阅读说明：本技术 牙齿图像匹配装置及方法 (Tooth image matching device and method ) 是由 金镇喆 金镇柏 于 2020-02-26 设计创作，主要内容包括：本发明提供一种牙齿图像匹配装置,包括：最大外廓检测部,检测在第一牙齿图像数据中作为牙列的最大外廓区域的第一最大外廓区域,以及检测在第二牙齿图像数据中作为牙列的最大外廓区域的第二最大外廓区域；及图像匹配部,以内切于第一最大外廓区域的第一内切圆及内切于第二最大外廓区域的第二内切圆为基础匹配第一及第二牙齿图像数据或者以第一最大外廓区域的第一中心点及第二最大外廓区域的第二中心点为基础匹配第一及第二牙齿图像数据。(The present invention provides a dental image matching apparatus, comprising: a maximum outline detection section that detects a first maximum outline region as a maximum outline region of the dentition in the first dental image data and detects a second maximum outline region as a maximum outline region of the dentition in the second dental image data; and an image matching section matching the first and second tooth image data based on a first inscribed circle inscribed in the first maximum outline region and a second inscribed circle inscribed in the second maximum outline region or matching the first and second tooth image data based on a first center point of the first maximum outline region and a second center point of the second maximum outline region.)

1. A dental image matching apparatus, comprising:

a maximum outline detection section that detects a first maximum outline region as a maximum outline region of the dentition in the first dental image data and detects a second maximum outline region as a maximum outline region of the dentition in the second dental image data; and

an image matching unit that matches the first and second tooth image data based on a first inscribed circle inscribed in the first maximum contour region and a second inscribed circle inscribed in the second maximum contour region or matches the first and second tooth image data based on a first center point of the first maximum contour region and a second center point of the second maximum contour region.

2. The dental image matching apparatus according to claim 1, further comprising:

an inscribed circle detection unit that detects a first inscribed circle inscribed in the first maximum outline region and detects a second inscribed circle inscribed in the second maximum outline region; and

an inscribed sphere detection unit that detects a first inscribed sphere that is a rotating body of the first inscribed circle and detects a second inscribed sphere that is a rotating body of the second inscribed circle;

wherein the image matching section matches the first and second tooth image data with the first and second inscribed spheres as a reference.

3. The dental image matching apparatus according to claim 1, further comprising:

a center point detecting unit configured to detect a first center point of the first maximum outline region and a second center point of the second maximum outline region;

the image matching section matches the first and second tooth image data with the first and second center points as a reference.

4. The dental image matching apparatus according to claim 2,

the image matching section compares a distance between a first vertex in the first inscribed sphere and a second vertex in the second inscribed sphere to match the first and second tooth image data.

5. The dental image matching apparatus according to claim 3,

the image matching section compares a distance between a first vertex in the first maximum contour region and a second vertex in the second maximum contour region to match the first and second dental image data.

6. The dental image matching apparatus according to claim 4 or 5,

the image matching unit repeatedly matches the first and second tooth image data until the sum of all distances between the first and second vertexes is equal to or smaller than a standard value.

7. The dental image matching apparatus according to claim 4 or 5,

the image matching unit repeats matching of the first and second tooth image data by a standard number of times.

8. A dental image matching device according to claim 4 or 5, further comprising:

and a preprocessor configured to convert voxel information of the first and second dental image data into vertex information while matching resolutions of the first and second dental image data.

9. The dental image matching apparatus according to claim 4 or 5,

the maximum outline detection unit detects the first and second maximum outline regions as polygonal shapes with corners contacting the most prominent tooth.

10. The dental image matching apparatus according to claim 4,

the inscribed circle detection unit detects that two circles having a first radius and contacting both sides of left and right upper corners constituting the first and second maximum contour regions, respectively, and one circle having a first radius and contacting a point where a bisector that bisects the first and second maximum contour regions between the two circles meets a side constituting lower ends of the first and second maximum contour regions are first and second inscribed circles.

11. The dental image matching apparatus according to claim 5,

the center point detecting unit detects the first center point using an average value of x-axis, y-axis, and z-axis coordinates of the first vertex, and detects the second center point using an average value of x-axis, y-axis, and z-axis coordinates of the second vertex.

12. The dental image matching apparatus according to claim 4 or 5,

the maximum contour detecting unit detects the first and second maximum contour regions using vertices having minimum and maximum position values with respect to x, y, and z axes in the first and second tooth image data.

13. A dental image matching method, comprising the steps of:

detecting a first maximum outline region as a maximum outline region of a dentition in the first dental image data;

detecting a second maximum outline region as a maximum outline region of the dentition in the second dental image data; and

matching the first and second dental image data based on a first inscribed circle inscribed in the first maximum contour region and a second inscribed circle inscribed in the second maximum contour region, or matching the first and second dental image data based on a first center point of the first maximum contour region and a second center point of the second maximum contour region.

