KR101613159B1 - Automatic dental image registration method, apparatus, and recording medium thereof - Google Patents

Abstract

The present invention relates to a method for automatically registering a dental image, an apparatus and a recording medium therefor. The apparatus for automatically registering a dental image according to the present invention detects a maximum outer region of teeth from dental image data and automatically performs image registration based on an image feature point extracted from the maximum outer region. The image registration is performed with high accuracy in comparison with user′s manual operation, and also user′s convenience is increased. In addition, reducing time necessary for an implant plan and accuracy of the implant plan are improved.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an automatic matching method for a tooth image,

The present invention relates to a tooth image matching method, an apparatus therefor, and a recording medium, and more particularly, to an automatic image matching method for automatically performing matching of a tooth image, an apparatus therefor, and a recording medium.

When a scene or an object is photographed at a different time or viewpoint from a computer vision, images according to different coordinate systems are obtained. Image matching refers to processing for transforming different images and displaying them in one coordinate system. Through the image matching, it is possible to confirm the correspondence relationship between images obtained through different measurement methods.

In the surgical guide software, the image is usually subjected to a process of image matching between the CT data and the scan data before entering the implant planning stage. The accuracy of the image matching is very important for the subsequent procedure because the matched image is the foundation of the implant planning work which determines the safe and optimum implant placement position by grasping the bone tissue and neural tube position.

1 is a reference diagram for explaining an image matching method provided in conventional medical software. Referring to FIG. 1, a user manually inputs a point as a reference of image matching, and image matching is performed based on the inputted point. According to the conventional image matching method, since the user roughly determines the reference point and selects the reference point, the result is very inaccurate, and the manual operation process of the user necessarily follows the image matching. The user changes the position of the point or reselects the point to correct the matching result. As described above, according to the related art, there is a problem that the user consumes a lot of time for image registration due to the repeated process of matching and correction, and a result satisfying the time spent can not be obtained.

As another conventional method, there is a method of acquiring an image including a marker for use as a reference in the oral cavity, and matching an image obtained from a heterogeneous sensor based on a marker in the image. However, It is troublesome to perform the marking for matching in the oral cavity of the patient, and it is inconvenient for the patient.

Accordingly, there is a need for a method that can automatically perform image matching with high accuracy without the use of a separate marker or manual operation.

The present invention has been made in order to solve the problems of the prior art in which there is the inaccuracy of the matching result according to the manual operation of the user and the inconvenience due to the application of the separate marker, The present invention provides an automatic matching method for a tooth image which can automatically perform matching of a tooth image with accuracy, an apparatus therefor, and a recording medium.

According to an embodiment of the present invention, there is provided an automatic matching apparatus for automatically matching two teeth images according to an embodiment of the present invention. The automatic matching apparatus includes a first maximum outer region and a second outer tooth region, A maximum outer circumference detection unit for detecting a second maximum outer circumference region which is the maximum outer circumference region of the teeth; A feature point extracting unit that extracts feature points that are reference points for image matching in the first maximum outer region and the second maximum outer region; And an image matching unit for matching the first tooth image data and the second tooth image data based on the minutiae point.

At this time, the feature point extracting unit may extract, as the feature points, the contact points of the first teeth image data, the contact points of the first maximum outline area, and the dental arrays of the second tooth image data and the second maximum outline area.

The display unit may further include a display unit for displaying the matching result of the first tooth image data and the second tooth image data so that the user can confirm the matching result. The display unit may display the first maximum outer- 2 maximum outer area are divided into a plurality of grid cells and the grid image is displayed by applying the minutiae points as reference coordinates and having the same coordinate system as the first grid image and the second grid image, I can help.

The maximum contour detection unit may detect the first maximum contour area and the second maximum contour area in the form of a polygon in which each corner of a graphic object is in contact with a tooth part protruding most in a corresponding corner direction.

The maximum contour detection unit may determine the depth coordinates of the first maximum outer region or the second maximum outer region within the tooth crown of the teeth in consideration of the tooth outer region that varies depending on the tooth depth, The maximum outline area can be calculated on the basis of the maximum outline area.

The image matching unit may further apply a reference point corresponding to a user input or a peripheral region of the reference point as a reference of image matching to correct the image matching result calculated based on the extracted feature point, Can be further increased.

Here, the first tooth image data and the second tooth image data may be one of a CT image, an oral scan image, and a magnetic resonance image, respectively.

