KR102155745B1 - Method and apparatus for fmx automatic construction - Google Patents

Abstract

A technology that automatically generates data of FMX (Full Mouth Series) is provided through analysis of a multi-layer tooth panorama image. The FMX automatic generation method according to an embodiment of the present invention automatically generates a representative image for each area according to the definition of FMX according to a predetermined quality criterion. The representative image may be an image of a layer having the best evaluation result according to the quality criterion among a plurality of layers of the region.

Description

FMX automatic generation method and its device {METHOD AND APPARATUS FOR FMX AUTOMATIC CONSTRUCTION}

The present invention relates to a method and apparatus for automatically generating FMX. In more detail, the present invention relates to a method and apparatus for automatically generating FMX (Full Mouth Series) through cropping of an image of a partial region in a tooth panoramic image.

FMX (Full Mouth Series) is a set of intraoral radiographic images that enable efficient placement of dental radiographic images to effectively obtain information necessary for clinical judgment. FMX is also expressed in other abbreviations such as FMS and CMRS (Complete Mouth Radiographic Series). In general, the FMX consists of a total of 18 photos including 14 periapical view images and 4 bitewing view images (FMX-18). However, the type of FMX-20, FMX-16, or FMX-14 is also used depending on the number of periapical view images, or the presence or absence of bite wing views and the number. Each view provides a view of a predefined group of teeth.

In order to compose the FMX from the tooth panorama image, there is an inconvenience of capturing an image with the highest quality among images of an area corresponding to each view and directly inputting information about the image. In particular, if an FMX is generated by using a multi-layer tooth panorama image including image data for each of a plurality of layers on an arch plane, there is a burden of finding the best quality layer for each region. For example, in the case of a layered tooth panorama image having 40 layers, an image must be captured for a total of 18 areas, so a total of 720 times (18x40) must be checked.

US Patent No. 8447378

The technical problem to be solved by the present invention is to provide a method and apparatus for automatically generating an optimal FMX from a multi-layer tooth panoramic image.

Another technical problem to be solved by the present invention is to provide a method and apparatus for generating an FMX including an optimal representative image and a clinically meaningful image for each region of interest.

Another technical problem to be solved by the present invention is to add information that can intuitively sense the anterior/posterior position of the optimal representative image and clinically meaningful image on the arch surface for each region of interest. It is to provide a method and apparatus for generating an FMX further including information.

Another technical problem to be solved by the present invention is to provide a method and apparatus for automatically selecting and outputting an optimal type of FMX that can be generated from a multi-layered tooth panorama image among a plurality of types of FMX.

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

An implant simulation method according to an embodiment of the present invention for solving the above technical problem includes the steps of obtaining a multi-layer tooth panorama image including image data for each layer on the arch surface, and according to a predetermined quality criterion, Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the layer tooth panorama image, and the image of a first view corresponding to the first region of interest. And automatically generating an FMX (Full Mouth Series) in which the representative image of the first region of interest is set.

In an embodiment, the automatically selecting the representative image includes selecting the representative image based on the sharpness of each of the images of a plurality of layers of the first region of interest.

In one embodiment, the step of automatically generating the FMX includes automatically generating an FMX including layer identification information of the representative image.

In an embodiment, the automatically selecting the representative image of the first region of interest is performed according to the predetermined quality criterion, the second region of interest among the images of a plurality of layers of the second region of interest of the multi-layer tooth panorama image. Including the step of selecting as the representative image of the region, and the step of automatically generating the FMX generates the FMX in which the representative image of the second region of interest is set as an image of a second view corresponding to the second region of interest It may include the step of. In this case, the representative image of the first region of interest and the representative image of the second region of interest are obtained from different layers.