14. The dental image matching method according to claim 13,

the first and second dental image data matching step includes the steps of:

respectively detecting a first inscribed circle and a second inscribed circle respectively in the first maximum outline area and the second maximum outline area;

detecting first and second inscribed balls as bodies of revolution of the first and second inscribed circles, respectively; and

and matching the first and second tooth image data with the first and second inscribed spheres as a reference.

15. The dental image matching method according to claim 13,

the first and second dental image data matching step includes the steps of:

detecting first and second center points of the first and second maximum outline regions, respectively; and

matching the first and second dental image data based on the first and second center points.

Technical Field

The present invention relates to a dental image matching apparatus and method, and more particularly, to a dental image matching apparatus and method capable of matching a dental image with high accuracy and high speed.

Background

When a scene or an object is photographed from different times or angles in computer vision, images of mutually different coordinate systems are obtained. Image matching refers to a process of deforming these mutually different images to be displayed in one coordinate system.

The correspondence relationship between the images acquired by the different measurement methods can be confirmed by such image matching.

In the dental surgical guidance (surgical guide) software, before entering the dental implant planning step, an image matching procedure between ct (computed tomography) image data and Oral Scan (Oral Scan) image data is usually performed.

The image matched through such an image matching process is a basis of a dental implant planning work for grasping bone tissue and neural tube positions and the like to decide a safe and optimal dental implant position, and thus the accuracy of image matching has a very important meaning in performing the subsequent steps.

In the image matching method provided by conventional medical software, a user manually inputs a point to be a reference of a matched image, and matches the image based on the point. According to such a conventional image matching method, since the reference point is roughly determined and selected by the eyes of the user, the result is very inaccurate, and the manual operation process of the user is inevitably followed after the images are matched. I.e. the person is used to change the position of the point or to reselect a point to modify the matching result. As described above, according to the conventional technique, since the matching and modification process is repeated, the user spends a lot of time on the matching image, and a problem arises that a satisfactory result cannot be obtained according to the time spent.

As another existing method, there may be a method of acquiring an image including a mark for use as a reference for intraoral matching, and matching images acquired from different image capturing apparatuses with the intra-image mark as a reference, but this is premised on a process of performing a mark for matching in the oral cavity of a patient at the time of acquiring an image, and therefore has a problem of being troublesome and also bringing inconvenience to the patient.

In the conventional method, since the distances between all vertices in the image are compared to match the image, the image matching speed is reduced, and there is a problem that a system load for comparing the distances between the vertices increases.

Thus, a scheme is required in which matching of images can be automatically performed at high speed and with high accuracy without the trouble of using a separate marker or manual operation.

In addition, the conventional method includes many unnecessary noise components such as a gum region, and thus has a problem of reducing the accuracy of image matching.

Disclosure of Invention

Technical problem to be solved

An object of the present invention is to provide a dental image matching apparatus and method which can improve an image matching speed and minimize a system load.

Another object of the present invention is to provide a dental image matching apparatus and method: image matching is automatically performed with high accuracy, convenience of the user is improved, and the time required for the planting plan is shortened and the accuracy of the planting plan can be improved.

Technical scheme for solving problems

In order to solve the above problems, the present invention provides a dental image matching apparatus comprising: a maximum outline detection section that detects a first maximum outline region as a maximum outline region of the dentition in the first dental image data and detects a second maximum outline region as a maximum outline region of the dentition in the second dental image data; and an image matching section matching the first and second tooth image data based on a first inscribed circle inscribed in the first maximum outline region and a second inscribed circle inscribed in the second maximum outline region or matching the first and second tooth image data based on a first center point of the first maximum outline region and a second center point of the second maximum outline region.

In addition, the dental image matching apparatus of the present invention further includes: an inscribed circle detection unit that detects a first inscribed circle inscribed in the first maximum outline region and detects a second inscribed circle inscribed in the second maximum outline region; and an inscribed sphere detection unit that detects a first inscribed sphere that is a rotating body of the first inscribed circle and detects a second inscribed sphere that is a rotating body of the second inscribed circle; the image matching unit matches the first and second tooth image data with the first and second inscribed spheres as a reference.

In addition, the dental image matching apparatus of the present invention further includes a central point detecting section that detects a first central point of the first maximum contour region and detects a second central point of the second maximum contour region; the image matching section matches the first and second tooth image data with the first and second center points as a reference.

Here, the image matching section compares a distance between a first vertex in the first inscribed sphere and a second vertex in the second inscribed sphere to match the first and second tooth image data.

In addition, the image matching section compares a distance between a first vertex in the first maximum contour region and a second vertex in the second maximum contour region to match the first and second tooth image data.

The image matching unit repeatedly matches the first and second tooth image data until the sum of all distances between the first and second vertexes is equal to or less than a standard value.

The image matching unit repeats matching of the first and second tooth image data by a standard number of times.

The tooth image matching device according to the present invention further includes a preprocessor for converting voxel information of the first and second tooth image data into vertex information while matching resolutions of the first and second tooth image data.

The maximum outline detection unit detects that the first and second maximum outline regions are polygonal shapes in which the most prominent tooth is in contact with each corner.

