Patents by Inventor Yukinobu Sakata

Yukinobu Sakata 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).

  • Publication number: 20200083019
    Abstract: According to one embodiment, a contour extraction method for extracting a contour of a target object from an image obtained using an electron beam includes: extracting the contour of the target object from a backscattered electron image; creating a dictionary for associating a secondary electron image obtained from a portion common to the backscattered electron image with the contour; calculating a likelihood of the contour of the target object in a plurality of positions of a newly obtained secondary electron image by referencing the dictionary regarding the newly obtained secondary electron image; and setting a route along which a total sum of the likelihood is maximized out of the plurality of positions as the contour of the target object.
    Type: Application
    Filed: February 27, 2019
    Publication date: March 12, 2020
    Applicant: TOSHIBA MEMORY CORPORATION
    Inventors: Chihiro IDA, Yukinobu SAKATA
  • Publication number: 20200069263
    Abstract: A medical image processing apparatus comprising: a first input interface configured to acquire a three-dimensional volume image of an object which is provided with at least one marker, the three-dimensional volume image being generated by imaging the object using a medical examination apparatus; a second input interface configured to acquire geometry information of an imaging apparatus which is used for imaging the object to generate a fluoroscopic image of the object; and a specific-setting-information generator configured to generate specific setting information based on the three-dimensional volume image and the geometry information, the specific setting information being used for setting of imaging for generating an image depicting the at least one marker or setting of image processing of the image depicting the at least one marker.
    Type: Application
    Filed: November 8, 2019
    Publication date: March 5, 2020
    Applicants: KABUSHIKI KAISHA TOSHIBA, Toshiba Energy Systems & Solutions Corporation
    Inventors: Yasunori TAGUCHI, Ryusuke HIRAI, Yukinobu SAKATA, Keiko OKAYA, Shinichiro MORI
  • Patent number: 10575823
    Abstract: A medical diagnostic apparatus according to one embodiment comprises processing circuitry. The processing circuitry is configured to acquire a three-dimensional shape of a first part based on a contour of the first part in each of a plurality of sectional images intersecting each other along an extending direction of the first part connecting to a cardiac chamber; acquire a three-dimensional shape of a second part, based on a contour of the second part in a sectional image along an extending direction of the second part connecting to the cardiac chamber; and generate a three-dimensional image representing at least some of the first part, the second part, and the cardiac chamber using a three-dimensional shape representing the cardiac chamber and the three-dimensional shapes of the first part and the second part acquired.
    Type: Grant
    Filed: September 29, 2015
    Date of Patent: March 3, 2020
    Assignee: Canon Medical Systems Corporation
    Inventors: Tomoya Okazaki, Yukinobu Sakata, Tomoyuki Takeguchi
  • Publication number: 20200012945
    Abstract: According to an embodiment, a learning method of optimizing a neural network, includes updating and specifying. In the updating, each of a plurality of weight coefficients included in the neural network is updated so that an objective function obtained by adding a basic loss function and an L2 regularization term multiplied by a regularization strength is minimized. In the specifying, an inactive node and an inactive channel are specified among a plurality of nodes and a plurality of channels included in the neural network.
    Type: Application
    Filed: February 27, 2019
    Publication date: January 9, 2020
    Applicant: KABUSHIKI KAISHA TOSHIBA
    Inventors: Atsushi YAGUCHI, Wataru ASANO, Shuhei NITTA, Yukinobu SAKATA, Akiyuki TANIZAWA
  • Patent number: 10517544
    Abstract: A medical image processing apparatus comprising: a first input interface configured to acquire a three-dimensional volume image of an object which is provided with at least one marker, the three-dimensional volume image being generated by imaging the object using a medical examination apparatus; a second input interface configured to acquire geometry information of an imaging apparatus which is used for imaging the object to generate a fluoroscopic image of the object; and a specific-setting-information generator configured to generate specific setting information based on the three-dimensional volume image and the geometry information, the specific setting information being used for setting of imaging for generating an image depicting the at least one marker or setting of image processing of the image depicting the at least one marker.
