Tooth image matching device and method

Abstract

The present invention provides a tooth image matching device, comprising: a maximum contour detection unit, detecting a first maximum contour area as the maximum contour area of ​​a tooth row in first tooth image data, and detecting a second maximum contour area as the maximum contour area of ​​a tooth row in second tooth image data; and an image matching unit, matching the first and second tooth image data based on a first inscribed circle inscribed in the first maximum contour area and a second inscribed circle inscribed in the second maximum contour area, or matching the first and second tooth image data based on a first center point of the first maximum contour area and a second center point of the second maximum contour area.

Description

Technical Field

[0001] The present invention relates to a tooth image matching device and method, and in particular, to a tooth image matching device and method capable of matching tooth images with high accuracy and high speed. Background Art

[0002] In computer vision, when a scene or object is photographed at different times or angles, images with different coordinate systems are obtained. Image matching refers to the process of deforming these different images so that they appear in one coordinate system.

[0003] By such image matching, the correspondence between images acquired by different measurement methods can be confirmed.

[0004] In dental surgical guide software, an image matching process between CT (Computed Tomography) image data and oral scan (Oral Scan) image data is usually performed before entering the dental implant planning step.

[0005] The images matched through this image matching process are the basis for dental implant planning work to determine the safe and optimal dental implant position by understanding the position of bone tissue and neural canal, so the accuracy of image matching is of great significance in executing subsequent steps.

[0006] The image matching method provided by the previous medical software is that the user manually inputs the points that become the reference of the matching image, and matches the image based on this. According to such previous image matching methods, the user roughly judges and selects the reference points with his eyes, so the results are very inaccurate, and the matching images are inevitably accompanied by the manual operation process of the user. That is, the user changes the position of the point or selects the point again to modify the matching result. In this way, according to the previous technology, because the matching and modification process is repeated continuously, the user spends a lot of time on matching images, and there is a problem that a satisfactory result corresponding to the time spent cannot be obtained.

[0007] As another existing method, there is a method of acquiring an image including a mark used as a reference for intra-oral matching, and matching images acquired from different image capturing devices based on the mark within the image. However, this requires that a process of marking for matching be performed within the patient's mouth when acquiring the image, which is troublesome and causes inconvenience to the patient.

[0008] The conventional method is to match images by comparing the distances between all vertices in the images, thereby reducing the image matching speed and also causing a problem of increased system load for comparing the distances between vertices.

[0009] Therefore, a scheme is required that can automatically perform matching of images at high speed and high accuracy without using a separate marker or the trouble of manual operation.

[0010] In addition, the conventional methods include many unnecessary noise components, such as the gum area, and thus have the problem of reducing the accuracy of image matching. Summary of the invention

[0011] Technical problems to be solved

[0012] The object of the present invention is to provide a tooth image matching device and method which can improve the image matching speed and minimize the system load.

[0013] In addition, the present invention aims to provide a tooth image matching device and method as follows: automatically performing image matching with high accuracy, improving the convenience of users, and shortening the time required for implant planning and improving the accuracy of implant planning.

[0014] Technical solutions to the problem

[0015] In order to solve the above-mentioned problems, the present invention provides a tooth image matching device, comprising: a maximum contour detection unit, detecting a first maximum contour area as the maximum contour area of ​​a tooth row in a first tooth image data, and detecting a second maximum contour area as the maximum contour area of ​​a tooth row in a second tooth image data; and an image matching unit, matching the first and second tooth image data based on a first inscribed circle inscribed in the first maximum contour area and a second inscribed circle inscribed in the second maximum contour area, or matching the first and second tooth image data based on a first center point of the first maximum contour area and a second center point of the second maximum contour area.

[0016] In addition, the tooth image matching device of the present invention also includes: an inscribed circle detection unit, detecting a first inscribed circle inscribed in the first maximum outer contour area, and detecting a second inscribed circle inscribed in the second maximum outer contour area; and an inscribed sphere detection unit, detecting a first inscribed sphere as a rotating body of the first inscribed circle, and detecting a second inscribed sphere as a rotating body of the second inscribed circle; wherein the image matching unit matches the first and second tooth image data based on the first and second inscribed spheres.

[0017] In addition, the tooth image matching device of the present invention also includes a center point detection unit, which detects the first center point of the first maximum outer contour area and the second center point of the second maximum outer contour area; the image matching unit matches the first and second tooth image data based on the first and second center points.

[0018] Here, the image matching unit matches the first and second tooth image data by comparing the distance between the first vertex in the first inscribed sphere and the second vertex in the second inscribed sphere.

[0019] In addition, the image matching unit compares the distance between the first vertex in the first maximum contour area and the second vertex in the second maximum contour area to match the first and second tooth image data.

[0020] In addition, the image matching unit repeatedly matches the first and second tooth image data until the sum of all distances between the first and second vertices is equal to or less than a standard value.

