-
公开(公告)号:US12148127B2
公开(公告)日:2024-11-19
申请号:US17846182
申请日:2022-06-22
Applicant: FUJIFILM Healthcare Corporation
Inventor: Yukio Kaneko , Toru Shirai , Atsuro Suzuki , Tomoki Amemiya , Suguru Yokosawa
Abstract: The invention provides a technique capable of effectively and appropriately removing noise from various kinds of images including noise and artifacts and images in which a noise pattern changes due to a difference in imaging conditions. Based on a noise removal technique using AI, noise characteristics including artifacts are analyzed for each image, the image is classified based on an analysis result, an optimal neural network for a noise processing is applied for each classification, and the noise and the artifacts are reduced.
-
2.
公开(公告)号:US20230401701A1
公开(公告)日:2023-12-14
申请号:US18203743
申请日:2023-05-31
Applicant: FUJIFILM Healthcare Corporation
Inventor: Suguru Yokosawa , Atsuro Suzuki , Toru Shirai
CPC classification number: G06T7/0012 , G06T5/50 , G16H30/20 , G16H30/40 , G06T2207/30168 , G06T2207/20092 , G06T2207/10088 , G06T2207/10081 , G06T2207/10132 , G06T2200/24 , G06T2207/30004
Abstract: Provided is a means of easily presenting conditions for obtaining an image quality desired by a user, and this achieves savings in time and effort required for repetitive adjustment of the image quality. A medical image processing apparatus comprises a reception unit configured to receive image quality data reflecting a user's desire for an image quality of a medical image, a feature value calculation unit configured to calculate an image feature value with respect to the image quality data, and a parameter presentation unit configured to use a database associating adjustment parameters related to the image quality with the image feature value, to determine and present the adjustment parameters suitable for the image quality data received by the reception unit.
-
公开(公告)号:US20220414837A1
公开(公告)日:2022-12-29
申请号:US17846182
申请日:2022-06-22
Applicant: FUJIFILM Healthcare Corporation
Inventor: Yukio Kaneko , Toru Shirai , Atsuro Suzuki , Tomoki Amemiya , Suguru Yokosawa
Abstract: The invention provides a technique capable of effectively and appropriately removing noise from various kinds of images including noise and artifacts and images in which a noise pattern changes due to a difference in imaging conditions. Based on a noise removal technique using AI, noise characteristics including artifacts are analyzed for each image, the image is classified based on an analysis result, an optimal neural network for a noise processing is applied for each classification, and the noise and the artifacts are reduced.
-
4.
公开(公告)号:US20220395188A1
公开(公告)日:2022-12-15
申请号:US17832772
申请日:2022-06-06
Applicant: FUJIFILM Healthcare Corporation
Inventor: Toru Shirai , Suguru Yokosawa , Yukio Kaneko , Atsuro Suzuki , Tomoki Amemiya
IPC: A61B5/055 , G01R33/56 , G01R33/3415 , G01R33/561 , G06T7/00
Abstract: The present invention is to perform appropriate noise reduction processing on an image having different signal levels or noise levels depending on an imaging condition or a reconstruction condition. A magnetic resonance imaging apparatus according to the invention includes: a measurement unit that receives a nuclear magnetic resonance signal generated in a subject by a receiving coil; an image reconstruction unit that processes the nuclear magnetic resonance signal received by the receiving coil and reconstructs an image of the subject; an SNR spatial distribution calculation unit that calculates spatial distribution of a signal-to-noise ratio of the image using spatial distribution of a noise level and spatial distribution of the signal of the image; and a noise reduction unit that reduces noise from the image based on the spatial distribution of the signal-to-noise ratio.
-
公开(公告)号:US11940520B2
公开(公告)日:2024-03-26
申请号:US17892495
申请日:2022-08-22
Applicant: FUJIFILM Healthcare Corporation
Inventor: Ryota Sato , Suguru Yokosawa , Toru Shirai , Kazuho Kamba , Yoshitaka Sato , Masahiro Takizawa
IPC: G01R33/56 , A61B5/055 , G01R33/565 , G06T11/00
CPC classification number: G01R33/565 , A61B5/055 , G06T11/005 , G06T2207/10088
Abstract: For a complex image to be complexly added, appropriate phase correction is executed by a simple method to prevent occurrence of an artifact in a signal region and to reduce noise in a background region. Two or more types of smoothing processing with different smoothing degrees are executed on a phase image of the complex image to obtain two or more types of smoothed phase images having different smoothing degrees. A weight for each of these smoothed phase images is calculated based on a signal value (SNR) of an intensity image, and addition is performed by a weight for each signal value to obtain a smoothed phase image for correction. After a phase of the complex image is corrected using the smoothed phase image, a phase-corrected complex image is complexly added. As a result, phase correction equivalent to phase correction in which a smoothing degree is weakened in the signal region and a smoothing degree is strengthened in the background region is realized.
-
6.