    Type: Grant
    Filed: November 20, 2017
    Date of Patent: December 31, 2019
    Assignees: KABUSHIKI KAISHA TOSHIBA, Toshiba Energy Systems & Solutions Corporation
    Inventors: Yasunori Taguchi, Ryusuke Hirai, Yukinobu Sakata, Keiko Okaya, Shinichiro Mori
  • Publication number: 20190187232
    Abstract: A magnetic resonance imaging apparatus according to an embodiment includes a processor and a memory. The memory stores processor-executable instructions that cause the processor to detect cross-sectional positions of a plurality of cross-sectional images to be acquired in an imaging scan from volume data; acquire the cross-sectional images in sequence based on the cross-sectional positions by executing the imaging scan; and after the first cross-sectional image is acquired in the imaging scan, generate a display image, and display the display image on a display, the display image being an image in which a cross-sectional position of a second cross-sectional image which is detected from the volume data is superimposed on the first cross-sectional image, the second cross-sectional image being a cross-sectional image before being acquired and intersecting with the first cross-sectional image.
    Type: Application
    Filed: February 19, 2019
    Publication date: June 20, 2019
    Inventors: Shuhei NITTA, Shigehide KUHARA, Tomoyuki TAKEGUCHI, Taichiro SHIODERA, Yukinobu SAKATA
  • Patent number: 10318841
    Abstract: A medical-image processing apparatus according to an embodiment includes processing circuitry. The processing circuit acquires an initial value of an outline corresponding vector that corresponds to an outline of a subject included in medical image data. The processing circuitry updates the outline corresponding vector based on a derivative that is acquired by differentiating a cost function with respect to the outline corresponding vector by the outline corresponding vector, and on the initial value of the outline corresponding vector.
    Type: Grant
    Filed: February 17, 2017
    Date of Patent: June 11, 2019
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Tomoya Okazaki, Yukinobu Sakata
  • Patent number: 10292684
    Abstract: An ultrasound diagnosis apparatus includes processing circuitry. The processing circuitry obtains three-dimensional medical image data, taken by using an ultrasound probe, of a region including a heart valve of a patient and a catheter inserted into a heart chamber of the patient. The processing circuitry determines an advancing direction of a tip end part of the catheter by obtaining information on a position and a posture of the tip end part included in the three-dimensional medical image data, by using at least one selected from shape information indicating the shape of the tip end part and reflection characteristic information indicating ultrasound reflection characteristics of the tip end part. The processing circuitry generates a display image from the three-dimensional medical image data in accordance with the position and the advancing direction of the tip end part. The processing circuitry causes the display image to be displayed.
    Type: Grant
    Filed: February 24, 2017
    Date of Patent: May 21, 2019
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Tomoya Okazaki, Yasuhiko Abe, Koji Ando, Shogo Fukuda, Yurika Ogawa, Yukinobu Sakata, Yasunori Taguchi
  • Patent number: 10258813
    Abstract: A medical image processing apparatus of an embodiment has acquisitor, a first landmark detector, and an estimator. The acquisitor acquires a perspective image of an object to be treated imaged by an imaging apparatus. The first landmark detector detects a position of a landmark that appears in the perspective image acquired by the acquisitor. The estimator, based on relationship information indicating a relationship between the position of landmark and the position of a target, estimates the position of the search-for location of the object to be treated from the position of the landmark detected by the first landmark detector.
    Type: Grant
    Filed: March 7, 2018
    Date of Patent: April 16, 2019
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Yasunori Taguchi, Ryusuke Hirai, Yukinobu Sakata, Kyoka Sugiura
  • Patent number: 10215824
    Abstract: A magnetic resonance imaging apparatus according to an embodiment includes a processor and a memory. The memory stores processor-executable instructions that cause the processor to detect cross-sectional positions of a plurality of cross-sectional images to be acquired in an imaging scan from volume data; acquire the cross-sectional images in sequence based on the cross-sectional positions by executing the imaging scan; and after the first cross-sectional image is acquired in the imaging scan, generate a display image, and display the display image on a display, the display image being an image in which a cross-sectional position of a second cross-sectional image which is detected from the volume data is superimposed on the first cross-sectional image, the second cross-sectional image being a cross-sectional image before being acquired and intersecting with the first cross-sectional image.
    Type: Grant
    Filed: December 22, 2014
    Date of Patent: February 26, 2019
    Assignee: TOSHIBA MEDICAL SYSTEMS CORPORATION
    Inventors: Shuhei Nitta, Shigehide Kuhara, Tomoyuki Takeguchi, Taichiro Shiodera, Yukinobu Sakata
  • Patent number: 10203385
    Abstract: A magnetic resonance apparatus of the present embodiment includes: a gantry which includes a static field magnet, a gradient coil and an RF coil to image an object; processing circuitry; a memory that stores processor-executable instructions that, when executed by the processing circuitry, cause the processing circuitry to detect at least one position of an aortic valve and a pulmonary valve from three-dimensional image data including a heart of the object, as at least one characteristic region inside the heart, specify a position of an imaging cross-section substantially orthogonal to a bloodstream path inside the heart based on the position of the aortic valve or the pulmonary valve, and cause the gantry to image the imaging cross-section of the object at the specified position of the imaging cross-section.
