KR20200006507A - Method and apparatus for extracting region of interest in ct image - Google Patents

Abstract

The present invention provides a method for extracting a region of interest of teeth in CT images. The method for extracting a region of interest of teeth in CT images comprises the steps of: calculating an average Hounsfield unit (HU) value by averaging an HU value for each pixel included in a plurality of CT images and generating an average map in which the average HU value is mapped to each pixel; generating a weighting mask in which weights are set for each region; extracting a tooth candidate region in which a weighted sum of a product of the average HU value and the weights are maximized while the weighting mask moves in the average map; generating a binary mask in which a threshold is applied to the weighting mask; and extracting a region of interest of teeth by applying the binary mask with regard to the tooth candidate region.

Description

Method and apparatus for extracting tooth region of interest from CT images {METHOD AND APPARATUS FOR EXTRACTING REGION OF INTEREST IN CT IMAGE}

The present invention relates to a method and apparatus for extracting a region of interest from a CT image, and more particularly, in matching a CT image with an oral scan image, automatically extracting a region including a tooth from the CT image as a region of interest. It relates to a method and an apparatus.

In general, an implant means a substitute that can replace human tissue when the original human tissue is lost, but in the dentist, an implant of artificial teeth is implanted.

The implant procedure is performed by forming a perforation in the alveolar bone using a drill and placing a fixture in the perforation. The procedure for forming a perforation and the implantation of the fixture are performed in a patient's dental condition or a position of a tooth requiring an implant procedure. And many differences occur from patient to patient according to the alveolar bone condition of the patient.

As such, drilling for alveolar bone drilling is difficult for beginners as well as experienced users to accurately measure depth and direction during the process. It is very difficult to measure the depth.

In addition, it is not easy for the operator to apply the force to the drill during drilling to determine the depth to which the drilling is currently performed, and to damage the nerve of the alveolar bone when the drill is inserted beyond a certain depth. You can also.

On the contrary, if the drilling operation is terminated before reaching a certain depth, the drilled drilling depth is shallow, and excessive force is required to fix the fixture, and the thread around the drilling is damaged or the fixture is not completely secured. There was a problem with the procedure.

Accordingly, an auxiliary device called a guide stent is used to identify the exact position and direction in which the drilling operation is to be performed.

Three-dimensional image data is required to produce the guide stent. The image data may be obtained by matching the three-dimensional oral image obtained through CT imaging with the three-dimensional oral image obtained through the oral scanner or the oral gypsum model. .

Here, the three-dimensional oral image obtained through the CT scan is a crown (part of the teeth exposed to the outside of the gum) and the root (parts combined with the alveolar bone inside the gum), and the shape of the alveolar bone and the crown, root, alveolar bone It includes information on bone density, and the 3D oral image obtained through the oral scanner or the oral gypsum model includes the appearance information of the oral tissue.

In order to automatically process such registration, a method for automatically extracting a region including a tooth from a 3D CT image is required.

In order to solve the above problems, an object of the present invention is to provide a method for extracting the region of interest in the three-dimensional CT image that can automatically extract the tooth region as the region of interest in the three-dimensional CT image.

Technical problems to be achieved in the present invention are not limited to the above-mentioned technical problems, and other technical problems not mentioned above may be clearly understood by those skilled in the art from the following description. There will be.

In order to solve the above problems, the present invention, the average HU value for each pixel included in the plurality of CT images to calculate the average HU value, and generating an average map in which the average HU value is mapped to each pixel and Generating a weighted mask having weights set for each region, extracting a tooth candidate region having a maximum weighted sum sum of a product of average HU values and weights while moving the weighted mask on an average map; A method of extracting a tooth region of interest from a CT image includes generating a binary mask to which a threshold is applied and extracting a tooth region of interest by applying a binary mask to a tooth candidate region.

Here, the weighting mask and the binary mask is characterized in that the horseshoe type.

Further, in the step of generating the weighting mask, the weighting mask may be set to a greater weight as the weighting mask is closer to the center of the horseshoe type.

