Granted Patent B2

US 12,383,217 · App. 18/144,417 · Granted Aug 12, 2025

Inventors: Min-Yeong Kang (Seoul, KR); Young Eon Kim (Seoul, KR)

Assignee: Medipixel, Inc.

A61B6/504A61B6/481G06T7/0012G06T2207/30101

Abstract

Claims (44)

1. A method performed by a computing device, the method comprising:

receiving a medical image associated with a blood vessel injected with a contrast agent, wherein the medical image comprises a plurality of frame images;

calculating an intensity for each of the plurality of frame images of the medical image;

approximating the calculated intensity for each of the plurality of frame images with a continuous function;

calculating a local maximum value of the continuous function;

determining, based on a distribution of a plurality of intensities corresponding to the plurality of frame images, a frame section corresponding to a plurality of consecutive frame images of the plurality of frame images; and

selecting, based on the determined frame section, a frame image from among the plurality of consecutive frame images,

wherein the determining the frame section comprises:

selecting, from among the plurality of frame images of the medical image, a plurality of consecutive frame images having intensities within a predefined threshold range, wherein the predefined threshold range is defined based on the calculated local maximum value; and

determining, as the frame section, a frame section corresponding to the selected plurality of consecutive frame images.

2. The method according to claim 1 , wherein the calculating the intensity for each of the plurality of frame images of the medical image comprises:

masking, using a machine learning model, a region determined to be the blood vessel in a first frame image of the plurality of frame images of the medical image; and

calculating, based on the masked region, the intensity for the first frame image of the plurality of frame images of the medical image.

3. The method according to claim 1 , wherein the calculating the intensity for each of the plurality of frame images of the medical image comprises:

calculating a reliability value for determining each of a plurality of pixels in each of the plurality of frame images of the medical image to be a blood vessel region; and

calculating, based on the calculated reliability value, the intensity for each of the plurality of frame images of the medical image.

4. The method according to claim 1 , wherein the determining the frame section further comprise:

as a criterion for determining the frame section, determining, based on a plurality of detected frame sections, a detected frame section having a largest local maximum value.

5. The method according to claim 4 , wherein the largest local maximum value corresponds to a largest value among of a plurality of local maximum values of the continuous function.

6. The method according to claim 1 , wherein the determining the frame section further comprises:

based on a plurality of detected frame sections, determining, as the frame section, a detected frame section having a largest number of frame images, or a detected frame section having one of a largest maximum intensity value, a largest minimum intensity value, or a largest average intensity for frame images.

7. The method according to claim 1 , wherein the selecting the frame image comprises selecting, as the frame image, a frame image having a highest intensity in the frame section or a last frame image in the frame section.

8. The method according to claim 1 , further comprising:

receiving electrocardiogram data measured when the medical image is captured,

wherein the selecting the frame image comprises

selecting a frame image corresponding to an end of diastole in the frame section using the electrocardiogram data.

9. The method according to claim 1 , wherein the selected frame image comprises:

a first region corresponding to the blood vessel; and

a second region distinguishable from the first region.

10. An information processing system, comprising:

one or more processors; and

a memory storing instructions that, when executed by the one or more processors, cause the information processing system to:

receive a medical image associated with a blood vessel injected with a contrast agent, wherein the medical image comprises a plurality of frame images;

calculate an intensity for each of the plurality of frame images of the medical image;

approximate the calculated intensity for each of the plurality of frame images with a continuous function;

calculate a local maximum value of the continuous function;

determine, based on a distribution of a plurality of intensities corresponding to the plurality of frame images, a frame section corresponding to a plurality of consecutive frame images of the plurality of frame images; and

select, based on the determined frame section, a frame image from among the plurality of consecutive frame images,

wherein the determining the frame section comprises:

selecting, from among the plurality of frame images of the medical image, a plurality of consecutive frame images having intensities within a predefined threshold range, wherein the predefined threshold range is defined based on the calculated local maximum value; and

determining, as the frame section, a frame section corresponding to the selected plurality of consecutive frame images.

11. The information processing system according to claim 10 , wherein the instructions, when executed by the one or more processors, cause the information processing system to determine the frame section by:

as a criterion for determining the frame section, determining, based on a plurality of detected frame sections, a detected frame section having a largest local maximum value.

12. The information processing system according to claim 11 , wherein the largest local maximum value corresponds to a largest value among of a plurality of local maximum values of the continuous function.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (11)