获得经处理的系数信号 以及编码部分，用于对所处理的系数信号执行编码处理以获得经处理的编码数据。 恢复部分包括用于对经处理的编码数据进行解码以获得经处理的系数信号的解码部分和用于对经处理的系数信号执行逆小波变换处理的逆小波变换部分，以获得经过图像处理的经处理的图像信号。 在将图像信号变换为编码数据的过程中，与编码处理并行地执行图像处理，使得只有通过执行恢复处理才能快速显示处理的图像。

公开(公告)号：US20060050944A1

公开(公告)日：2006-03-09

申请号：US11216146

申请日：2005-09-01

Applicant: Hideya Takeo ,  Chou Shi

Inventor： Hideya Takeo ,  Chou Shi

IPC: G06K9/00

CPC classification number: G06T7/0012 ,  G06K9/3233 ,  G06K2209/051 ,  G06T7/12 ,  G06T7/155 ,  G06T7/70 ,  G06T2207/10116 ,  G06T2207/30068

Abstract: The outline of a breast is detected based on breast image data representing a breast image obtained by photographing the breast. Then, a nipple projection portion, which locally projects outward from the outline of the breast, is detected based on the information about the outline of the breast.

Abstract translation: 基于通过拍摄乳房获得的表示乳房图像的乳房图像数据来检测乳房的轮廓。 然后，基于关于乳房轮廓的信息来检测从乳房轮廓向外突出的乳头突出部。

公开(公告)号：US20050036669A1

公开(公告)日：2005-02-17

申请号：US10897397

申请日：2004-07-23

Applicant: Hideya Takeo ,  Akio Ofuji

Inventor： Hideya Takeo ,  Akio Ofuji

IPC: A61B6/00 ,  G06K9/00 ,  G06T5/00 ,  G06T7/00

CPC classification number: G06T7/0012

Abstract: Microcalcification patterns within images are more accurately detected. A candidate point extracting means extracts candidate points for calcification points from an image. A first removal means performs judgment regarding whether the candidate points are calcification points or noise, based on first characteristic amounts that focus on the calcification points themselves, and based on second characteristic amounts that focus on the vicinities of calcification points. Candidate points which are judged to be noise components are removed. A second removal means performs judgment regarding whether the candidate points, which remain after the removal process by the first removal means, are calcification points or noise, based on third characteristic amounts that focus on cluster regions of calcification points. Cluster regions formed of noise components are removed, and a detecting means 240 detects the remaining cluster regions as microcalcification patterns.

Abstract translation: 更准确地检测图像内的微钙化模式。 候选点提取装置从图像中提取钙化点的候选点。 第一去除装置根据基于钙化点本身的第一特征量，并且基于关注于钙化点附近的第二特征量来判定候选点是钙化点还是噪声。 被判断为噪声成分的候选点被去除。 第二去除装置根据关注于钙化点的聚类区域的第三特征量来执行关于由第一去除装置移除处理之后留下的候选点是否为钙化点或噪声的判断。 去除由噪声分量形成的簇区域，检测装置240将剩余的簇区域作为微钙化模式进行检测。

公开(公告)号：US06269178B1

公开(公告)日：2001-07-31

申请号：US08927257

申请日：1997-09-11

Applicant: Hideya Takeo

Inventor： Hideya Takeo

IPC: G06K900

CPC classification number: G06T7/0012

Abstract: Iris filter processing is carried out on an image signal, which has been obtained by reading out a radiation image of an object. An output value of the iris filter processing and a predetermined threshold value are compared with each other. In the comparison, the threshold value is decreased as an image signal value, which represents a picture element subjected to the iris filter processing, becomes small. A prospective abnormal pattern, which is embedded in the radiation image, is extracted in accordance with the results of the comparison. The prospective abnormal pattern is thus detected accurately such that considerable time and labor may not be required for a person, who views a radiation image, to make a judgment.