In addition, in the step of generating the weighting mask, the weighting mask may be set to a greater weight in the lower portion than the top of the horseshoe type.

Further, in the step of generating the binary mask, pixels having a weight greater than or equal to the threshold may be set to binary value 1 and pixels having a weight less than or equal to the threshold may be set to binary value 0.

In addition, the extracting of the tooth region of interest may include extracting a region including the pixels having a binary value of 1 as the tooth region of interest.

In addition, in the generating of the binary mask, the pixels included in the tooth candidate region may be set to the binary value 1, and the pixels included in the remaining regions may be set to the binary value 0.

In addition, in the generating of the binary mask, the pixels included in the tooth candidate region and the peripheral region may be set to the binary value 1, and the pixels included in the remaining regions may be set to the binary value 0.

In addition, the present invention, an average map generation unit for calculating the average HU value by averaging the HU value for each pixel included in the plurality of CT images, and generates an average map in which the average HU value is mapped to each pixel, and for each region A weighted mask generator for generating a weighted mask to which weights are set, a candidate region extracting unit for extracting a tooth candidate region having a maximum weighted sum of the product of average HU values and weights while moving the weighted mask on an average map; Provides a tooth region of interest extraction device in a CT image including a binary mask generator for generating a binary mask to which the threshold is applied to the weighted mask, and a region of interest extractor for extracting the region of interest by applying a binary mask to the tooth candidate region do.

According to the method for extracting the region of interest from the CT image according to the embodiment of the present invention, in registering the 3D CT image and the 3D oral scan image, a portion unnecessary for registration such as the neck bone included in the 3D CT image is automatically Since the tooth region is automatically extracted as the region of interest on the 3D CT image, the accuracy of registration and the processing time may be shortened during registration of the 3D oral scan image.

Effects obtained in the present invention are not limited to the above-mentioned effects, and other effects not mentioned above may be clearly understood by those skilled in the art from the following description. will be.

1 is a block diagram of a tooth region of interest extraction apparatus in a CT image according to an embodiment of the present invention.
2 is a flowchart of a method for extracting a region of interest of a tooth from a CT image according to an exemplary embodiment of the present invention.
3 is an exemplary diagram for describing a method of generating an average map in a method for extracting a region of interest of a tooth from a CT image according to an exemplary embodiment of the present invention.
4 is an exemplary diagram of a weighting mask for extracting a tooth candidate region from a CT image according to an exemplary embodiment of the present invention.
5 is an exemplary diagram of a binary mask for extracting a region of interest from a CT image according to an exemplary embodiment of the present invention.
6 illustrates an example of extracting a tooth candidate region in a method of extracting a region of interest of a tooth from a CT image according to an exemplary embodiment of the present invention.
FIG. 7 is an exemplary view of extracting a tooth region of interest in a method of extracting a tooth region of interest in a 3D CT image according to an exemplary embodiment of the present invention.

The objects and effects of the present invention and the technical configurations for achieving them will be apparent with reference to the embodiments described later in detail in conjunction with the accompanying drawings. In describing the present invention, when it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted. The terms to be described later are terms defined in consideration of structures, roles, functions, and the like in the present invention, which may vary according to intentions or customs of users and operators.

However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various forms. The present embodiments are merely provided to complete the disclosure of the present invention, and to fully inform those of ordinary skill in the art to which the present invention pertains, and the present invention is only described in the claims. It is only defined by the scope of the claims. Therefore, the definition should be made based on the contents throughout the specification.

Throughout the specification, when a part is said to "include" a certain component, it means that it can further include other components, except to exclude other components unless specifically stated otherwise.

On the other hand, in the embodiment of the present invention, each of the components, functional blocks or means may be composed of one or more sub-components, the electrical, electronic, mechanical functions performed by each component is an electronic circuit, It may be implemented by various known elements or mechanical elements such as an integrated circuit, an application specific integrated circuit (ASIC), and may be implemented separately or two or more may be integrated into one.