[0021] Furthermore, the image matching unit repeats the matching of the first and second tooth image data approximately a standard number of times.

[0022] Furthermore, the tooth image matching device of the present invention further includes a preprocessing unit that makes the resolutions of the first and second tooth image data consistent and converts voxel information of the first and second tooth image data into vertex information.

[0023] Furthermore, the maximum outer contour detection unit detects that the first and second maximum outer contour regions are polygonal shapes whose corners are in contact with the most protruding teeth.

[0024] In addition, the inscribed circle detection unit detects two circles with a first radius that respectively touch the two sides of the left and right upper corners constituting the first and second maximum outer contour areas, and a circle with a first radius that touches the point where the bisector that divides the first and second maximum outer contour areas into two equal parts between the two circles connects with the side constituting the lower end of the first and second maximum outer contour areas as the first and second inscribed circles.

[0025] The center point detection unit detects the first center point using the average value of the x-axis, y-axis, and z-axis coordinates of the first vertex, and detects the second center point using the average value of the x-axis, y-axis, and z-axis coordinates of the second vertex.

[0026] In addition, the maximum contour detection unit detects the first and second maximum contour areas using vertices having minimum and maximum position values ​​with respect to the x-axis, the y-axis, and the z-axis in the first and second tooth image data.

[0027] In addition, the dental image matching method of the present invention includes the following steps: detecting a first maximum outer contour area as the maximum outer contour area of ​​a dental arch in the first dental image data; detecting a second maximum outer contour area as the maximum outer contour area of ​​a dental arch 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 outer contour area and a second inscribed circle inscribed in the second maximum outer contour area, or matching the first and second dental image data based on a first center point of the first maximum outer contour area and a second center point of the second maximum outer contour area.

[0028] Here, the first and second dental image data matching steps include the following steps: respectively detecting the first and second inscribed circles respectively inscribed in the first and second maximum outer contour areas; respectively detecting the first and second inscribed spheres as rotating bodies of the first and second inscribed circles; and matching the first and second dental image data based on the first and second inscribed spheres.

[0029] In addition, the first and second tooth image data matching steps include the following steps: detecting the first and second center points of the first and second maximum contour areas respectively; and matching the first and second tooth image data based on the first and second center points.

[0030] Effects of the Invention

[0031] According to the present invention, images are matched by comparing only the distances between vertices in the inscribed sphere of the first and second dental image data or the distances between vertices in the maximum outer contour area of ​​the first and second dental image data. Therefore, compared with matching images by comparing the distances between all vertices in the first and second dental image data, the image matching speed can be improved. Not only that, it has the effect of minimizing the load of the system for comparing the distances between vertices.

[0032] In addition, according to the present invention, there is an effect of improving the convenience of users by automatically performing image matching with high accuracy, along with shortening the time required for implantation planning and improving the accuracy of implantation planning.

[0033] The effects obtainable in the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood from the following description by a person having ordinary knowledge in the technical field to which the present invention belongs. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 is a block diagram of a tooth image matching device according to a first embodiment of the present invention.

[0035] Figure 2 and Figure 3 This is a diagram for explaining a method of detecting a maximum outer contour area in tooth image data when all teeth in a dentition are complete as a first embodiment of the present invention.

[0036] Figure 4 and Figure 5 This is a diagram for explaining a method of detecting a maximum outer contour area in a tooth image when a part of teeth is missing from a dental row as a first embodiment of the present invention.

[0037] Figure 6 and Figure 7This is a diagram for explaining a method of detecting an inscribed circle in a maximum outer contour area when all teeth in a dentition are complete as a first embodiment of the present invention.

[0038] Figure 8 and Fig. 9 This is a diagram for explaining a method of detecting an inscribed circle in a maximum outer contour area when a part of teeth is missing from a dentition as a first embodiment of the present invention.

[0039] Fig.10 It is a diagram for explaining a method in which the image matching unit according to the first embodiment of the present invention matches the first and second tooth image data.

[0040] Fig.11 is a flowchart of a tooth image matching method according to a first embodiment of the present invention.

[0041] Fig.12 is a block diagram of a tooth image matching device according to a second embodiment of the present invention.

[0042] Fig.13 and Fig.14 This is a diagram showing a method of detecting a maximum outer contour area and a center point in two-dimensional tooth image data as a second embodiment of the present invention.

[0043] Fig.15 and Fig.16 It is a diagram for explaining a method of detecting a maximum outer contour area and a center point in three-dimensional tooth image data as a second embodiment of the present invention.

[0044] Fig.17 It is a diagram for explaining a method in which the image matching unit according to the second embodiment of the present invention matches the first and second tooth image data.

