公开(公告)号：US20200069967A1

公开(公告)日：2020-03-05

申请号：US16347048

申请日：2017-07-20

Applicant: Shimadzu Corporation

Inventor： Shinichiro MORI ,  Wataru TAKAHASHI

IPC: A61N5/10 ,  A61N5/01 ,  G06T7/00 ,  A61B6/00

Abstract: A control unit 30 includes: an image storage unit 31 constituted by a first image storage unit 32 that stores multiple templates created on the basis of an image including a specific site of a subject and a second image storage unit 33 that stores multiple positive images created on the basis of an image including the specific site of the subject; a learning unit 34 that, on the basis of the multiple positive images, creates a discriminator by machine learning; a position selection unit 35 that, with use of multiple images obtained by collecting an image including the specific site of the subject at a predetermined frame rate, selects a region including the specific site by machine learning using the discriminator; and a position detection unit 36 that detects the position of the specific site by performing template matching using the multiple templates on the region including the specific site selected by the position selection unit 35.

公开(公告)号：US20190060672A1

公开(公告)日：2019-02-28

申请号：US16107368

申请日：2018-08-21

Applicant: SHIMADZU CORPORATION

Inventor： Wataru TAKAHASHI ,  Michel DARGIS ,  Shinichiro MORI

IPC: A61N5/10 ,  A61B6/12 ,  A61B6/00

Abstract: A radiotherapy tracking apparatus for tracking a position of a specific region with markerless tracking even when visual recognition of the specific region of the subject is poor and for eliminating preliminary work such as preparation of a template. A control element comprises a DRR image generation element, a phase-based position calculation element, an X-ray fluoroscopic image obtaining element, a phase adjuster, a frame-based position calculation element, a gating element and a memory storage. The frame-based position calculation element calculates the position of the specific region of the subject in the X-ray fluoroscopic image having the plurality of frames frame-by-frame based on the DRR image adjusted with the X-ray fluoroscopic image in the phase adjustment element and the position of the specific region calculated by the phase-based position calculation element.

公开(公告)号：US20210350513A1

公开(公告)日：2021-11-11

申请号：US17282229

申请日：2018-10-03

Applicant: Shimadzu Corporation

Inventor： Wataru TAKAHASHI ,  Yusuke TAGAWA

IPC: G06T5/00 ,  A61B6/00 ,  G06N20/00 ,  G06T5/50

Abstract: This production method of a trained model (10) includes a step of optimizing a training model (11) so that a value of a loss function (A) becomes small. The loss function (A) is configured to output a relatively large value in a case where the contrast of the predetermined area (PA) in a brightness-adjusted image adjusted in brightness becomes high with respect to training data (20) than in a case where the contrast of the predetermined area in the brightness-adjusted image (3) becomes low with respect to the training data.

公开(公告)号：US20210398254A1

公开(公告)日：2021-12-23

申请号：US17281781

申请日：2019-09-27

Applicant: Shimadzu Corporation

Inventor： Shota OSHIKAWA ,  Wataru TAKAHASHI

IPC: G06T5/00 ,  G06K9/62 ,  G06N20/00

Abstract: This image generation device is provided with: a learning image generation unit (1) for generating a training input image and a training output image based on three-dimensional data; a noise addition unit (2) for adding the same noise to the training input image and the training output image; a learning unit (3) for learning a learning model for extracting or removing a specific portion by performing machine learning based on the training input image to which the noise has been added and the training output image to which the noise has been added; and an image generation unit (4) for generating an image from which the specific portion has been extracted or removed by using a learned learning model.

公开(公告)号：US20210272288A1

公开(公告)日：2021-09-02

申请号：US17265760

申请日：2018-08-06

Applicant: Shimadzu Corporation

Inventor： Wataru TAKAHASHI ,  Ayako AKAZAWA ,  Shota OSHIKAWA

IPC: G06T7/11 ,  G06N20/00 ,  G06T7/00 ,  G06K9/62

Abstract: A training label image correction method includes performing a segmentation process on an input image (11) of training data (10) by a trained model (1) using the training data to create a determination label image (14), comparing labels of corresponding portions in the determination label image (14) and a training label image (12) with each other, and correcting label areas (13) included in the training label image based on label comparison results.

