WO2016108453A1

WO2016108453A1 - Teeth image automatic matching method, apparatus therefor, and recording medium therefor

Info

Publication number: WO2016108453A1
Application number: PCT/KR2015/013259
Authority: WO
Inventors: 김태환; 정정운
Original assignee: 오스템임플란트 주식회사
Priority date: 2014-12-31
Filing date: 2015-12-04
Publication date: 2016-07-07
Also published as: KR101613159B1

Abstract

The present invention relates to a teeth image automatic matching method, an apparatus therefor, and a recording medium therefor. A teeth image automatic matching apparatus according to the present invention detects the outermost boundary of teeth in teeth image data, and automatically performs image matching on the basis of image characteristic points extracted from the outermost boundary. As such, the present invention can perform image matching at a higher accuracy than manual operation by a user, and can simultaneously enhance user convenience. Further, the present invention has the effects of reducing the time required for a dental implant treatment plan, and enhancing the accuracy of the dental implant treatment plan.

Description

Automatic dental image registration method, apparatus and recording medium therefor

The present invention relates to a dental image registration method, an apparatus and a recording medium therefor, and more particularly, to an automatic image registration method for automatically performing the registration of the dental image, an apparatus and a recording medium for the same.

In computer vision, when one scene or object is photographed at different times or perspectives, images according to different coordinate systems are obtained. Image registration refers to a process for transforming such different images and displaying them in one coordinate system. Through image matching, the correspondence of images obtained through different measurement methods can be confirmed.

In surgical guide software, an image registration process is typically performed between CT and scan data prior to entering the implant planning phase. Since the matched images serve as the basis for implant planning, which determines the location of bone tissue and neural tube, and determines the safe and optimal implant placement, the accuracy of image registration is very important for the further procedure.

1 is a reference diagram for explaining an image matching method provided by a conventional medical software. Referring to FIG. 1, a user manually inputs a point that is a reference for image matching, and image matching is performed based on this. According to the conventional image matching method, since the user selects the reference point by roughly judging by the eye, the result is very inaccurate, and the user's manual operation process is inevitably followed after the image registration. The user modifies the matching result by changing the location of the point or reselecting the point. As described above, according to the related art, a user spends a lot of time for image registration due to the continuous repetitive process of registration and correction, and there is a problem that a result that satisfies the consumed time cannot be obtained.

As another conventional method, a method including acquiring an image including a marker for use as an oral registration criterion and matching an image obtained from a heterogeneous sensor based on a marker in the image may be used. Since the process of performing marking for registration in the mouth of the premise is cumbersome, there was a problem causing inconvenience to the patient.

Therefore, there is a need for a method for automatically performing image registration with high accuracy without the use of a separate marker or manual operation.

The present invention has been proposed in order to solve the problems of the prior art in which the inaccuracy of the matching result according to the manual operation of the user and the inconvenience of applying a separate marker exists, while excluding the user's intervention or the use of separate equipment as much as possible, It is an object of the present invention to provide an automatic tooth image matching method, an apparatus and a recording medium therefor, which can automatically perform tooth image registration with accuracy.

The above object is an automatic registration device for automatically matching two tooth images according to an aspect of the present invention, wherein the first maximum outer region and the second tooth image data, which are the maximum outer regions of the teeth of the first dental image data, are A maximum outer edge detector configured to detect a second maximum outer side region that is a maximum outer side region of the dental dentition; A feature point extracting unit extracting a feature point as a reference for image registration in the first maximum outer region and the second maximum outer region; And an image matching unit configured to match the first tooth image data and the second tooth image data based on the feature point.

In this case, the feature point extractor may extract the teeth of the first dental image data and the contact point of the first maximum outer region and the teeth of the second tooth image data and the contact point of the second maximum outer region as the feature points.

The display apparatus may further include a display unit configured to display a matching result of the first tooth image data and the second tooth image data so that a user may check the matching result. The display unit may include the first maximum outer area and the first tooth image. 2 is a grid image obtained by dividing a maximum outer area into a plurality of grid cells, and displays the first grid image and the second grid image that have been gridized to have the same coordinate system by applying the feature points as reference coordinates, thereby improving user understanding. Can help.