[0045] Fig.18 is a flowchart of a tooth image matching method according to a second embodiment of the present invention. DETAILED DESCRIPTION

[0046] 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 components should be represented by the same reference numerals as much as possible in the accompanying drawings. Then, the detailed description of the known functions and structures that may make the main points of the present invention unclear may be omitted.

[0047] In the embodiments of the present invention, each component may be composed of one or more subordinate components, and the electrical, electronic and mechanical functions performed by each component may be implemented by various well-known devices or mechanical components such as electronic circuits, integrated circuits and ASICs (Application Specific Integrated Circuits), and may also be implemented individually or by combining two or more into one.

[0048] (First embodiment)

[0049] Figure 1 is a block diagram of a tooth image matching device according to a first embodiment of the present invention.

[0050] like Figure 1 As shown, the tooth image matching device 100 according to the first embodiment of the present invention may include: a maximum outer contour detection unit 110 , an inscribed circle detection unit 120 , an inscribed sphere detection unit 130 and an image matching unit 140 .

[0051] The tooth image matching apparatus 100 according to the first embodiment of the present invention matches first tooth image data and second tooth image data.

[0052] Here, the first dental image data and the second dental image data, which are image data having different coordinate systems or resolutions due to being acquired through different image capturing devices or at different time points, may be CT (Computed Tomography) image data, oral scan image data, and magnetic resonance image (MRI) data, respectively.

[0053] On the other hand, although not shown in the drawings, the tooth image matching device 100 according to the embodiment of the present invention may further include a direction alignment unit (not shown) and a pre-processing unit (not shown).

[0054] Here, a direction alignment unit (not shown) aligns the first tooth image data and the second tooth image data before matching the images so that the first tooth image data and the second tooth image data face the same direction.

[0055] Then, the preprocessing unit (not shown) makes the unit distance of the object represented in the volume space of the first tooth image data and the second tooth image data the same, thereby making the resolution of the first tooth image data and the second tooth image data consistent. Then, the voxel information of the first tooth image data and the second tooth image data is converted into vertex information using a marching cube algorithm.

[0056] Here, the marching cubes algorithm is an algorithm for extracting isosurfaces in three-dimensional image data. It is an algorithm widely used in the field of image technology, and therefore a detailed description thereof is omitted.

[0057] Figure 2 and Figure 3is a diagram for explaining a method for detecting a maximum outer contour area in tooth image data when all teeth in a dentition are complete as a first embodiment of the present invention; Figure 4 and Figure 5 This is a diagram for explaining a method of detecting a maximum outer contour area in a tooth image when a part of teeth is missing from a dental row as a first embodiment of the present invention.

[0058] Reference Figure 2 and Figure 4 The maximum outer contour detection unit 110 detects the first maximum outer contour area A1 as the maximum outer contour area of ​​the dentition in the first tooth image data. Figure 3 and Figure 5 , a second maximum outer contour area A2 which is the maximum outer contour area of ​​the tooth row in the second tooth image data is detected.

[0059] Here, the maximum outer contour areas A1 and A2 are in the shape of a figure that can accommodate all teeth in the dentition, and can be defined as a region set so that each corner of the figure contacts the most protruding tooth portion in the direction of the corner. That is, the maximum outer contour detection unit 110 can detect that the first and second maximum outer contour areas A1 and A2 are polygonal shapes in which each corner contacts the most protruding tooth.

[0060] For example, Figure 2 and Figure 3 As shown, when all teeth in the dentition are complete and neatly arranged, it can be detected that the first and second largest outer contour areas A1 and A2 are right-angled quadrilaterals; Figure 4 and Figure 5 As shown, when a part of the teeth (eg, molars) are missing from the dentition, the first and second maximum outer contour areas A1 and A2 can be detected as being in a trapezoidal shape.

[0061] The maximum contour detection unit 110 can detect the first and second maximum contour areas A1 and A2 in three dimensions, including the depth coordinate as the Z-axis coordinate within the tooth crown length, in addition to the two-dimensional x-axis and y-axis.

[0062] The maximum contour detection unit 110 performs structure and shape analysis in the first and second tooth image data and image analysis processing based on a grayscale algorithm to distinguish the tooth area from other areas, such as soft tissue and bone tissue such as gums, and thus can detect the first and second maximum contour areas A1 and A2 in the tooth area without including other areas.

[0063] Here, the maximum contour detection unit 110 may detect the first and second maximum contour areas A1 and A2 using vertices having minimum and maximum position values ​​based on the x-axis, y-axis, and z-axis in the first and second tooth image data.

[0064] Specifically, the lower side of the first and second maximum outline areas A1 and A2 detects the vertex with the minimum position value based on the y-axis, and generates a horizontal extension line to include the vertex. Then, the left and right sides of the first and second maximum outline areas A1 and A2 detect the vertices with the minimum position value and the maximum position value respectively based on the x-axis, and generate a vertical extension line to include these vertices. Then, the upper side of the first and second maximum outline areas A1 and A2 detects the vertices with the maximum position value in the left and right areas respectively based on the bisector L that divides the x-axis into two equal parts, and generates an extension line to include these vertices. Then, the first and second maximum outline areas A1 and A2 are generated with the points that intersect the generated extension lines as vertices.