公开(公告)号:US11918337B2
公开(公告)日:2024-03-05
申请号:US17832772
申请日:2022-06-06
Applicant: FUJIFILM Healthcare Corporation
Inventor: Toru Shirai , Suguru Yokosawa , Yukio Kaneko , Atsuro Suzuki , Tomoki Amemiya
IPC: A61B5/055 , G01R33/3415 , G01R33/56 , G01R33/561 , G06T7/00
CPC classification number: A61B5/055 , G01R33/3415 , G01R33/5608 , G01R33/5611 , G06T7/0012 , G06T2207/10088
Abstract: The present invention is to perform appropriate noise reduction processing on an image having different signal levels or noise levels depending on an imaging condition or a reconstruction condition. A magnetic resonance imaging apparatus according to the invention includes: a measurement unit that receives a nuclear magnetic resonance signal generated in a subject by a receiving coil; an image reconstruction unit that processes the nuclear magnetic resonance signal received by the receiving coil and reconstructs an image of the subject; an SNR spatial distribution calculation unit that calculates spatial distribution of a signal-to-noise ratio of the image using spatial distribution of a noise level and spatial distribution of the signal of the image; and a noise reduction unit that reduces noise from the image based on the spatial distribution of the signal-to-noise ratio.
-
7.
公开(公告)号:US20240361413A1
公开(公告)日:2024-10-31
申请号:US18619828
申请日:2024-03-28
Applicant: FUJIFILM Healthcare Corporation
Inventor: Toru Shirai , Yukio Kaneko , Yosuke Otake , Suguru Yokosawa
IPC: G01R33/561 , G01R33/36 , G01R33/54
CPC classification number: G01R33/5611 , G01R33/3664 , G01R33/546
Abstract: Provided is an MRI apparatus that supports re-setting of an imaging condition for preventing occurrence of aliasing in a phase encoding direction. A region in which an aliasing signal causing aliasing occurs is estimated by using a FOV set at the beginning and a positioning image, a range of the FOV to be changed or a weighting amount of each channel of a reception coil is calculated based on an estimation result, and an imaging condition is changed. Thereafter, a main scan is executed, and in a case where a weight of the reception coil is changed, channel combination is performed using the changed weight.
-
8.
公开(公告)号:US20240273714A1
公开(公告)日:2024-08-15
申请号:US18412271
申请日:2024-01-12
Applicant: FUJIFILM Healthcare Corporation
Inventor: Suguru Yokosawa , Atsuro Suzuki , Toru Shirai
CPC classification number: G06T7/0012 , G06T5/50 , G06T5/70 , G06V10/25 , G06T2207/20104 , G06T2207/20221 , G06T2207/20224 , G06T2207/30016
Abstract: Provided is a noise-reduced image in which noise and artifacts, which pose a problem in intraoperative MRI, are reduced for each pixel in a manner desired by a user and a preference of the user for a tissue or a site that the user wants to observe is reflected. In a case of generating and presenting a third medical image by using a first medical image acquired by an MRI apparatus and a second medical image obtained by performing processing of reducing noise and artifacts with respect to the first medical image, a difference for each pixel between the first medical image and the second medical image is taken, a weighting value for each pixel is calculated using a generated difference image, and a user's change for weighting is received. The finally decided-on weighting value is used to combine the first medical image and the second medical image through weighted averaging for each pixel, and the combined image is presented.
-
9.
公开(公告)号:US20240268778A1
公开(公告)日:2024-08-15
申请号:US18412221
申请日:2024-01-12
Applicant: FUJIFILM Healthcare Corporation
Inventor: Suguru Yokosawa , Atsuro Suzuki , Toru Shirai
CPC classification number: A61B6/5258 , A61B6/5235 , G06T5/50 , G06T5/70 , G06V10/25 , G06V10/56 , G06T2207/10088 , G06T2207/20221 , G06T2207/20224
Abstract: Provided is an image in which noise and artifacts, which pose a problem in intraoperative MRI, are reduced and a decrease in sharpness due to noise reduction for a tissue or a site, for which high visibility is required, is suppressed. In a case of generating and presenting a third MR image by using a first MR image acquired by an MRI apparatus and a second MR image obtained by performing processing of reducing noise and artifacts with respect to the first MR image, a difference for each pixel between the first MR image and the second MR image is taken, and a weighting value for each pixel is calculated using a generated difference image. The weighting value is used to combine the first MR image and the second MR image through weighted averaging for each pixel, and the combined image is presented.
-
公开(公告)号:US20230062864A1
公开(公告)日:2023-03-02
申请号:US17892495
申请日:2022-08-22
Applicant: FUJIFILM Healthcare Corporation
Inventor: Ryota Sato , Suguru Yokosawa , Toru Shirai , Kazuho Kamba , Yoshitaka Sato , Masahiro Takizawa
IPC: G01R33/565 , A61B5/055 , G06T11/00
Abstract: For a complex image to be complexly added, appropriate phase correction is executed by a simple method to prevent occurrence of an artifact in a signal region and to reduce noise in a background region. Two or more types of smoothing processing with different smoothing degrees are executed on a phase image of the complex image to obtain two or more types of smoothed phase images having different smoothing degrees. A weight for each of these smoothed phase images is calculated based on a signal value (SNR) of an intensity image, and addition is performed by a weight for each signal value to obtain a smoothed phase image for correction. After a phase of the complex image is corrected using the smoothed phase image, a phase-corrected complex image is complexly added. As a result, phase correction equivalent to phase correction in which a smoothing degree is weakened in the signal region and a smoothing degree is strengthened in the background region is realized.
-
-
-
-
-
-
-
-
-