-
公开(公告)号：US11961276B2
公开(公告)日：2024-04-16
申请号：US17477547
申请日：2021-09-17
Applicant: FUJIFILM Corporation
Inventor： Yoshiro Kitamura , Akimichi Ichinose
IPC: G06V10/44 , A61B6/50 , G06F18/213 , G06F18/214 , G06F18/2431 , G06T3/4046 , G06T7/00 , G06V10/25 , G06V10/94
CPC classification number: G06V10/44 , A61B6/504 , G06F18/213 , G06F18/214 , G06F18/2431 , G06T3/4046 , G06T7/0012 , G06V10/25 , G06V10/95 , G06T2207/20081 , G06T2207/20084 , G06T2207/30101 , G06V2201/03
Abstract: Provided are a linear structure extraction device, a method, a program, and a learned model which can detect a linear structure in an image. A linear structure extraction device according to an embodiment of the present disclosure includes a learning model that is learned to receive an input of the image and output, as a prediction result, one or more element points which constitute the linear structure from the image, in which the learning model includes a first processing module that receives the image and generates a feature map representing a feature amount of the image by convolution processing, and a second processing module that calculates a shift amount from a unit center point to the element point of the linear structure closest to the unit center point, for each unit obtained by dividing the feature map into a plurality of the units including regions having a predetermined size in a grid pattern.
-
公开(公告)号：US11948349B2
公开(公告)日：2024-04-02
申请号：US17400150
申请日：2021-08-12
Applicant: FUJIFILM Corporation
Inventor： Akira Kudo , Yoshiro Kitamura
IPC: G06K9/62 , G06F18/21 , G06F18/214 , G06K9/68 , G06V10/10 , G06V10/12 , G06V10/82 , G06V30/24 , A61B6/03
CPC classification number: G06V10/82 , G06F18/2148 , G06F18/2185 , G06V10/12 , G06V10/16 , G06V30/2504 , A61B6/032 , G06V2201/03
Abstract: Provided are a learning method, a learning device, a generative model, and a program that generate an image including high resolution information without adjusting a parameter and largely correcting a network architecture even in a case in which there is a variation of the parts of an image to be input. Only a first image is input to a generator of a generative adversarial network that generates a virtual second image having a relatively high resolution by using the first image having a relatively low resolution, and a second image for learning or the virtual second image and part information of the second image for learning or the virtual second image are input to a discriminator that identifies the second image for learning and the virtual second image.
-
公开(公告)号：US20150016686A1
公开(公告)日：2015-01-15
申请号：US14484046
申请日：2014-09-11
Applicant: FUJIFILM Corporation
Inventor： Yoshiro Kitamura
IPC: G06T7/00
CPC classification number: G06T7/0081 , A61B5/489 , A61B2576/00 , G06T7/0012 , G06T7/11 , G06T7/12 , G06T7/149 , G06T7/168 , G06T2207/10081 , G06T2207/10088 , G06T2207/10104 , G06T2207/20016 , G06T2207/20024 , G06T2207/20048 , G06T2207/20056 , G06T2207/20072 , G06T2207/20116 , G06T2207/20152 , G06T2207/30008 , G06T2207/30061 , G06T2207/30088 , G06T2207/30101
Abstract: An image processing apparatus, including a filtering unit that performs filtering on an image using a second order partial differential and calculates a Hessian matrix and an evaluation unit that discriminates a structure included in the image using eigenvalues and eigenvectors of the Hessian matrix, in which the filtering unit includes a correction unit that performs filtering on the image using a first order partial differential of a function representing a hollow sphere having the same radius as the radius of the solid sphere and obtains first order partial differential vectors, and carries out correction to cancel out one of response waveforms of the function representing the solid sphere in each direction, the response waveforms appearing at two positions symmetrically separated with respect to the center of the solid sphere, using values obtained by projecting the first order partial differential vectors onto directions of the eigenvectors.
