KR102471937B1 - Method for Determining the Likelihood of Dental Caries Using an X-ray Image - Google Patents

Abstract

A method for determining the possibility of dental caries using an X-ray image is disclosed. The disclosed method includes generating a tooth image by separating a region representing a tooth from an X-ray image, generating a segmented image by performing image segmentation on the tooth image, and different characteristics of a normal tooth in the segmented image. Including the step of examining whether there is a region of a feature, and determining that a tooth corresponding to the tooth image has a possibility of caries when it is determined that there is a region of a feature different from that of a normal tooth in the segmented image. can do.

Description

Method for determining the likelihood of dental caries using an X-ray image {Method for Determining the Likelihood of Dental Caries Using an X-ray Image}

The present invention relates to X-ray medical image processing, and more particularly, to a technique for determining the possibility of dental caries by analyzing an X-ray image of a tooth.

Dental X-ray images are widely used for dental diagnosis and treatment. There are various uses of dental X-ray images, one of which is to detect dental caries at an early stage. It is possible to detect dental caries at an early stage and treat it effectively by visually inspecting dental X-ray images to identify areas expected to be caries. However, inspection of X-ray images by the naked eye has limitations. Identification can be difficult if the size of the caries is small or if the lesion is outside the area of interest. For this reason, research on techniques for automatically detecting areas with a high possibility of dental caries in dental X-ray images is being conducted, but remarkable results have not yet been achieved.

An object of the present invention is dental caries using X-ray images, which is of little interest in dental X-ray images, but automatically detects caries-expected areas and / or small caries-expected areas so that caries can be more accurately and easily diagnosed. It is to provide a possibility determination method and apparatus.

The problems to be solved by the present invention are not limited to the above-mentioned problems, and other problems not mentioned will be clearly understood by those skilled in the art from the following description.

According to embodiments of the present invention, an apparatus for determining the likelihood of dental caries is provided. The apparatus includes an image segmentation unit configured to generate segmented images by performing image segmentation on an X-ray tooth image, and examining whether there are regions of characteristics different from those of normal teeth in the segmented image. , It may include a tooth caries possibility determination unit configured to determine whether there is a possibility of caries in the tooth corresponding to the X-ray tooth image.

In one embodiment, the dental caries possibility determination unit may be further configured to examine whether there are two or more regions separated from each other, having a representative luminance value belonging to a range of luminance values representing tooth enamel in the divided image. have.

In an embodiment, the representative luminance value may be an average luminance value.

In one embodiment, the tooth caries possibility determination unit may be further configured to examine whether the left and right features of the divided image are asymmetrical.

In one embodiment, the dental caries possibility determination unit is further configured to generate projection data in a vertical direction of the divided image, and to examine whether there is a difference between left and right profiles of the projection data. can

In one embodiment, the dental caries possibility determination unit, when it is determined that there are two or more areas separated from each other, may be further configured to determine an area between the two or more areas separated from each other as a dental caries expected area. have.

In one embodiment, the dental caries possibility determination unit, when it is determined that there is a difference between the left and right profiles of the projection data, the area of the X-ray tooth image corresponding to the lower profile of the left and right profiles is a dental caries expected area. It can be further configured to determine.

According to embodiments of the present invention, a method for determining the possibility of dental caries using an X-ray image is provided. The method includes the steps of generating a tooth image by separating a region representing a tooth from an X-ray image, performing image segmentation on the tooth image to generate a segmented image, and the segmented image having different characteristics from normal teeth. Including the step of examining whether there is a region of a feature, and determining that a tooth corresponding to the tooth image has a possibility of caries when it is determined that there is a region of a feature different from that of a normal tooth in the segmented image. can do.

In one embodiment, the step of examining whether there is a region of a characteristic different from a characteristic of a normal tooth in the divided image may include a representative luminance value belonging to a range of luminance values representing tooth enamel in the divided image. It may include checking whether there are two or more separated regions.

In an embodiment, the representative luminance value may be an average luminance value.

In one embodiment, the step of examining whether there is a region having a characteristic different from a characteristic of a normal tooth in the divided image may include examining whether left and right features of the divided image are asymmetrical.

In one embodiment, the step of checking whether the left and right characteristics of the divided image are asymmetrical includes generating projection data in a vertical direction of the divided image and examining whether there is a difference between the left and right profiles of the projection data. steps may be included.