[0065] Figure 6 and Figure 7 is a diagram for explaining a method for detecting an inscribed circle in a maximum outer contour area when all teeth in a dentition are complete as a first embodiment of the present invention; Figure 8 and Fig. 9 This is a diagram for explaining a method of detecting an inscribed circle in a maximum outer contour area when a part of teeth is missing from a dentition as a first embodiment of the present invention.

[0066] Reference Figure 6 and Figure 8 , the inscribed circle detection unit 120 detects a first inscribed circle S1 inscribed in the first maximum outer contour area A1. Then, referring to Figure 7 and Fig. 9 , detect the second inscribed circle S2 inscribed in the second maximum outer contour area A2.

[0067] The inscribed circle detection unit 120 can detect three first inscribed circles S1 in the first maximum outer contour area A1. Specifically, the inscribed circle detection unit 120 detects two circles having a first radius that are in contact with both sides of the left and right upper corners of the first maximum outer contour area A1, respectively, and a circle having a first radius that is in contact with a point where a bisector L that bisects the first maximum outer contour area A1 between the two detected circles and a side that forms the lower end of the first maximum outer contour area A1 meet as the first inscribed circle S1.

[0068] Similarly, the inscribed circle detection unit 120 can detect three second inscribed circles S2 in the second maximum outer contour area A2. Specifically, the inscribed circle detection unit 120 detects two circles that are in contact with the two sides of the left and right upper end corners of the second maximum outer contour area A2 and have the first radius, and detects a circle that is in contact with the point where the bisector L that bisects the second maximum outer contour area A2 between the two detected circles and the side that constitutes the lower end of the second maximum outer contour area A2 and has the first radius as the second inscribed circle S2.

[0069] The inscribed sphere detection unit 130 detects a first inscribed sphere which is a rotating body of the first inscribed circle S1.

[0070] 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 .

[0071] Then, the inscribed sphere detection unit 130 calculates the average value of the z-axis coordinates of the depth information of the first vertices in the first inscribed circle S1 as the z-axis coordinate of the center of the first inscribed sphere, and detects the first inscribed sphere having the first radius based on the center of the first inscribed sphere.

[0072] Likewise, the inscribed sphere detection unit 130 detects a second inscribed sphere which is a rotating body of the second inscribed circle S2.

[0073] 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.

[0074] Then, the inscribed sphere detection unit 130 calculates the average value of the z-axis coordinates of the depth information of the second vertices in the second inscribed circle S2 as the z-axis coordinate of the center of the second inscribed sphere, and can detect the second inscribed sphere having the first radius based on the center of the second inscribed sphere.

[0075] On the other hand, the first and second inscribed spheres thus detected may include teeth.

[0076] Fig.10 It is a diagram for explaining a method in which the image matching unit according to the first embodiment of the present invention matches the first and second tooth image data.

[0077] The image matching unit 140 matches the first and second tooth image data based on the first and second inscribed spheres.

[0078] Specifically, refer to Fig.10 The image matching unit 140 overlaps the first and second tooth image data based on the first and second inscribed spheres and then compares the distance between the first vertex in the first inscribed sphere and the second vertex in the second inscribed sphere to match the first tooth image data and the second tooth image data.

[0079] The image matching unit 140 may repeatedly match the first tooth image data and the second tooth image data until the sum of all distances between the first vertices and the second vertices is less than a standard value.

[0080] Here, the standard value may be set in advance by a user and may be different according to the image matching accuracy of the target. That is, the higher the image matching accuracy of the target, the smaller the standard value.

[0081] Specifically, refer 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 can be repeated to shorten the distances l1, l2, l3 of the extension lines extending from the plane in contact with the second vertices d1, d2, d3 to the first vertices s1, s2, s3 and the distances between the extension lines and the perpendicular vectors of the second vertices d1, d2, d3.

[0082] In contrast, the image matching unit 140 may repeat the matching of the first tooth image data and the second tooth image data approximately a standard number of times.

[0083] Here, the standard number of times can be set in advance by the user and can be different according to the image matching accuracy of the target. That is, the more the image matching times are repeated, the higher the image matching accuracy is, so the higher the image matching accuracy of the target is, the greater the standard number is.

[0084] In this way, the dental image matching device 100 of the first embodiment of the present invention only compares the distances between the vertices in the inscribed sphere of the first and second dental image data to match the images. Therefore, compared with matching the images by comparing the distances between all the vertices in the first dental image data and the second dental image data, the image matching speed can be improved. Not only that, the load of the system used to compare the distances between the vertices can also be minimized.