In addition, the above-mentioned object can be achieved by a method of automatically matching two teeth images according to another aspect of the present invention, comprising: detecting a first maximum outer region as a maximum outer region of teeth of a first tooth image data; Detecting a second maximum outer region as a maximum outer region of a tooth array of the second tooth image data; Extracting a feature point that is a reference of image matching within the first maximum outer region and the second maximum outer region; And matching the first tooth image data and the second tooth image data on the basis of the minutiae point.

The above-described object can also be achieved by a computer-readable recording medium on which a program for executing the above-mentioned automatic method of matching teeth images is recorded.

As described above, according to the present invention, it is possible to improve the convenience of the user by automatically performing image matching with a high accuracy, thereby shortening the time required for the implant planning and improving the accuracy of the implant plan .

FIG. 1 is a reference diagram for explaining a tooth image matching method according to the related art; FIG.
2 is a block diagram of a tooth image automatic matching apparatus according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method of automatic matching of teeth images according to an embodiment of the present invention; FIG.
FIG. 4 is a diagram for explaining an example of a method of detecting a tooth maximal outer region in the first tooth image data; FIG.
FIG. 5 is a diagram for explaining an example of a method of detecting a tooth maximum maximum area from a second tooth image data; FIG.
FIG. 6 is a view for explaining an example of extracting minutiae points in the tooth maximum outer region; FIG. And
7 is an example of a lattice image obtained by latticing the tooth maximum outer region of each tooth image data.

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In the following description and the accompanying drawings, detailed description of well-known functions or constructions that may obscure the subject matter of the present invention will be omitted. It should be noted that the same constituent elements are denoted by the same reference numerals as possible throughout the drawings.

The terms and words used in the present specification and claims should not be construed to be limited to ordinary or dictionary meanings and the inventor is not limited to the concept of terminology for describing his or her invention in the best way. It should be interpreted as meaning and concept consistent with the technical idea of the present invention. Therefore, the embodiments described in the present specification and the configurations shown in the drawings are merely the most preferred embodiments of the present invention, and not all of the technical ideas of the present invention are described. Therefore, It is to be understood that equivalents and modifications are possible.

2 is a block diagram of an apparatus 100 for automatically matching teeth images according to an embodiment of the present invention. Referring to FIG. 2, an automatic tooth image matching apparatus 100 according to an embodiment of the present invention includes a maximum outer contour detection unit 10, a feature point extraction unit 20, an image matching unit 30, and a display unit 40 .

The maximal contour detecting unit 10 processes the first tooth image data and the second tooth image data to detect the maximum outer region of each tooth in the two image data. For reference, the first and second tooth image data are images having different coordinate systems due to the reasons such as being acquired through the heterogeneous sensor, acquired at different points in time, and the like, respectively. The CT image is a computerized tomography (CT) image, A three-dimensional image, or a multi-dimensional image captured through various types of equipment including a magnetic resonance image (MRI).

At this time, the maximum outer region of the tooth can be defined as a region configured to accommodate both of the teeth in the teeth, and configured such that each corner of the figure contacts the tooth portion protruding most in the corresponding corner direction. The maximum outline detection unit 10 detects the outermost outermost area out of a plurality of outline areas.

The maximum outer contour detection unit 10 can detect the maximum outer circumferential region on the three-dimensional plane including the depth coordinates which are the Z-axis coordinates within the crown length as well as the two-dimensional image on the X and Y axes.

The maximum outline extracting unit 10 performs image analysis processing on an image based on structure and shape analysis and an algorithm based on a gray scale so as to distinguish tooth regions and other regions such as gums and soft tissues and bone tissues, It is possible to detect the maximum outer region within the tooth region without being included.

The feature point extraction unit 20 extracts feature points within each of the maximum outer regions extracted from the tooth image data. The feature point extracting unit 20 extracts a feature point of the image data from the edges of the edge of the image data in which the brightness of the pixel changes drastically in one direction, A point as a reference of image matching such as a corner point is extracted as a feature point. As an example of minutia extraction, the minutia extraction unit 20 can extract the teeth of the tooth image data and the contact points of the maximum outline region as minutiae.

The image matching unit 30 performs matching between the first tooth image data and the second tooth image data on the basis of the extracted feature points through the feature point extracting unit 20. At this time, the matching can be performed by various matching algorithms based on the characteristics of the image.

