公开(公告)号：WO9954705A3

公开(公告)日：2002-12-27

申请号：PCT/US9904290

申请日：1999-04-02

Applicant: ARCH DEV CORP

Inventor： ISHIDA TAKAYUKI ,  KATSURAGAWA SHIGEHIKO ,  DOI KUNIO

IPC: A61B6/00 ,  G01N20060101 ,  G06K9/00 ,  G06K9/80 ,  G06T1/00 ,  G06T3/00 ,  G06T5/40 ,  G06T7/00 ,  G06T7/20 ,  H04N5/325

CPC classification number: G06T7/0016 ,  G06T3/0068 ,  G06T7/254 ,  G06T7/337 ,  G06T2207/30061

Abstract: A method of computerized analysis of temporally sequential digital images, including (a) determining first shift values between pixels of a first digital image and corresponding pixels of a second digital image (440); (b) warping the second digital image based on the first shift values to obtain a first warped image in which spatial locations of pixels are varied in relation to the first shift values (450); (c) determining second shift values between pixels of the first digital image and pixels of the first warped image; and (d) warping the first warped image based on the second shift values to obtain a second warped image (470). Iterative warping enhances image for the first subtraction of the first digital image and the final warped image to produce a difference image (480).

Abstract translation: 一种对时间顺序数字图像进行计算机化分析的方法，包括：（a）确定第一数字图像的像素与第二数字图像的对应像素之间的第一移位值（440）; （b）基于第一移位值对第二数字图像进行翘曲以获得其中像素的空间位置相对于第一移位值变化的第一翘曲图像（450）; （c）确定第一数字图像的像素与第一翘曲图像的像素之间的第二移位值; 和（d）基于第二偏移值使第一翘曲图像翘曲以获得第二扭曲图像（470）。 迭代翘曲增强了第一数字图像和最终的弯曲图像的第一次减法的图像以产生差分图像（480）。

公开(公告)号：WO9905503A3

公开(公告)日：1999-04-15

申请号：PCT/US9815154

申请日：1998-07-24

Applicant: ARCH DEV CORP

Inventor： NISHIKAWA ROBERT M ,  JIANG YULEI ,  ASHIZAWA KAZUTO ,  DOI KUNIO

IPC: A61B6/00 ,  G06T1/00 ,  G06T7/00 ,  A61B5/05

CPC classification number: G06T7/0012 ,  Y10S128/925

Abstract: A computer-aided method for detecting, classifying, and displaying candidate abnormalities, such as microcalcifications and interstitial lung disease in digitized medical images, such as mammograms and chest radiographs, a computer programmed to implement the method, and a data structure for storing required parameters, wherein in the classifying method candidate abnormalities in a digitized medical image are located, regions are generated around one or more of the located candidate abnormalities, features are extracted from at least one of the located candidate abnormalities within the region and from the region itself, the extracted features are applied to a classification technique, such as an artificial neural network (ANN) to produce a classification result (i.e., probability of malignancy in the form of a number and a bar graph), and the classification result is displayed along with the digitized medical image annotated with the region and the candidate abnormalities within the region.

Abstract translation: 一种用于检测，分类和显示诸如乳房X线照片和胸片的数字医学图像中的微钙化和间质性肺病等候选异常的计算机辅助方法，用于实现该方法的程序化计算机以及用于存储所需参数的数据结构 其中，在所述分类方法中，定位了数字化医学图像中候选异常的区域，围绕所述定位候选异常中的一个或多个产生区域，从所述区域内和所述区域本身中的位置候选异常中的至少一个提取特征， 提取的特征被应用于诸如人造神经网络（ANN）的分类技术以产生分类结果（即以数字和条形图的形式的恶性的概率），并且分类结果与 用区域注释的数字化医学图像和r内的候选异常 egion。

公开(公告)号：WO0030021A9

公开(公告)日：2000-10-19

申请号：PCT/US9925998

申请日：1999-11-12

Applicant: ARCH DEV CORP ,  DOI KUNIO ,  NAKAMURA KATSUMI

Inventor： DOI KUNIO ,  NAKAMURA KATSUMI

IPC: A61B6/03 ,  A61B6/00 ,  G06K9/00 ,  G06T1/00 ,  G06T7/00

CPC classification number: G06T7/0012 ,  G06K9/00127

Abstract: A method, computer program product, and system (100) for computerized analysis of the likelihood of malignancy in a pulmonary nodule using artificial neural networks (ANNs) (S4). The method, on which the computer program product and the system is based on, includes obtaining a digital outline of a nodule; generating objective measures corresponding to physical features of the outline of the nodule; applying the generated objective measures to an ANN; and determining a likelihood of malignancy of the nodule based on an output of the ANN. Techniques include novel developments and implementations of artificial neural networks and feature extraction for digital images. Output from the inventive method yields an estimate of the likelihood of malignancy (S7) for a pulmonary nodule.