The inscribed circle detection unit detects that two circles having a first radius and contacting both sides of left and right upper corners constituting the first and second maximum contour regions, respectively, and one circle having the first radius and contacting a point where a bisector bisecting the first and second maximum contour regions between the two circles meets a side constituting lower ends of the first and second maximum contour regions are first and second inscribed circles.

The center point detecting unit detects the first center point by using an average value of x-axis, y-axis, and z-axis coordinates of the first vertex, and detects the second center point by using an average value of x-axis, y-axis, and z-axis coordinates of the second vertex.

The maximum contour detecting unit detects first and second maximum contour regions using vertices having minimum and maximum position values with respect to the x, y, and z axes in the first and second tooth image data.

In addition, the dental image matching method of the present invention includes the steps of: detecting a first maximum outline region as a maximum outline region of a dentition in the first dental image data; detecting a second maximum outline region as a maximum outline region of the dentition in the second dental image data; and matching the first and second tooth image data based on a first inscribed circle inscribed in the first maximum outline region and a second inscribed circle inscribed in the second maximum outline region, or matching the first and second tooth image data based on a first center point of the first maximum outline region and a second center point of the second maximum outline region.

Here, the first and second dental image data matching steps include the steps of: respectively detecting a first inscribed circle and a second inscribed circle respectively in the first maximum outline area and the second maximum outline area; detecting first and second inscribed balls as bodies of revolution of the first and second inscribed circles, respectively; and matching the first and second dental image data with the first and second inscribed spheres as a reference.

In addition, the first and second dental image data matching steps include the steps of: detecting first and second center points of the first and second maximum outline regions, respectively; the first and second dental image data are matched based on the first and second center points.

Effects of the invention

According to the present invention, since images are matched by comparing only the distance between vertexes in the inscribed sphere of the first and second tooth image data or the distance between vertexes in the maximum outline region of the first and second tooth image data, it is possible to increase the image matching speed compared to matching images by comparing the distances between all vertexes in the first and second tooth image data, and it is possible to have an effect of minimizing the load of a system for comparing the distances between vertexes.

In addition, according to the present invention, the following effects are obtained: image matching is automatically performed with high accuracy to improve the convenience of the user, along with shortening the time required for the planting plan and improving the accuracy of the planting plan.

The effects obtainable in the present invention are not limited to the above-mentioned effects, and those having ordinary knowledge in the art to which the present invention pertains for other effects not mentioned can be clearly understood from the following descriptions.

Drawings

Fig. 1 is a block diagram of a dental image matching apparatus according to a first embodiment of the present invention.

Fig. 2 and 3 are diagrams for explaining a method of detecting a maximum outline region in tooth image data in a case where all teeth of a dentition are complete as a first embodiment of the present invention.

Fig. 4 and 5 are views for explaining a method of detecting a maximum outline region in a tooth image in the case where a part of teeth is not present in a dentition as a first embodiment of the present invention.

Fig. 6 and 7 are views for explaining a method of detecting an inscribed circle in the maximum outline area in the case where all teeth of the dentition are complete as the first embodiment of the present invention.

Fig. 8 and 9 are views for explaining a method of detecting an inscribed circle in a maximum outline area in a case where a part of teeth is not present in a dentition as a first embodiment of the present invention.

Fig. 10 is a diagram for explaining a method of matching the image matching section to the first and second tooth image data according to the first embodiment of the present invention.

Fig. 11 is a flowchart of a dental image matching method according to a first embodiment of the present invention.

Fig. 12 is a block diagram of a dental image matching apparatus according to a second embodiment of the present invention.

Fig. 13 and 14 are diagrams illustrating a method for detecting a maximum contour region and a center point in two-dimensional tooth image data according to a second embodiment of the present invention.

Fig. 15 and 16 are diagrams for explaining a method of detecting a maximum contour region and a center point in three-dimensional tooth image data according to a second embodiment of the present invention.

Fig. 17 is a diagram for explaining a method of matching the image matching section to the first and second tooth image data according to the second embodiment of the present invention.

Fig. 18 is a flowchart of a dental image matching method according to a second embodiment of the present invention.

Detailed Description

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. At this time, it should be noted that the same members are denoted by the same reference numerals as much as possible in the drawings. Then, a detailed description of known functions and configurations which may make the gist of the present invention unclear will be omitted.

In the embodiment of the present invention, each component may be configured by one or more lower-level components, and the electric, electronic, and mechanical functions performed by each component may be implemented by various known devices or mechanical components such as an electronic circuit, an Integrated circuit, and an asic (application Specific Integrated circuit), or may be implemented individually or by combining two or more components.

(first embodiment)

Fig. 1 is a block diagram of a dental image matching apparatus according to a first embodiment of the present invention.

As shown in fig. 1, the dental image matching apparatus 100 according to the first embodiment of the present invention may include: a maximum outline detection unit 110, an inscribed circle detection unit 120, an inscribed sphere detection unit 130, and an image matching unit 140.

