Patents by Inventor Kazuyoshi Nishino

Kazuyoshi Nishino has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 10950012
    Abstract: An image processing element 9 of the present invention includes a weighting factor setting element 9a that sets up a weighting factors wnn, wbi of the weight addition combing a nearest neighbor interpolation and a bilinear interpolation based on an absolute value |Ibi?Inn| of the difference between the pixel value Inn acquired by the nearest neighbor interpolation and the pixel value Ibi acquired by the bilinear interpolation; and a weight addition element 9b that implement a weighting addition based on the set-up weighting factors wnn, wbi. A reconstructed image can be acquired by arranging the backprojection pixel value Inew every pixel following the weighting.
    Type: Grant
    Filed: January 9, 2015
    Date of Patent: March 16, 2021
    Assignee: SHIMADZU CORPORATION
    Inventors: Tomonori Sakimoto, Kazuyoshi Nishino
  • Patent number: 10902594
    Abstract: A medical X-ray image processing apparatus (1) includes a controller (12) configured to acquire positional information of an imaging system (7) based on positional information of positional references (60) and evaluate symmetry of imaging positions of a plurality of X-ray captured images (15) with respect to a reference position (18) on a movement path of the imaging system (7) based on the acquired positional information of the imaging system (7).
    Type: Grant
    Filed: September 26, 2017
    Date of Patent: January 26, 2021
    Assignee: Shimadzu Corporation
    Inventors: Junya Yamamoto, Takahiro Miyajima, Kazuyoshi Nishino
  • Patent number: 10803564
    Abstract: Provided is an image processing apparatus capable of assuredly finding a lung field that appears in an image even if a subject image appears in a radiation image in a rotated manner and assuredly performing a contrast adjustment with excellent visibility for the lung field. The image processing apparatus is provided with a sideways determination means 13 configured to determine that the subject image is turned sideways in the original image P0 when a minimum point P of a profile generated by summing or averaging pixel values belonging to each pixel column of the original image P0 for each pixel column is away from the center position of the subject image. The original image P0 determined as being turned sideways by the sideways determination portion 13 is rotated by the image rotation portion 16 and used for searching of the lung field.
    Type: Grant
    Filed: August 17, 2018
    Date of Patent: October 13, 2020
    Assignee: Shimadzu Corporation
    Inventors: Takahiro Miyajima, Junya Yamamoto, Kazuyoshi Nishino
  • Publication number: 20200234436
    Abstract: A medical X-ray image processing apparatus (1) includes a controller (12) configured to acquire positional information of an imaging system (7) based on positional information of positional references (60) and evaluate symmetry of imaging positions of a plurality of X-ray captured images (15) with respect to a reference position (18) on a movement path of the imaging system (7) based on the acquired positional information of the imaging system (7).
    Type: Application
    Filed: September 26, 2017
    Publication date: July 23, 2020
    Inventors: Junya YAMAMOTO, Takahiro MIYAJIMA, Kazuyoshi NISHINO
  • Patent number: 10685258
    Abstract: According to the present invention, a total value profile to be used for searching a lung field end is generated based on a radiation image. A pacemaker and an annotation reflected in a radiation image are merely reflected darkly in the image, and the existence is not particularly emphasized by edge enhancement. Therefore, the total value profile according to the present invention is not significantly affected by a pacemaker and/or an annotation. Therefore, according to the present invention, there occurs no false recognition regarding the end of the lung field due to a pacemaker and/or an annotation.
    Type: Grant
    Filed: June 15, 2018
    Date of Patent: June 16, 2020
    Assignee: Shimadzu Corporation
    Inventors: Takahiro Miyajima, Junya Yamamoto, Kazuyoshi Nishino
  • Publication number: 20200064502
    Abstract: A radiation image processing apparatus includes: a group processing unit classifying a plurality of metal markers into a first group relatively far from a detector and a second group relatively close to the detector based on the area of each image of the plurality of metal markers in a captured image; a marker classification unit classifying the plurality of metal markers based on the relative positions of the plurality of metal markers to on the image plane of the captured image for each of the classified groups; and a pair processing unit selecting the metal markers of the first group and the metal markers of the second group, of which the relative positions match each other, as a pair.