Abstract translation: 对通过读出对象的放射线图像而获得的图像信号进行虹膜滤波处理。 将虹膜滤波处理的输出值和规定的阈值进行比较。 在比较中，由于表示经过虹膜滤波处理的像素的图像信号值变小，阈值减小。 根据比较结果提取嵌入放射线图像的预期异常模式。 因此准确地检测到预期的异常模式，使得对于观察放射线图像的人作出判断可能不需要相当长的时间和劳动。

公开(公告)号：US6125215A

公开(公告)日：2000-09-26

申请号：US299231

申请日：1999-04-26

Applicant: Hideya Takeo ,  Masahiko Yamada ,  Nobuyoshi Nakajima

Inventor： Hideya Takeo ,  Masahiko Yamada ,  Nobuyoshi Nakajima

IPC: G06K9/00 ,  G06K9/36 ,  G06K9/40 ,  G06K9/42 ,  G06K9/56 ,  G06T5/20 ,  G06T5/30 ,  G06T5/40 ,  G06T7/00 ,  H04N1/387 ,  H04N1/393

CPC classification number: G06T7/0012 ,  G06K9/4609 ,  G06T5/004 ,  G06T5/008 ,  G06T5/30 ,  G06T7/0004 ,  G06T2207/10116 ,  G06T2207/20044 ,  G06T2207/30068

Abstract: An operation of an iris filter is carried out on an original image signal representing an image, and the degree of centralization of gradients of the original image signal with respect to a picture element is thereby calculated, each of picture elements constituting the image being taken as the picture element. An image portion, which is associated with a high degree of centralization, in the image is detected in accordance with the calculated degree of centralization. Image emphasis processing is then selectively carried out on the detected image portion. Alternatively, a morphology operation is carried out on an original image signal Dorg by using a multiply structure element Bi and a scale factor .lambda., and a morphology signal Dmor is thereby obtained. The morphology signal Dmor represents whether each of picture elements constituting the image is or is not the one corresponding to an image portion, at which the original image signal Dorg fluctuates in a spatially narrower range than the multiply structure element Bi. Image emphasis processing is then carried out on the original image signal Dorg and in accordance with the morphology signal Dmor.

公开(公告)号：US5796870A

公开(公告)日：1998-08-18

申请号：US635387

申请日：1996-04-19

Applicant: Hideya Takeo

Inventor： Hideya Takeo

IPC: G03B42/02 ,  A61B6/00 ,  G06T5/20 ,  H04N1/407 ,  H04N1/41 ,  G06K9/00

CPC classification number: G06T5/004 ,  G06T5/20

Abstract: An unsharp mask signal Lu, which corresponds to super-low frequency, is calculated from an original image signal Dorg representing an original image. The rate of compression, at which the dynamic range of the original image is compressed, is changed in accordance with the unsharp mask signal Lu. A dynamic range compressing process is carried out with respect to each of picture elements in the original image, with the rate of compression being thus changed for each of the picture elements. The dynamic range compressing process is carried out with Formula (1) Dproc=Dorg+f(Lu) (1) and a processed image signal Dproc is thereby obtained. The unsharp mask signal Lu represents the mean value of the image signal values of all picture elements located within a rectangular unsharp mask having shorter sides, which extend across an edge of a region of interest in the original image, and longer sides extending in the direction along which the edge extends.

Abstract translation: 从表示原始图像的原始图像信号Dorg计算对应于超低频率的钝化掩模信号Lu。 压缩原始图像的动态范围的压缩率根据钝化掩模信号Lu而改变。 对于原始图像中的每个图像元素执行动态范围压缩处理，因此针对每个图像元素改变压缩率。 通过公式（1）Dproc = Dorg + f（Lu）（1）进行动态范围压缩处理，从而获得经处理的图像信号Dproc。 钝化掩模信号Lu表示位于具有短边的矩形钝化掩模内的所有图像元素的图像信号值的平均值，其延伸越过原始图像中的感兴趣区域的边缘，并且沿着方向 沿边缘延伸。

