Hitachi, Ltd.

Fujifilm Healthcare Corporation

Yoshihisa Sotome

Hisaaki Ochi

Yo Taniguchi

Toru Shirai

Ryota Satoh

Yoshitaka Bito

Suguru Yokosawa

Tomoki Amemiya

Masahiro Takizawa

Yukio Kaneko

Masahiro Ogino

Yasuhiro Kamada

Takenori Murase

Zisheng Li

In an image acquired by a plurality of receiver coils with the use of MRI, separated images are obtained by separating spatially overlapping signals according to PI method, and noise in the separated images is eliminated with a high degree of precision. A complex image spatially overlapping is measured from nuclear magnetic resonance signals received by a plurality of receiver coils, and spatially overlapping signals are separated and a plurality of separated images are calculated, by using sensitivity information of the plurality of receiver coils. Then, noise is eliminated based on a correlation of noise mixed between the separated images.

Magnetic resonance imaging apparatus and noise elimination method

An image diagnostic device that obtains a prediction model indicating a higher accuracy diagnosis prediction result includes: an observation unit that collects an image of an examination object; and an image processing unit that generates first image data from the image, and performs image processing of the first image data. The image processing unit is provided with: a feature extraction unit that extracts a first feature from the first image data; a feature transformation unit that converts the first feature to a second feature to be extracted from second image data; and an identification unit that calculates a prescribed parameter value using the converted second feature. The feature extraction unit includes a prediction model learned using a plurality of combinations of the first image data and feature, and the feature transformation unit includes a feature transformation model learned using a plurality of combinations of the first and second features.

Image diagnostic device, image processing method, and program for obtaining diagnostic prediction models using deep learning

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. At this time, a plurality of division regions are set in the physical property dependent image, and the combination parameter satisfying a condition that a difference between a pixel value of the specific tissue and a pixel value of a tissue other than the specific tissue increases is determined at each of the division regions in the actually measured two or more kinds of physical property dependent images, using standard data of the two or more kinds of physical property dependent images, and the combination parameter is used to combine the two or more kinds of images.

Magnetic resonance imaging apparatus and magnetic resonance image processing method

Accuracy degradation due to a signal loss is reduced, and susceptibility is calculated with high accuracy where, by using an MRI, at least one echo is acquired where spatial magnetic field inhomogeneity is reflected, and a complex image is calculated from the acquired echo. Three masks are calculated from the calculated complex image; a low-signal region mask representing a low signal region, a first high-signal region mask representing a high signal and high fat content region, and a second high-signal region mask representing a high signal and low fat content region. In calculating a susceptibility image from a frequency image or a magnetic field image generated from the complex image, the susceptibility image is obtained under the constraint that a region defined by the low-signal region is set as a background and the susceptibility of the region defined by the second high-signal region mask is set to a specific value.

Magnetic resonance imaging device, magnetic resonance imaging method and susceptibility calculation program

A plurality of subject parameter maps are acquired at high speed. In addition to using an imaging sequence for generating both a gradient echo and a spin echo in a single imaging sequence, one or more parameters such as the longitudinal relaxation time T1 and the apparent transverse relaxation time T2* are calculated using the gradient echo and another parameter such as true transverse relaxation time T2 is calculated using the spin echo. When a value of one parameter is calculated, a value of the parameter calculated at the time of calculating the other parameter can be used.

Magnetic resonance imaging apparatus and calculation image generation method using pulse sequence

Provided is a technique for calculating an oxygen extraction fraction by using MRI where the oxygen extraction fraction in a brain including brain parenchyma is calculated via a simple processing without an impact on an examinee, such as administration of caffeine. For this purpose, an MRI apparatus of the present invention measures a complex image of nuclear magnetic resonance signals, and calculates from thus measured complex image, a physical property distribution for obtaining a physical property image reflecting the oxygen extraction fraction. Then, thus calculated physical property distribution is separated into tissue-specific physical property distributions for at least two tissues (separated tissue images). After converting any of the separated tissue images into the oxygen extraction fraction, a distribution of the oxygen extraction fraction is estimated based on the condition that a value of any selected pixel is substantially equal to a mean value of pixels surrounding the selected pixel.

Growing community of inventors

Tokyo, Japan

Yoshihisa Sotome