The dental image matching apparatus 100 of the first embodiment of the present invention matches the first dental image data and the second dental image data.

The first tooth Image data and the second tooth Image data may be one of ct (computed tomography) Image data, Oral Scan (Oral Scan) Image data, and Magnetic Resonance Image (MRI) data, respectively, as Image data having different coordinate systems or resolutions due to being acquired by different Image capturing devices or at different time points.

On the other hand, although not shown in the drawings, the dental image matching device 100 according to the embodiment of the present invention may further include a direction alignment section (not shown) and a preprocessing section (not shown).

Here, a direction aligning part (not shown) aligns the first dental image data and the second dental image data before matching the images so that the first dental image data and the second dental image data face the same direction.

Then, the preprocessor (not shown) makes the unit distances of the objects in the volume space of the first dental image data and the second dental image data the same, and can further make the resolutions of the first dental image data and the second dental image data uniform. Then, Voxel (Voxel) information of the first tooth image data and the second tooth image data is converted into Vertex (Vertex) information using a Marching Cube Algorithm (Marching Cube Algorithm).

Here, the marching cubes algorithm is an algorithm widely used in the field of image technology as an algorithm for extracting an iso surface (iso surface) from three-dimensional image data, and thus detailed description thereof is omitted.

Fig. 2 and 3 are views for explaining a method of detecting a maximum outline region in tooth image data in a case where all teeth of a dentition are complete as a first embodiment of the present invention; fig. 4 and 5 are views for explaining a method of detecting a maximum outline region in a tooth image in the case where a part of teeth is not present in a dentition as a first embodiment of the present invention.

Referring to fig. 2 and 4, the maximum outline detection unit 110 detects a first maximum outline region a1, which is a maximum outline region of a dentition in the first tooth image data. Then, referring to fig. 3 and 5, a second maximum outline region a2, which is a maximum outline region of the dentition in the second tooth image data, is detected.

The maximum outline regions a1 and a2 are shaped as a figure that can accommodate all the teeth in the dentition, and can be defined as regions set so that the corners of the figure are in contact with the most prominent tooth portions in the direction of the corners. That is, the maximum outline detector 110 may detect that the first and second maximum outline areas a1, a2 are polygonal shapes having corners contacting the most protruded teeth.

For example, as shown in fig. 2 and 3, in a state where all the teeth of the dentition are complete and aligned, it can be detected that the first and second maximum outer regions a1, a2 are rectangular quadrangles; as shown in fig. 4 and 5, in the case where there is no part of the teeth (e.g., molars) in the dentition, the first and second maximum outer contour regions a1, a2 can be detected to have a trapezoidal shape.

The maximum-profile detecting unit 110 includes a depth coordinate as a Z-axis coordinate in the crown length in addition to two dimensions of the x-axis and the y-axis, and can detect the first and second maximum-profile regions a1 and a2 in three dimensions.

The maximum contour detecting unit 110 performs image analysis processing by a grayscale algorithm to analyze the structure and shape of the first and second tooth image data, thereby distinguishing a tooth region from other regions, for example, soft tissue such as a gum and bone tissue, and can detect the first and second maximum contour regions a1 and a2 in the tooth region without including other regions.

Here, the maximum contour detecting unit 110 may detect the first and second maximum contour regions a1, a2 using the vertices having the minimum position values and the maximum position values based on the x-axis, the y-axis, and the z-axis in the first and second tooth image data.

Specifically, the lower edges of the first and second maximum profile regions a1, a2 detect the vertex having the smallest position value with respect to the y-axis, and generate the horizontally extending line to include the vertex. Then, the left and right sides of the first and second maximum outline areas a1, a2 detect vertices having minimum and maximum position values, respectively, at the x-axis level, and generate a vertically extended line to include the vertices. Then, the upper edges of the first and second maximum contour regions a1, a2 detect vertices having maximum position values in the left and right regions, respectively, based on a bisector L that bisects the x-axis, and generate extension lines to include the vertices. Then, first and second maximum outline regions a1, a2 are generated with points intersecting the generated extension lines as vertices.

Fig. 6 and 7 are views for explaining a method of detecting an inscribed circle in a maximum outline area in a case where all teeth of a dentition are complete as the first embodiment of the present invention; fig. 8 and 9 are views for explaining a method of detecting an inscribed circle in a maximum outline area in a case where a part of teeth is not present in a dentition as a first embodiment of the present invention.

Referring to fig. 6 and 8, the inscribed circle detection unit 120 detects a first inscribed circle S1 inscribed in the first maximum outline area a 1. Then, referring to fig. 7 and 9, a second inscribed circle S2 inscribed in the second maximum outline area a2 is detected.

The inscribed circle detection unit 120 may detect 3 first inscribed circles S1 in the first maximum outline area a 1. Specifically, inscribed circle detector 120 detects two circles having a first radius and contacting both sides of the upper corner on the left and right sides constituting first maximum contour region a1, respectively, and may detect a point, which contacts bisector L, which bisects first maximum contour region a1 between the two detected circles, and a side constituting the lower end of first maximum contour region a1, and has a first radius, as first inscribed circle S1.