Abstract translation: 一种使用人工神经网络（ANN）（S4）对肺结节中的恶性可能性进行计算机化分析的方法，计算机程序产品和系统（100）。 计算机程序产品和系统所基于的方法包括获得结节的数字轮廓; 产生与结节轮廓的物理特征相对应的客观量度; 将所产生的客观措施应用于ANN; 以及基于ANN的输出确定结节恶性的可能性。 技术包括人工神经网络的新颖开发和实现以及数字图像的特征提取。 本发明方法的输出产生肺结节恶性可能性的估计（S7）。

公开(公告)号：WO9905639A8

公开(公告)日：1999-06-17

申请号：PCT/US9815278

申请日：1998-07-24

Applicant: ARCH DEV CORP

Inventor： YOSHIDA HIROYUKI ,  KATUSURAGAWA SHIGEHIKO ,  AMIT YALI ,  DOI KUNIO

IPC: G06K9/64 ,  G06T7/00 ,  G06K9/00

CPC classification number: G06K9/6206 ,  G06T7/0012

Abstract: A method and apparatus for discrimination of nodules and false positive in digital chest radiographs, using a wavelet snake technique (1802; 1804; 1806; 1808). The wavelet snake is a deformable contour designed to identify the boundary of a relatively round object (1900). The shape of the snake is determined by a set of wavelet coefficient in a certain range of scales. Portions of the boundary of a nodule are first extracted using a multiscale edge representation. The multiscale edge are then fitted (2000; 1814) by a gradient descent procedure which deforms the shape of a wavelet snake by changing its wavelet coefficients. The degree of overlap between the fitted snake and the multiscale edges is calculated and used as a fit quality indicator for discrimination of nodules and false detection (1816; 1818; 1820).

Abstract translation: 一种使用小波蛇技术（1802; 1804; 1806; 1808）来鉴别数字胸部X光片中的结节和假阳性的方法和装置。 小波蛇是一种可变形的轮廓，用于识别相对圆形物体的边界（1900）。 蛇的形状由一定尺度范围内的一组小波系数决定。 首先使用多尺度边缘表示来提取结节边界的部分。 然后通过梯度下降程序拟合多尺度边（2000; 1814），其通过改变其小波系数来变形小波蛇的形状。 计算拟合蛇和多尺度边缘之间的重叠程度，并将其用作区分结节和错误检测的适合质量指标（1816; 1818; 1820）。

公开(公告)号：WO0129770A3

公开(公告)日：2001-12-06

申请号：PCT/US0041299

申请日：2000-10-20

Applicant: ARCH DEV CORP

Inventor： LI QIANG ,  KATSURAGAWA SHIGEHIKO ,  DOI KUNIO

IPC: A61B6/00 ,  G06K9/00 ,  G06T1/00 ,  G06T3/00 ,  G06T5/00 ,  G06T5/50 ,  G06T7/00 ,  G06T7/60

CPC classification number: G06T3/0068 ,  G06T5/50 ,  G06T7/0012 ,  G06T7/12 ,  G06T7/149 ,  G06T7/174 ,  G06T7/344 ,  G06T2207/20061 ,  G06T2207/30008 ,  G06T2207/30061 ,  Y10S128/922

Abstract: A method, system and computer readable medium of computerized processing of chest images including obtaining digital first and second images of a chest and detecting rib edges in at least one of the first and second images. The rib edges are detected by correlating points in the at least one of the first and second images to plural rib edge models using a Hough transform to identify approximate rib edges in one of the images, and delineating actual rib edges derived from the identified approximate rib edges using a snake model. The method system and computer readable medium further include deriving the shift values using the actual rib edges and warping one of the first and second images to produce a warped image which is registered to the other of the first and second images based at least in part on the shift values.

Abstract translation: 一种用于胸部图像的计算机化处理的方法，系统和计算机可读介质，包括获得胸部的数字第一和第二图像以及检测第一和第二图像中的至少一个中的肋缘。 通过使用霍夫变换将第一和第二图像中的至少一个图像中的点与多个肋边缘模型相关联来检测肋边缘，以识别其中一个图像中的近似肋边缘，并且描绘从识别的近似肋导出的实际肋边缘 边缘使用蛇模型。 方法系统和计算机可读介质进一步包括使用实际的肋边缘导出移位值，并使第一和第二图像之一变形，以产生至少部分地基于第一和第二图像被注册到第一和第二图像中的另一个的扭曲图像 移位值。

