Granted Patent B2

US 12,333,718 · App. 17/955,810 · Granted Jun 17, 2025

Inventors: Yuki Sakaguchi (Isehara, JP); Yusuke Seki (Tokyo, JP); Akira Iguchi (Mishima, JP)

Assignee: TERUMO KABUSHIKI KAISHA

G06T7/0012G06T7/62G06T2207/10101G06T2207/10132G06T2207/20081G06T2207/30101

Abstract

Claims (41)

1. A non-transitory computer-readable storage medium storing a computer program which, when executed by a computer of a diagnostic imaging apparatus, causes the computer to perform processing of:

acquiring a plurality of medical images generated based on signals detected by a catheter inserted into a lumen organ while the catheter is moving a sensor along a longitudinal direction of the lumen organ, the lumen organ including a main trunk, a side branch branched from the main trunk, and a bifurcated portion of the main trunk and the side branch; and

recognizing, in units of pixels in the plurality of medical images, a main trunk cross-section region, a side branch cross-section region, and a bifurcated portion cross-section region by inputting the acquired medical images into a learning model configured to recognize the main trunk cross-section region, the side branch cross-section region, and the bifurcated portion cross-section region in units of pixels in the plurality of medical images.

2. The non-transitory computer-readable storage medium according to claim 1 , wherein the processing further comprises:

recognizing at least the main trunk cross-section region or the side branch cross-section region by inputting an acquired first medical image into the learning model;

recognizing the bifurcated portion cross-section region by inputting an acquired second medical image into the learning model; and

discriminating between a main trunk portion and a side branch portion constituting the bifurcated portion cross-section region based on a recognition result based on the first medical image.

3. The non-transitory computer-readable storage medium according to claim 2 , wherein the processing further comprises:

specifying a bifurcating structure of the main trunk and the side branch based on a recognition result based on a plurality of first medical images; and

specifying the main trunk portion and the side branch portion included in the bifurcated portion cross-section region based on the specified bifurcating structure.

4. The non-transitory computer-readable storage medium according to claim 3 ,

wherein the learning model is configured to recognize a plaque formed in the bifurcated portion, and

the processing further comprises:

recognizing the bifurcated portion cross-section region and the plaque by inputting the acquired second medical image into the learning model; and

specifying a plaque portion included in the bifurcated portion cross-section region based on the bifurcating structure.

5. The non-transitory computer-readable storage medium according to claim 2 , wherein the processing further comprises:

specifying the bifurcating structure of the main trunk and the side branch based on the recognition result based on the plurality of first medical images, and calculating a cross-sectional diameter, a cross-sectional area, or a volume per unit length of the side branch.

6. The non-transitory computer-readable storage medium according to claim 2 , wherein the processing further comprises:

specifying the bifurcating structure of the main trunk and the side branch based on the recognition result based on the plurality of first medical images, and generating model images of the main trunk and the side branch.

7. The non-transitory computer-readable storage medium according to claim 1 , wherein the processing further comprises:

superimposing an image showing the main trunk portion or the side branch portion on a medical image including the bifurcated portion cross-section region.

8. The non-transitory computer-readable storage medium according to claim 1 ,

wherein the lumen organ is a blood vessel, and

the processing further comprises:

acquiring a medical image of the blood vessel generated based on signals detected by the catheter.

9. An information processing device comprising:

an acquisition unit configured to acquire a plurality of medical images generated based on signals detected by a catheter inserted into a lumen organ while the catheter is moving a sensor along a longitudinal direction of the lumen organ, the lumen organ including a main trunk, a side branch branched from the main trunk, and a bifurcated portion of the main trunk and the side branch; and

a learning model configured to recognize, when the acquired medical images are input, a main trunk cross-section region, a side branch cross-section region, and a bifurcated portion cross-section region in units of pixels in the plurality of medical images, and output information indicating the main trunk cross-section region, the side branch cross-section region, and the bifurcated portion cross-section region in units of pixels in the plurality of medical images.

10. The information processing device according to claim 9 , wherein the learning model is further configured to:

recognize at least the main trunk cross-section region or the side branch cross-section region based on an acquired first medical image;

recognize the bifurcated portion cross-section region based on an acquired second medical image; and

discriminate between a main trunk portion and a side branch portion constituting the bifurcated portion cross-section region based on a recognition result based on the first medical image.

11. The information processing device according to claim 10 , wherein the learning model is further configured to:

specify a bifurcating structure of the main trunk and the side branch based on a recognition result based on a plurality of first medical images; and

specify the main trunk portion and the side branch portion included in the bifurcated portion cross-section region based on the specified bifurcating structure.

12. The non-transitory computer-readable storage medium according to claim 11 , wherein the learning model is further configured to:

recognize the bifurcated portion cross-section region and a plaque formed in the bifurcated portion based on the acquired second medical image; and

specify a plaque portion included in the bifurcated portion cross-section region based on the bifurcating structure.

13. A method for generating a model, the method comprising performing the following processing in a computer:

generating training data in which data indicating a lumen cross-section is attached to a plurality of medical images each including a main trunk cross-section region, a plurality of medical images each including the main trunk cross-section region and a side branch cross-section region, and a plurality of medical images each including a bifurcated portion cross-section region that are generated based on signals detected by a catheter inserted into a lumen organ while the catheter is moving a sensor along a longitudinal direction of the lumen organ, the lumen organ including a main trunk, a side branch branched from the main trunk, and a bifurcated portion of the main trunk and the side branch; and

generating, based on the generated training data, a learning model configured to recognize, in units of pixels in the plurality of medical images, the main trunk cross-section region, the side branch cross-section region, and the bifurcated portion cross-section region when the medical images are input.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (30)