Combinations of each block in the accompanying block diagram and in each step of the flowchart may also be performed by computer program instructions. These computer program instructions may be mounted on a processor of a general purpose computer, a special purpose computer, a portable notebook computer, a network computer, or other programmable data processing equipment, such that the instructions executed by the processor of the computer device or other programmable data processing equipment may be used. It will create means for performing the functions described in each block of the block diagram or flow diagram described below. These computer program instructions may also be stored in memory or computer readable memory available to a computer device capable of directing the computer device or other programmable data processing equipment to implement functionality in a particular manner, so that each block in the block diagram Alternatively, it is also possible to produce an article containing instruction means for performing the functions described in each step of the flowchart. The computer program instructions may also be mounted on a computer device or other programmable data processing equipment, thereby creating a process for performing a series of operational steps on the computer device or other programmable data processing equipment, so that each block and flowchart in the block diagram. It is also possible to provide steps for executing the functions described in each step of.

In addition, each block or step may represent a portion of a module, segment, or code that includes one or more executable instructions for executing a specified logical function (s). It should also be noted that in some alternative embodiments, the functions noted in the blocks or steps may occur out of order. For example, the two blocks or steps shown in succession may in fact be executed substantially concurrently, or the blocks or steps may sometimes be performed in the reverse order, depending on the functionality involved.

Hereinafter, referring to the accompanying drawings, a method of extracting a region of interest from a CT image according to an embodiment of the present invention will be described.

1 is a block diagram of an apparatus for extracting a tooth region of interest in a CT image according to an embodiment of the present invention, and FIG. 2 is a flowchart of a method for extracting a tooth region of interest in a CT image according to an embodiment of the present invention.

As shown in FIG. 1, the apparatus for extracting a region of interest in a CT image according to an exemplary embodiment of the present invention includes an average map generator 110, a weighted mask generator 120, a candidate region extractor 130, and a binary mask. The generator 140 and the ROI extractor 150 are included.

3 is an exemplary diagram for describing a method of generating an average map in a method for extracting a region of interest of a tooth from a CT image according to an exemplary embodiment of the present invention.

In general, among a plurality of 2D CT images constituting the 3D CT image, a phenomenon in which only a part of the tooth appears in a specific 2D CT image may occur due to the curvature of the tooth and may be affected by noise.

In order to solve this problem, as illustrated in FIG. 3, the average map generator 110 averages and averages a Hounsfield Unit (HU) value for each pixel included in a plurality of two-dimensional CT images in an axial direction. An HU value is calculated and an average map in which the average HU value is mapped to each pixel is generated (S100). By creating an average map in this way, all tooth shapes can be used and the influence of noise can be minimized.

On the other hand, if a simple average of the HU values due to the high HU value of a specific pixel included in a specific CT image, the average HU value may be calculated too high.

4 is an exemplary diagram of a weighted mask for extracting a tooth candidate region from a CT image according to an embodiment of the present invention, and FIG. 5 is a diagram of a binary mask for extracting a tooth ROI from a CT image according to an embodiment of the present invention. It is an illustration.

Referring to FIG. 4, the weighted mask generator 120 generates a weighted mask 200 in which weights are set for each region (S200). 5, the binary mask generator 140 generates a binary mask 300 to which a threshold is applied to the weighted mask 200 (S400).

As shown in FIGS. 4 and 5, the weight mask 200 and the binary mask 300 may be formed in a horseshoe shape to correspond to the axial shape of the tooth region.

Here, the weight of the portion other than the horseshoe type of the weight mask 200 may be set to 0, and the weight of the horseshoe type may be set differently for each region as a value greater than zero. In addition, the binary value of the horseshoe portion of the double mask 300 may be set to 1, and the binary value of the portions other than the horseshoe type may be set to 0.