公开(公告)号：WO0028466A9

公开(公告)日：2000-09-28

申请号：PCT/US9924007

申请日：1999-11-05

Applicant: ARCH DEV CORP ,  DOI KUNIO ,  LI QIANG ,  KATSURAGAWA SHIGEHIKO ,  ISHIDA TAKAYUKI

Inventor： DOI KUNIO ,  LI QIANG ,  KATSURAGAWA SHIGEHIKO ,  ISHIDA TAKAYUKI

IPC: A61B6/00 ,  G06T1/00 ,  G06T3/00 ,  G06T5/50 ,  G06T7/60 ,  G06K9/00

CPC classification number: G06T3/0068 ,  G06T5/50 ,  G06T7/174

Abstract: A method, system and computer readable medium for computerized processing of chest images including obtaining a digital first image of a chest (S100); producing a second image which is a mirror image (S300) of the first image; performing image warping on one of the first and second images to produce a warped image (S400) which is registered to the other of the first and second images; and subtracting the warped image from the other image to generate a subtraction image (S600). Another embodiment includes obtaining a digital first image of the chest of a subject; detecting ribcage edges on both sides of the lungs in the first chest image; determining average horizontal locations of the left and right ribcage edges at plural vertical locations; fitting the determined average horizontal locations to a straight line to derive a midline; rotating the chest image so that the midline is vertical; and shifting the rotated image to produce a lateral inclination corrected (S200) second image with the midline centered in the lateral inclination corrected image.

Abstract translation: 一种用于计算机化处理胸部图像的方法，系统和计算机可读介质，包括获得胸部的数字第一图像（S100）; 产生作为第一图像的镜像（S300）的第二图像; 在第一和第二图像之一上执行图像扭曲以产生被注册到第一和第二图像中的另一个的翘曲图像（S400）; 并从另一图像中减去翘曲图像以产生减法图像（S600）。 另一实施例包括获得对象胸部的数字第一图像; 在第一胸部图像中检测肺两侧的肋骨边缘; 确定在多个垂直位置处的左和右胸腔边缘的平均水平位置; 将确定的平均水平位置拟合到直线以导出中线; 旋转胸部图像，使中线垂直; 并移动旋转的图像以产生横向倾斜校正（S200）第二图像，其中心线位于横向倾斜校正图像中。

公开(公告)号：WO9942949A9

公开(公告)日：1999-11-04

申请号：PCT/US9903282

申请日：1999-02-22

Applicant: ARCH DEV CORP

Inventor： XU XIN-WEI ,  DOI KUNIO

IPC: G06T5/50 ,  G06T7/20 ,  G06K9/00

CPC classification number: G06T5/50 ,  A61B6/027 ,  G06T7/254

Abstract: Method and system for detection of interval change in medical images. Three-dimensional images, such as previous and current section images (10 and 11) in CT scans, are obtained. An anatomic feature, such as lungs, is used to select sections containing lung by a gray-level thresholding technique (13). The section correspondence between the current and previous scans is determined automatically. The initial registration of the corresponding sections in the two scans is achieved by a rotation correction (14) and a cross-correlation (15) technique. A more accurate registration between the corresponding current and previous section images is achieved by local matching (17). A nonlinear warping process (18) which is also based on the cross-correlation technique is applied to the previous image to yield a warped image after the matching. The final subtracted section images (19) were derived by subtracting of the previous section images from the corresponding current section images. Interval changes such as a change in tumor size and a newly developed pleural effusion are enhanced significantly.

Abstract translation: 用于检测医学图像间隔变化的方法和系统。 获得三维图像，例如CT扫描中的先前和当前部分图像（10和11）。 使用解剖学特征，如肺，通过灰度阈值技术选择含有肺的部位（13）。 自动确定当前扫描和以前扫描之间的部分对应关系。 通过旋转校正（14）和互相关（15）技术来实现两次扫描中相应部分的初始配准。 通过局部匹配（17）实现相应的当前和前一个截面图像之间的更准确的配准。 还将基于互相关技术的非线性翘曲过程（18）应用于先前的图像，以在匹配之后产生翘曲图像。 通过从相应的当前部分图像中减去前一部分图像导出最终减法部分图像（19）。 肿瘤大小变化和新发胸腔积液等间期变化明显增强。

公开(公告)号：WO9905639A9

公开(公告)日：1999-04-22

申请号：PCT/US9815278

申请日：1998-07-24

Applicant: ARCH DEV CORP

Inventor： YOSHIDA HIROYUKI ,  KATUSURAGAWA SHIGEHIKO ,  AMIT YALI ,  DOI KUNIO

IPC: G06K9/64 ,  G06T7/00 ,  G06K9/00

CPC classification number: G06K9/6206 ,  G06T7/0012

Abstract: A method and apparatus for discrimination of nodules and false positive in digital chest radiographs, using a wavelet snake technique (1802; 1804; 1806; 1808). The wavelet snake is a deformable contour designed to identify the boundary of a relatively round object (1900). The shape of the snake is determined by a set of wavelet coefficient in a certain range of scales. Portions of the boundary of a nodule are first extracted using a multiscale edge representation. The multiscale edge are then fitted (2000; 1814) by a gradient descent procedure which deforms the shape of a wavelet snake by changing its wavelet coefficients. The degree of overlap between the fitted snake and the multiscale edges is calculated and used as a fit quality indicator for discrimination of nodules and false detection (1816; 1818; 1820).

