Granted Patent B2

US 12,731,249 · App. 18/033,171 · Granted Sep 8, 2026

Inventors: Jong Woong Baek (Seoul, KR); Young Mok Cho (Seoul, KR)

Assignee: MEDIT CORP.

G06T7/0012A61B5/0062A61B5/0088G06T7/11G06T7/90G06T17/00G06T2207/30036G06T2210/41

Abstract

Claims (55)

1 . An image processing method comprising:

acquiring two-dimensional image data of visible light by scanning an object comprising a tooth;

generating a mask region in the two-dimensional image data upon determining caries of the tooth through two-dimensional image data by using artificial intelligence;

mapping caries expression values to the mask region of the two-dimensional image data;

generating a three-dimensional model of an oral cavity surface including at least one voxel from the two-dimensional image data in which the caries expression values are mapped, the three-dimensional model expressing color and shape of the object in a three-dimensional manner; and

displaying the caries expression values on the three-dimensional model,

wherein at least part of voxel among the at least one voxel constituting the three-dimensional model displays the caries expression values only in portions where the caries expression values are mapped in the two-dimensional image data.

2 . The image processing method of claim 1 , wherein generating the three-dimensional model of the oral cavity surface from the two-dimensional image data comprises:

dividing the two-dimensional image data into at least one large region;

determining caries for each large region; and

a step of generating the three-dimensional model from the two-dimensional image data in which the caries has been determined.

3 . The image processing method of claim 2 , wherein the large region is a superpixel comprising at least one small region.

4 . The image processing method of claim 2 , wherein dividing the two-dimensional image data into the at least one large region comprises:

generating multiple large regions by dividing the two-dimensional image data;

comparing characteristic values between the multiple large regions; and

adjusting a boundary between the large regions, based on the comparison of the characteristic values.

5 . The image processing method of claim 4 , wherein the characteristic values are color information acquired from the two-dimensional image data.

6 . The image processing method of claim 2 , wherein determining the caries for each large region comprises:

determining presence or absence of caries for each large region of the two-dimensional image data; and

wherein generating mask region in the two-dimensional image data upon determining caries of the tooth comprises:

generating a mask comprising the mask region, based on the determined presence or absence of caries.

7 . The image processing method of claim 6 , wherein the caries expression value is at least one of a predetermined color or a predetermined pattern.

8 . The image processing method of claim 6 , wherein the mask to which the caries expression value is mapped overlaps the two-dimensional image data.

9 . The image processing method of claim 8 , wherein the two-dimensional image data overlapped with the mask is generated as the three-dimensional model, and the caries expression value is displayed on the three-dimensional model.

10 . The image processing method of claim 2 , wherein determining the caries for each large region comprises:

determining a caries class for each large region of the two-dimensional image data according to preconfigured criteria;

wherein generating mask region in the two-dimensional image data upon determining caries of the tooth comprises:

generating a mask comprising the mask region, based on the determined caries class; and

wherein mapping caries expression values to the mask region of the two-dimensional image data comprises:

mapping a caries expression value corresponding to the caries class to the mask region.

11 . The image processing method of claim 10 , wherein the caries expression value has a different color or pattern for each caries class.

12 . An image processing apparatus comprising:

a scanner configured to acquire two-dimensional image data of visible light by scanning an object comprising a tooth;

a control unit configured to:

generate mask region in the two-dimensional image data upon determining caries of the tooth through two-dimensional image data by using artificial intelligence;

map caries expression values to the mask region of the two-dimensional image; and

generate a three-dimensional model of an oral cavity surface including at least one voxel from the two-dimensional image data in which the caries expression values are mapped, the three-dimensional model expressing color and shape of the object in a three-dimensional manner; and

a display unit configured to display the caries expression values on a three-dimensional model which expresses color and shape of the object in a three-dimensional manner, and is generated from the two-dimensional image data in which the caries expression values are mapped,

wherein at least part of voxel among the at least one voxel constituting the three- dimensional model displays the caries expression values only in portions where the caries expression values are mapped in the two-dimensional image data.

13 . The image processing apparatus of claim 12 , wherein the control unit is configured to:

divide the two-dimensional image data into at least one large region; and

determine caries for each large region.

14 . The image processing apparatus of claim 13 , wherein the large region is a superpixel comprising at least one small region.

15 . The image processing apparatus of claim 13 , wherein the control unit is configured to:

(1) generate multiple large regions by dividing the two-dimensional image data;

(2) compare characteristic values of the multiple large regions; and

(3) adjust a boundary between the large regions, based on the comparison of the characteristic values.

16 . The image processing apparatus of claim 15 , wherein the characteristic values are color information acquired from the two-dimensional image data.

17 . The image processing apparatus of claim 13 , wherein the control unit is configured to determine presence or absence of caries for each large region of the two-dimensional image data.

18 . The image processing apparatus of claim 13 , wherein the control unit is configured to determine a caries class for each large region of the two-dimensional image data.

19 . The image processing apparatus of claim 13 , wherein the control unit further is configured to:

generate a mask comprising the mask region as a result of determining presence or absence of caries or a caries class for each large region, and

map a caries expression value corresponding to the presence or absence of caries or the caries class to the mask region so that the mask overlaps the two-dimensional image data.

20 . The image processing apparatus of claim 19 , wherein the control unit further comprises a three-dimensional model generation unit configured to generate the two-dimensional image data, which is overlapped by the mask, as the three-dimensional model, and

wherein the display unit is configured to display the three-dimensional model and the caries expression value overlapping the three-dimensional model together.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (37)