# US 2023/0058183 A1 · Medical image processing apparatus and medical image processing method

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

- Number: US 2023/0058183 A1
- Document ID: US20230058183A1
- Status: Published application
- Kind: A1
- Application number: 17/814,904
- Filed: 2022-07-26
- Published: 2023-02-23
- Earliest claimed: 2021-08-17
- Assignees: Canon Medical Systems Corporation
- Applicants: Canon Medical Systems Corporation
- Inventors: Yanhua WANG; Bing LI; Qilin XIAO; Fuyue WANG; Gengwan LI; Lixin YAN; Longfei ZHAO
- Web page: https://patentgrep.com/patent/US20230058183A1

## CPC

- G06T 7/0012: {Biomedical image inspection}
- G06T 7/11: Region-based segmentation
- G06T 11/00: Two-dimensional [2D] image generation
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10088: Magnetic resonance imaging [MRI]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/20156: Automatic seed setting
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- G06T 2207/30172: Centreline of tubular or elongated structure
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A medical image processing apparatus according to an embodiment includes processing circuitry configured: to generate a projection image by implementing an intensity projection on a plurality of two-dimensional images structuring three-dimensional volume data rendering a tubular organ; to obtain a mapping matrix of the intensity projection; to annotate the tubular organ in the projection image; and to identify the tubular organ in the three-dimensional volume data, by inversely mapping the tubular organ annotated in the projection image onto the three-dimensional volume data while using the mapping matrix.

## Claims

### Claim 1

A medical image processing apparatus comprising processing circuitry configured:
to generate a projection image by implementing an intensity projection on a plurality of two-dimensional images structuring three-dimensional volume data rendering a tubular organ;
to obtain a mapping matrix of the intensity projection;
to annotate the tubular organ in the projection image; and
to identify the tubular organ in the three-dimensional volume data, by inversely mapping the tubular organ annotated in the projection image onto the three-dimensional volume data while using the mapping matrix.

### Claim 2 (depends on 1)

The medical image processing apparatus according to claim 1, wherein the processing circuitry generates a three-dimensional tubular organ image, by inversely mapping the tubular organ annotated in the projection image onto the three-dimensional volume data while using the mapping matrix.

### Claim 3 (depends on 1)

The medical image processing apparatus according to claim 1, wherein
the mapping matrix indicates, with respect to each of pixels in the projection image, a correspondence relationship as to which one of the plurality of two-dimensional images corresponds to the pixel,
on the basis of the correspondence relationship, the processing circuitry identifies a two-dimensional image corresponding to each of pixels of the tubular organ annotated in the projection image in accordance with a pixel position of the pixel, and
the processing circuitry generates a three-dimensional tubular organ image, by using the pixel positions and image number information indicating an ordinal number of a sequential position of each of the identified two-dimensional images among the plurality of two-dimensional images.

### Claim 4 (depends on 1)

The medical image processing apparatus according to claim 1, wherein
the processing circuitry annotates a key point on a centerline of the tubular organ, and
the processing circuitry generates a key point on a centerline of the tubular organ that is three-dimensional.

### Claim 5 (depends on 4)

The medical image processing apparatus according to claim 4, wherein
the processing circuitry further performs a fitting process on the centerline of the three-dimensional tubular organ, on a basis of the key point on the centerline of the three-dimensional tubular organ, and
the processing circuitry annotates a three-dimensional tubular organ image on a basis of the centerline of the fitted three-dimensional tubular organ.

### Claim 6 (depends on 1)

The medical image processing apparatus according to claim 1, wherein
the processing circuitry obtains two or more of the projection images, by implementing a local intensity projection on each set of two-dimensional images including the plurality of two-dimensional images,
the processing circuitry obtains the mapping matrix with respect to each of the sets,
the processing circuitry annotates the tubular organ in each of the projection images, and
the processing circuitry identifies the tubular organ in the three-dimensional volume data, by inversely mapping the tubular organ onto the three-dimensional volume data while using the mapping matrix corresponding to each of the sets.

### Claim 7 (depends on 1)

The medical image processing apparatus according to claim 1, wherein
the processing circuitry generates the projection image corresponding to each of a plurality of directions, by implementing the intensity projection on each of the two-dimensional images structuring the three-dimensional volume data and corresponding to the plurality of directions,
the processing circuitry obtains the mapping matrix corresponding to each of the plurality of directions,
the processing circuitry annotates the tubular organ in each of the projection images corresponding to the plurality of directions, and
the processing circuitry identifies the tubular organ in the three-dimensional volume data, by inversely mapping the tubular organ corresponding to the plurality of directions onto the three-dimensional volume data, while using the mapping matrix corresponding to each of the directions.

### Claim 8 (depends on 1)

The medical image processing apparatus according to claim 1, wherein a quantity of the two-dimensional images to be used for generating the projection image is variable.

### Claim 9 (depends on 1)

The medical image processing apparatus according to claim 1, wherein the tubular organ is a blood vessel.

### Claim 10

A medical image processing apparatus comprising processing circuitry configured:
to generate a projection image by implementing an intensity projection on a plurality of two-dimensional images structuring three-dimensional volume data rendering a tubular organ;
to obtain a mapping matrix of the intensity projection;
to compare the projection image with a preliminary annotation result obtained by annotating the tubular organ in the three-dimensional volume data, so as to obtain a missing part of the tubular organ in the preliminary annotation result and to further annotate the missing part of the tubular organ in the projection image; and
to identify the missing part of the tubular organ in the three-dimensional volume data, by inversely mapping the missing part of the tubular organ annotated in the projection image onto the three-dimensional volume data while using the mapping matrix and further combining a result of the inverse mapping with the preliminary annotation result.

### Claim 11

A medical image processing method comprising:
a projection step of generating a projection image by implementing an intensity projection on a plurality of two-dimensional images structuring three-dimensional volume data rendering a tubular organ;
a mapping matrix obtaining step of obtaining a mapping matrix of the intensity projection implemented in the projection step;
an annotation step of annotating the tubular organ in the projection image; and
an inverse mapping step of identifying the tubular organ in the three-dimensional volume data, by inversely mapping the tubular organ annotated in the projection image onto the three-dimensional volume data while using the mapping matrix.