The maximum outer edge detector may detect the first maximum outer region and the second maximum outer region in a polygonal shape in which each corner of the figure is in contact with the tooth portion protruding most in the direction of the corresponding corner.

In addition, the maximum outer detector detects a depth of the first maximum outer region or the second maximum outer region within the crown length of the tooth in the dental cavity in consideration of the tooth outer region that varies depending on the depth of the tooth, respectively, in three dimensions. The maximum outer area can be calculated.

On the other hand, the image matching unit by applying a reference point or a peripheral region of the reference point in accordance with the user input as a reference for the image registration by modifying the image matching result calculated on the basis of the feature point extracted from the feature point extraction unit to correct the accuracy of the image registration Can be further increased.

In this case, the first tooth image data and the second tooth image data may each be one of a CT image, an oral scan image, and a magnetic resonance image.

In addition, the above object is a method for automatically matching two teeth image according to another aspect of the present invention, the method comprising the steps of: detecting the first maximum outer area which is the maximum outer area of the teeth of the first dental image data; Detecting a second maximum outer region that is a maximum outer region of the teeth of the second dental image data; Extracting a feature point which is a reference for image registration in the first maximum outer region and the second maximum outer region; And matching the first tooth image data with the second tooth image data based on the feature point.

The above object can also be achieved by a computer readable recording medium having recorded thereon a program for executing the above-described method for automatically matching teeth images.

As described above, according to the present invention, it is possible to automatically perform image matching with high accuracy, thereby improving user convenience, and consequently, reducing the time required for implant planning and improving the accuracy of the implant planning. .

1 is a reference diagram for explaining a dental image registration method according to the prior art;

2 is a block diagram of a dental image automatic matching device according to an embodiment of the present invention;

3 is a flowchart of a method for automatically matching a dental image according to an exemplary embodiment of the present invention;

4 is a view for explaining an example of a method for detecting a maximum tooth outer region in first tooth image data;

5A and 5B are views for explaining an example of a method for detecting a maximum tooth outer region in second tooth image data;

6A and 6B are diagrams for explaining an example of extracting feature points in a tooth maximum outer region; And

7A and 7B are examples of a lattice image obtained by lattice the maximum outer region of the tooth image data.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. However, in the following description and the accompanying drawings, detailed descriptions of well-known functions or configurations that may obscure the subject matter of the present invention will be omitted. In addition, it should be noted that like elements are denoted by the same reference numerals as much as possible throughout the drawings.

The terms or words used in the specification and claims described below should not be construed as being limited to ordinary or dictionary meanings, and the inventors are appropriate as concepts of terms for explaining their own invention in the best way. It should be interpreted as meanings and concepts in accordance with the technical spirit of the present invention based on the principle that it can be defined. Therefore, the embodiments described in the present specification and the configuration shown in the drawings are only the most preferred embodiments of the present invention, and do not represent all of the technical ideas of the present invention, and various alternatives may be substituted at the time of the present application. It should be understood that there may be equivalents and variations.

2 is a block diagram of the dental image automatic matching device 100 according to an embodiment of the present invention. Referring to FIG. 2, the automatic tooth image matching device 100 according to the embodiment of the present invention may include a maximum edge detector 10, a feature point extractor 20, an image matcher 30, and a display 40. Include.

The maximum outline detector 10 processes the first tooth image data and the second tooth image data to detect the maximum outer region of the teeth from the two image data. For reference, the first and second tooth image data may be obtained through heterogeneous sensors, or may have different coordinate systems due to a different point of view, and may be computed tomography (CT) images, oral scan images, It includes 2D image, 3D image, or more multidimensional image taken through various kinds of equipment including magnetic resonance image (MRI).

In this case, the maximum outer region of the tooth may be defined as a region in which each corner of the figure is in contact with the tooth portion most protruding in the corresponding corner direction while taking the form of a figure that can accommodate all the teeth in the tooth. The maximum outer detection unit 10 detects a maximum outer area that is the outermost area among the plurality of outer areas.

The maximum outer detector 10 may detect the maximum outer region in three dimensions including not only two-dimensional images of the X-axis and Y-axis, but also depth coordinates that are Z-axis coordinates within the crown length.

The maximum outer extraction unit 10 performs image analysis through structure and morphology analysis and gray scale based algorithm in the image to distinguish the tooth region from other regions, for example, soft tissue such as gum, bone tissue, and the like. It is possible to detect the maximum outer area within the tooth area without being included.