Abstract translation: 一种图像处理装置，包括：使用二阶偏差对图像进行滤波并使用Hessian矩阵的特征值和特征向量来计算Hessian矩阵的滤波单元和评估单元，所述滤波单元使用特征值和特征向量来区分包含在图像中的结构， 滤波单元包括校正单元，该校正单元使用表示具有与实心球半径相同的半径的中空球的函数的一阶偏微分来对图像进行滤波，并获得一阶偏微分矢量，并执行校正以取消 将表示每个方向上的实心球的函数的响应波形中的一个反应波形，使用通过将一阶偏微分矢量投影到方向上获得的值，出现在相对于实心球的中心对称分开的两个位置处的响应波形 特征向量
-
公开(公告)号：US12100155B2
公开(公告)日：2024-09-24
申请号：US17407179
申请日：2021-08-19
Applicant: FUJIFILM Corporation
Inventor： Akimichi Ichinose , Yoshiro Kitamura
CPC classification number: G06T7/0016 , G06F18/2132 , G06N3/08 , G06V10/25 , G06V10/82
Abstract: A region specification apparatus specifies a region of an object which is included in an input image and which includes a plurality of subclass objects having different properties. The region specification apparatus includes a first discriminator that specifies an object candidate included in the input image. The first discriminator has a component configured to predict at least one of movement or transformation of a plurality of anchors according to the property of the subclass object and specify an object candidate region surrounding the object candidate.
-
5.发明公开公开(公告)号：US20230316517A1
公开(公告)日：2023-10-05
申请号：US18329538
申请日：2023-06-05
Applicant: FUJIFILM Corporation
Inventor： Tsubasa GOTO , Yoshiro Kitamura
CPC classification number: G06T7/0012 , G06T7/11 , G06V10/25 , G06V10/44 , G06V10/764 , G16H50/20 , G06T2207/30061
Abstract: A processor is configured to: divide a target image into a plurality of first regions through a first division; divide the target image into a plurality of second regions through a second division different from the first division; derive a feature vector that represents at least a feature of each of the second regions for each of the first regions; derive a determination result for a target object included in the target image based on the feature vector; specify, among elements of the feature vector, an influential element that affects the determination result; and specify an influential region that affects the determination result in the target image based on the influential element.
-
Patent Agency Ranking
公开(公告)号：US11087465B2
公开(公告)日：2021-08-10
申请号：US16553636
申请日：2019-08-28
Applicant: FUJIFILM Corporation
Inventor： Mizuki Takei , Yoshiro Kitamura
IPC: G06T7/00 , G16H30/20 , G06T7/11 , A61B6/00 , G16H30/40 , A61B5/00 , A61B6/03 , A61B5/055 , G06T7/68 , G06N20/00 , G06T7/33 , G16H50/20
Abstract: A determination processing unit determines a disease region in a medical image including an axisymmetric structure. A first determination section of the determination processing unit generates a feature amount map of the medical image from the medical image. A second determination section second inverts the feature amount map with reference to a symmetry axis to generate an inverted feature amount map. A third determination section superimposes the feature amount map and the inverted feature amount map on each other and determines the disease region in the medical image using the feature amount map and the inverted feature amount map superimposed on each other.
-
公开(公告)号：US09183637B2
公开(公告)日：2015-11-10
申请号：US14484046
申请日：2014-09-11
Applicant: FUJIFILM Corporation
Inventor： Yoshiro Kitamura
CPC classification number: G06T7/0081 , A61B5/489 , A61B2576/00 , G06T7/0012 , G06T7/11 , G06T7/12 , G06T7/149 , G06T7/168 , G06T2207/10081 , G06T2207/10088 , G06T2207/10104 , G06T2207/20016 , G06T2207/20024 , G06T2207/20048 , G06T2207/20056 , G06T2207/20072 , G06T2207/20116 , G06T2207/20152 , G06T2207/30008 , G06T2207/30061 , G06T2207/30088 , G06T2207/30101
Abstract: An image processing apparatus, including a filtering unit that performs filtering on an image using a second order partial differential and calculates a Hessian matrix and an evaluation unit that discriminates a structure included in the image using eigenvalues and eigenvectors of the Hessian matrix, in which the filtering unit includes a correction unit that performs filtering on the image using a first order partial differential of a function representing a hollow sphere having the same radius as the radius of the solid sphere and obtains first order partial differential vectors, and carries out correction to cancel out one of response waveforms of the function representing the solid sphere in each direction, the response waveforms appearing at two positions symmetrically separated with respect to the center of the solid sphere, using values obtained by projecting the first order partial differential vectors onto directions of the eigenvectors.