In one embodiment, when it is determined that there is a region of characteristics different from the characteristics of normal teeth in the divided image, determining that there is a possibility of caries in the tooth corresponding to the tooth image is the tooth in the divided image. When it is determined that there are two or more areas separated from each other having representative luminance values belonging to the range of luminance values representing enamel, determining the area between the two or more areas separated from each other as a dental caries expected area. can include

In one embodiment, when it is determined that there is a region of characteristics different from the characteristics of normal teeth in the divided image, the step of determining that there is a possibility of caries in the tooth corresponding to the tooth image, the left and right profiles of the projection data When it is determined that there is a difference between the left and right profiles, the method may include determining an area of the tooth image corresponding to a lower profile of the left and right profiles as a dental caries expected area.

In an embodiment, the image segmentation may be image segmentation using a luminance value as a similarity measure.

According to the embodiments of the present invention, there is a technical effect that caries can be diagnosed more accurately and easily by automatically detecting a caries-expected area and / or a small caries-expected area of little interest in a dental X-ray image. .

1 is a diagram showing an embodiment of a device for determining the possibility of dental caries according to the present invention.
Figure 2 is a diagram showing one embodiment of a flow chart for explaining a method for determining the possibility of dental caries using an X-ray image according to the present invention.
3 is a diagram for illustrating one tooth region to be separated from an X-ray image according to an embodiment of the present invention.
4 is a diagram for illustrating one tooth region to be separated from an X-ray image according to an embodiment of the present invention.
FIG. 5 is a diagram illustrating a segmented image generated by performing image segmentation on a region representing one tooth indicated in FIG. 3 according to an embodiment of the present invention.
FIG. 6 is a diagram illustrating a segmented image generated by performing image segmentation on a region representing one tooth indicated in FIG. 4 according to an embodiment of the present invention.

The advantages and features of the present invention and how to achieve them will become clear with reference to the detailed description of the following embodiments in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but will be implemented in a variety of different forms, and these embodiments merely make the disclosure of the present invention complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully inform the person of the scope of the invention, and the invention is defined only by the scope of the claims.

Terms used in this specification are only used to describe specific embodiments and are not intended to limit the present invention. For example, a component expressed in the singular number should be understood as a concept including a plurality of components unless the context clearly means only the singular number. In addition, in the specification of the present invention, terms such as 'include' or 'have' are only intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, and these Use of the term does not exclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof. Also, in the embodiments described in this specification, 'module' or 'unit' may mean a functional part that performs at least one function or operation.

In addition, unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and interpreted in an ideal or excessively formal meaning unless explicitly defined in the specification of the present invention. It doesn't work.

Hereinafter, embodiments of the present invention will be described in more detail with reference to the accompanying drawings. However, in the following description, if there is a risk of unnecessarily obscuring the gist of the present invention, detailed descriptions of well-known functions or configurations will be omitted.

1 is a diagram showing an embodiment of a device for determining the possibility of dental caries according to the present invention.

As shown in FIG. 1 , the device 100 may include an input interface 110 , an image processing unit 120 , a storage unit 130 and a display unit 140 . The input interface 110 may include hardware and software modules for inputting user commands to perform image processing according to various embodiments of the present disclosure. The input interface 110 inputs various necessary commands to the image processing unit 120 or uses X-rays to obtain an X-ray image, an X-ray panoramic image, an X-ray CT image, etc. obtained from an I/O (Intra Oral) imaging device. It can be advantageously used to input an X-ray image of the storage unit 130 or to indicate a part or all of a displayed image to perform various image processing accordingly. In one embodiment, the input interface 110 may include a keyboard, keypad, touchpad, mouse, etc. of a computer, but the type of input interface is not limited thereto. . For example, the input interface 110 may include a graphical user interface controllable using the aforementioned input devices. The display unit 140 is for displaying images formed according to various embodiments of the present invention, and may include various display devices such as an LCD display, an LED display, an AMOLED display, and a CRT display.

The storage unit 130 may be used to store X-ray images such as an X-ray image, an X-ray panoramic image, and an X-ray CT image acquired by an intra-oral (I/O) imaging device using X-rays. The storage unit 130 stores image data of intermediate results resulting from image processing according to various embodiments of the present invention, resultant image data obtained by performing image processing according to various embodiments of the present invention, and It may be used to store variable values required to perform image processing according to various embodiments. The storage unit 130 may further store software/firmware necessary for implementing the image processing unit 120 . The storage unit 130 may be a flash memory type, a hard disk type, a MultiMedia Card (MMC), or a card-type memory (eg, a Secure Digital (SD) card or an XD card). (eXtream Digital) card, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory) , it may be implemented as any one storage medium of a magnetic memory, a magnetic disk, and an optical disk, but those skilled in the art will recognize that the implementation form of the storage unit 130 is not limited thereto.