[0085] In addition, the tooth 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 implant planning and improving the accuracy of implant planning.

[0086] The tooth image matching device 100 of the first embodiment of the present invention may further include a display unit 150 for displaying the matching result of the first tooth image data and the second tooth image data.

[0087] The display unit 150 displays the matching result of the first and second tooth image data so that the user can confirm it.

[0088] Specifically, when displaying the matching results, the display unit 150 provides marks that can quantitatively grasp the accuracy of the image matching results, such as displaying matching misalignment or relatively inaccurate parts in different colors in the matching image, so that users can objectively grasp the accuracy of the matching.

[0089] The display unit 150 as described above includes a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electromechanical system (MEMS) display, and an electronic paper display. Here, the display unit 150 can be combined with an input unit (not shown) to realize a touch screen.

[0090] Fig.11 is a flowchart of a tooth image matching method according to a first embodiment of the present invention.

[0091] Below, refer to Figures 1 to 11 The tooth image matching method according to the first embodiment of the present invention will be described, and description of the same contents as those of the tooth image matching device according to the first embodiment of the present invention will be omitted.

[0092] First, the tooth image matching method according to the first embodiment of the present invention detects a first maximum outer contour area A1 which is a maximum outer contour area of ​​a tooth row in first tooth image data (S11).

[0093] Then, a first inscribed circle S1 inscribed in the first maximum outer contour area A1 is detected ( S21 ), and a first inscribed sphere which is a rotating body of the first inscribed circle S1 is detected ( S31 ).

[0094] Likewise, a second maximum outer contour area A2 which is the maximum outer contour area of ​​the tooth row in the second tooth image data is detected ( S12 ).

[0095] Then, a second inscribed circle S2 inscribed in the second maximum outer contour area A2 is detected ( S22 ), and a second inscribed sphere which is a rotating body of the second inscribed circle S2 is detected ( S32 ).

[0096] Then, the first and second tooth image data are matched based on the first and second inscribed spheres ( S40 ).

[0097] Here, the first and second tooth image data matching step (S40) is to overlap the first and second tooth image data based on the first and second inscribed spheres and then compare 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.

[0098] In addition, 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 vertices is below a standard value.

[0099] In addition, the first and second tooth image data matching step (S40) may be a step of repeating the matching of the first and second tooth image data approximately a standard number of times.

[0100] As described above, the dental image matching method of the first embodiment of the present invention only compares the distances between the vertices in the inscribed sphere of the first and second dental image data to match the images. Therefore, compared with matching the images by comparing the distances between all the vertices in the first dental image data and the second dental image data, the image matching speed can be improved. Not only that, the load of the system used to compare the distances between the vertices can also be minimized.

[0101] In addition, the tooth image matching method of the first embodiment of the present invention automatically performs image matching with high accuracy to improve the convenience of users, along with shortening the time required for implant planning and improving the accuracy of implant planning.

[0102] On the other hand, the tooth image matching method of the first embodiment of the present invention is written as a program that can also be executed on a computer and can be implemented in various recording media, such as magnetic storage media, optical reading media and digital storage media.

[0103] In the first embodiment described above, an example of matching images of CT image data and oral scan data is given. For various combinations between two-dimensional image data, between two-dimensional and three-dimensional image data, and between three-dimensional image data, such as between CT image data, between oral scan image data, and between magnetic resonance image data and CT image data, the same as described above can be applied. The maximum outer contour area of ​​the dentition is detected in the image data, and the inscribed sphere is detected in the maximum outer contour area, and image matching can be performed. At this time, as described above, when detecting the maximum outer contour area of ​​the tooth in the three-dimensional image data, in addition to the X-axis and Y-axis coordinates, the outer contour of the dentition is also considered to be different according to the length of the crown. The depth coordinate calculated as the Z-axis coordinate within the length of the crown can detect the final maximum outer contour area of ​​the tooth. In addition, in addition to the above-mentioned three-dimensional image data, it can also be applied to multi-dimensional images including four-dimensional image data.

[0104] (Second embodiment)

[0105] Fig.12 is a block diagram of a tooth image matching device according to a second embodiment of the present invention.

[0106] like Fig.12As shown, the tooth image matching device 200 according to the second embodiment of the present invention may include: a maximum contour detection unit 210 , a center point detection unit 220 and an image matching unit 240 .

[0107] The tooth image matching device 200 according to the second embodiment of the present invention matches first tooth image data and second tooth image data.

[0108] Here, the first dental image data and the second dental image data, which are image data having different coordinate systems or resolutions due to being acquired through different image capturing devices or at different time points, may be CT (Computed Tomography) image data, oral scan image data, and magnetic resonance image (MRI) data, respectively.

[0109] On the other hand, although not shown in the drawings, the tooth image matching device 200 according to the second embodiment of the present invention may further include a direction alignment unit (not shown) and a pre-processing unit (not shown).