Abstract translation: 一种图像处理装置，包括：使用二阶偏差对图像进行滤波并使用Hessian矩阵的特征值和特征向量来计算Hessian矩阵的滤波单元和评估单元，所述滤波单元使用特征值和特征向量来区分包含在图像中的结构， 滤波单元包括校正单元，该校正单元使用表示具有与实心球半径相同的半径的中空球的函数的一阶偏微分来对图像进行滤波，并获得一阶偏微分矢量，并执行校正以取消 将表示每个方向上的实心球的函数的响应波形中的一个反应波形，使用通过将一阶偏微分矢量投影到方向上获得的值，出现在相对于实心球的中心对称分开的两个位置处的响应波形 特征向量
-
8.发明公开公开(公告)号：US20240029246A1
公开(公告)日：2024-01-25
申请号：US18357140
申请日：2023-07-23
Applicant: FUJIFILM Corporation
Inventor： Deepak Keshwani , Yoshiro Kitamura
CPC classification number: G06T7/0012 , G06T7/11 , G16H50/30 , A61B6/504 , A61B6/032 , A61B6/482 , G06T2207/20021 , G06T2207/20081 , G06T2207/30104 , G06T2207/30048 , G06T2207/10081 , G06T2207/20084 , A61B6/541
Abstract: An information processing apparatus includes one or more processors, and one or more storage devices that store a program including an image generation model trained to generate, from a first image, a second image that imitates an image obtained by an imaging protocol different from an imaging protocol of the first image. The image generation model is a model trained, through machine learning using training data in which a training image captured by a first imaging protocol is associated with a correct answer clinical parameter calculated from a corresponding image captured by a second imaging protocol different from the first imaging protocol for the same subject as the training image using a modality of the same type as a modality used to capture the training image, such that a clinical parameter calculated from a generation image output by the image generation model approaches the correct answer clinical parameter.
-
公开(公告)号：US10452957B2
公开(公告)日：2019-10-22
申请号：US15868240
申请日：2018-01-11
Applicant: FUJIFILM CORPORATION
Inventor： Yoshiro Kitamura
Abstract: An extraction unit extracts a target object from a three-dimensional image, and a feature point detection unit detects at least one feature point included in the three-dimensional image. A reference axis setting unit sets a reference axis in the three-dimensional image based on the feature amount, and a two-dimensional image generation unit generates a two-dimensional image by projecting a target object, which is included in the three-dimensional image, in a specific projection direction using the reference axis as a reference. A classification unit classifies each pixel of the target object into a plurality of classes based on the two-dimensional image.
-
公开(公告)号：US09965698B2
公开(公告)日：2018-05-08
申请号：US14865616
申请日：2015-09-25
Applicant: FUJIFILM Corporation
Inventor： Yoshiro Kitamura
IPC: G06K9/52 , G06K9/62 , G06T7/149 , A61B6/03 , A61B6/00 , G06T7/73 , G06T7/11 , G06T7/12 , G06T7/162 , G06T7/68 , G06K9/46
CPC classification number: G06K9/52 , A61B6/032 , A61B6/503 , G06K9/6267 , G06K2009/4666 , G06T7/11 , G06T7/12 , G06T7/149 , G06T7/162 , G06T7/68 , G06T7/73 , G06T2200/04 , G06T2207/10081 , G06T2207/20021 , G06T2207/20072 , G06T2207/20112 , G06T2207/20116 , G06T2207/30101 , G06T2207/30172
Abstract: When binary labeling is performed, an outline specification unit specifies a first outline present toward a target region and a second outline present toward a non-target region, and which have shapes similar to an outline of the target region. A voxel selection unit selects an N number of voxels constituting all of the first outline and the second outline. The energy setting unit sets N-order energy when a condition that all of the voxels of the first outline belong to the target region and all of the voxels of the second outline belong to the non-target region is satisfied smaller than the N-order energy when the condition is not satisfied. After then, labeling is performed by minimizing energy.
-
-
-
-
-
-
-
-
-
Search Results
27
records
(took 0.018 seconds)