Also, the image matching unit 30 applies the reference point input from the user input means (not shown) or the peripheral region of the inputted reference point as an additional reference of image registration, and outputs the reference point extracted from the feature point extracting unit 20 as a reference It is possible to correct the applied primary image registration result.

The display unit 40 displays the matching result of the tooth image data so that the user can confirm the matching result. When displaying the matching result, the display unit 40 provides a marking that quantitatively grasps the accuracy of the image matching result by, for example, matching out of the matching image or displaying a relatively inaccurate portion with different colors, The accuracy of the matching can be grasped objectively.

In addition, the display unit 40 may provide a grid image obtained by dividing the maximum outer region of the first tooth image data and the second tooth image data into a plurality of grid cells and grating the grid image. The lattice image is obtained by applying the minutiae extracted through the minutiae point extracting unit 20 as reference coordinates so that the maximum outer regions of the first tooth image data and the second tooth image data have the same coordinate system. Through this, it is possible to understand the user when evaluating or modifying the image registration result. In addition, the feature points extracted at the time of displaying the grid image may be superimposed and displayed on the grid so that the user can utilize the conventional feature points as guide information for selecting more effective reference points in image registration correction.

FIG. 3 is a flowchart illustrating a matching process according to an automatic matching method according to an embodiment of the present invention, and FIGS. 4 to 7 are schematic diagrams illustrating an example of each process of image matching. Hereinafter, an organic operation process of the configuration of the video-matching device 100 of FIG. 2 will be described with reference to FIG. 3 and FIGS. 4 to 7. FIG.

When the first tooth image data and the second tooth image data to be subjected to image matching are obtained by using the image equipment, the maximum outer circumference detection unit 10 detects the tooth maximum outer circumference region from each tooth image data (S10, S11).

4 and 5 are schematic diagrams for explaining an example of a method of extracting the tooth maximum outer regions R1 and R2 from the first tooth image data and the second tooth image data, respectively. FIG. 4 shows an example of a CT image, and FIG. 5 shows an example in which a tooth maximal outer region is extracted from an oral scan image.

First, referring to FIG. 4, a two-dimensional axial image reconstructed through a maximum intensity projection (MIP) is shown. As a reference, the maximum intensity projection technique is one of rendering methods, in which voxels having the maximum intensity signal are selected when the two-dimensional sectional images obtained in the first place are sequentially stacked and projected in a predetermined direction, It is a method of reconstruction.

As shown in FIG. 4, the maximum outer contour detection unit 10 detects a tooth maximum outer circumferential region R1 that can accommodate all the tooth regions in a dental portion excluding other tissues such as bones and gums. FIG. 4 shows an example in which the maximum outer circumferential region R1 is detected in a rectangular shape. However, when the detected maximum outer circumferential region R1 takes the form of a figure capable of accommodating all the teeth in the teeth, May be configured to detect various polygonal shaped areas other than the rectangular shape as the maximum outer peripheral area R1 if it is configured to contact the tooth part protruding most in the corresponding corner direction.

Next, FIG. 5 shows an example of detecting the tooth maximum outer region R2 in the oral scan three-dimensional image. Unlike FIG. 4 in which the maximum outer region R1 is detected in the reconstructed two-dimensional image, according to FIG. 5, since the tooth maximum outer region R2 is detected in the three-dimensional image, By detecting the coordinates together, it is possible to detect the tooth maximum outer region R2 having depth coordinates.

5 (a), the maximum outer contour detecting section 10 detects the two-dimensional coordinates of the X-axis and the Y-axis of the tooth maximum outer region R2, and as shown in FIG. 5 (b) , The Z coordinate of the maximum outer tooth area R2, i.e., the depth coordinate, is detected within the tooth crown length 1 in consideration of the outer tooth of the tooth which varies with the tooth depth, The region R2 is derived. Thereby, it is possible to obtain the actual maximum outer peripheral region R2 of the tooth outer region that varies depending on the tooth height. At this time, it is needless to say that various polygonal regions can be detected as the maximum outer region R2.

Subsequently, the feature point extracting unit 20 extracts feature points serving as a reference of image matching in the maximum outer region detected from each tooth image data (S13). A minutia is a point extracted in the maximum outer area of the image, which means a characteristic point of an image such as an edge or a corner point of the tooth that is easy to identify.