[0110] Here, a direction alignment unit (not shown) aligns the first tooth image data and the second tooth image data before matching the images so that the first tooth image data and the second tooth image data face the same direction.

[0111] Then, the preprocessing unit (not shown) makes the unit distance of the object represented in the volume space of the first tooth image data and the second tooth image data the same, thereby making the resolution of the first tooth image data and the second tooth image data consistent. Then, the voxel information of the first tooth image data and the second tooth image data is converted into vertex information using a marching cube algorithm.

[0112] Here, the marching cubes algorithm is an algorithm for extracting isosurfaces in three-dimensional image data. It is an algorithm widely used in the field of image technology, and therefore a detailed description thereof is omitted.

[0113] Fig.13 and Fig.14 is a diagram of a method for detecting a maximum outer contour area and a center point in two-dimensional tooth image data as a second embodiment of the present invention; Fig.15 and Fig.16 It is a diagram for explaining a method of detecting a maximum outer contour area and a center point in three-dimensional tooth image data as a second embodiment of the present invention.

[0114] Reference Fig.13The maximum outer contour detection unit 210 detects the first maximum outer contour area A1 as the maximum outer contour area of ​​the dentition in the first tooth image data. Fig.14 , a second maximum outer contour area A2 which is the maximum outer contour area of ​​the tooth row in the second tooth image data is detected.

[0115] Here, the maximum outer contour areas A1 and A2 may be in the shape of a figure that can accommodate all teeth in the dentition, and may be defined as a region set so that each corner of the figure contacts the most protruding tooth portion in the direction of the corner. That is, the maximum outer contour detection unit 210 may detect that the first and second maximum outer contour areas A1 and A2 are polygonal shapes in which each corner contacts the most protruding tooth.

[0116] For example, Fig.13 and Fig.14 As shown, when all teeth of the dentition are complete, it can be detected that the first and second maximum outer contour areas A1 and A2 are right-angled quadrilaterals.

[0117] On the other hand, unlike the drawings, even when a part of teeth (for example, molars) are missing from the dentition, the first and second maximum outline areas A1 and A2 can be detected as trapezoidal shapes.

[0118] Reference Fig.15 and Fig.16 The maximum contour detection unit 210 includes a depth coordinate as a Z-axis coordinate within the crown length in addition to the two-dimensional x-axis and y-axis, and can detect the first and second maximum contour areas A1 and A2 in three dimensions.

[0119] The maximum contour detection unit 210 performs structure and shape analysis in the first and second tooth image data and image analysis processing based on a grayscale algorithm to distinguish the tooth area from other areas, such as soft tissue and bone tissue such as gums, and thus can detect the first and second maximum contour areas A1 and A2 in the tooth area without including other areas.

[0120] Here, the maximum contour detection unit 210 may detect the first and second maximum contour areas A1 and A2 using vertices having minimum and maximum position values ​​based on the x-axis, y-axis, and z-axis in the first and second tooth image data.

[0121] Specifically, the lower side of the first and second maximum outline areas A1 and A2 detects the vertex with the minimum position value based on the y-axis, and generates a horizontal extension line to include the vertex. Then, the left and right sides of the first and second maximum outline areas A1 and A2 detect the vertices with the minimum position value and the maximum position value respectively based on the x-axis, and generate a vertical extension line to include these vertices. Then, the upper side of the first and second maximum outline areas A1 and A2 detects the vertices with the maximum position value in the left and right areas respectively based on the bisector L that divides the x-axis into two equal parts, and generates an extension line to include these vertices. Then, the first and second maximum outline areas A1 and A2 are generated with the points that intersect the generated extension lines as vertices.

[0122] Reference Fig.13 , the center point detection unit 220 detects the first center point C1 of the two-dimensional first maximum outer contour area A1. Then, referring to Fig.14 , detect the second center point C2 of the two-dimensional second maximum outer contour area A2.

[0123] Specifically, the center point detection unit 220 detects the first center point C1 using the average value of the x-axis and y-axis coordinates of the first vertex in the first maximum contour area A1, and then detects the second center point C2 using the average value of the x-axis and y-axis coordinates of the second vertex in the second maximum contour area A2.

[0124] In addition, refer to Fig.15 , the center point detection unit 220 detects the first center point C1 of the three-dimensional first maximum outer contour area A1. Then, referring to Fig.16 , detect the second center point C2 of the three-dimensional second maximum outer contour area A2.

[0125] Specifically, the center point detection unit 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 outer contour area A1, and then detects the second center point C2 using the average values ​​of the x-axis, y-axis, and z-axis coordinates of the second vertex in the second maximum outer contour area A2.

[0126] Fig.17 It is a diagram for explaining a method in which the image matching unit according to the second embodiment of the present invention matches the first and second tooth image data.