The feature point extractor 20 extracts a feature point within each maximum outer region extracted from the dental image data. The feature point extractor 20 is an edge where the brightness value of the pixel changes rapidly in one direction or a portion where the brightness value changes abruptly in all directions within the maximum edge region of each image data through processing of the image data. The point that is the basis of image registration, such as the corner point, is extracted as the feature point. As an example of feature point extraction, the feature point extractor 20 may extract a contact point between the teeth of the dental image data and the maximum outer area as the feature point.

The image matching unit 30 performs registration of the first tooth image data and the second tooth image data based on the feature points extracted by the feature point extractor 20. In this case, the matching may be performed by various matching algorithms based on the characteristics of the image.

In addition, the image matching unit 30 applies the reference point input from the user input means (not shown) or the peripheral area of the input reference point as an additional reference for image matching, based on the feature points extracted by the feature point extractor 20. The applied primary image registration result can be modified.

The display unit 40 displays the result of registration of the dental image data so that the user can check it. When the matching result is displayed, the display unit 40 displays a mark that can quantitatively determine the accuracy of the matching result by displaying different portions of the matching or relatively inaccurate parts in the matching image. You will be able to objectively determine the correctness of the match.

In addition, the display 40 may provide the user with a grid image obtained by dividing the maximum outer area of the first tooth image data and the second tooth image data into cells of a plurality of grids. The grid image is formed by applying the feature points extracted by the feature point extractor 20 as reference coordinates so that the maximum outer region of the first tooth image data and the second tooth image data have the same coordinate system. Through this, it is possible to improve the user's understanding when evaluating or correcting the image registration result. In addition, the feature points extracted during the grid image display may be overlapped and displayed on the grid so that the user may exclude the conventional feature points and use them as guide information for selecting a reference point that is more effective in correcting image registration.

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

When the first tooth image data and the second tooth image data to perform image registration using the imaging equipment are acquired, the maximum outer edge detector 10 detects the maximum tooth outer region from each tooth image data (S10 and S11).

4 and 5 are diagrams for describing an example of a method in which the maximum outer edge detection unit 10 extracts the maximum tooth outer regions R1 and R2 from the first tooth image data and the second tooth image data, respectively. For reference, FIG. 4 shows an example in which the maximum outer region of the tooth is extracted from the CT image and FIG. 5.

First, referring to FIG. 4, a two-dimensional axial image of the acquired CT image is reconstructed through a maximum intensity projection (MIP) technique. For reference, the maximum intensity projection technique is a rendering technique, in which a first two-dimensional cross-sectional image obtained first is sequentially stacked, and the voxels having the maximum intensity signal are projected by projecting in a predetermined direction. How to reconstruct

As shown in FIG. 4, the maximum outer detection unit 10 detects the maximum tooth outer region R1 that can accommodate all the tooth regions in the orthodontic portion except for other tissues such as bone and gum in the image. 4 shows an example in which the maximum outer region R1 is detected in a rectangular shape, but the detected maximum tooth outer region R1 takes the form of a figure that can accommodate all the teeth in the teeth, and each corner of the figure If is configured to contact the tooth portion most protruding in the corner direction, it may be implemented to detect a variety of polygonal shape area other than the rectangular shape as the maximum outer area (R1).

5A and 5B show an example of detecting the maximum outer region R2 of the tooth in the oral scan 3D image. Unlike FIG. 4, where the maximum outer region R1 is detected in the reconstructed two-dimensional image, according to FIGS. 5A and 5B, since the maximum outer region R2 of the tooth is detected in the three-dimensional image, only the X and Y axes are detected. By detecting the Z-axis coordinates together, the maximum tooth outer region R2 having the depth coordinates can be detected.

In this regard, as illustrated in FIG. 5A, the maximum outer detector 10 detects two-dimensional coordinates of the X and Y axes of the tooth maximum outer region R2, and as shown in FIG. 5B, the tooth depth. In consideration of the tooth outline that varies according to the Z-axis coordinate, that is, depth coordinate of the tooth maximum outer region (R2) within the crown length (l) is finally detected to derive the maximum tooth outer region (R2) in three dimensions. . As a result, a substantially maximum outer region R2 may be obtained among the outer regions of the tooth that vary according to the height of the tooth. Meanwhile, in this case as well, various polygonal regions may be detected as the maximum outer region R2.

