Fujifilm Corporation

Caihua Wang

Keigo Nakamura

Yoshiyuki Moriya

Tsubasa Goto

Jun Masumoto

Noriaki Ida

Satoshi Ihara

Provided are an information processing device, a program, a trained model, a diagnostic support device, a learning device, and a prediction model generation method that can perform prediction with high accuracy using images. An information processing device includes: an information acquisition unit that receives an input of image data and non-image data related to a target matter; and a prediction unit that predicts an aspect related to the matter at a time different from a time when the image data is captured on the basis of the image data and the non-image data input through the information acquisition unit. The prediction unit performs weighting calculation by a calculation method, which outputs a combination of products of elements of a first feature amount calculated from the image data and a second feature amount calculated from the non-image data, to calculate a third feature amount in which the first feature amount and the second feature amount are fused and performs the prediction on the basis of the third feature amount.

Information processing device, program, trained model, diagnostic support device, learning device, and prediction model generation method

There is provided a medical information acquisition device including an information acquisition unit that acquires functional change information obtained on the basis of a reference image and a past image acquired by capturing images of the same subject at a reference time and a past time closer to the past than the reference time, respectively, using a trained model.

Trained model, learning method, learning program, medical information acquisition device, medical information acquisition method, and medical information acquisition program

The medical information display apparatus includes a first data acquisition unit that acquires a table showing relevance between at least one item included in clinical diagnostic information on dementia and a brain area, a second data acquisition unit that acquires clinical diagnostic information on dementia of a subject, an image acquisition unit that receives an input of a three-dimensional brain image, a brain area division unit that divides the three-dimensional brain image of the subject, an image analysis unit that calculates an analysis value for each brain area, an operation unit that selects one item among items included in the clinical diagnostic information of the subject, a display unit, and a display controller that specifies a brain area corresponding to the one item selected by the operation unit and displays brain area specifying information for specifying the specified brain area and an analysis value of the brain area.

Medical information display apparatus, medical information display method, and medical information display program

There are provided an information output apparatus, an information output method, and an information output program capable of outputting information effective for diagnosis or evaluation of dementia. In a case where a brain area having a high atrophy rate is input, the information output apparatus can output a test item highly relevant to the input brain area using a first table Tthat stores the relevance between a plurality of divided brain areas of a brain image and a plurality of test items of a dementia diagnostic test. In addition, in a case where a test item of interest is input, a brain area highly relevant to the input test item can be output.

Information output apparatus, information output method, and information output program

A medical image processing apparatus having a processor configured to detect at least four reference landmarks among the left eye, the right eye, the diencephalon, the fornix, the corpus callosum, the left hippocampus, and the right hippocampus from a brain image, performs first registration including registration by similarity transformation using reference landmarks between the brain image and a standard brain image, and perform second registration by nonlinear transformation between the brain image and the standard brain image after the first registration.

Medical image processing apparatus, medical image processing method, and medical image processing program

The medical information display apparatus includes an image acquisition unit that acquires a first brain image which is a brain image of a subject captured at a first time point and a second brain image captured at a second time point later in time than the first time point, a registration unit that performs registration between the first and the second brain image, an image analysis unit that extracts a first cavity region and a second cavity region from the first brain image and the second brain image, respectively, a display unit, and a display controller displays, a cavity expansion part included in a first non-cavity region, which is a region other than the first cavity region, and included in the second cavity region in a distinguishable manner from a region other than the cavity expansion part from a result of the registration between the first and second brain image.

Medical information display apparatus displaying cavity region in brain image, medical information display method, and medical information display program

A brain image normalization apparatus, having a processor configured to: detect at least four reference landmarks of a left eye, a right eye, a diencephalon, a fornix, a corpus callosum, a left hippocampus, and a right hippocampus from a brain image including a brain of a subject; perform registration between the detected reference landmarks and reference landmarks corresponding to the detected reference landmarks included in a standard brain image; and normalize the brain image based on a result of the registration.

Brain image normalization apparatus, brain image normalization method, and brain image normalization program

A medical image display apparatus includes an image acquisition unit that receives an input of a three-dimensional brain image of a subject, a brain area division unit that divides the three-dimensional brain image of the subject into a plurality of brain areas, an image analysis unit that calculates an analysis value for each brain area from the three-dimensional brain image of the subject, a data acquisition unit that acquires information indicating a correspondence between the brain area and a function of the brain, a display unit, and a display controller that displays an image showing the brain image of the subject divided into the brain areas, a function of the brain corresponding to each of the brain areas, and the analysis value on the display unit in association with each other.

