公开(公告)号：US20210407048A1

公开(公告)日：2021-12-30

申请号：US17214970

申请日：2021-03-29

Applicant: Hitachi, Ltd.

Inventor： Chizue TANAKA ,  Yukio KANEKO

IPC: G06T5/00 ,  G16H30/40 ,  G16H30/20 ,  G06T7/00

Abstract: Provided are an image processing apparatus, a medical imaging apparatus, and an image processing program that remove noise from an image having different noise levels depending on regions in the image at a low calculation cost, and enable high quality according to a preference of a reader. A plurality of image generators receive measurement data or a captured image obtained by an image data acquisition apparatus and generate different images for a same imaging range. An image selection and combination unit selects different image regions from a plurality of images generated by the plurality of image generators according to a predetermined region selection pattern, and generates one image by combining the images of the selected image regions.

公开(公告)号：US20200286214A1

公开(公告)日：2020-09-10

申请号：US16804054

申请日：2020-02-28

Applicant: Hitachi, Ltd.

Inventor： Yukio KANEKO ,  Masahiro OGINO ,  Yoshimi NOGUCHI ,  Yoshitaka BITO

IPC: G06T5/20 ,  G06T5/00 ,  G06T7/00 ,  G06T11/00 ,  G16H30/40 ,  G16H30/20 ,  G06N20/00 ,  G06N3/08

Abstract: Image processing using a machine learning model is enabled, thereby accurately reducing noise to improve image quality. A medical image is acquired; and it is evaluated whether noise in the medical image exceeds a predetermined reference value. A noise reducer reduces the noise of the medical image that has been determined to include noise that exceeds the reference value. The noise of the medical image is reduced using a machine learning model constructed by collecting a plurality of learning data sets that include an image with noise as input data and an image without noise as output data. The machine learning model includes a plurality of layers that perform convolution on an image that is input, one layer of which includes a filter layer in which a plurality of linear or nonlinear filters are incorporated, and convolution coefficients of the plurality of linear or nonlinear filters are predetermined.

公开(公告)号：US20220101983A1

公开(公告)日：2022-03-31

申请号：US17197445

申请日：2021-03-10

Applicant: Hitachi, Ltd.

Inventor： Yukio KANEKO ,  Yun LI ,  Zisheng LI ,  Aya KISHIMOTO ,  Kazuki MATSUZAKI ,  Peifei ZHU ,  Masahiro OGINO

IPC: G16H30/40 ,  G16H50/20 ,  G06T7/00 ,  G06T5/40

Abstract: An image diagnosis supporting device includes a model reader that reads an image diagnostic model that outputs a diagnostic result for a diagnostic image that is an input medical image, a storage unit that stores facility data that is a plurality of medical images associated with diagnostic results held in a facility, and an adjuster that adjusts, based on the facility data, the image diagnostic model or the diagnostic image input to the image diagnostic model.

公开(公告)号：US20210272277A1

公开(公告)日：2021-09-02

申请号：US17134843

申请日：2020-12-28

Applicant: Hitachi, Ltd.

Inventor： Masahiro OGINO ,  Zisheng LI ,  Yukio KANEKO

IPC: G06T7/00 ,  G06K9/46 ,  G06K9/32 ,  G06K9/62 ,  G16H30/20 ,  G06N20/00 ,  G06N5/02 ,  A61B5/055 ,  A61B5/00 ,  A61B6/03 ,  A61B6/00 ,  A61B8/00 ,  A61B8/08

Abstract: To obtain a predictive model that shows a diagnostic prediction result with higher accuracy and high medical validity. A medical imaging apparatus includes an imaging unit that collects an image signal of an inspection target, and an image processing unit that generates first image data from the image signal and performs image processing of the first image data. The image processing unit includes a feature quantity extraction unit that extracts a first feature quantity from the first image data, a feature quantity abstraction unit that abstracts the first feature quantity to extract a second feature quantity, a feature quantity conversion unit that converts the second feature quantity into a third feature quantity extracted by second image data, and an identification unit that uses the converted third feature quantity to calculate a predetermined parameter value.

公开(公告)号：US20180085026A1

公开(公告)日：2018-03-29

申请号：US15701640

申请日：2017-09-12

Applicant: Hitachi, Ltd.

Inventor： Yukio KANEKO ,  Hisaaki OCHI ,  Yoshihisa SOUTOME

IPC: A61B5/053 ,  A61B5/055 ,  A61B5/00 ,  G01R33/24

CPC classification number: A61B5/0537 ,  A61B5/0536 ,  A61B5/055 ,  A61B5/7278 ,  A61B5/743 ,  G01R33/24 ,  G01R33/443

Abstract: When an electrical characteristic of a predetermined region of a subject placed in a static magnetic field space is measured by using magnetic resonance signals measured from the region, measurement data measured by coinciding direction of a tissue structure of the subject with the direction of the static magnetic field, and measurement data measured with a direction of the tissue structure of the subject crossing the direction of the static magnetic field are used. A rotating magnetic field map of the region is created from the measurement data, and the electrical characteristic is calculated by using the rotating magnetic field map. The electrical characteristic is calculated as an electrical characteristic including anisotropy by using information about the direction of tissue structure. According to the present invention, electrical characteristic such as electrical conductivity including anisotropy can be measured with good precision with an electrical characteristic measuring apparatus using nuclear magnetic resonance.

公开(公告)号：US20200286229A1

公开(公告)日：2020-09-10

申请号：US16803774

申请日：2020-02-27

Applicant: Hitachi, Ltd.

Inventor： Masahiro OGINO ,  Yukio KANEKO ,  Zisheng LI ,  Yoshihisa SOTOME

IPC: G06T7/00 ,  A61B6/00 ,  A61B5/055

Abstract: An image diagnostic device that obtains a prediction model indicating a higher accuracy diagnosis prediction result includes: an observation unit that collects an image of an examination object; and an image processing unit that generates first image data from the image, and performs image processing of the first image data. The image processing unit is provided with: a feature extraction unit that extracts a first feature from the first image data; a feature transformation unit that converts the first feature to a second feature to be extracted from second image data; and an identification unit that calculates a prescribed parameter value using the converted second feature. The feature extraction unit includes a prediction model learned using a plurality of combinations of the first image data and feature, and the feature transformation unit includes a feature transformation model learned using a plurality of combinations of the first and second features.