Likewise, the inscribed circle detection unit 120 may detect 3 second inscribed circles S2 in the second maximum outline area a 2. Specifically, inscribed circle detector 120 detects two circles having a first radius and contacting both sides of the upper corner on the left and right sides constituting second maximum contour region a2, respectively, and detects a circle having a first radius and contacting a point at which bisector L, which bisects second maximum contour region a2 between the two detected circles, meets a side constituting the lower end of second maximum contour region a2 as second inscribed circle S2.

The inscribed ball detection unit 130 detects a first inscribed ball that is a rotational body of the first inscribed circle S1.

Here, the x-axis and y-axis center coordinates of the first inscribed sphere coincide with the x-axis and y-axis center coordinates of the first inscribed circle S1, and the x-axis and y-axis center coordinates of the second inscribed sphere coincide with the x-axis and y-axis center coordinates of the second inscribed circle S2.

Then, the inscribed sphere detection unit 130 calculates an average value of z-axis coordinates, which are depth information of the first vertex in the first inscribed circle S1, as z-axis coordinates of the first inscribed sphere center, and can detect the first inscribed sphere having the first radius with the center of the first inscribed sphere as a reference.

Similarly, the inscribed ball detection unit 130 detects a second inscribed ball that is a rotational body of the second inscribed circle S2.

Here, the x-axis and y-axis center coordinates of the second inscribed sphere coincide with the x-axis and y-axis center coordinates of the second inscribed circle S2, and the x-axis and y-axis center coordinates of the second inscribed sphere coincide with the x-axis and y-axis center coordinates of the second inscribed circle S2.

Then, the inscribed sphere detection unit 130 calculates an average value of z-axis coordinates, which are depth information of the second vertex in the second inscribed circle S2, as z-axis coordinates of the second inscribed sphere center, and can detect a second inscribed sphere having the first radius with respect to the second inscribed sphere center.

Alternatively, the first and second inscribed spheres thus detected may include teeth.

Fig. 10 is a diagram for explaining a method of matching the image matching section to the first and second tooth image data according to the first embodiment of the present invention.

The image matching section 140 matches the first and second tooth image data with the first and second inscribed spheres as a criterion.

Specifically, referring to fig. 10, the image matching unit 140 overlaps (over lap) the first and second tooth image data with the first and second inscribed spheres as a quasi-overlap, and then compares distances between a first vertex in the first inscribed sphere and a second vertex in the second inscribed sphere to match the first tooth image data and the second tooth image data.

The image matching section 140 may repeatedly match the first dental image data and the second dental image data until the sum of all distances between the first vertex and the second vertex is below a standard value.

Here, the standard value may be set in advance by a user, and the image matching accuracy may be different according to the target. That is, the higher the image matching accuracy of the target is, the smaller the standard value is.

Specifically, referring to fig. 10, if the matching process is repeated to sufficiently shorten the distance between the first vertices s1, s2, s3 and the second vertices d1, d2, d3, the matching process may be repeated to shorten the distance between the distances l1, l2, l3 extending from the planes contacting the second vertices d1, d2, d3 to the extension lines of the first vertices s1, s2, s3, and the vertical vectors of the extension lines and the second vertices d1, d2, d 3.

In contrast, the image matching unit 140 may repeat matching of the first dental image data and the second dental image data about the standard number of times.

Here, the number of times for the criterion may be set in advance by a user, and the image matching accuracy may be different according to the target. That is, the more the number of image matching repetitions is, the higher the image matching accuracy is, and thus the higher the image matching accuracy of the target is, the larger the standard number is.

As such, the dental image matching apparatus 100 according to the first embodiment of the present invention matches images by comparing only the distances between the vertexes in the inscribed sphere of the first and second dental image data, and thus can improve the image matching speed as compared to matching images by comparing the distances between all the vertexes in the first dental image data and the second dental image data, and not only can minimize the load of the system for comparing the distances between the vertexes.

In addition, the dental image matching device 100 of the embodiment of the present invention automatically performs image matching with high accuracy to improve the convenience of the user, along with shortening the time required for the implant plan and improving the accuracy of the implant plan.

The dental image matching device 100 according to the first embodiment of the present invention may further include a display part 150 that displays a matching result of the first dental image data and the second dental image data.

The display unit 150 displays the matching result of the first and second tooth image data so that the user can confirm the matching result.

Specifically, the display section 150 provides a mark capable of quantitatively grasping the accuracy of the image matching result when displaying the matching result, such as displaying a misaligned or relatively inaccurate portion of the matching with a different color within the matching image, or the like, so that the user can objectively grasp the accuracy of the matching.

The display portion 150 includes a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, an Organic Light Emitting Diode (OLED) display, a Micro Electro Mechanical Systems (MEMS) display, and an electronic paper (electronic paper) display. Here, the display part 150 may implement a touch screen (touch screen) in combination with an input part (not shown).

