Abstract: A technology is provided for stably synthesizing a blood vessel image while suppressing a decrease in brightness of a blood vessel in a case of synthesizing the blood vessel image. Optimization of an imaging parameter set for quantitative value map calculation is performed by adding at least one condition in which there is no decrease in brightness of a blood vessel in a region where no blood vessel is depicted in either an original image or a quantitative value image.

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.

Abstract: In an image noise reduction process using a CNN, noise can be reduced effectively irrespective of signal levels and noise levels of the image. Noise information and signal level information are calculated from an image inputted in the CNN. Using the calculated information, a normalization factor suitable for the CNN is determined, and normalization of the input image is performed. The noise information is estimated from magnitude of background noise of the input image in the case where the input image is an MRI image. The signal information can be calculated, for example, as a mean value of pixel values of a subject region with respect to an image obtained by dividing the input image by the magnitude of the background noise.

Abstract: Provided is a method for performing reconstruction and noise removal with high accuracy on various undersampling patterns including equidistant undersampling. An image processing unit that processes measurement data acquired by an MRI apparatus performs image reconstruction by using measurement data on respective channels measured in a predetermined undersampling pattern and sensitivity distributions of respective reception coils. At this time, denoising of a reconstructed image and a calculation for maintaining consistency between original measurement data and the measurement data on the respective channels created from denoised images are sequentially processed. Accordingly, image restoration and denoising with high accuracy are possible without depending on the undersampling pattern.

Abstract: The most appropriate image for a diagnostic target among a plurality of images is selected and accurate diagnosis support information is presented regardless of the type of a selected image, a modality, or the like. An image diagnosis support apparatus includes: a diagnostic information generation unit that generates diagnostic information based on a plurality of medical images; a reliability calculation unit that evaluates an image quality and calculates an image reliability for each of the plurality of medical images; and a degree-of-contribution calculation unit that calculates a degree of contribution of each of the plurality of medical images to the diagnostic information using an internal parameter indicating a degree of appropriateness of each medical image for a diagnostic target and the reliability calculated by the reliability calculation unit. An image for detection used by the diagnostic information generation unit is generated based on the degree of contribution.

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.

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.

Abstract: In brain analysis, anatomical standardization is performed when analyzing a region of interest (ROI). There are individual differences in the shape and size of the brain and by converting the brain into a standard brain, these differences can be compared with each other and subjected to statistical analysis. When generating a standard brain analysis, a large number of pieces of image data are classified into a plurality of groups based on their anatomical features. An intermediate template that is an intermediate conversion image and a conversion map is calculated for each group, and the calculation of the intermediate template and the generation of the intermediate conversion image are repeated while gradually reducing the number of classifications, so that a final standard image is generated. Using the standard image and the intermediate template calculated during the generation of the standard image, spatial standardization of the measured image is performed.

Abstract: In MRI, upon simultaneously generating computed images of multiple parameters, imaging time is efficiently reduced while preventing decrease in spatial resolution and SN ratio as much as possible. A plurality of original images is reconstructed from nuclear magnetic resonance signals acquired under various imaging conditions, and a computed image is obtained by calculation performed among the plurality of original images. The various imaging conditions include an imaging condition that a repetition time of an imaging sequence is different from one another, and upon imaging, the number of phase encoding steps is made smaller when the repetition time is long. An image is reconstructed in such a manner that a matrix size of the image obtained when the number of phase encoding steps is small is made equal to the matrix size of the image obtained when the number of phase encoding steps is large.

Abstract: Provided is a technique for supporting a diagnosis in determining disease by using various types of measured values acquired by a medical image acquisition apparatus. An image diagnosis support device includes a measured-value receiving unit configured to receive various types of measured values at a plurality of positions within a living body, a group generator configured to generate groups of the measured values depending on the position or the type of the measured value, an intermediate index calculator configured to calculate an intermediate index from the measured values included in the group on a per-group basis, and a comprehensive index calculator configured to calculate a comprehensive index from values of the intermediate index calculated on a per-group basis. The intermediate index and the comprehensive index are displayed on a display unit in a display mode such as numerical values and in the form of an image.

Abstract: Two or more learning images generated for a first subject or a second subject and one or more correct answer images generated for the second subject or a third subject are received. In a case where pixel values of corresponding pixels of the two or more learning images are synthesized by using a synthesis parameter value, the parameter value at which the synthesized pixel values are close to a pixel value of a corresponding pixel of the correct answer image is obtained. An image generated for the first subject and having the same type as the two or more learning images is received as an examination target image. A synthesized image desired by a user is generated by synthesizing pixel values of corresponding pixels of the two or more examination target images by using the synthesis parameter value.

