-
公开(公告)号：JPH09185714A
公开(公告)日：1997-07-15
申请号：JP26416296
申请日：1996-10-04
Applicant: ARCH DEV CORP
Inventor： JINNUEI JIYU , DOI KUNIO
Abstract: PROBLEM TO BE SOLVED: To precisely detect a small node from a chest X-ray image. SOLUTION: In a computer supported diagnostic method for detecting a lung small node in a digitized chest image, this method takes the difference between the signal emphasized image and the signal suppressed image of the chest image to generate a difference picture (a), repeats the threshold value processing of the difference picture by plural threshold values concerning gradation while changing a threshold value, executes a prescribed morphological test to a pixel group with a value larger than each threshold value to specify the candidate of the small node (b), executes plural regular tests to the prescribed feature of the image appearing at the difference image and the chest image by corresponding spatially to excludes the small nodes of pseudo positive reaction from the candidates of the small nodes (c), and additionally excludes the small nodes of pseud positive reaction from the candidates of the residual small nodes at the step (c) by an artificial neural network to specify the residual candidates of the small nodes as the candidates of the true small nodes (d).
-
公开(公告)号：JPH09179843A
公开(公告)日：1997-07-11
申请号：JP26851596
申请日：1996-10-09
Applicant: ARCH DEV CORP
Abstract: PROBLEM TO BE SOLVED: To provide the shift unchanged artificial neural network for detecting disease in a digital image. SOLUTION: This network includes an input layer and at least hidden layer and an output layer includes at least one neuron. Each hidden layer includes at least one hidden group. Each hidden group having at least one hidden unit includes at least one neuron. For learning using error back propagation algorithm so that the mean weight of a group becomes substantially zero, respective neurons need to be equal in connection weight between two groups in adjacent layers. A digital image of a patient is obtained to extract a suspicious area of interest and this area of interest is converted into numeric data, which are inputted to the neural network after the learning to detect a fine calcare part.
-
公开(公告)号：JPH0737074A
公开(公告)日：1995-02-07
申请号：JP28488493
申请日：1993-11-15
Applicant: ARCH DEV CORP
Inventor： KANO AKIKO , DOI KUNIO
Abstract: PURPOSE: To provide a computerized method and device for improving the precision of diagnosis through the use of a picture emphasized for detecting secular change between hourly consecutive digital medical picture. CONSTITUTION: A pair of pictures are digitized (steps 10 and 20) and in order to make corresponding positions at the two pictures equal, the positioning of the pictures including the distortion of one of the pictures to be nonlinear is executed (step 40). After this, the distorted picture and the other picture are subtraction-processed (step 50). A slightly opaque part existing at a picture photographed later is detected at a subtraction picture.
-
公开(公告)号：JPH08335271A
公开(公告)日：1996-12-17
申请号：JP9685296
申请日：1996-04-18
Applicant: ARCH DEV CORP
Inventor： DOI KUNIO , SHIN UEI SHIYUU , KATSURAGAWA SHIGEHIKO , MORISHITA JIYUNJI
Abstract: PROBLEM TO BE SOLVED: To provide a new and improved method for automatic detection of the exact boundary of a chest part in a digitized chest part X-ray picture. SOLUTION: This is a computerized method for detecting and characterizing a disease by a picture obtained from a chest part X-ray picture. The picture in the chest part X-ray picture is processed for deciding the boundary of the chest part including the edge of a lung upper end, right and left chest part edges, and right and left half diaphragm edges. An organizational scale including the RMS change of pixel values in a concerned area is converted into relative exposure, and a system noise component which is present in a system used for the generation of the picture is compensated. An organizational index and a geometrical pattern index are generated. Also, the histogram of the index is generated, and inputted to a learned artificial neural network for classifying the normality and abnormality of the picture to be applied.
-
公开(公告)号：JPH07299053A
公开(公告)日：1995-11-14
申请号：JP10330695
申请日：1995-04-27
Applicant: ARCH DEV CORP
Inventor： ROBAATO EMU NISHIKAWA , EMA TAKEHIRO , YOSHIDA HIROYUKI , DOI KUNIO
Abstract: PURPOSE: To enable an anatomically abnormal region to be automatically detected by specifying a plurality of locations in a digital image having a possibility as an abnormal region through digital image processing of a subject having an anatomically abnormal region, and by deciding an edge gradient to each region and comparing their threshold values. CONSTITUTION: In the case that a position of cluster containing a signal of a microcalcified part is detected, firstly, it is photographed by an X-ray system and a signal extraction processing 300 is carried out after producing a differential image 200 imputting a digital mammogram 100 digitalized by a laser scanner. Next, with a possible location as a microcalcified part which becomes a problem in the differential image specified, the differential image data in the circumferential region of the specified location is processed in a characteristic extraction processing 600. Next, an area vs contrast test 700 and a contrast vs background test 800 are carried out and a cluster is processed in highlighting by carrying out a cluster filter processing 900.