FIG. 6 is a diagram for explaining an example of extracting minutiae points P1 and P2 within the tooth maximum outer region.

Referring to FIG. 6, the feature point extracting unit 20 extracts feature points for image matching, including a contact point P1 of the first maximum outer region extracted from the tooth region of the first tooth image data and the first maximum image region extracted from the first tooth image data, It is possible to extract, as feature points, the contact point P2, which is in contact with the tooth area of the tooth image data and the second maximum outer area.

At this time, when a plurality of feature points are extracted in the image, the feature point extracting unit 20 sets the extracted feature points to a predetermined number based on the position of the feature points in the dentition and the distance to the adjacent feature points It is possible to select some feature points among a plurality of feature points using the selection criterion.

As described above, when the minutiae are extracted from each tooth image data, the image matching unit 30 matches the two tooth image data with reference to the minutiae point (S15). As described above, matching can be performed by various matching algorithms that perform matching based on image characteristics.

The display unit 40 displays the image registration result so that the user can check the image registration result (S17). At this time, a quantitative marking that can objectively grasp the registration accuracy can be added to the result display window. This can help the user to determine whether the matching result needs to be modified.

Meanwhile, as shown in FIG. 7, the display unit 40 provides a grid image obtained by dividing the maximum outer region of the first tooth image data and the second tooth image data into a plurality of grid cells and lattice- .

Referring to FIG. 7, it can be seen that the lattice image is applied as a reference coordinate extracted from each image data, so that the maximum outer regions of the first tooth image data and the second tooth image data are gridded so as to have the same coordinate system have. According to this, the minutiae will be located at the same coordinates in the grid coordinate system of each tooth image data. On the other hand, feature points extracted from each image data may be superimposed on the grid image of FIG. According to such a lattice image, since positions corresponding to each other in each tooth image data can be easily grasped, the user can help evaluate the image matching result or select a reference point for correcting the image matching.

When the reference point is inputted from the user through the user input means, the image matching unit 30 determines that it is necessary to correct the image matching result, and inputs the inputted reference point or a region around the reference point inputted for more accurate image matching A new image registration result is added, and the previous image registration result is corrected (S19, S21).

In the above-described embodiment, for example, the reconstruction of the two-dimensional CT image and the 3D oral scan image is performed. However, the CT image-CT image, the scan image-scan image, and the MRI- For the various combinations of 2D-2D image, 2D 3D image and 3D 3D image, the maximum outer edge region of the dentition is detected in the same manner as above, and the feature points are extracted in the maximum outer edge region, Lt; / RTI > At this time, considering the fact that not only the X-axis and Y-axis coordinates but also the outline of the dentition vary depending on the crown length in the calculation of the maximum outer-tooth area in the 3D image, the depth coordinates of the Z-axis coordinate within the crown length are calculated, The outer region can be detected as described above. In addition to the above-described three-dimensional image, it is applicable to a multi-dimensional image including a four-dimensional image.

Meanwhile, the method of automatic matching of tooth images according to the embodiment of the present invention may be embodied as a program that can be executed in a computer, and may be implemented by various recording media such as a magnetic storage medium, an optical reading medium, and a digital storage medium.

As described above, according to the automatic image matching method, the apparatus and the recording medium according to the present invention, the user manually inputs the point as a reference for image matching, and the complicated operation is performed. It is possible to solve the problem of the conventional technique which can not be realized and it is unnecessary to apply a separate device for image matching, so that the convenience of the user and the patient can be increased. In addition, it is expected that the time required for the implant planning and the accuracy of the implant plan can be improved.

Implementations of the various techniques described herein may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or combinations thereof. Implementations may be implemented in a computer program product, such as an information carrier, e.g., a machine readable storage device, such as a computer readable storage medium, for example, for processing by a data processing apparatus, Apparatus (computer readable medium) or as a computer program tangibly embodied in a propagation signal. A computer program, such as the computer program (s) described above, may be written in any form of programming language, including compiled or interpreted languages, and may be stored as a stand-alone program or in a module, component, subroutine, As other suitable units for use in the present invention. A computer program may be deployed to be processed on one computer or multiple computers at one site or distributed across multiple sites and interconnected by a communications network.