Referring to FIG. 4, the weighting mask 200 may be designed to have a greater weight as it is closer to the center of the horseshoe type. This is to ensure that the teeth in the tooth candidate region are located at the center of the weighting mask 200. In addition, the weighting mask 200 may be designed to have more weight at the lower side than the upper side with respect to the center, which is generally the upper part of the tooth is extracted, the lower part of the jawbone is extracted because the lower teeth of the patient Even if it is to use the information of the jawbone.

Referring to FIG. 5, the binary mask 300 may be designed by binarizing by applying a specific threshold to the weight mask 200.

6 illustrates an example of extracting a tooth candidate region in a method of extracting a region of interest of a tooth from a CT image according to an exemplary embodiment of the present invention.

The candidate region extraction unit 130 extracts the tooth candidate region having the maximum weighted sum obtained by adding the product of the average HU value and the weight while moving the weight mask 200 on the average map (S300). Here, the candidate region extractor 130 may adjust the size of the weighted mask 200 and the binary mask 300 by using the information of the CT image. In detail, the original mask corresponds to a 200x200 image having a size of 0.4 mm per pixel, and the size of the weighted mask 200 and the binary mask 300 may be adjusted in consideration of the actual size of each CT image. For example, in the case of a CT image having a size of 0.2 mm per pixel, the weighted mask 200 and the binary mask 300 may be doubled in width and length, respectively.

That is, the candidate region extracting unit 130 converts the size of the weight mask 200 and moves it on the average map while selecting the tooth candidate region having the maximum weighted sum of the product of the average HU value and the weight for each pixel. Search.

In the process of moving the weight mask 200 on the average map, the weight mask 200 is moved by one pixel starting from the upper left corner as shown in FIG. 6, and the weighted sum is calculated for each movement. This process continues until the weight mask 200 reaches the lower right corner. The position of the weighting mask 200 having the largest value among all the weighted sums calculated is determined as the tooth candidate region.

Specifically, when at least one of the average HU value of a specific pixel or the weight of the weighting mask 200 located in the specific pixel is 0, the product of the average HU value and the weight is 0, so the product of the average HU value and the weight is not 0. The weighted sum is maximized at the position of the weighting mask 200 that includes the most pixels, and this position may be determined as the tooth candidate region.

On the other hand, the step of extracting the tooth candidate region (S300) and the step of generating the binary mask 300 (S400) by using the weighting mask 200 described above may proceed separately, respectively.

FIG. 7 is an exemplary view of extracting a tooth ROI in a method of extracting a tooth ROI from a 3D CT image according to an exemplary embodiment of the present invention.

As shown in FIG. 7, the ROI extractor 150 extracts the ROI of interest by applying a binary mask 300 to the tooth candidate region (S500).

Here, the binary mask 300 is generated by applying a threshold to the weight mask 200, and the threshold may be a value predetermined by the user.

The binary value of the binary mask 300 may be calculated by Equation 1 below.

[Equation 1]

Where Mw is the weight of the weighted mask, Mb is the binary value of the double mask, (x, y) is the position coordinate on the X-Y plane of the pixel, and τ is the threshold.

Referring to Equation 1, a pixel whose weight Mw is greater than or equal to the threshold τ is set to a binary value Mb, and a pixel whose weight Mw is less than a threshold τ is set to a binary value Mb of 0. Can be.

For example, the pixels included in the tooth candidate region may be set to the binary value Mb 1, and the pixels included in the remaining regions may be set to the binary value Mb 0.

In some cases, the pixels included in the tooth candidate region and the peripheral region may be set to the binary value Mb 1, and the pixels included in the remaining areas may be set to the binary value Mb 0.

Accordingly, the ROI extractor 150 may extract a region including the pixels having the binary value Mb as 1 as the dental ROI.

According to the method of extracting a region of interest of a tooth from a CT image according to an embodiment of the present invention, in registering a 3D CT image and a 3D oral scan image, a portion unnecessary for registration such as a neck bone included in the 3D CT image is automatically Since the tooth region is removed and the tooth region is automatically extracted as the region of interest on the 3D CT image, the accuracy of registration can be improved and the processing time can be shortened at the time of image registration.