Subsequently, the feature point extractor 20 extracts a feature point which is a reference of image registration in the maximum outer region detected from each tooth image data (S13). The feature point is a point extracted within the maximum outer region of the image, and means a characteristic point of the image that is easily identified such as an edge or a corner point of the tooth.

6A and 6B are diagrams for explaining an example of extracting feature points P1 and P2 within a tooth maximum outer region.

6A and 6B, the feature point extractor 20 is a feature point for image registration, and includes a contact point P1 between a dental region of the first dental image data and a first maximum outer region extracted from the first dental image data. And a contact point P2 between the dental region and the second maximum outer region of the second dental image data as a feature point.

In this case, when a plurality of feature points are extracted from the image, when the extracted feature points exceed a preset reference number, the feature point extractor 20 is set based on the position of the feature points and the distance to the adjacent feature points in the dental column. The selection criteria may be used to select some of the feature points.

As described above, when the feature point is extracted from each tooth image data, the image matching unit 30 matches the two tooth image data based on the feature point (S15). As described above, the matching may be performed by various matching algorithms that perform matching based on the characteristics of the image.

The display unit 40 displays an image matching result for the user to check (S17), and may add a quantitative mark to objectively determine the matching accuracy on the result display window. This may help the user determine if the matching result needs to be corrected.

Meanwhile, as illustrated in FIGS. 7A and 7B, the display unit 40 performs grid matching by dividing the maximum outer region of the first dental image data and the second dental image data into a plurality of grid cells as shown in FIGS. 7A and 7B. Can be provided.

Referring to FIGS. 7A and 7B, the grid image is gridized such that the maximum outer region of the first dental image data and the second dental image data have the same coordinate system by applying feature points extracted from each image data as reference coordinates. It can be seen that. According to this, the feature points in the grid coordinate system of each tooth image data will be located at the same coordinates. Meanwhile, feature points extracted from each image data may be superimposed and displayed on the grid images of FIGS. 7A and 7B. According to the grid image, since the position corresponding to each other in each tooth image data can be easily identified, it can help the user to evaluate the image registration result or select a reference point for correcting the image registration.

When the reference point is input from the user image through the user input means, the image matching unit 30 determines that the image matching result needs to be corrected, and thus the input reference point or the region around the input reference point for more accurate image matching is determined. The new image registration result is newly added as a criterion of image registration (S19, S21).

In the above-described embodiment, the reconstruction of the reconstructed two-dimensional CT image and the three-dimensional oral scan image have been described as an example. However, two images, such as a CT image, a CT image, a scanned image, a scanned image, a magnetic resonance image, and a CT image, are described. For the various combinations of 2D-3D, 3D-3D, and 3D-3D images, the maximum outer region of the dentition is detected within the image, and the feature points are extracted within the maximum outer region to match the image. This could be done. At this time, in calculating the maximum outer area of the tooth in the 3D image, the depth coordinates of the Z axis coordinates are calculated within the length of the crown in consideration of not only the X-axis and Y-axis coordinates but also the outer contour of the dental dentition depending on the length of the tooth. The detection of the outer region is as described above. In addition, the present invention may be widely applied to a multidimensional image including a 4D image in addition to the above-described 3D image.

Meanwhile, the method for automatically matching a dental image according to an exemplary embodiment of the present invention may be implemented as a program that may be executed in a computer, and may be implemented as 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 according to the present invention, an apparatus and a recording medium therefor, the user manually inputs a point which is a standard of image matching, followed by a hassle, thereby ensuring accuracy of image matching. It is possible to solve the problems of the prior art that can not be solved, and it is not necessary to apply a separate equipment for image registration can increase the convenience of the user and the patient. In addition, it is expected that the time required for the implant planning and the accuracy of the implant planning can be improved.

Implementations of the various techniques described herein may be implemented in digital electronic circuitry, or in computer hardware, firmware, software, or in combinations of them. Implementations may be implemented for processing by, or to control the operation of, a data processing device, eg, a programmable processor, a computer, or multiple computers, a computer program product, ie an information carrier, for example a machine readable storage. It can be implemented as a device (computer readable medium) or as a computer program tangibly embodied in a radio signal. Computer programs, 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 written as standalone programs or in modules, components, subroutines, or computing environments. It can be deployed in any form, including as other units suitable for use. The computer program can be deployed to be processed on one computer or multiple computers at one site or distributed across multiple sites and interconnected by a communication network.