    Type: Grant
    Filed: December 22, 2015
    Date of Patent: February 12, 2019
    Assignee: TOSHIBA MEDICAL SYSTEMS CORPORATION
    Inventors: Shigehide Kuhara, Shuhei Nitta, Taichiro Shiodera, Yukinobu Sakata, Tomoyuki Takeguchi
  • Patent number: 10143431
    Abstract: A medical image processing apparatus, includes: a reconstructed moving image obtainer that obtains a reconstructed moving image; a focus region identifier that identifies a first focus region corresponding to the designated focus; a fluoroscopic moving image obtainer that obtains at least one-period data on a fluoroscopic moving image; a second characteristics identifier that identifies each of two or more second characteristics regions corresponding to the internal body portion; a comparison selector that compares the two or more first characteristic regions; a conversion parameter calculation unit that calculates a conversion parameter for converting the first characteristic region.
    Type: Grant
    Filed: February 15, 2017
    Date of Patent: December 4, 2018
    Assignees: TOSHIBA ENERGY SYSTEMS & SOLUTIONS CORPORATION, NATIONAL INSTITUTES FOR QUANTUM AND RADIOLOGICAL SCIENCE AND TECHNOLOGY
    Inventors: Ryusuke Hirai, Yukinobu Sakata, Yasunori Taguchi, Fumi Maruyama, Shinichiro Mori
  • Patent number: 10101450
    Abstract: According to one embodiment, a medical image processing apparatus includes storage circuitry and processing circuitry. The storage circuitry stores a plurality of images acquired by transmitting ultrasonic waves in different scanning parameters to a target region. The processing circuitry separates a pixel value of a pixel in the images into at least two components. The processing circuitry forms a compound image concerning to the images by using at least one of the components.
    Type: Grant
    Filed: November 10, 2015
    Date of Patent: October 16, 2018
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Saori Asaka, Satoshi Kawata, Yukinobu Sakata, Toshiyuki Ono, Nobuyuki Matsumoto
  • Publication number: 20180264288
    Abstract: An object positioning apparatus comprising: a radiographic image input interface configured to acquire a radiographic image that is generated by causing a fluoroscopic imaging apparatus to image an object and includes a first region and a second region, the first region depicting an index region for positioning of the object, the second region depicting a non-index region other than the index region; and a positioning processor configured to perform the positioning of the object by performing matching processing between a previously generated reference image and the first region that is specified from the radiographic image based on three-dimensional model information of the non-index region.
    Type: Application
    Filed: March 14, 2018
    Publication date: September 20, 2018
    Applicant: Toshiba Energy Systems & Solutions Corporation
    Inventors: Yukinobu Sakata, Yasunori Taguchi, Ryusuke Hirai, Keiko Okaya, Shinichiro Mori
  • Publication number: 20180193670
    Abstract: A medical image processing apparatus of an embodiment has acquisitor, a first landmark detector, and an estimator. The acquisitor acquires a perspective image of an object to be treated imaged by an imaging apparatus. The first landmark detector detects a position of a landmark that appears in the perspective image acquired by the acquisitor. The estimator, based on relationship information indicating a relationship between the position of landmark and the position of a target, estimates the position of the search-for location of the object to be treated from the position of the landmark detected by the first landmark detector.
    Type: Application
    Filed: March 7, 2018
    Publication date: July 12, 2018
    Applicant: Kabushiki Kaisha Toshiba
    Inventors: Yasunori TAGUCHI, Ryusuke HIRAI, Yukinobu SAKATA, Kyoka SUGIURA
  • Patent number: 10016625
    Abstract: A medical image processing apparatus of an embodiment has acquisitor, a first landmark detector, and an estimator. The acquisitor acquires a perspective image of an object to be treated imaged by an imaging apparatus. The first landmark detector detects a position of a landmark that appears in the perspective image acquired by the acquisitor. The estimator, based on relationship information indicating a relationship between the position of landmark and the position of a target, estimates the position of the search-for location of the object to be treated from the position of the landmark detected by the first landmark detector.