公开(公告)号：US5157733A

公开(公告)日：1992-10-20

申请号：US712214

申请日：1991-06-07

Applicant: Hideya Takeo ,  Kazuhiro Hishinuma ,  Kazuo Shimura ,  Nobuyoshi Nakajima ,  Shoji Hara ,  Hiroshi Tanaka ,  Takefumi Nagata

Inventor： Hideya Takeo ,  Kazuhiro Hishinuma ,  Kazuo Shimura ,  Nobuyoshi Nakajima ,  Shoji Hara ,  Hiroshi Tanaka ,  Takefumi Nagata

IPC: G06T7/00

CPC classification number: G06T7/004 ,  G06T7/00 ,  G06T2207/30004 ,  Y10S128/925

Abstract: In a radiation image processing apparatus, signal processing for determining the shape and location of an irradiation field, adjusting read-out conditions for a final readout from a preliminary read-out image signal, adjusting image processing conditions, and/or detecting an abnormal pattern is carried out on an image signal representing a radiation image by using a neural network. After the neural network, the learning operations of which have been carried out, is incorporated into the radiation image processing apparatus, modifying information is entered from an input device into the neural network. The modifying information is used to modify the signal processing carried out by the neural network and thereby to carry out re-learning operations of the neural network.

Abstract translation: 在放射线图像处理装置中，用于确定照射场的形状和位置的信号处理，从初步读出图像信号调整用于最终读出的读出条件，调整图像处理条件和/或检测异常模式 通过使用神经网络对表示放射线图像的图像信号进行。 在已经进行了学习操作的神经网络被并入放射线图像处理装置之后，将修改信息从输入装置输入到神经网络中。 修改信息用于修改由神经网络执行的信号处理，从而执行神经网络的重新学习操作。

公开(公告)号：US5055682A

公开(公告)日：1991-10-08

申请号：US397818

申请日：1989-08-24

Applicant: Hideya Takeo

Inventor： Hideya Takeo

IPC: G06T7/00

CPC classification number: G06T7/004 ,  G06T2207/30004

Abstract: A method for judging an irradiation field comprising steps to obtain an image signal including a plurality of image signal components corresponding to picture elements located on a recording medium from an image readout from the recording medium on which a radiation image of an object has been recorded. The shape and location of a region, which is considered to be an irradiation field formed on the recording medium, are determined on the basis of the image signal components. The ratio of the number of picture elements located in the region to the total number of the picture elements located on the recording medium is calculated and compared with a predetermined value. In cases where the ratio is not larger than the predetermined value, it is judged that the region is not the whole are of the irradiation field.

Abstract translation: 一种用于判断照射场的方法，包括以下步骤：从已经记录了物体的放射线图像的记录介质读出的图像中获得包括对应于位于记录介质上的像素的多个图像信号分量的图像信号。 基于图像信号分量确定被认为是形成在记录介质上的照射场的区域的形状和位置。 计算位于该区域中的图像元素数目与位于记录介质上的图像元素总数之比，​​并将其与预定值进行比较。 在比例不大于预定值的情况下，判断该区域不是整个照射场。

公开(公告)号：US07499577B2

公开(公告)日：2009-03-03

申请号：US11493596

申请日：2006-07-27

Applicant: Hideya Takeo

Inventor： Hideya Takeo

IPC: G06K9/00

CPC classification number: G06T7/0012 ,  G06T2207/30068 ,  Y10S128/92 ,  Y10S128/922

Abstract: A prospective abnormal shadow detecting system detects a prospective abnormal shadow in an image on the basis of image data representing the image and outputs information on the prospective abnormal shadow detected by the prospective abnormal shadow detecting means. Whether the detected prospective abnormal shadow is malignant or benignant is judged, and the information on the prospective abnormal shadow is output in such a manner that whether the prospective abnormal shadow is malignant or benignant can be distinguished.

Abstract translation: 预期异常阴影检测系统基于表示图像的图像数据检测图像中的预期异常阴影，并输出由预期异常阴影检测装置检测到的预期异常阴影的信息。 判断检测到的预期异常阴影是恶性还是良性，并且以预测异常阴影是否恶性或良性可以区分的方式输出关于预期异常阴影的信息。