    Type: Application
    Filed: August 2, 2019
    Publication date: February 27, 2020
    Inventors: Takahiro MIYAJIMA, Junya YAMAMOTO, Kazuyoshi NISHINO
  • Publication number: 20200058108
    Abstract: Provided is an image processing apparatus capable of assuredly finding a lung field that appears in an image even if a subject image appears in a radiation image in a rotated manner and assuredly performing a contrast adjustment with excellent visibility for the lung field. The image processing apparatus is provided with a sideways determination means 13 configured to determine that the subject image is turned sideways in the original image P0 when a minimum point P of a profile generated by summing or averaging pixel values belonging to each pixel column of the original image P0 for each pixel column is away from the center position of the subject image. The original image P0 determined as being turned sideways by the sideways determination portion 13 is rotated by the image rotation portion 16 and used for searching of the lung field.
    Type: Application
    Filed: August 17, 2018
    Publication date: February 20, 2020
    Inventors: Takahiro MIYAJIMA, Junya YAMAMOTO, Kazuyoshi NISHINO
  • Publication number: 20200013147
    Abstract: A center of gravity of a chest front image is obtained by a center of gravity calculation using pixel values in the chest front image, and a vicinity pixel position of the center of gravity is set as a center position P of a circular search region having a radius of a predetermined length. The shortest line segment of four line segments obtained by drawing perpendicular lines down from the center position P of an irradiation field to boundary lines of the upper, lower, left and right irradiation fields. The line segment, which is a radius of the circular search region, is rotationally displaced for each predetermined angle ?0, and the profile of the average value for each predetermined angle ? is obtained. From the displacement angle ? of the line segment in which the average value becomes minimum, the orientation of the subject from the head to the abdomen reflected in the chest front image is determined.
    Type: Application
    Filed: February 26, 2018
    Publication date: January 9, 2020
    Applicant: Shimadzu Corporation
    Inventors: Takahiro MIYAJIMA, Junya YAMAMOTO, Kazuyoshi NISHINO
  • Patent number: 10521907
    Abstract: The apparatus is equipped with an intersection identification unit configured to generate a pixel value profile which is a profile indicating relevance between a position of each pixel in a pixel array crossing a contour and a lung field of a subject and a corresponding pixel value and a moving average profile which is a profile indicating relevance between the position of each target pixel and a moving average of a corresponding pixel value and search an intersection of both the profiles located at a position where the pixel value profile surpasses the moving average profile from a direction from a rear end to a front end of the pixel array.
    Type: Grant
    Filed: March 21, 2018
    Date of Patent: December 31, 2019
    Assignee: Shimadzu Corporation
    Inventors: Takahiro Miyajima, Junya Yamamoto, Kazuyoshi Nishino
  • Publication number: 20190385015
    Abstract: According to the present invention, a total value profile to be used for searching a lung field end is generated based on a radiation image. A pacemaker and an annotation reflected in a radiation image are merely reflected darkly in the image, and the existence is not particularly emphasized by edge enhancement. Therefore, the total value profile according to the present invention is not significantly affected by a pacemaker and/or an annotation. Therefore, according to the present invention, there occurs no false recognition regarding the end of the lung field due to a pacemaker and/or an annotation.
    Type: Application
    Filed: June 15, 2018
    Publication date: December 19, 2019
    Inventors: Takahiro MIYAJIMA, Junya YAMAMOTO, Kazuyoshi NISHINO
  • Publication number: 20190295247
    Abstract: The apparatus is equipped with an intersection identification unit configured to generate a pixel value profile which is a profile indicating relevance between a position of each pixel in a pixel array crossing a contour and a lung field of a subject and a corresponding pixel value and a moving average profile which is a profile indicating relevance between the position of each target pixel and a moving average of a corresponding pixel value and search an intersection of both the profiles located at a position where the pixel value profile surpasses the moving average profile from a direction from a rear end to a front end of the pixel array.