In an embodiment, the selecting of the representative image further selects a clinical reference image in which a difference value according to a predetermined criterion with the representative image exceeds a reference value from among images of a plurality of layers of the first region of interest And generating the FMX automatically comprises generating an FMX in which the representative image and the clinical reference image are set as the image of the first view. In this case, the default image of the first view may be the representative image, and the clinical reference image may be displayed auxiliary in response to a predetermined user input. In addition, the step of further selecting the clinical reference image includes selecting an image having a different number of roots than the representative image among images of a plurality of layers of the first region of interest as the clinical reference image. can do. In this case, the step of selecting an image having a different number of roots and the representative image as the clinical reference image may include, based on sharpness, some of the plurality of images having a different number of roots and the representative image as the clinical reference image. It may include the step of selecting. In addition, the step of further selecting the clinical reference image may include selecting, as the clinical reference image, an image in which the representative image and the root length are different from the reference value among images of a plurality of layers of the first region of interest. I can.

In one embodiment, the obtaining of the multi-layer tooth panoramic image includes obtaining a tooth outline by applying tooth segmentation to the multi-layer tooth panoramic image, and the FMX type based on the tooth outline. It may include the step of partitioning the first region of interest defined by. In this case, the first region of interest is a region including a plurality of teeth corresponding to the first view, and the step of partitioning the first region of interest defined by the type of the FMX corresponds to the first view. A step of forming an outline of the first region of interest by merging a square formed by the tooth outline of each of the plurality of teeth.

In one embodiment, the FMX automatic generation method includes repeating the steps of automatically generating the representative image and automatically generating the FMX while changing the type of the FMX, and each FMX generated for each FMX type. It may further include scoring, determining a type of an output target FMX based on a score for each FMX according to the scoring, and outputting the determined type of FMX. In this case, scoring each FMX generated for each FMX type may include scoring each FMX using a concentration of a layer distribution of a representative image for each view included in the FMX.

An FMX automatic generation device according to another embodiment of the present invention includes a network interface for receiving data of a multi-layer tooth panorama image including image data for each layer on the arch surface, and a storage for storing software for automatically generating an FMX template. And, a memory in which a plurality of instructions is loaded according to the execution of the software, and a processor that executes the plurality of instructions. In this case, the plurality of instructions include an instruction for automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion, and the An instruction for automatically generating an FMX (Full Mouth Series) in which a representative image of the first ROI is set as an image of a first view corresponding to the first ROI may be included.

An FMX automatic generation computer program according to another embodiment of the present invention, in combination with a computing device, obtains a multi-layered tooth panoramic image including image data for each layer on the arch surface, and according to a predetermined quality standard, Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image, and an image of a first view corresponding to the first region of interest As a result, the representative image of the first region of interest may be recorded on a computer-readable recording medium so that the step of automatically generating the FMX (Full Mouth Series) set is executed.

1 is a block diagram of an automatic FMX generation system according to an embodiment of the present invention.
2 is a conceptual diagram illustrating a multi-layer tooth panorama image that can be referred to in some embodiments of the present invention.
3 is a flowchart of a method for automatically generating FMX according to another embodiment of the present invention.
4 and 5 are conceptual diagrams for explaining tooth segmentation that can be performed in some embodiments of the present invention and FMX region-of-interest partition based on the tooth segmentation.
6A and 6B are diagrams for explaining an FMX automatically generated in some embodiments of the present invention.
7 is a diagram illustrating a method for checking a clinical reference image in an FMX automatically generated in some embodiments of the present invention.
FIG. 8 is a flowchart illustrating in detail some operations of the method described with reference to FIG. 3.
9 is a conceptual diagram illustrating selection of a clinical reference image based on the number of roots in some embodiments of the present invention.
10 is a flowchart illustrating an exemplary embodiment in which the method described with reference to FIG. 3 is partially modified.
11 is a hardware configuration diagram of an automatic FMX generation apparatus according to another embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Advantages and features of the present invention, and a method of achieving them will become apparent with reference to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments to be posted below, but may be implemented in a variety of different forms, and only these embodiments make the posting of the present invention complete, and common knowledge in the technical field to which the present invention pertains. It is provided to completely inform the scope of the invention to those who have it, and the invention is only defined by the scope of the claims. The same reference numerals refer to the same components throughout the specification.