-
Patent Agency Ranking
公开(公告)号：JP2004048655A
公开(公告)日：2004-02-12
申请号：JP2003056062
申请日：2003-03-03
Applicant: Arch Dev Corp , アーチ・デベロップメント・コーポレーション
Inventor： DOI KUNIO , YOSHIMURA HITOSHI
CPC classification number: G06T5/40 , G06T5/007 , G06T2207/10144 , G06T2207/20192
Abstract: PROBLEM TO BE SOLVED: To provide a film image correcting method and system for improving a picture quality of a copied image including nonlinear characteristics to be corrected.
SOLUTION: A film image is digitized to create a histogram of digital image data. At least a first pixel value indicating a parameter in the case of obtaining the film image is extracted from the histogram and at least partially based upon the first pixel value, a specific correction curve and a prescribed corrected pixel value are selected out of a plurality of nonlinear correction curves for relating source pixel values stored in a memory for each of parameters in advance to corrected pixel values. Based upon a relationship of a source pixel value and a corrected pixel value determined by the selected correction curve, pixel values of the image are converted into corrected pixel values. Thus, a nonlinear corrected image is created based upon resultant corrected image data.
COPYRIGHT: (C)2004,JPO-
公开(公告)号：AU3545299A
公开(公告)日：1999-11-08
申请号：AU3545299
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
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; (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; (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 in which spatial locations of pixels of the first warped image are varied in relation to the second shift values. Additional iterations of image warping are possible to enhance image registration between the first digital image and the warped version of the second digital image, followed by image subtraction of the first digital image and the final warped image to produce a difference image from which diagnosis of temporal changes ensues. Temporal subtraction assists radiologists in the detection of interval changes on chest radiographs, and particularly to overcome severe misregistration errors in the temporally sequential images mainly due to differences in a subject's inclination and/or rotation. In the production of shift values used in image warping, initial shift values are obtained by cross-correlation techniques using a template and search regions of interest. Shift vectors and a histogram of shift vectors in each lung are obtained from initial shift values. The histograms of shift vectors are used in the selection of sets of shift values for smoothing, using two-dimensional fitting and subsequent use of fitted shift values in image warping.
-
公开(公告)号：CA2326776A1
公开(公告)日：1999-10-28
申请号：CA2326776
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
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; (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; (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 in which spatial locations of pixels of the first warped image are varied in relation to the second shift values. Additional iterations of image warping are possible to enhance image registration between the first digital image and the warped version of the second digital image, followed by image subtraction of the first digital image and the final warped image to produce a difference image from which diagnosis of temporal changes ensues.
-
29.发明专利
公开(公告)号：AU8509998A
公开(公告)日：1999-02-16
申请号：AU8509998
申请日：1998-07-24
Applicant: ARCH DEV CORP
Inventor： YOSHIDA HIROYUKI , KATUSURAGAWA SHIGEHIKO , AMIT YALI , DOI KUNIO
Abstract: A method and apparatus for discrimination of nodules and false positives in digital chest radiographs, using a wavelet snake technique. The wavelet snake is a deformable contour designed to identify the boundary of a relatively round object. The shape of the snake is determined by a set of wavelet coefficients in a certain range of scales. Portions of the boundary of a nodule are first extracted using a multiscale edge representation. The multiscale edges are then fitted 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 detections.
-
公开(公告)号：CA2186135A1
公开(公告)日：1995-10-12
申请号：CA2186135
申请日：1995-03-30
Applicant: ARCH DEV CORP
Inventor： GIGER MARYELLEN L , BAE KYONGATE TY , DOI KUNIO
Abstract: A method and system for the automated detection of lesions in computed tomographic images, including generating image data from at least one selected portion of an object, for example, from CT images of the thorax. The image data are then analyzed in order to produce the boundary of the thorax. The image data within the thoracic boundary is then further analyzed to produce boundaries of the lung regions using predetermined criteria. Features within the lung regions are then extracted using multi-gray-level thresholding and correlation between resulting multi-level threshold images and between at least adjacent sections. Classification of the features as abnormal lesions or normal anatomic features is then performed using geometric features yielding a likelihood of being an abnormal lesion along with its location in either the 2-D image section or in the 3-D space of the object.
-
-
-
-
-
-
-
-
-
Search Results
61
records
(took 0.026 seconds)