Processors suitable for processing a computer program include, by way of example, both general purpose and special purpose microprocessors, and any one or more processors of any kind of digital computer. Generally, a processor will receive instructions and data from a read-only memory or a random access memory or both. The elements of a computer may include at least one processor for executing instructions and one or more memory devices for storing instructions and data. Generally, a computer may include one or more mass storage devices for storing data, such as magnetic, magneto-optical disks, or optical disks, or may receive data from them, transmit data to them, . ≪ / RTI > Information carriers suitable for embodying computer program instructions and data include, for example, semiconductor memory devices, for example, magnetic media such as hard disks, floppy disks and magnetic tape, compact disk read only memory A magneto-optical medium such as a floppy disk, an optical disk such as a DVD (Digital Video Disk), a ROM (Read Only Memory), a RAM , Random Access Memory), a flash memory, an EPROM (Erasable Programmable ROM), an EEPROM (Electrically Erasable Programmable ROM), and the like. The processor and memory may be supplemented or included by special purpose logic circuitry.

While the specification contains a number of specific implementation details, it should be understood that they are not to be construed as limitations on the scope of any invention or claim, but rather on the description of features that may be specific to a particular embodiment of a particular invention Should be understood. Certain features described herein in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented in multiple embodiments, either individually or in any suitable subcombination. Further, although the features may operate in a particular combination and may be initially described as so claimed, one or more features from the claimed combination may in some cases be excluded from the combination, Or a variant of a subcombination.

Likewise, although the operations are depicted in the drawings in a particular order, it should be understood that such operations must be performed in that particular order or sequential order shown to achieve the desired result, or that all illustrated operations should be performed. In certain cases, multitasking and parallel processing may be advantageous. Also, the separation of the various system components of the above-described embodiments should not be understood as requiring such separation in all embodiments, and the described program components and systems will generally be integrated together into a single software product or packaged into multiple software products It should be understood.

It should be noted that the embodiments of the present invention disclosed in the present specification and drawings are only illustrative of specific examples for the purpose of understanding and are not intended to limit the scope of the present invention. It will be apparent to those skilled in the art that other modifications based on the technical idea of the present invention are possible in addition to the embodiments disclosed herein.

10: maximum outer contour detection unit 20:
30: image matching unit 40: display unit

Claims (10)

An automatic matching apparatus for automatically matching two tooth images,
A maximum outer circumferential detection unit for detecting a first maximum outer circumferential region of a tooth array of the first tooth image data and a second maximum outer circumferential region of a tooth array of the second tooth image data;
A feature point extracting unit that extracts feature points that are reference points for image matching in the first maximum outer region and the second maximum outer region; And
And an image matching unit for matching the first tooth image data and the second tooth image data based on the feature points.
The method according to claim 1,
Wherein the feature point extracting unit extracts a contact point between the first tooth image data array and the first maximum outline area and the contact point between the tooth array of the second tooth image data and the second maximum outer area using the feature points, .
The method according to claim 1,
And a display unit for displaying a result of matching the first tooth image data and the second tooth image data.
The method of claim 3,
Wherein the display unit divides the first maximum outer region and the second maximum outer region into a plurality of grid cells and applies the feature points as reference coordinates to generate a first grid image And a second grid image.
The method according to claim 1,
Wherein the maximum outer circumference detection unit detects the first maximum outer circumference area and the second maximum outer circumference area in a polygonal shape in which each corner of a figure is in contact with a tooth part protruding most in the corner direction.
The method according to claim 1,
Wherein the maximum outer contour detecting unit determines the depth coordinates of the first maximum outer region or the second maximum outer region within the tooth crown length of the tooth in consideration of the tooth outer region that varies depending on the tooth depth, Device.
The method according to claim 1,
Wherein the image matching unit further applies a reference point corresponding to a user input or a peripheral region of the reference point as a reference of image matching to correct the image matching result calculated based on the minutiae extracted by the minutiae point extracting unit.
The method according to claim 1,
Wherein the first tooth image data and the second tooth image data are one of a CT image, an oral scan image, and a magnetic resonance image, respectively.
A method for automatically matching two tooth images,
Detecting a first maximum outer region as a maximum outer region of a tooth array of the first tooth image data;
Detecting a second maximum outer region as a maximum outer region of a tooth array of the second tooth image data;
Extracting a feature point that is a reference of image matching within the first maximum outer region and the second maximum outer region; And
And matching the first tooth image data and the second tooth image data based on the feature points.
A computer-readable recording medium having recorded thereon a program for executing the method of automatic matching of teeth images according to claim 9.

Images