Unless otherwise defined, all terms (including technical and scientific terms) used in the present specification may be used as meanings that can be commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in a commonly used dictionary are not interpreted ideally or excessively unless explicitly defined specifically. The terms used in the present specification are for describing exemplary embodiments and are not intended to limit the present invention. In this specification, the singular form also includes the plural form unless specifically stated in the phrase. Hereinafter, some embodiments of the present invention will be described with reference to the drawings.

In the present specification, FMX (Full Mouth Series) may be understood to mean a set of intraoral radiographic images in which tooth images of a plurality of predetermined views are arranged. Each of the plurality of views is pre-matched to one or more teeth. For information on the definition of FMX and the like, refer to documents such as the web document'https://en.wikipedia.org/wiki/Dental_radiography'. It should be understood that the FMX of the present specification extends not only to the widely used FMX type, but also to the modification of the number of views and the arrangement of each view within a range that can achieve the purpose of FMX in the widely used FMX type. .

Referring to Figure 1, the configuration and operation of the automatic FMX generation system according to an embodiment of the present invention will be described. The automatic FMX generation system according to the present embodiment includes a photographing device 20 and an automatic FMX generation device 100.

The photographing device 20 is a device that generates image data for determining the patient's tooth arrangement, and may be, for example, a tooth panorama image photographing device. In particular, the photographing apparatus 20 may be a device that generates data of a multi-layer tooth panorama image.

The multi-layer tooth panoramic image will be described with reference to FIG. 2. The multi-layered tooth panorama image is composed of a plurality of layered images focused on a plurality of layers (1, 2, 3, 4) virtually formed on an arch plane. The plurality of layers (1, 2, 3, 4) are arranged in parallel in a row on the arch surface, but are arranged so that the position of the anterior or the posterior is different. As a result, the multi-layered tooth panorama image includes a plurality of multi-layered images having different depths when viewed from an anterior to a posterior with respect to the arch surface. This means that although the multi-layered tooth panoramic image is a 2D panoramic image, it partially functions as a 3D image.

The automatic FMX generation device 100 receives the data of the multi-layer tooth panorama image from the photographing device 20, and according to a predetermined quality criterion, among images of a plurality of layers of the first ROI of the multi-layer tooth panorama image A representative image is automatically selected, and an FMX in which the representative image of the first region of interest is set as the image corresponding to the first region of interest is automatically generated. The quality criterion may refer to a model that calculates a quality value based on one or more image quality evaluation factors such as sharpness. The first region of interest may be understood as a region including a tooth or a tooth group corresponding to the first view of the FMX.

The automatic FMX generation apparatus 100 may further set a clinical reference image for the first region of interest. The clinical reference image is obtained in a layer different from the representative image as a difference value according to a predetermined criterion with the representative image exceeds a reference value. For example, in the clinical reference image, the representative image and the number of roots are different from each other, or the length of the root is greater than or equal to the reference value, and the tooth morphological shape of the crown is different from the reference value. Since the image is significantly different from the representative image, it may be understood as indicating an image that needs to be referenced together with the representative image. The predetermined criteria for selecting a clinical reference image will be described in detail later.

The FMX is composed of a plurality of view images, and at least some of the view images may be obtained from different layers. That is, the representative image of the first ROI corresponding to the first view may be obtained from the first layer, and the representative image of the second ROI corresponding to the second view may be obtained from the second layer. Since the FMX generated by the FMX automatic generating device 100 according to the present embodiment is composed of a representative image obtained from an optimal layer for each region of interest, it is effective in identifying the patient's condition, and is more effective than an FMX manually created by a person. Its quality is good. A method of automatically generating FMX performed by the automatic FMX generating device 100 will be described in more detail with reference to FIGS. 3 to 10.

The automatic FMX generation device 100 may transmit the generated FMX to an external server such as the insurance company server 20. The generated FMX may be transmitted together with patient identification information. In addition, the FMX automatic generation device 100 may inquire about the type of FMX requested to the insurance company server 20 in advance before generating the FMX, and automatically generate an FMX having the FMX type received in response to the inquiry. There will be.