Meanwhile, the method of extracting a region of interest from a 3D CT image according to an embodiment of the present invention may be implemented by storing computer readable codes in a computer readable storage medium. The computer readable storage medium includes all kinds of storage devices for storing data that can be read by a computer system.

The computer readable code is configured to perform the steps of the automatic alignment method of the three-dimensional external shape image of the oral cavity according to the embodiment of the present invention when read and executed by the processor from the computer readable storage medium. The computer readable code may be implemented in various programming languages. And the functional program, code and code segments for implementing the embodiments of the present invention can be easily programmed by those skilled in the art.

Examples of computer readable storage media include ROM, RAM, CD-ROM, magnetic tape, floppy disks, optical data storage devices, and the like. The computer readable storage medium can also be distributed over network coupled computer systems so that the computer readable code is stored and executed in a distributed fashion.

As mentioned above, although embodiment of this invention was described, those of ordinary skill in the art should add, change, delete, add, etc. the component within the range which does not deviate from the idea of this invention described in the claim. It is to be understood that the present invention may be modified and changed in various ways, which are also included within the scope of the present invention.

110: average map generation unit
120: weighted mask generator
130: candidate region extraction unit
140: binary mask generator
150: region of interest extraction unit

Claims (10)

Calculating an average HU value by averaging HU values for each pixel included in a plurality of CT images, and generating an average map in which the average HU values are mapped to each pixel;
Generating a weighting mask in which weights are set for each region;
Extracting a tooth candidate region having a maximum weighted sum obtained by adding the product of the average HU value and the weight while moving the weighted mask on the average map;
Generating a binary mask to which a threshold is applied to the weighting mask; And
Extracting a region of interest of a tooth by applying the binary mask to the tooth candidate region;
Method of extracting the region of interest from the CT image comprising a.
The method of claim 1,
The weighting mask and the binary mask is characterized in that the horseshoe type
Method of extracting tooth region of interest from CT images.
The method of claim 2,
In the step of generating the weighted mask
As the weighting mask is closer to the center of the horseshoe type, a larger weight is set.
Method of extracting tooth region of interest from CT images.
The method of claim 2,
In the step of generating the weighted mask
The weighting mask has a greater weight at the bottom than the top of the horseshoe type.
Method of extracting tooth region of interest from CT images.
The method of claim 1,
In generating the binary mask
Pixels whose weight is greater than or equal to the threshold are set to binary value 1, and pixels whose weight are less than the threshold are set to binary value 0.
Method of extracting tooth region of interest from CT images.
The method of claim 5, wherein
Extracting the tooth region of interest
Extracting an area including the pixels having the binary value of 1 into the tooth region of interest;
Method of extracting tooth region of interest from CT images.
The method of claim 1,
In generating the binary mask
Pixels included in the tooth candidate region are set to binary value 1, and pixels included in the remaining region are set to binary value 0.
Method of extracting tooth region of interest from CT images.
The method of claim 1,
In generating the binary mask
Pixels included in the tooth candidate region and its peripheral region are set to binary value 1, and pixels included in the remaining region are set to binary value 0.
Method of extracting tooth region of interest from CT images.
An average map generator for calculating an average HU value by averaging HU values for each pixel included in a plurality of CT images, and generating an average map in which the average HU values are mapped to each pixel;
A weighted mask generator configured to generate a weighted mask in which weights are set for each region;
A candidate region extracting unit extracting a tooth candidate region having a maximum weighted sum obtained by adding the product of the average HU value and the weight while moving the weight mask on the average map;
A binary mask generator configured to generate a binary mask to which a threshold is applied to the weighted mask; And
A region of interest extractor which extracts a region of interest of a tooth by applying the binary mask to the tooth candidate region.
Device for extracting the region of interest from the CT image comprising a.
The method of claim 9,
The weighting mask and the binary mask is characterized in that the horseshoe type
Device for extracting tooth region of interest from CT images.

Images