The image processing unit 120 will be configured to read all or part of the X-ray image data from the storage unit 130 and perform a method of determining the possibility of dental caries using an X-ray image according to various embodiments of the present invention. can As shown in FIG. 1 , the image processing unit 120 may include an image segmentation unit 122 and a dental caries possibility determination unit 124 . The image segmentation unit 122 may be configured to generate segmented images by performing image segmentation on the X-ray tooth image. In one embodiment, the image segmentation unit 122 may use clustering methods, compression-based methods, histogram-based methods, edge detection methods, and region growth. It may be configured to perform image segmentation using an image segmentation technique such as region-growing methods. Dental caries possibility determination unit 124 may be configured to determine whether there is a possibility of caries in the tooth corresponding to the X-ray tooth image by examining whether there is a region of characteristics different from the characteristics of normal teeth in the divided image. . In one embodiment, the dental caries possibility determination unit 124 is further configured to examine whether there are two or more regions separated from each other, each having a representative luminance value belonging to a range of luminance values representing tooth enamel in the segmented image. can In one embodiment, the dental caries possibility determination unit 124 generates projection data in the vertical direction of the divided images, and further examines whether there is a difference between the left and right profiles of the generated projection data. can be configured. In one embodiment, the dental caries possibility determination unit 124 counts the number of regions having the same / similar representative luminance value for each of the left and right regions of the tooth in the divided image, and the left and right regions are selected in terms of the counted number It may be further configured to check whether the difference is greater than or equal to a threshold value.

The image processing unit 120, in terms of hardware, includes Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), programmable At least one of Programmable Logic Devices (PLDs), Field-Programmable Gate Arrays (FPGAs), processors, controllers, micro-controllers, and microprocessors It can be implemented using one. The image processing unit 120 may also be implemented as a firmware/software module executable on the aforementioned hardware platform. In this case, the firmware/software module may be implemented by one or more software applications written in an appropriate program language.

Figure 2 is a diagram showing one embodiment of a flow chart for explaining a method for determining the possibility of dental caries using an X-ray image according to the present invention. 3 and 4 are views for illustrating one tooth region to be separated from an X-ray image according to an embodiment of the present invention. 5 and 6 are diagrams respectively illustrating divided images generated by performing image segmentation on a region representing one tooth indicated in FIGS. 3 and 4 according to an embodiment of the present invention.

One embodiment of the method for determining the possibility of dental caries according to the present invention starts from step S210 of generating a tooth image by separating a region representing a tooth from an X-ray image. In one embodiment, it is possible to detect boundaries between teeth in an X-ray image and separately separate a region representing one tooth based on the detected boundaries (reference numerals 330 and 430 in FIGS. 3 and 4). ), see the area indicated by). In step S220, segmented images may be generated by performing image segmentation on the tooth image by the image segmentation unit 122. Image segmentation is a technique that divides an image into a plurality of segments/clusters. Pixels with the same characteristics are divided into the same segment/cluster based on similarity measures such as color, luminance, and texture. It is known as a process of clustering pixels with the same characteristics by assigning them to clusters. In an embodiment, image segmentation may be performed using luminance as a similarity measure. Segmented images generated by performing image segmentation on the regions 330 and 430 representing one tooth indicated in FIGS. 3 and 4 are shown in FIGS. 5 and 6 , respectively.

In step S230, the dental caries possibility determination unit 124 may examine whether there is a region having characteristics different from the characteristics of normal teeth in the segmented image. In one embodiment, as the area having characteristics different from those of normal teeth, an area between two or more enamel areas separated from each other or a portion of one left and right area of a tooth having different left and right characteristics, that is, an asymmetrical tooth, may be used. However, it should be recognized that the region of characteristics different from those of normal teeth is not limited thereto.

In order to examine whether there are two or more enamel regions separated from each other in the divided image, whether there are two or more regions separated from each other having a representative luminance value belonging to a range of luminance values representing tooth enamel in the divided image can be inspected In one embodiment, the representative luminance value may be an average luminance value. Referring to FIG. 5 , it can be observed that both regions 550 and 570 have bright luminance values representing tooth enamel and are separated from each other. Accordingly, it can be seen that region 550 and region 570 correspond to two enamel regions separated from each other.