Fig. 11 is a flowchart of a dental image matching method according to a first embodiment of the present invention.

Hereinafter, a dental image matching method according to a first embodiment of the present invention will be described with reference to fig. 1 to 11, and the same contents as those of the dental image matching apparatus according to the first embodiment of the present invention will be omitted.

First, the dental image matching method of the first embodiment of the present invention detects a first maximum outline region a1 as a maximum outline region of dentition in the first dental image data (S11).

Then, a first inscribed circle S1 inscribed in the first maximum outline area a1 is detected (S21), and a first inscribed sphere that is a rotation body of the first inscribed circle S1 is detected (S31).

Likewise, a second maximum outline region a2, which is the maximum outline region of the dentition in the second tooth image data, is detected (S12).

Then, a second inscribed circle S2 inscribed in the second maximum outline area a2 is detected (S22), and a second inscribed sphere that is a rotation body of the second inscribed circle S2 is detected (S32).

Then, the first and second tooth image data are matched with respect to the first and second inscribed spheres (S40).

Here, the first and second tooth image data matching step (S40) is a step of overlapping (over lap) the first and second tooth image data with the first and second inscribed spheres as the quasi-points and then comparing the distance between the first vertex in the first inscribed sphere and the second vertex in the second inscribed sphere to match the first and second tooth image data.

The first and second tooth image data matching step (S40) may be a step of repeatedly matching the first and second tooth image data until the sum of all distances between the first and second vertexes is equal to or less than a standard value.

The first and second dental image data matching step (S40) may be a step of repeating the matching of the first and second dental image data by a standard number of times or so.

As described above, the dental image matching method according to the first embodiment of the present invention matches images by comparing only the distances between the vertexes in the inscribed spheres of the first and second dental image data, and thus can improve the image matching speed as compared to matching images by comparing the distances between all the vertexes in the first dental image data and the second dental image data, and thus can minimize the load of the system for comparing the distances between the vertexes.

In addition, the dental image matching method of the first embodiment of the present invention automatically performs image matching with high accuracy to improve the convenience of the user, along with shortening the time required for the implant plan and improving the accuracy of the implant plan.

On the other hand, the dental image matching method according to the first embodiment of the present invention is written as a program executable also in a computer, and can be implemented in various recording media, such as a magnetic storage medium, an optical reading medium, and a digital storage medium.

While the images matching the CT image data and the oral scan data are exemplified in the first embodiment described above, the maximum outline region of the dentition is detected within the image data, the inscribed sphere is detected within the maximum outline region, and image matching can be performed, as described above, for various combinations between two-dimensional image data, between two-dimensional and three-dimensional image data, between three-dimensional image data, such as between CT image data, between oral scan image data, between magnetic resonance image data and CT image data, and the like. In this case, as described above, when the maximum outline region of the tooth is detected in the three-dimensional image data, the final maximum outline region of the tooth can be detected by calculating the depth coordinate as the Z-axis coordinate within the length of the crown, taking into consideration that the outline of the dentition differs depending on the length of the crown in addition to the X-axis and Y-axis coordinates. In addition, the present invention is also applicable to a multi-dimensional image including four-dimensional image data in addition to the three-dimensional image data described above.

(second embodiment)

Fig. 12 is a block diagram of a dental image matching apparatus according to a second embodiment of the present invention.

As shown in fig. 12, the dental image matching apparatus 200 according to the second embodiment of the present invention may include: a maximum outline detection unit 210, a center point detection unit 220, and an image matching unit 240.

The dental image matching apparatus 200 of the second embodiment of the present invention matches the first dental image data and the second dental image data.

The first tooth Image data and the second tooth Image data may be one of ct (computed tomography) Image data, Oral Scan (Oral Scan) Image data, and Magnetic Resonance Image (MRI) data, respectively, as Image data having different coordinate systems or resolutions due to being acquired by different Image capturing devices or at different time points.

On the other hand, although not shown in the drawings, the dental image matching device 200 according to the second embodiment of the present invention may further include a direction alignment section (not shown) and a preprocessing section (not shown).

Here, a direction aligning part (not shown) aligns the first dental image data and the second dental image data before matching the images so that the first dental image data and the second dental image data face the same direction.

Then, the preprocessor (not shown) makes the unit distances of the objects in the volume space of the first dental image data and the second dental image data the same, and can further make the resolutions of the first dental image data and the second dental image data uniform. Then, Voxel (Voxel) information of the first tooth image data and the second tooth image data is converted into Vertex (Vertex) information using a Marching Cube Algorithm (Marching Cube Algorithm).

Here, the marching cubes algorithm is an algorithm widely used in the field of image technology as an algorithm for extracting an iso surface (iso surface) from three-dimensional image data, and thus detailed description thereof is omitted.

Fig. 13 and 14 are diagrams of a method of detecting a maximum contour region and a center point in two-dimensional dental image data as a second embodiment of the present invention; fig. 15 and 16 are diagrams for explaining a method of detecting a maximum contour region and a center point in three-dimensional tooth image data according to a second embodiment of the present invention.

