# US 2024/0005459 A1 · Program, image processing method, and image processing device

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

- Number: US 2024/0005459 A1
- Document ID: US20240005459A1
- Status: Published application
- Kind: A1
- Application number: 18/468,205
- Filed: 2023-09-15
- Published: 2024-01-04
- Earliest claimed: 2021-03-26
- Assignees: Terumo Kabushiki Kaisha
- Applicants: Terumo Kabushiki Kaisha
- Inventors: Yuki SAKAGUCHI; Kohtaroh KUSU
- Web page: https://patentgrep.com/patent/US20240005459A1

## CPC

- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 7/0012: {Biomedical image inspection}
- G06T 7/12: Edge-based segmentation
- G06T 7/62: of area, perimeter, diameter or volume
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/752: {Contour matching}
- G06V 10/764: using classification, e.g. of video objects
- A61B 6/487: {involving fluoroscopy}
- A61B 8/0891: {for diagnosis of blood vessels}
- A61B 8/12: in body cavities or body tracts, e.g. by using catheters
- A61B 8/14: Echotomography
- A61B 8/5261: {combining images from different diagnostic modalities, e.g. ultrasound and X-ray}
- G06T 2207/10016: Video; Image sequence
- G06T 2207/10072: Tomographic images
- G06T 2207/10101: Optical tomography; Optical coherence tomography [OCT]
- G06T 2207/10121: Fluoroscopy
- G06T 2207/10132: Ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- G06V 2201/03: Recognition of patterns in medical or anatomical images
- G06V 2201/031: of internal organs
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

A non-transitory computer-readable medium storing a computer program executed by a computer, a method, and an image processing device are disclosed that are capable of compensating a missing region in a tomographic image in a state in which a part of a lumen organ is missing. In accordance with the program, a computer acquires a plurality of tomographic images of a cross section of the lumen organ captured at a plurality of places using a catheter. In addition, the computer extracts, from the plurality of tomographic images, a tomographic image in which the part of the lumen organ is missing. Then, the computer compensates a missing region of the lumen organ for the extracted tomographic image.

## Claims

### Claim 1

A non-transitory computer-readable medium storing a program executed by a computer that executes a process comprising:
acquiring a plurality of tomographic images of a cross section of a lumen organ captured at a plurality of places using a catheter;
extracting, from the plurality of tomographic images, a tomographic image in which a part of the lumen organ is missing; and
compensating a missing region of the lumen organ for the extracted tomographic image.

### Claim 2 (depends on 1)

The computer-readable medium according to claim 1, further comprising:
inputting the plurality of acquired tomographic images to a learning model trained to output information indicating regions of a lumen and a lumen wall of a lumen organ in a tomographic image when the tomographic image is input and outputting a lumen and a lumen wall of a lumen organ in each of the tomographic images; and
extracting the tomographic image in which the part of the lumen organ is missing when a part of a contour line of the output lumen or lumen wall of the lumen organ matches a contour line of the tomographic image.

### Claim 3 (depends on 1)

The computer-readable medium according to claim 1, further comprising:
in the tomographic image in which the part of the lumen organ is missing, compensating a contour line of the missing region of the lumen organ based on a contour line of the lumen organ which is not missing.

### Claim 4 (depends on 1)

The computer-readable medium according to claim 1, further comprising:
compensating the missing region of the lumen organ in the missing tomographic image based on a tomographic image in which the lumen organ is not missing in tomographic images captured in a vicinity of the missing tomographic image.

### Claim 5 (depends on 1)

The computer-readable medium according to claim 1, further comprising:
inputting the extracted missing tomographic image to a second learning model trained to output the missing region of the lumen organ in the tomographic image when the tomographic image in which the part of the lumen organ is missing is input and outputting the missing region of the lumen organ in the missing tomographic image; and
compensating the missing region of the lumen organ in the missing tomographic image based on the output missing region of the lumen organ.

### Claim 6 (depends on 1)

The computer-readable medium according to claim 1, further comprising:
adding, to the tomographic image in which the part of the lumen organ is missing, a contour line of the compensated missing region of the lumen organ in a mode of indicating a compensated place.

### Claim 7 (depends on 2)

The computer-readable medium according to claim 2, wherein the lumen organ is a blood vessel, the lumen is an intravascular lumen, and the lumen wall is a vessel wall.