Processors suitable for the processing of 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. In general, a processor will receive instructions and data from a read only memory or a random access memory or both. Elements of a computer may include at least one processor that executes instructions and one or more memory devices that store instructions and data. In general, a computer may include one or more mass storage devices that store data, such as magnetic, magneto-optical disks, or optical disks, or receive data from, transmit data to, or both. It may be combined to be. 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. ), Optical media such as DVD (Digital Video Disk), magneto-optical media such as floppy disk, ROM (Read Only Memory), RAM , Random Access Memory, Flash Memory, Erasable Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), and the like. The processor and memory may be supplemented by or included by special purpose logic circuitry.

Although the specification includes numerous specific implementation details, these should not be construed as limiting to any invention or the scope of the claims, but rather as a description of features that may be specific to a particular embodiment of a particular invention. It must be understood. Certain features that are described in this specification in the context of separate embodiments may be implemented in combination in a single embodiment. Conversely, various features that are described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable subcombination. Furthermore, while the features may operate in a particular combination and may be initially depicted as so claimed, one or more features from the claimed combination may in some cases be excluded from the combination, the claimed combination being a subcombination Or a combination of subcombinations.

Likewise, although the operations are depicted in the drawings in a specific order, it should not be understood that such operations must be performed in the specific order or sequential order shown in order to obtain desirable results or that all illustrated operations must be performed. In certain cases, multitasking and parallel processing may be advantageous. Moreover, 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 that it can.

On the other hand, the embodiments of the present invention disclosed in the specification and drawings are merely presented specific examples for clarity and are not intended to limit the scope of the present invention. It is apparent to those skilled in the art that other modifications based on the technical idea of the present invention can be carried out in addition to the embodiments disclosed herein.

Claims

An automatic registration device for automatically matching two teeth images,

A maximum outer edge detector configured to detect a first maximum outer region that is the maximum outer region of the teeth of the first dental image data and a second maximum outer region that is the maximum outer region of the teeth of the second dental image data;

A feature point extracting unit extracting a feature point as a reference for image registration in the first maximum outer region and the second maximum outer region; And

And an image matching unit configured to match the first tooth image data and the second tooth image data based on the feature point.
The method of claim 1,

The feature point extractor extracts the teeth of the first dental image data and the contact point of the first maximum outer region and the teeth of the second tooth image data and the contact of the second maximum outer region as the feature point .
The method of claim 1,

And a display unit configured to display a matching result of the first tooth image data and the second tooth image data.
The method of claim 3,

The display unit is a grid image obtained by dividing the first maximum outer region and the second maximum outer region into a plurality of grid cells, respectively, and the first grid image which is gridized to have the same coordinate system by applying the feature points as reference coordinates. And an image matching device for displaying a second grid image.
The method of claim 1,

The maximum edge detector is a tooth image automatic registration device for detecting the first maximum outer area and the second maximum outer area in a polygonal shape in which each corner of the figure is in contact with the tooth portion most protruding in the direction of the corner.
The method of claim 1,

The maximum outer detector detects a tooth outer region that depends on the depth of the tooth, and automatically determines the depth coordinates of the first maximum outer region or the second maximum outer region within the crown length of the tooth in the dental dentition. Device.
The method of claim 1,

And an image matching unit adapted to apply a reference point according to a user input or a peripheral region of the reference point as an image matching criterion to modify an image matching result calculated based on the feature points extracted by the feature point extracting unit.
The method of claim 1,

And 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.
In the method of automatically matching two tooth images,

Detecting a first maximum outer region that is a maximum outer region of the teeth of the first dental image data;

Detecting a second maximum outer region that is a maximum outer region of the teeth of the second dental image data;

Extracting a feature point which is a reference for image registration in the first maximum outer region and the second maximum outer region; And

And automatically matching the first tooth image data to the second tooth image data based on the feature point.
A computer-readable recording medium having recorded thereon a program for executing the method of automatically matching a dental image according to claim 9.