Referring to fig. 13, the maximum outline detection unit 210 detects a first maximum outline region a1, which is a maximum outline region of a dentition, in the first tooth image data. Then, referring to fig. 14, a second maximum outline region a2, which is a maximum outline region of the dentition in the second tooth image data, is detected.

The maximum outline regions a1 and a2 are shaped as a figure that can accommodate all the teeth in the dentition, and can be defined as regions set so that the corners of the figure are in contact with the most prominent tooth portions in the direction of the corners. That is, the maximum outline detector 210 may detect that the first and second maximum outline areas a1, a2 are polygonal shapes having corners contacting the most protruded teeth.

For example, as shown in fig. 13 and 14, in a state where all the teeth of the dentition are complete, it is detected that the first and second maximum outer regions a1, a2 are rectangular quadrangles.

On the other hand, unlike the drawings, in the case where there is no part of the teeth (for example, molars) in the dentition, it is also possible to detect that the first and second maximum outer-contour regions a1, a2 have a trapezoidal shape.

Referring to fig. 15 and 16, the maximum-profile detecting unit 210 includes a depth coordinate as a Z-axis coordinate within the length of the crown in addition to two dimensions of the x-axis and the y-axis, and can detect the first and second maximum-profile regions a1 and a2 in three dimensions.

The maximum contour detecting unit 210 analyzes the structure and shape of the first and second tooth image data and performs image analysis processing by a grayscale-based algorithm to distinguish a tooth region from other regions, for example, soft tissue such as a gum and bone tissue, and can detect the first and second maximum contour regions a1 and a2 in the tooth region without including other regions.

Here, the maximum contour detecting unit 210 may detect the first and second maximum contour regions a1, a2 using vertices having minimum and maximum position values based on the x-axis, the y-axis, and the z-axis in the first and second tooth image data.

Specifically, the lower edges of the first and second maximum profile regions a1, a2 detect the vertex having the smallest position value with respect to the y-axis, and generate the horizontally extending line to include the vertex. Then, the left and right sides of the first and second maximum outline areas a1, a2 detect vertices having minimum and maximum position values, respectively, at the x-axis level, and generate a vertically extended line to include the vertices. Then, the upper edges of the first and second maximum contour regions a1, a2 detect vertices having maximum position values in the left and right regions, respectively, based on a bisector L that bisects the x-axis, and generate extension lines to include the vertices. Then, first and second maximum outline regions a1, a2 are generated with points intersecting the generated extension lines as vertices.

Referring to fig. 13, the center point detector 220 detects a first center point C1 of the two-dimensional first maximum contour region a 1. Then, referring to fig. 14, a second center point C2 of a two-dimensional second maximum outline area a2 is detected.

Specifically, the center point detector 220 detects the first center point C1 using the average values of the x-axis and y-axis coordinates of the first vertex in the first maximum contour region a 1. Then, the second center point C2 is detected using the average value of the x-axis and y-axis coordinates of the second vertex in the second maximum outline area a 2.

Referring to fig. 15, the center point detector 220 detects the first center point C1 of the three-dimensional first maximum contour region a 1. Then, referring to fig. 16, a second center point C2 of a three-dimensional second maximum outline area a2 is detected.

Specifically, the center point detector 220 detects the first center point C1 using the average values of the x-axis, y-axis, and z-axis coordinates of the first vertex in the first maximum contour region a 1. Then, the second center point C2 is detected using the average values of the x-axis, y-axis, and z-axis coordinates of the second vertex in the second maximum outline area a 2.

Fig. 17 is a diagram for explaining a method of matching the image matching section to the first and second tooth image data according to the second embodiment of the present invention.

The image matching unit 240 matches the first and second tooth image data based on the first and second center points C1 and C2.

Specifically, referring to fig. 17, the image matching unit 240 overlaps (over lap) the first and second tooth image data with the first and second center points C1 and C2 as a quasi-overlap, and then compares distances between first vertices in the first maximum contour region a1 and second vertices in the second maximum contour region a2 to match the first tooth image data and the second tooth image data.

The image matching section 240 may repeatedly match the first dental image data and the second dental image data until the sum of all distances between the first vertex and the second vertex is below a standard value.

Here, the standard value may be set in advance by a user, and the image matching accuracy may be different according to the target. That is, the higher the image matching accuracy of the target is, the smaller the standard value is.

Specifically, referring to fig. 17, if the matching process is repeated to sufficiently shorten the distance between the first vertices s1, s2, s3 and the second vertices d1, d2, d3, the matching process may be repeated to shorten the distance between the distances l1, l2, l3 extending from the planes contacting the second vertices d1, d2, d3 to the extension lines of the first vertices s1, s2, s3, and the vertical vectors of the extension lines and the second vertices d1, d2, d 3.

In contrast to the above, the image matching unit 240 may repeat the matching of the first dental image data and the second dental image data about the standard number of times.