Abstract translation: 使用小波蛇技术（1802; 1804; 1806; 1808）在数字胸片中鉴别结节和假阳性的方法和装置。 小波蛇是一种可变形轮廓，用于识别相对圆形物体的边界（1900）。 蛇的形状由一定范围的小波系数确定。 首先使用多尺度边缘表示提取结节边界的部分。 然后通过梯度下降程序将多尺度边缘拟合（2000; 1814），其通过改变其小波系数来变形小波蛇的形状。 计算拟合蛇和多尺度边缘之间的重叠程度，并将其用作辨别结节和错误检测的适合质量指标（1816; 1818; 1820）。

公开(公告)号：EP1129426A4

公开(公告)日：2002-08-21

申请号：EP99958770

申请日：1999-11-12

Applicant: ARCH DEV CORP

Inventor： DOI KUNIO ,  NAKAMURA KATSUMI

IPC: A61B6/03 ,  A61B6/00 ,  G06K9/00 ,  G06T1/00 ,  G06T7/00 ,  G06F19/00 ,  G06K9/66

CPC classification number: G06T7/0012 ,  G06K9/00127

Abstract: A method, computer program product, and system (100) for computerized analysis of the likelihood of malignancy in a pulmonary nodule using artificial neural networks (ANNs) (S4). The method, on which the computer program product and the system is based on, includes obtaining a digital outline of a nodule; generating objective measures corresponding to physical features of the outline of the nodule; applying the generated objective measures to an ANN; and determining a likelihood of malignancy of the nodule based on an output of the ANN. Techniques include novel developments and implementations of artificial neural networks and feature extraction for digital images. Output from the inventive method yields an estimate of the likelihood of malignancy (S7) for a pulmonary nodule.

公开(公告)号：EP0998721A4

公开(公告)日：2003-12-10

申请号：EP98936980

申请日：1998-07-24

Applicant: ARCH DEV CORP

Inventor： DOI KUNIO ,  ISHIDA TAKAYUKI ,  KATSURAGAWA SHIGEHIKO

IPC: A61B6/00 ,  G06T1/00 ,  G06T3/00 ,  G06T5/50 ,  G06T7/00 ,  G06T7/60 ,  G06K9/60

CPC classification number: G06T7/0016 ,  G06T3/0081 ,  G06T5/50 ,  G06T7/254 ,  G06T7/337 ,  G06T2207/10116 ,  G06T2207/30061

Abstract: A method and computerized automated initial image matching algorithm technique for enhancing detection of interval changes between temporally subsequent radiographic images via image subtraction. The method includes the steps of digitizing images (100), normalizing density and contrast in the digital images (102), correcting for lateral inclination in the digital images (104), detecting edges of a same feature in each image (106), converting the images into low resolution matrices (108), blurring the low resolution images (110), segmenting portions of the blurred low resolution matrices based on the detected edges (112), matching the digital images based on a cross-correlation match between the segmented portions, performing non-linear warping to further match Regions of Interest (ROI), and performing image subtraction between the matched digital images (120). The low resolution matrices are greater than 64x64 in size and are produced by averaging. Blurring of the low resolution matrices is performed via a Gaussian filter that removes fine structure in each image such as small vessels, bronchia, etc. The method may be performed by a computer system according to instructions stored on a computer readable medium.

Abstract translation: 一种方法和计算机化的自动化初始图像匹配技术，用于通过图像减法来增强在时间上随后的放射照相图像之间的间隔变化的检测。 该方法包括数字化图像数字化，标准化数字图像中的浓度和对比度，校正数字图像中的横向倾斜，检测每个图像中相同特征的边缘，将图像转换成低分辨率矩阵，模糊低分辨率图像 基于检测到的边缘对模糊的低分辨率矩阵进行分段，基于分段部分之间的互相关匹配匹配数字图像，执行非线性翘曲以进一步匹配感兴趣区域（ROI），并执行图像相减 在匹配的数字图像之间。 低分辨率矩阵的大小大于64x64，并通过平均生成。 通过高斯滤波器执行低分辨率矩阵的模糊，其去除每个图像中的精细结构，例如小血管，支气管等。该方法可以由计算机系统根据存储在计算机可读介质上的指令执行。