Medical image display apparatus, medical image display method, and medical image display program

A division unitdivides a brain included in a first brain image into a plurality of regions by performing registration between the first brain image including a brain of a subject and a standard brain image divided into a plurality of regions. A registration unitperforms registration between the first brain image and a second brain image that includes the brain of the subject and has a different imaging date and time from the first brain image. A change amount acquisition unitacquires the amount of change from a corresponding region in the brain included in the first brain image, for at least one region of the plurality of regions in the brain included in the second brain image, based on the registration result.

Image processing for calculation of amount of change of brain

A medical image processing apparatus, having a processor configured to divide brains included in a brain image and a standard brain image into a plurality of regions corresponding to each other, calculate a first correction amount between the pixel value of a first reference pixel included in each of the plurality of region in the brain image and the pixel value of a second reference pixel and a second correction amount for matching first other pixel values other than the first reference pixel included in each of the plurality of regions in the brain image with pixel values of second other pixels, and correct the brain image based on the first correction amount and the second correction amount.

In a medical image processing apparatus, a medical image processing method, and a medical image processing program, in a case where there are a plurality of past brain images, it is possible to select a past brain image with which the atrophy rate of the brain can be accurately calculated. An image acquisition unit acquires a target brain image Bt as a diagnostic target and a plurality of past brain images Bpi, which have earlier imaging dates and times than the target brain image Bt, for the same subject. A similarity calculation unit calculates the similarity between each of the plurality of past brain images Bpi and a standard brain image Bs. A selection unit selects a reference brain image Bserving as a reference for calculating the amount of change of the brain from the plurality of past brain images Bpi.

An image obtaining unit obtains actual endoscope images, and a virtual endoscope image generating unit generates virtual endoscope images including a plurality of virtual endoscope branch images. A corresponding virtual endoscope image determining unit obtains a plurality of actual endoscope images which were obtained within a predetermined amount of time before the endoscope reached its current position, compares the plurality of actual endoscope images and the plurality of virtual endoscope branch images, and determines a corresponding virtual endoscope image that corresponds to the branch structure closest to the current position of the endoscope, through which the endoscope has passed. A matching unit performs matching between each of a plurality of actual endoscope path images and a plurality of virtual endoscope path images for each of a plurality of paths. A position identifying unit identifies the current position of a leading end of the endoscope based on the results of matching.

Endoscope position identifying apparatus, endoscope position identifying method, and recording medium having an endoscope position identifying program recorded therein

A three-dimensional common coordinate system is defined and a first correspondence relationship between each pixel of a first three-dimensional image which has at least a portion of a human body as a subject and coordinates on the common coordinate system is set. A second three-dimensional image which has at least a portion of the human body as a subject that at least partially overlaps the subject in the first three-dimensional image is aligned with the first three-dimensional image to calculate a correspondence relationship between pixels of the first three-dimensional image and the second three-dimensional image. A second correspondence relationship between each pixel of the second three-dimensional image and coordinates on the common coordinate system is calculated on the basis of the calculated correspondence relationship and the set first correspondence relationship. The first correspondence relationship and the second correspondence relationship are stored.

Image processing device, method, and recording medium having an image processing program recorded therein

A first 3D image and a second 3D image imaged a target organ in different phases of respiration are acquired. A 3D deformation model of the target organ which is stored in advance and represents nonlinear 3D deformation of the target organ due to respiration, and which has been generated based on information about movement of the target organ due to respiration of plural patients, is read. The positions of pixels on the second 3D image representing the same positions on the target organ as plural sampled pixels in a target organ region on the first 3D image are estimated using displacement due to changes in phase of points on the 3D deformation model corresponding to the positions on the target organ represented by the pixels. Non-rigid alignment is performed between the first 3D image and the second 3D image using the estimated positions of the pixels.

Image alignment device, method, and program, and method for generating 3-D deformation model

A first image and a second image obtained by imaging the same subject with different types of modalities are obtained. The first image is deformed, and similarity between the deformed first image and the second image is evaluated by an evaluation function that evaluates correlation between distributions of corresponding pixel values of the two images to estimate an image deformation amount of the first image. Based on the estimated image deformation amount, a deformed image of the first image is generated. The evaluation function includes a term representing a measure of correlation between a pixel value of the deformed first image and a corresponding pixel value of the second image, wherein the term evaluates the correlation based on probability information that indicates a probability of each combination of corresponding pixel values of the first image and the second image.

Growing community of inventors

Tokyo, Japan

Caihua Wang