    Type: Application
    Filed: March 21, 2018
    Publication date: September 26, 2019
    Inventors: Takahiro MIYAJIMA, Junya YAMAMOTO, Kazuyoshi NISHINO
  • Patent number: 10307128
    Abstract: An X-ray imaging device and method acquiring a long-length image that is connected. A configuration data of the signal intensity depending on the position along a moving direction of the long-length imaging is acquired by acquiring a model data prior to the long-length imaging, to obtain an approximate configuration A long-length imaging is conducted and a brightness difference takes place along the data line in overlapping pixel regions relative to two X-ray images adjacent each other. An offset correction value C in pixels in the region other than the pixel regions from the difference ? of pixel values in such overlapping pixel regions, the slot width D and the overlapping width d. An offset correction is conducted based on such offset correction value, C and the X-ray images following the offset correction are connected to generate the long-length imaging to obtain a long-length image that is naturally connected.
    Type: Grant
    Filed: May 12, 2016
    Date of Patent: June 4, 2019
    Assignee: SHIMADZU CORPORATION
    Inventor: Kazuyoshi Nishino
  • Patent number: 9922418
    Abstract: An image processing method provides a step of detecting the pedicle region of vertebral arch detects the region having the higher pixel value compared to the periphery thereof is detected by classifying three classes ABC (detection of the pedicle of vertebral arch) of the step S2. Then, in the case of a failure to detect the intervertebral region, e.g., when the intervertebral region is crushed, the boundary, contacting to the cervical vertebra side of the pedicle of vertebral arch detected by the step of classifying three classes ABC (detecting the pedicle of vertebral arch) described above is drawn by classifying ABC three classes (drawing the boundary) of the step S2. Accordingly, even when the intervertebral region is crushed or when the intervertebral region is undetectable, the boundary between the vertebral bodies can be detected accurately.
    Type: Grant
    Filed: August 21, 2013
    Date of Patent: March 20, 2018
    Assignee: SHIMADZU CORPORATION
    Inventors: Tomohiro Nakaya, Kazuyoshi Nishino
  • Publication number: 20180025513
    Abstract: An image processing element 9 of the present invention includes a weighting factor setting element 9a that sets up a weighting factors wnn, wbi of the weight addition combing a nearest neighbor interpolation and a bilinear interpolation based on an absolute value |Ibi?Inn| of the difference between the pixel value acquired by the nearest neighbor interpolation and the pixel value Inn acquired by the bilinear interpolation; and a weight addition element 9b that implement a weighting addition based on the set-up weighting factors wnn, wbi. A reconstructed image can be acquired by arranging the backprojection pixel value Inew every pixel following the weighting.
    Type: Application
    Filed: January 9, 2015
    Publication date: January 25, 2018
    Inventors: Tommonori SAKIMOTO, Kazuyoshi NISHINO
  • Publication number: 20170325773
    Abstract: An X-ray imaging device and method of operation is capable of acquiring a long-length image and is naturally connected. A configuration data of the signal intensity depending on the position along a moving direction of the long-length imaging is acquired by acquiring a model data prior to the long-length imaging, in order to obtain an approximate configuration. Next, the long-length imaging as to the subject is conducted and a brightness difference (difference of pixel values) takes place along the data line in the overlapping pixel regions relative to two X-ray images adjacent each other. According to the configuration data of the signal intensity, the offset correction value C in pixels (pixel coordinate) in the region other than the pixel regions from the difference ? of pixel values in such overlapping pixel regions, the slot width D and the overlapping width d.
    Type: Application
    Filed: May 12, 2016
    Publication date: November 16, 2017
    Applicant: SHIMADZU CORPORATION
    Inventor: Kazuyoshi NISHINO
  • Patent number: 9697624
    Abstract: An image processing apparatus and a radiation tomography apparatus capable of acquiring a tomographic image of high visibility are provided. The image processing apparatus initially generates a map m showing an extending direction of a linear structural object seen in an original image P0. Then, the apparatus generates an extrapolated image P1 by adding the area positioned at the side section of the original image P0 to the side section so as to extend the linear structural object seen in the side section by referring to the map m. By adding the side section to the original image P0 while shifting the pattern of the side section so as to extend the linear structural object seen in the side section of the image, the subject image can be naturally compensated. After this operation, by generating the tomographic image D, a tomographic image D having improved visibility can be generated.