Abstract: An MRI device for executing an imaging operation at least three times or more with a different combination of at least a repetition time and a flip angle in the same imaging sequence, includes: a receiving unit which receives information specifying an imaging target and a constraint condition relating to an imaging time or quantitative value accuracy; and a scan parameter set generation unit which calculates at least three or more scan parameter sets having a different combination of at least the repetition time and the flip angle on the basis of the constraint condition. The MRI device uses three or more scan parameter sets generated by the optimal scan parameter set generation unit and calculates quantitative values (T1, T2,and the like) of the imaging target from a plurality of images obtained by the imaging operation.

Abstract: An image including contrast is standardized and an area is divided, a measurement cross section that most matches a measurement cross section determined to be appropriate for measuring a predetermined index is determined based on a feature of a notable tissue in the divided area, and a measurement value serving as an index is calculated in the measurement cross section.

Abstract: A learning model learned to provide high image quality of a first image is generated. A first image and a second image are received from the same target, high image quality of the first image is provided by using the learned model, and a first high image quality image is obtained. By using the first high image quality image and the second image as inputs, a high image quality image of the second image having the image quality of the first high image quality image is generated while maintaining contrast of the second image.

Abstract: In MRI, upon simultaneously generating computed images of multiple parameters, imaging time is efficiently reduced while preventing decrease in spatial resolution and SN ratio as much as possible. A plurality of original images is reconstructed from nuclear magnetic resonance signals acquired under various imaging conditions, and a computed image is obtained by calculation performed among the plurality of original images. The various imaging conditions include an imaging condition that a repetition time of an imaging sequence is different from one another, and upon imaging, the number of phase encoding steps is made smaller when the repetition time is long. An image is reconstructed in such a manner that a matrix size of the image obtained when the number of phase encoding steps is small is made equal to the matrix size of the image obtained when the number of phase encoding steps is large.

Abstract: An MRI apparatus in which, when a quantitative value, which does not depend on imaging parameter values, is computed from a plurality of image data having different pixel values that are acquired by performing imaging the plurality of times with different imaging parameter values in the same pulse sequence, pixel values which are acquired from the imaging parameter values are predicted for each of a plurality of predetermined quantitative-value candidate group, and an initial value of the quantitative value is selected from the quantitative-value candidate groups with reference to the predicted pixel values. The optimal quantitative value is computed through a localized optimization technique using the selected initial value.

Abstract: A system is disclosed to simultaneously acquire a magnetic resonance angiography (MRA) image and a plurality of images in which the structure of a tissue other than a blood vessel can be ascertained without performing imaging for the MRA image, and to shorten a time of MR examination. Two or more kinds of physical property dependent images obtained from a nuclear magnetic resonance signal measured in accordance with a predetermined pulse sequence under a plurality of imaging conditions are combined using a predetermined combination function.

Abstract: To provide an MRI apparatus that acquires a plurality of contrast images including an FLAIR image in the shortest imaging time. An imaging controller of the MRI apparatus includes, as a prescribed pulse sequence, an IR (inversion recovery) sequence that includes application of an inversion pulse and a signal acquisition sequence to collect a signal after an inversion time has elapsed from the application of the inversion pulse, and acquires images in a first slice group, and an imaging sequence that is inserted into an inversion pulse of the IR sequence at a single time and an inversion pulse of the IR sequence at the next time, and acquires images in a second slice group different from the first slice group that are images having different contrasts from that of the IR sequence.

Abstract: To provide an MRI apparatus that acquires a plurality of contrast images including an FLAIR image in the shortest imaging time. An imaging controller of the MRI apparatus includes, as a prescribed pulse sequence, an IR (inversion recovery) sequence that includes application of an inversion pulse and a signal acquisition sequence to collect a signal after an inversion time has elapsed from the application of the inversion pulse, and acquires images in a first slice group, and an imaging sequence that is inserted into an inversion pulse of the IR sequence at a single time and an inversion pulse of the IR sequence at the next time, and acquires images in a second slice group different from the first slice group that are images having different contrasts from that of the IR sequence.

Abstract: The most appropriate image for a diagnostic target among a plurality of images is selected and accurate diagnosis support information is presented regardless of the type of a selected image, a modality, or the like. An image diagnosis support apparatus includes: a diagnostic information generation unit that generates diagnostic information based on a plurality of medical images; a reliability calculation unit that evaluates an image quality and calculates an image reliability for each of the plurality of medical images; and a degree-of-contribution calculation unit that calculates a degree of contribution of each of the plurality of medical images to the diagnostic information using an internal parameter indicating a degree of appropriateness of each medical image for a diagnostic target and the reliability calculated by the reliability calculation unit. An image for detection used by the diagnostic information generation unit is generated based on the degree of contribution.