### Claim 8

An image processing method of executing processes by a computer, the image processing method comprising:
acquiring a plurality of tomographic images of a cross section of a lumen organ captured at a plurality of places using a catheter;
extracting, from the plurality of tomographic images, a tomographic image in which a part of the lumen organ is missing; and
compensating a missing region of the lumen organ for the extracted tomographic image.

### Claim 9 (depends on 8)

The method according to claim 8, further comprising:
inputting the plurality of acquired tomographic images to a learning model trained to output information indicating regions of a lumen and a lumen wall of a lumen organ in a tomographic image when the tomographic image is input and outputting a lumen and a lumen wall of a lumen organ in each of the tomographic images; and
extracting the tomographic image in which the part of the lumen organ is missing when a part of a contour line of the output lumen or lumen wall of the lumen organ matches a contour line of the tomographic image.

### Claim 10 (depends on 8)

The method according to claim 8, further comprising:
in the tomographic image in which the part of the lumen organ is missing, compensating a contour line of the missing region of the lumen organ based on a contour line of the lumen organ which is not missing.

### Claim 11 (depends on 8)

The method according to claim 8, further comprising:
compensating the missing region of the lumen organ in the missing tomographic image based on a tomographic image in which the lumen organ is not missing in tomographic images captured in a vicinity of the missing tomographic image.

### Claim 12 (depends on 8)

The method according to claim 8, further comprising:
inputting the extracted missing tomographic image to a second learning model trained to output the missing region of the lumen organ in the tomographic image when the tomographic image in which the part of the lumen organ is missing is input and outputting the missing region of the lumen organ in the missing tomographic image; and
compensating the missing region of the lumen organ in the missing tomographic image based on the output missing region of the lumen organ.

### Claim 13 (depends on 8)

The method according to claim 8, further comprising:
adding, to the tomographic image in which the part of the lumen organ is missing, a contour line of the compensated missing region of the lumen organ in a mode of indicating a compensated place.

### Claim 14 (depends on 9)

The method according to claim 9, wherein the lumen organ is a blood vessel, the lumen is an intravascular lumen, and the lumen wall is a vessel wall.

### Claim 15

An image processing device comprising:
a processor configured to:
acquire a plurality of tomographic images of a cross section of a lumen organ captured at a plurality of places using a catheter;
extract, from the plurality of tomographic images, a tomographic image in which a part of the lumen organ is missing; and
compensate a missing region of the lumen organ for the extracted tomographic image.

### Claim 16 (depends on 15)

The image processing device according to claim 15, wherein the processor is further configured to:
input the plurality of acquired tomographic images to a learning model trained to output information indicating regions of a lumen and a lumen wall of a lumen organ in a tomographic image when the tomographic image is input and outputting a lumen and a lumen wall of a lumen organ in each of the tomographic images; and
extract the tomographic image in which the part of the lumen organ is missing when a part of a contour line of the output lumen or lumen wall of the lumen organ matches a contour line of the tomographic image.

### Claim 17 (depends on 15)

The image processing device according to claim 15, wherein the processor is further configured to:
in the tomographic image in which the part of the lumen organ is missing, compensate a contour line of the missing region of the lumen organ based on a contour line of the lumen organ which is not missing.

### Claim 18 (depends on 15)

The image processing device according to claim 15, wherein the processor is further configured to:
compensate the missing region of the lumen organ in the missing tomographic image based on a tomographic image in which the lumen organ is not missing in tomographic images captured in a vicinity of the missing tomographic image.

### Claim 19 (depends on 15)

The image processing device according to claim 15, wherein the processor is further configured to:
input the extracted missing tomographic image to a second learning model trained to output the missing region of the lumen organ in the tomographic image when the tomographic image in which the part of the lumen organ is missing is input and outputting the missing region of the lumen organ in the missing tomographic image; and
compensate the missing region of the lumen organ in the missing tomographic image based on the output missing region of the lumen organ.

### Claim 20 (depends on 15)

The image processing device according to claim 15, wherein the processor is further configured to:
add, to the tomographic image in which the part of the lumen organ is missing, a contour line of the compensated missing region of the lumen organ in a mode of indicating a compensated place.
