# US 2019/0378270 A1 · Medical image diagnostic apparatus

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

- Number: US 2019/0378270 A1
- Document ID: US20190378270A1
- Status: Published application
- Kind: A1
- Application number: 16/431,240
- Filed: 2019-06-04
- Published: 2019-12-12
- Earliest claimed: 2018-06-07
- Assignees: Canon Medical Systems Corporation
- Applicants: Canon Medical Systems Corporation
- Inventors: Takashi IDA; Kenzo ISOGAWA
- Web page: https://patentgrep.com/patent/US20190378270A1

## 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)}
- G06T 7/0012: {Biomedical image inspection}
- A61B 5/055: involving electronic [EMR] or nuclear [NMR] magnetic resonance, e.g. magnetic resonance imaging
- A61B 5/704: {Tables}
- G01R 33/4818: {MR characterised by data acquisition along a specific k-space trajectory or by the temporal order of k-space coverage, e.g. centric or segmented coverage of k-space}
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 5/70: Denoising; Smoothing
- G01R 33/565: Correction of image distortions, e.g. due to magnetic field inhomogeneities
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/20084: Artificial neural networks [ANN]
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

According to one embodiment, a medical image diagnostic apparatus includes processing circuitry. The processing circuitry inputs a noise correlation map and a medical image or an intermediate image to a learned model that is functioned to generate a denoise image, in which noise of the medical image or noise of the intermediate image is reduced, based on the medical image generated based on data collected with respect to a subject or the intermediate image at a front stage for generating the medical image and the noise correlation map correlated with the noise included in the medical image or the intermediate image, and generates the denoise image, in which the noise of the medical image or the noise of the intermediate image is reduced.

## Claims

### Claim 1

A medical image diagnostic apparatus comprising processing circuitry that
inputs a noise correlation map and a medical image or an intermediate image to a learned model, wherein the learned model is functioned to generate a denoise image, in which noise of the medical image or noise of the intermediate image is reduced, based on the medical image generated based on data collected with respect to a subject or the intermediate image at a front stage for generating the medical image and the noise correlation map correlated with the noise included in the medical image or the intermediate image, and
generates the denoise image, in which the noise of the medical image or the noise of the intermediate image is reduced.

### Claim 2 (depends on 1)

The medical image diagnostic apparatus according to claim 1, wherein
the data is magnetic resonance data,
the medical image is a magnetic resonance image,
the intermediate image is a complex number image, and
the noise correlation map corresponds to a map generated by using at least one of a sensitivity map that indicates spatial sensitivity of an RF coil related to collecting the magnetic resonance data, a g map that indicates distribution of a g-factor calculated based on the magnetic resonance data, a static magnetic field inhomogeneity map showing inhomogeneity of a static magnetic field, a gradient magnetic field inhomogeneity map showing inhomogeneity of a gradient magnetic field, and a density map that corresponds to density of data in a k-space, or at least two among the sensitivity map, the g map, the static magnetic field inhomogeneity map, the gradient magnetic field inhomogeneity map, and the density map.

### Claim 3 (depends on 1)

The medical image diagnostic apparatus according to claim 1, wherein
the data is projection data,
the medical image is an X-ray computed tomography imaging image,
the intermediate image is a sinogram based on the projection data, and
the noise correlation map is a transmission length map that indicates a transmission length of the subject along a ray of X-rays passing through the subject for each view in the medical image, or is a transmission length reconstruction image that is reconstructed by using the transmission length map.

### Claim 4 (depends on 1)

The medical image diagnostic apparatus according to claim 1, wherein
the learned model is a neural network, and
the processing circuitry inputs the medical image or the intermediate image and the noise correlation map to different channels of an input layer in the neural network.

### Claim 5 (depends on 1)

The medical image diagnostic apparatus according to claim 1, wherein
the learned model is a neural network, and
the processing circuitry
inputs the medical image or the intermediate image to an input layer in the neural network, and
inputs the noise correlation map to at least one of a plurality of intermediate layers in the neural network.

### Claim 6 (depends on 1)

The medical image diagnostic apparatus according to claim 1, wherein the processing circuitry
inputs the medical image or the intermediate image to a second learned model that is functioned to generate the noise correlation map based on the medical image or the intermediate image, and
generates the noise correlation map.