In order to examine whether the left and right features of the divided image are asymmetrical, the dental caries possibility determination unit 124 generates, for example, projection data in the vertical direction of the divided image, and left and right profiles of the projection data. ) can be checked for differences. Referring to FIG. 6 , since the right area 650 has a lower luminance value than the corresponding left area, the projection data profile near the area 650 will be expressed with lower values than the corresponding left projection data profile. In another embodiment, the dental caries possibility determination unit 124 counts the number of regions having the same / similar representative luminance value for each of the left and right regions of the tooth in the divided image, and the left and right regions are selected in terms of the counted number It can be checked whether there is a difference greater than or equal to a threshold value. Referring to FIG. 6 , assuming that the right region 650 has a representative luminance value of A, the number of regions having a luminance value of A will be significantly greater in the right region of the tooth than in the left region of the tooth. As such, it is possible to check whether the left and right features of the divided image are asymmetrical by various techniques, but it should be recognized that such a check does not have to be performed using only the techniques described above.

In step S230, when regions having characteristics different from those of normal teeth are found in the segmented image, it may be determined in step S240 that the tooth corresponding to the tooth image has a possibility of caries. In one embodiment, when it is confirmed that there are two or more enamel regions separated from each other in the divided image, a region between the two or more separated enamel regions may be determined as a dental caries expected region. In one embodiment, when it is confirmed that the left and right characteristics of the divided image are asymmetric, a region of the tooth image corresponding to a lower profile among the left and right profiles of the projection data may be determined as a dental caries expected region. In step S250, a warning message including information about the position of the dental caries expected region determined in step S240 may be displayed on the display unit 140.

In the embodiments disclosed herein, the arrangement of the illustrated components may vary depending on the environment or requirements in which the invention is implemented. For example, some components may be omitted or some components may be integrated and implemented as one. In addition, the arrangement order and connection of some components may be changed.

Although various embodiments of the present invention have been shown and described above, the present invention is not limited to the specific embodiments described above, and the above-described embodiments go beyond the scope of the present invention claimed in the appended claims. Without this, various modifications can be carried out by those skilled in the art to which the present invention pertains, and these modified embodiments should not be understood separately from the technical spirit or scope of the present invention. Therefore, the technical scope of the present invention should be defined only by the appended claims.

110: input interface
120: image processing unit
122: video segmentation unit
124: dental caries possibility determination unit
130: storage unit
140: display unit
330, 430, 550, 570, 650: area of the image

Claims (15)

delete delete delete delete delete delete delete As a method for determining the possibility of dental caries using an X-ray image,
Generating an X-ray image of an individual tooth by performing image segmentation on an X-ray tooth image of at least one tooth;
Examining whether there are two or more regions separated from each other having an average luminance value representing normal tooth enamel in the X-ray image of the individual tooth; and
When there are two or more regions separated from each other in the X-ray image of the individual tooth, determining that the tooth corresponding to the X-ray image of the individual tooth has a possibility of caries. delete delete According to claim 8,
The step of determining that there is a possibility of caries, comprising the step of determining the area between the two or more areas separated from each other as a dental caries expected area, dental caries possibility determination method. As a method for determining the possibility of dental caries using an X-ray image,
Generating an X-ray image of an individual tooth by performing image segmentation on an X-ray tooth image of at least one tooth;
generating projection data in the vertical direction of the X-ray image of the individual teeth;
checking whether there is a difference between the left and right profiles of the projection data; and
When there is a difference between the left and right profiles of the projection data, determining that there is a possibility of caries in the tooth corresponding to the X-ray image of the individual tooth. delete According to claim 12,
The step of determining that there is a possibility of caries includes determining a region corresponding to a lower profile of the left and right profiles as a dental caries expected region. As a method for determining the possibility of dental caries using an X-ray image,
Generating an X-ray image of an individual tooth by performing image segmentation on an X-ray tooth image of at least one tooth;
Examining whether there is a region having characteristics different from those of normal teeth in the X-ray image of the individual tooth; and
When it is determined that there is a region of characteristics different from the characteristics of normal teeth in the X-ray image of the individual tooth, determining that the tooth corresponding to the X-ray image of the individual tooth has a possibility of caries,
The image segmentation is an image segmentation using a luminance value as a similarity scale, a method for determining the possibility of dental caries.

Images