Here, the number of times for the criterion may be set in advance by a user, and the image matching accuracy may be different according to the target. That is, the more the number of image matching repetitions is, the higher the image matching accuracy is, and thus the higher the image matching accuracy of the target is, the larger the number of criteria is.

As described above, the dental image matching apparatus 200 according to the second embodiment of the present invention matches images by comparing only the distances between the vertexes in the first and second maximum contour regions a1, a2 of the first and second dental image data, and thus can improve the image matching speed as compared to matching images by comparing the distances between all the vertexes in the first dental image data and the second dental image data, and not only can minimize the load of the system for comparing the distances between the vertexes.

In addition, the dental image matching device 200 of the second embodiment of the present invention automatically performs image matching with high accuracy to improve the convenience of the user, along with shortening the time required for the implant plan and possibly improving the accuracy of the implant plan.

The dental image matching apparatus 200 according to the second embodiment of the present invention may further include a display part 250 that displays a matching result of the first dental image data and the second dental image data.

The display unit 250 displays the matching result of the first and second tooth image data so that the user can confirm the matching result.

Specifically, the display section 250 provides a mark capable of quantitatively grasping the accuracy of the image matching result when displaying the matching result, such as displaying a misaligned or relatively inaccurate portion of the matching with a different color within the matching image, or the like, so that a user can objectively grasp the accuracy of the matching.

The display portion 250 includes a Liquid Crystal Display (LCD), a Light Emitting Diode (LED) display, an Organic Light Emitting Diode (OLED) display, a Micro Electro Mechanical Systems (MEMS) display, and an electronic paper (electronic paper) display. Here, the display part 250 may implement a touch screen (touch screen) in combination with an input part (not shown).

Fig. 18 is a flowchart of a dental image matching method according to a second embodiment of the present invention.

Hereinafter, a dental image matching method according to a second embodiment of the present invention will be described with reference to fig. 12 to 18, and the same contents as those of the dental image matching apparatus according to the second embodiment of the present invention will be omitted.

First, the dental image matching method of the second embodiment of the present invention detects a first maximum outline region a1 as a maximum outline region of dentition in the first dental image data (S110).

Then, the first center point C1 of the first maximum outline area a1 is detected (S210).

Similarly, a second maximum contour region a2, which is the maximum contour region of the dentition in the second tooth image data, is detected (S120).

Then, the center point C2 of the second maximum outline area a2 is detected (S220).

Then, the first and second tooth image data are matched based on the first and second center points C1, C2 (S300).

Here, the first and second tooth image data matching step (S300) is a step of matching the first and second tooth image data by comparing distances between first vertices in the first maximum contour region a1 and second vertices in the second maximum contour region a2 after overlapping (over lap) the first and second tooth image data with the first and second center points C1, C2 as a quasi-point.

The first and second tooth image data matching step (S300) may be a step of repeatedly matching the first and second tooth image data until the sum of all distances between the first and second vertexes is equal to or less than a standard value.

The first and second dental image data matching step (S300) may be a step of repeating the matching of the first and second dental image data by a standard number of times or so.

As described above, the dental image matching method according to the second embodiment of the present invention matches images by comparing only the distances between the vertexes in the first and second maximum contour regions of the first and second dental image data, and thus can increase the image matching speed as compared to matching images by comparing the distances between all the vertexes in the first dental image data and the second dental image data, and not only can minimize the load of the system for comparing the distances between the vertexes.

In addition, the dental image matching method of the second embodiment of the present invention automatically performs image matching with high accuracy to improve the convenience of the user, along with shortening the time required for the implant plan and possibly improving the accuracy of the implant plan.

The dental image matching method according to the second embodiment of the present invention is written as a program executable also in a computer, and can be implemented in various recording media, such as a magnetic storage medium, an optical reading medium, and a digital storage medium.

In the second embodiment described above, the images matching the CT image data and the intraoral scan data are exemplified, and for various combinations between two-dimensional image data, between two-dimensional and three-dimensional image data, between three-dimensional image data, such as between CT image data, between intraoral scan image data, between magnetic resonance image data and CT image data, and the like, the maximum outline region of the dentition is detected within the image data, the central point is detected within the maximum outline region, and image matching can be performed. In this case, as described above, when the maximum outline region of the tooth is detected in the three-dimensional image data, the final maximum outline region of the tooth can be detected by calculating the depth coordinate as the Z-axis coordinate within the length of the crown, taking into consideration that the outline of the dentition differs depending on the length of the crown in addition to the X-axis and Y-axis coordinates. In addition, the present invention is also applicable to a multi-dimensional image including four-dimensional image data in addition to the three-dimensional image data described above.

On the other hand, the embodiments of the present invention disclosed in the present specification and the drawings are only for easy explanation of technical contents of the present invention and to facilitate understanding of the present invention, and show specific examples, and are not intended to limit the scope of the present invention. That is, it is obvious to those having ordinary knowledge in the art to which the present invention pertains that other modifications may be implemented based on the technical idea of the present invention.

Industrial applicability

The tooth detection device and method of the present invention can be used in various dental treatment fields, such as implant surgery.