公开(公告)号：US20210030374A1

公开(公告)日：2021-02-04

申请号：US16959814

申请日：2018-01-09

Applicant: Shimadzu Corporation

Inventor： Wataru TAKAHASHI ,  Shota OSHIKAWA

IPC: A61B6/03 ,  A61B6/00 ,  G06T7/00

Abstract: An image generating device for generating an image which is an X-ray image of an area including a bone portion of a subject with the bone portion removed has a control unit 70 including: a DRR imager 81 configured to generate a first DRR image of an area including a bone portion and a second DRR image showing the bone portion, by performing, for a set of CT image data of an area including the bone portion of a subject, a virtual fluoroscopic projection simulating a geometric fluoroscopy condition of an X-ray irradiator and an X-ray detector for the subject; a training section 82 configured to generate a machine learning model for recognizing the bone portion, by performing machine learning using the first DRR image and the second DRR image serving as a training image; an image converter 83 configured to perform conversion of the X-ray image of the area including the bone portion of the subject, using the machine learning model trained in the training section 82, to generate an image showing the bone portion; and a bone portion subtractor 84 configured to subtract the image showing the bone portion from the X-ray image of the area including the bone portion of the subject.

公开(公告)号：US20190282190A1

公开(公告)日：2019-09-19

申请号：US15922977

申请日：2018-03-16

Applicant: Shimadzu Corporation

Inventor： Michel Dargis ,  Wataru TAKAHASHI ,  Keiichi GOTO

IPC: A61B6/00 ,  G06T7/11

Abstract: [Purpose] To provide a radiographic imaging apparatus capable of quickly acquiring three-dimensional image data of a target-of-interest when performing an operative procedure such as interventional treatment[Solving Means] A region-of-interest extraction unit 39 extracts a predetermined region as a region-of-interest from each of a series of two-dimensional images. The reconstruction unit 41 reconstructs a three-dimensional image of a region including a stent based on each of the images of the portion corresponding to the region-of-interest. That is, since the reconstruction unit 41 reconstructs each of a series of two-dimensional images P using an image of the region-of-interest corresponding to a part of the whole, the time required to reconstruct the three-dimensional image of the region including the stent can be shortened. As a result, since three-dimensional image data can be quickly obtained for the region requiring the reconstruction, the time required for diagnosis can be greatly shortened, which can reduce the burden on a surgeon and a subject.

公开(公告)号：US20190015056A1

公开(公告)日：2019-01-17

申请号：US16066568

申请日：2015-12-28

Applicant: SHIMADZU CORPORATION

Inventor： Shota SATO ,  Wataru TAKAHASHI ,  Michel DARGIS ,  Takihito SAKAI ,  Keiichi GOTO ,  Sebastien MATTE

IPC: A61B6/12 ,  A61B6/00 ,  G06K9/46

Abstract: A radiography apparatus sequentially determines, on the basis of the positions of markers as time-sequential feature points (of a plurality of frames), positions at which the markers in the frames are displayed. This makes it possible to display a moving object while the position, direction and size thereof are properly set. Another advantage is that when a plurality of markers are extracted, information relating to the direction and size of the object is retained and the proximal and distal directions of the object and the length of a device (e.g., stent) can be intuitively determined from an image. Since positioning is performed using the plurality of positions of markers and the plurality of display positions, the position and direction of a corrected image to be finally displayed can also be set properly.

公开(公告)号：US20180276851A1

公开(公告)日：2018-09-27

申请号：US15467510

申请日：2017-03-23

Applicant: SHIMADZU CORPORATION

Inventor： Wataru TAKAHASHI ,  Shinichiro MORI

IPC: G06T11/00 ,  A61B6/03 ,  A61B6/00 ,  A61N5/10

CPC classification number: G06T11/003 ,  A61B6/032 ,  A61B6/461 ,  A61B6/487 ,  A61B6/5205 ,  A61B6/5258 ,  A61B6/54 ,  A61N5/1077 ,  G06T2210/41

Abstract: A DRR image generation method and a DRR image generation apparatus provide the equivalent image-quality to the X-ray radiograph and includes an image processing element 80, a calculation point setting element 81 that sets a ray connecting an X-ray tube relative to the geometrical arrangement of the X-ray radiography system reconstructed on a computer and each pixel of the X-ray CT data, and in addition, sets a plurality of calculation points on the ray; a CT value correction element 82 that compensates the CT value of each calculation point set by the calculation point setting element 81 based on the cumulative CT value from the X-ray tube to the calculation point; a CT value cumulation element 83 that cumulates the CT value of the calculation point located on the ray using the CT value of each calculation point after corrected by the CT value correction element 82; and a DRR image generation element 84 that that generates the DRR image based on the CT value cumulated by the CT value cumulation element 83.