# US 2026/0309822 A1 · Magnetic resonance imaging apparatus, image processing apparatus, image processing method, and program

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0309822 A1
- Document ID: US20260309822A1
- Status: Published application
- Kind: A1
- Application number: 19/460,041
- Filed: 2026-01-26
- Published: 2026-10-08
- Earliest claimed: 2025-01-28
- Assignees: FUJIFILM Corporation
- Applicants: FUJIFILM Corporation
- Inventors: Atsuro SUZUKI; Toru SHIRAI; Suguru YOKOSAWA; Hiroki SHOJI; Yuya HIRAKAWA
- Web page: https://patentgrep.com/patent/US20260309822A1

## CPC

- G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)}
- G01R 33/482: {using a Cartesian trajectory}
- G01R 33/561: by reduction of the scanning time, i.e. fast acquiring systems, e.g. using echo-planar pulse sequences
- G01R 33/56545: {caused by finite or discrete sampling, e.g. Gibbs ringing, truncation artefacts, phase aliasing artefacts}
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)

## Abstract

Provided are a magnetic resonance imaging apparatus, an image processing apparatus, an image processing method, and a program that can suppress the occurrence of striped noise in an image reconstructed based on partial k-space data acquired within an asymmetrical measurement region of the k-space and generate a high-quality image. A magnetic resonance imaging apparatus estimates data of a k-space by applying a half-Fourier method or a POCS method to partial measurement data of an asymmetrical measurement region of the k-space, acquires a corrected image in which the data of the k-space is reconstructed, acquires a smoothing-corrected image obtained by performing smoothing filter processing on the corrected image, replaces data of the unmeasured region of the smoothing-corrected image with zero data, and estimates the data of the unmeasured region using a first trained model.

## Claims

### Claim 1

A magnetic resonance imaging apparatus comprising:
a processor that converts data acquired by imaging a subject into an image,
wherein the processor
acquires partial measurement data of an asymmetrical measurement region of a k-space,
estimates data of an unmeasured region other than the measurement region of the k-space by applying a half-Fourier method or a projection onto convex sets (POCS) method to the partial measurement data,
acquires a corrected image in which data of the k-space including the partial measurement data of the measurement region and the estimated data of the unmeasured region is reconstructed,
acquires a smoothing-corrected image obtained by performing smoothing filter processing on the corrected image,
acquires smoothing-corrected data of the k-space obtained by performing a Fourier transform on the smoothing-corrected image,
replaces the data of the unmeasured region in the smoothing-corrected data of the k-space with zero data,
acquires a smoothed image in which the data of the k-space including the smoothing-corrected data of the measurement region and the zero data of the unmeasured region is reconstructed, and
estimates an output image by inputting the smoothed image to a first trained model that has been trained to receive an input of an input reconstruction image in which the data of the k-space including data of the measurement region is reconstructed and output an estimated reconstruction image in which the data of the unmeasured region is estimated.

### Claim 2 (depends on 1)

The magnetic resonance imaging apparatus according to claim 1,
wherein the processor uses, for the smoothing filter processing, a second trained model that has been trained to receive an input of a noise image having noise and output a noise-reduced image in which the noise is reduced.

### Claim 3 (depends on 2)

The magnetic resonance imaging apparatus according to claim 2,
wherein the second trained model has been trained using a ground-truth image having relatively less noise as ground-truth data and an image in which the noise is added to the ground-truth image as training data.

### Claim 4 (depends on 1)

The magnetic resonance imaging apparatus according to claim 1,
wherein the processor acquires the partial measurement data by performing a Fourier transform on a reconstruction image having striped noise.

### Claim 5 (depends on 1)

The magnetic resonance imaging apparatus according to claim 1,
wherein the first trained model is a trained model that has been trained through machine learning to receive an input of an input image in which the data of the k-space consisting of the measurement region filled with input measurement region data and the unmeasured region filled with zero data is reconstructed, and estimate and output the estimated reconstruction image of the real space reconstructed from the data of the k-space consisting of the measurement region filled with estimated measurement region data and the unmeasured region filled with estimated unmeasured region data.

### Claim 6 (depends on 1)

The magnetic resonance imaging apparatus according to claim 1,
wherein the first trained model is a trained model that has been trained through machine learning to receive an input of an input image in which the data of the k-space consisting of the measurement region filled with input measurement region data and the unmeasured region filled with zero data is reconstructed, and estimate and output an estimated residual image indicating a residual between the input image and the estimated reconstruction image of the real space reconstructed from the data of the k-space consisting of the measurement region filled with estimated measurement region data and the unmeasured region filled with estimated unmeasured region data.

### Claim 7 (depends on 1)

The magnetic resonance imaging apparatus according to claim 1,
wherein the processor
acquires first measurement region data of the measurement region of the k-space obtained by performing a Fourier transform on the output image,
generates an edge-enhanced image obtained by performing edge enhancement filter processing on the output image,
acquires first unmeasured region data of the unmeasured region of the k-space obtained by performing a Fourier transform on the edge-enhanced image, and
generates a resolution-improved image by reconstructing the data of the k-space including the first measurement region data and the first unmeasured region data.

### Claim 8 (depends on 7)

The magnetic resonance imaging apparatus according to claim 7,
wherein the processor
acquires a first adjacent region data corresponding to an adjacent region that is adjacent to the measurement region and extends a predetermined distance from the measurement region in second unmeasured region data of the unmeasured region of the k-space obtained by performing a Fourier transform on the output image,
acquires second adjacent region data corresponding to the adjacent region in the first unmeasured region data,
generates third adjacent region data from the first adjacent region data of which a weight is gradually decreased as a distance from the measurement region increases and the second adjacent region data of which a weight is gradually increased as the distance from the measurement region increases, and
generates the resolution-improved image by reconstructing the data of the k-space including the first measurement region data, the third adjacent region data, and the first unmeasured region data other than the adjacent region.

### Claim 9

An image processing method executed by a processor that converts data acquired by imaging a subject into an image, the image processing method comprising:
acquiring partial measurement data of an asymmetrical measurement region of a k-space;
estimating data of an unmeasured region other than the measurement region of the k-space by applying a half-Fourier method or a projection onto convex sets (POCS) method to the partial measurement data;
acquiring a corrected image in which data of the k-space including the partial measurement data of the measurement region and the estimated data of the unmeasured region is reconstructed;
acquiring a smoothing-corrected image obtained by performing smoothing filter processing on the corrected image;
acquiring smoothing-corrected data of the k-space obtained by performing a Fourier transform on the smoothing-corrected image;
replacing the data of the unmeasured region in the smoothing-corrected data of the k-space with zero data;
acquiring a smoothed image in which the data of the k-space including the smoothing-corrected data of the measurement region and the zero data of the unmeasured region is reconstructed; and
estimating an output image by inputting the smoothed image to a first trained model that has been trained to receive an input of an input reconstruction image in which the data of the k-space including data of the measurement region is reconstructed and output an estimated reconstruction image in which the data of the unmeasured region is estimated.

### Claim 10 (depends on 9)

A non-transitory, computer-readable tangible recording medium on which a program for causing a computer to execute the image processing method according to claim 9 is recorded.