    Type: Grant
    Filed: September 8, 2015
    Date of Patent: July 10, 2018
    Assignee: Kabushiki Kaisha Toshiba
    Inventors: Yasunori Taguchi, Ryusuke Hirai, Yukinobu Sakata, Kyoka Sugiura
  • Publication number: 20180140260
    Abstract: A medical image processing apparatus comprising: a first input interface configured to acquire a three-dimensional volume image of an object which is provided with at least one marker, the three-dimensional volume image being generated by imaging the object using a medical examination apparatus; a second input interface configured to acquire geometry information of an imaging apparatus which is used for imaging the object to generate a fluoroscopic image of the object; and a specific-setting-information generator configured to generate specific setting information based on the three-dimensional volume image and the geometry information, the specific setting information being used for setting of imaging for generating an image depicting the at least one marker or setting of image processing of the image depicting the at least one marker.
    Type: Application
    Filed: November 20, 2017
    Publication date: May 24, 2018
    Applicants: KABUSHIKI KAISHA TOSHIBA, Toshiba Energy Systems & Solutions Corporation
    Inventors: Yasunori TAGUCHI, Ryusuke HIRAI, Yukinobu SAKATA, Keiko OKAYA, Shinichiro MORI
  • Patent number: 9919164
    Abstract: According to one embodiment, a medical image processing apparatus, includes: a first acquisition unit; a second acquisition unit; and a part-removed image generation unit, wherein the first acquisition unit is adapted to acquire a first radiograph that is a virtual radiograph generated to have a specified part or a predetermined part, among parts included in volume data indicative of a three-dimensional structure of an inside of a body of a patient, being emphasized, the second acquisition unit is adapted to acquire a second radiograph of the inside of the body of the patient, and the part-removed image generation unit is adapted to generate a part-removed image by removing the specified or predetermined part or parts other than the specified or predetermined part from the second radiograph with reference to the first radiograph.
    Type: Grant
    Filed: November 18, 2015
    Date of Patent: March 20, 2018
    Assignees: KABUSHIKI KAISHA TOSHIBA, National Institute of Radiological Sciences
    Inventors: Yasunori Taguchi, Yukinobu Sakata, Ryusuke Hirai, Kyoka Sugiura, Tomoyuki Takeguchi, Shinichiro Mori, Fumi Maruyama
  • Patent number: 9888905
    Abstract: A medical diagnosis apparatus of embodiments includes a scanner and processing circuitry. The scanner configured to scan a three-dimensional region including a target region and acquire data of the three-dimensional region. The processing circuitry is configured to discretely arrange fixed points framing three-dimensional shape of the target region in a first medical image based on the data. The processing circuitry is configured to set a boundary of region of interest (ROI) on the three-dimensional shape of the target region according to a position of the fixed point. The processing circuitry is configured to receive an instruction to change a position of the boundary from an input device controlled by a user. The processing circuitry is configured to change the position of the boundary based on a position or positions of at least one of the fixed points according to the instruction while maintaining positions of the fixed points.
    Type: Grant
    Filed: September 21, 2015
    Date of Patent: February 13, 2018
    Assignee: Toshiba Medical Systems Corporation
    Inventors: Tomoya Okazaki, Yukinobu Sakata, Tomoyuki Takeguchi, Yasuhiko Abe
  • Patent number: 9892526
    Abstract: A radiotherapy apparatus includes an receiver receiving a first projection image of a calibration object under X-ray imaging; a storing portion storing an ideal projection image of the calibration object, the ideal projection image generated based on design information of an X-ray imaging structure, positional information of the calibration object, and volume data of the calibration object; a calculator calculating a transformation parameter for transforming the first projection image into an ideal projection image; a transformed image generator generating a transformed projection image of the patient by transforming a second projection image of a patient obtained under X-ray imaging with the transformation parameter; a reconstructed image generator generating a reconstructed projection image based on volume data of the patient, positional information of the patient, and the design information; and a matching image generator generating a matching reference image used for matching between the transformed proje
    Type: Grant
    Filed: August 10, 2016
    Date of Patent: February 13, 2018
    Assignees: KABUSHIKI KAISHA TOSHIBA, National Institutes for Quantum and Radiological Science and Technology
    Inventors: Ryusuke Hirai, Yukinobu Sakata, Yasunori Taguchi, Tomoyuki Takeguchi, Shinichiro Mori, Fumi Maruyama