[0127] The image matching unit 240 matches the first and second tooth image data based on the first and second center points C1 and C2.

[0128] Specifically, refer to Fig.17The image matching unit 240 overlaps the first and second tooth image data based on the first and second center points C1 and C2, and then compares the distance between the first vertex in the first maximum contour area A1 and the second vertex in the second maximum contour area A2 to match the first tooth image data and the second tooth image data.

[0129] The image matching unit 240 may repeatedly match the first tooth image data and the second tooth image data until the sum of all distances between the first vertices and the second vertices is less than a standard value.

[0130] Here, the standard value may be set in advance by a user and may be different according to the image matching accuracy of the target. That is, the higher the image matching accuracy of the target, the smaller the standard value.

[0131] Specifically, refer 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 can be repeated to shorten the distances l1, l2, l3 of the extension lines extending from the plane in contact with the second vertices d1, d2, d3 to the first vertices s1, s2, s3 and the distances between the extension lines and the perpendicular vectors of the second vertices d1, d2, d3.

[0132] Different from the above, the image matching unit 240 may repeat the matching of the first tooth image data and the second tooth image data approximately a standard number of times.

[0133] Here, the standard number of times can be set in advance by the user and may be different according to the image matching accuracy of the target. That is, the more the image matching times are repeated, the higher the image matching accuracy is, so the higher the image matching accuracy of the target is, the greater the standard number of times is.

[0134] As described above, the dental image matching device 200 of the second embodiment of the present invention only compares the distances between the vertices in the first and second maximum contour areas A1 and A2 of the first and second dental image data to match the images. Therefore, compared with matching the images by comparing the distances between all the vertices in the first dental image data and the second dental image data, the image matching speed can be improved. Not only that, the load of the system for comparing the distances between the vertices can also be minimized.

[0135] In addition, the tooth 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 implant planning and improving the accuracy of implant planning.

[0136] The tooth image matching device 200 of the second embodiment of the present invention may further include a display unit 250 for displaying the matching result of the first tooth image data and the second tooth image data.

[0137] The display unit 250 displays the matching result of the first and second tooth image data so that the user can confirm it.

[0138] Specifically, when displaying the matching results, the display unit 250 provides marks that can quantitatively grasp the accuracy of the image matching results, such as displaying matching misalignment or relatively inaccurate parts in different colors in the matching image, so that users can objectively grasp the accuracy of the matching.

[0139] The display unit 250 as described above includes a liquid crystal display (LCD), a light emitting diode (LED) display, an organic light emitting diode (OLED) display, a micro electromechanical system (MEMS) display, and an electronic paper display. Here, the display unit 250 can be combined with an input unit (not shown) to realize a touch screen.

[0140] Fig.18 is a flowchart of a tooth image matching method according to a second embodiment of the present invention.

[0141] Below, refer to Figures 12 to 18 A tooth image matching method according to a second embodiment of the present invention will be described, and description of the same contents as those of the tooth image matching device according to the second embodiment of the present invention will be omitted.

[0142] First, the tooth image matching method according to the second embodiment of the present invention detects a first maximum outer contour area A1 which is a maximum outer contour area of ​​a tooth row in first tooth image data ( S110 ).

[0143] Then, a first center point C1 of the first maximum outline area A1 is detected ( S210 ).

[0144] Likewise, a second maximum outer contour area A2 which is the maximum outer contour area of ​​the tooth row in the second tooth image data is detected ( S120 ).

[0145] Then, the center point C2 of the second maximum outline area A2 is detected (S220).

[0146] Then, the first and second tooth image data are matched based on the first and second center points C1 and C2 ( S300 ).

[0147] Here, the first and second dental image data matching step (S300) is a step of matching the first and second dental image data by overlapping the first and second dental image data with the first and second center points C1 and C2 as the quasi-overlap, and then comparing the distance between the first vertex in the first maximum contour area A1 and the second vertex in the second maximum contour area A2.

[0148] In addition, 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 vertices is below a standard value.

[0149] In addition, the first and second tooth image data matching step (S300) may be a step of repeating the matching of the first and second tooth image data approximately a standard number of times.

[0150] As described above, the dental image matching method of the second embodiment of the present invention only compares the distances between the vertices in the first and second maximum contour areas of the first and second dental image data to match the images. Therefore, compared with matching the images by comparing the distances between all the vertices in the first dental image data and the second dental image data, the image matching speed can be improved. Not only that, the load of the system used to compare the distances between the vertices can also be minimized.

[0151] In addition, the tooth image matching method of the second embodiment of the present invention automatically performs image matching with high accuracy to improve the convenience of users, along with shortening the time required for implant planning and improving the accuracy of implant planning.

[0152] The tooth image matching method of the second embodiment of the present invention is written into a program that can also be executed on a computer and can be implemented in various recording media, such as magnetic storage media, optical reading media and digital storage media.