    Type: Grant
    Filed: August 28, 2014
    Date of Patent: July 4, 2017
    Assignee: Shimadzu Corporation
    Inventors: Tomonori Sakimoto, Kazuyoshi Nishino
  • Patent number: 9486178
    Abstract: This invention identifies a metal area of actual measurement projection data from the actual measurement projection data and an actual measurement reconstruction image obtained by image reconstruction of the actual measurement projection data, to acquire metal area identification data. In the actual measurement projection data, a resulting image has pixel values in the metal area such as of wire or screws, for example, not so different from pixel values of other areas, which makes it difficult to identify the metal area accurately. However, the metal area can be identified with increased accuracy. Based on the metal area identification data, data replacement of the metal area of the actual measurement projection data p1 is carried out with data obtained from pixels adjacent the metal area, thereby to acquire replacement projection data, which is put to image reconstruction to generate a replacement reconstruction image without the metal area.
    Type: Grant
    Filed: August 31, 2012
    Date of Patent: November 8, 2016
    Assignee: SHIMADZU CORPORATION
    Inventors: Tomonori Sakimoto, Kazuyoshi Nishino
  • Publication number: 20160203598
    Abstract: An image processing method provides a step of detecting the pedicle region of vertebral arch detects the region having the higher pixel value compared to the periphery thereof is detected by classifying three classes ABC (detection of the pedicle of vertebral arch) of the step S2. Then, in the case of a failure to detect the intervertebral region. e.g., when the intervertebral region is crushed, the boundary, contacting to the cervical vertebra side of the pedicle of vertebral arch detected by the step of classifying three classes ABC (detecting the pedicle of vertebral arch) described above is drawn by classifying ABC three classes (drawing the boundary) of the step S2. Accordingly. even when the intervertebral region is crushed or when the intervertebral region is undetectable, the boundary between the vertebral bodies can be detected accurately.
    Type: Application
    Filed: August 21, 2013
    Publication date: July 14, 2016
    Applicant: SHIMADZU CORPORATION
    Inventors: Tomohiro NAKAYA, Kazuyoshi NISHINO
  • Publication number: 20160063740
    Abstract: An image processing apparatus and a radiation tomography apparatus capable of acquiring a tomographic image of high visibility are provided. The image processing apparatus initially generates a map m showing an extending direction of a linear structural object seen in an original image P0. Then, the apparatus generates an extrapolated image P1 by adding the area positioned at the side section of the original image P0 to the side section so as to extend the linear structural object seen in the side section by referring to the map m. By adding the side section to the original image P0 while shifting the pattern of the side section so as to extend the linear structural object seen in the side section of the image, the subject image can be naturally compensated. After this operation, by generating the tomographic image D, a tomographic image D having improved visibility can be generated.
    Type: Application
    Filed: August 28, 2014
    Publication date: March 3, 2016
    Inventors: Tomonori SAKIMOTO, Kazuyoshi NISHINO
  • Publication number: 20150305702
    Abstract: This invention identifies a metal area of actual measurement projection data from the actual measurement projection data and an actual measurement reconstruction image obtained by image reconstruction of the actual measurement projection data, to acquire metal area identification data. In the actual measurement projection data, a resulting image has pixel values in the metal area such as of wire or screws, for example, not so different from pixel values of other areas, which makes it difficult to identify the metal area accurately. However, the metal area can be identified with increased accuracy. Based on the metal area identification data, data replacement of the metal area of the actual measurement projection data p1 is carried out with data obtained from pixels adjacent the metal area, thereby to acquire replacement projection data, which is put to image reconstruction to generate a replacement reconstruction image without the metal area.
    Type: Application
    Filed: August 31, 2012
    Publication date: October 29, 2015
    Applicant: SHIMADZU CORPORATION
    Inventors: Tomonori SAKIMOTO, Kazuyoshi NISHINO