[0153] In the second embodiment described above, an example of matching images of CT image data and oral scan data is given. For various combinations between two-dimensional image data, between two-dimensional and three-dimensional image data, and between three-dimensional image data, such as between CT image data, between oral scan image data, and between magnetic resonance image data and CT image data, the same as described above can be applied. The maximum outer contour area of ​​the dentition is detected in the image data, and the center point is detected in the maximum outer contour area, and image matching can be performed. At this time, as described above, when detecting the maximum outer contour area of ​​the tooth in the three-dimensional image data, in addition to the X-axis and Y-axis coordinates, the outer contour of the dentition is also considered to be different according to the length of the crown. The depth coordinate calculated as the Z-axis coordinate within the length of the crown can detect the final maximum outer contour area of ​​the tooth. In addition, in addition to the above-mentioned three-dimensional image data, it can also be applied to multi-dimensional images including four-dimensional image data.

[0154] On the other hand, the embodiments of the present invention disclosed in this specification and the drawings are only specific examples for the purpose of easily explaining the technical content of the present invention and helping to understand the present invention, and are not intended to limit the scope of the present invention. That is, it is obvious to a person with ordinary knowledge in the technical field to which the present invention belongs that other variations can be implemented based on the technical idea of ​​the present invention.

[0155] Industrial Applicability

[0156] The tooth detection device and method of the present invention can be used in various dental treatment fields, such as implant surgery.

Claims

1. A tooth image matching device, comprising: a maximum outer contour detection unit that detects a first maximum outer contour region as a maximum outer contour region of a dentition in the first tooth image data, and detects a second maximum outer contour region as a maximum outer contour region of a dentition in the second tooth image data; A center point detection unit, detecting a first center point of the first maximum outer contour area, and detecting a second center point of the second maximum outer contour area; An image matching unit matches the first and second tooth image data based on the first and second center points, The image matching unit matches the first and second dental image data by comparing the distance between the first vertex in the first maximum contour area and the second vertex in the second maximum contour area, and shortens the distance from the plane contacting the second vertex to the extension line of the first vertex and the distance between the extension line and the perpendicular vector of the second vertex.

2. The tooth image matching device according to claim 1, characterized in that: The image matching unit repeatedly matches the first and second tooth image data until a sum of all distances between the first and second vertices is less than a standard value.

3. The tooth image matching device according to claim 1, characterized in that: The image matching unit repeats matching of the first and second tooth image data approximately a standard number of times.

4. The tooth image matching device according to claim 1, characterized in that: Also includes: The preprocessing unit makes the resolutions of the first and second tooth image data consistent and converts the voxel information of the first and second tooth image data into vertex information.

5. The tooth image matching device according to claim 1, characterized in that: The maximum outer contour detection unit detects that the first and second maximum outer contour areas are polygonal shapes whose corners are in contact with the most protruding teeth.

6. The tooth image matching device according to claim 1, characterized in that: The center point detection unit detects the first center point using an average value of the x-axis, y-axis, and z-axis coordinates of the first vertex, and detects the second center point using an average value of the x-axis, y-axis, and z-axis coordinates of the second vertex.

7. The tooth image matching device according to claim 1, characterized in that: The maximum contour detection unit detects the first and second maximum contour areas using vertices having minimum and maximum position values ​​with respect to an x-axis, a y-axis, and a z-axis in the first and second tooth image data.

8. The tooth image matching device according to claim 1, characterized in that: The device may further include a display unit for displaying a matching result of the first and second tooth image data.

9. The tooth image matching device according to claim 1, characterized in that: The first and second tooth image data are different image data and are one of CT image data, oral scan image data and magnetic resonance image data.

10. A tooth image matching method, comprising the following steps: The maximum outer contour detection unit detects a first maximum outer contour area as a maximum outer contour area of ​​a tooth row in the first tooth image data; The center point detection unit detects a first center point of the first maximum outer contour area; The maximum outer contour detection unit detects a second maximum outer contour area as a maximum outer contour area of ​​a dentition in the second tooth image data; The center point detection unit detects a second center point of the second maximum outer contour area; as well as The image matching unit matches the first and second tooth image data based on the first and second center points. The step of matching the first and second dental image data is: matching the first and second dental image data by comparing the distance between the first vertex in the first maximum outer contour area and the second vertex in the second maximum outer contour area, and shortening the distance from the plane contacting the second vertex to the extension line of the first vertex and the distance between the extension line and the perpendicular vector of the second vertex.

11. The tooth image matching method according to claim 10, characterized in that: The step of matching the first and second tooth image data is a step of repeatedly matching the first and second tooth image data until the sum of all distances between the first and second vertices is below a standard value.

12. The tooth image matching method according to claim 10, characterized in that: The step of matching the first and second tooth image data includes repeating the matching of the first and second tooth image data approximately a standard number of times.

Images