The implant simulation system according to the present embodiment is not implemented only with the device configuration shown in FIG. 2, but if necessary, a plurality of devices of FIG. 2 are combined into one physical device and provided, or conversely, each device of FIG. It could also be implemented by dividing it into physical devices. For example, the photographing device 20 and the automatic FMX generation device 100 may be implemented as one device. That is, the photographing apparatus 20 may be provided with a function of outputting a multi-layer tooth panorama image and the FMX together. In addition, for example, the automatic FMX generation device 100 and the insurance company server 20 may be implemented as one device. That is, the insurance company server 20 may be provided with a module for automatically configuring the FMX by receiving a multi-layer dental panoramic image.

Next, an implant simulation method according to another embodiment of the present invention will be described with reference to FIG. 3. The method according to the present exemplary embodiment may be executed by a computing device or a multi-layer tooth panoramic image capturing device having a computing unit. For example, the method according to the present embodiment may be executed by the automatic FMX generation apparatus 100 described with reference to FIG. 1. Hereinafter, when the subject of each operation is omitted in the description of the present embodiment, it will be understood that it can be performed by the above-described apparatus. In addition, it goes without saying that in the method according to the present embodiment, the execution order of each operation may be changed within a range in which the execution order can be logically changed as necessary.

In step S100, a photographed image is obtained. It has already been described that the image may be, for example, a multi-layer tooth panorama image.

In step S102, the data of the multi-layer tooth panorama image is input to a tooth segmentation logic to obtain a tooth region partition line of the image. As a result of the tooth segmentation, a tooth region partition line 30 as shown in FIG. 4 may be formed. Regarding the tooth segmentation method, various documents such as "A Problem of Automatic Segmentation of Digital Dental Panoramic X-Ray Images for Forensic Human Identication", Robert Wanat, 2011, etc. may be referred. However, in the tooth segmentation, it is preferable to use an algorithm of a method of forming the tooth region partition line 30 so that the root side partition line is formed and the tooth region is closed in a box shape.

In step S104, a plurality of regions of interest are partitioned on the tooth panoramic image. Each ROI is a one-to-one correspondence with each view of the FMX, and is an area including a designated tooth of each view according to the FMX type.

The division of the region of interest may be performed based on the tooth region division line 30. As a result of the tooth segmentation, a tooth number corresponding to each tooth region may be identified. In addition, it has been described that each view of the FMX has a designated tooth. In this case, in most cases, each view of the FMX has a plurality of designated teeth. For example, when a specific view corresponds to two premolar teeth, a square formed by merging a square constituting a tooth outline of each of the two premolar teeth may be a region of interest corresponding to the specific view. FIG. 5 shows a result of forming a region of interest 40 corresponding to each view by merging squares formed by tooth outlines of a plurality of teeth corresponding to each view.

In step S106, one representative image is selected for each region of interest. The representative image is obtained from any one of a plurality of layers of images. The criterion for selecting the representative image is the quality of the image in which the entire region of interest is considered. The quality may be calculated based on one or more image quality evaluation factors such as sharpness.

The operation of selecting a representative image for each region of interest is repeated until a representative image is selected for all regions of interest (S108 and S110). In addition, the selection of the representative image is independently performed for each region of interest, and the result of selecting the representative image of one region of interest does not affect the result of selecting the representative image of the other region of interest. Accordingly, representative images can be obtained in different layers for each region of interest.

In step S112, an FMX in which a representative image for each region of interest is set is automatically generated. 6A shows an example 50 of the automatically generated FMX. The FMX includes a plurality of views 50-1. In one embodiment, the automatically generated FMX may include layer identification information of the representative image. 6A shows an example 50a of an FMX in which layer identification information is overlaid on a representative image of each view.

It is preferable that the layer identification information is provided so that an anterior/posterior position of the layer can be intuitively recognized. For example, the layer identification information may be a layer number. For example, layer numbers may be sequentially assigned in such a way that #1 is assigned to a layer positioned in the anterior and the layer number increases as the layer is positioned behind. In this case, the position of the front and rear of the representative image can be intuitively sensed through the layer number displayed overlaid on the representative image of the view. For example, since the representative image of the view 50a-1 is obtained from the #2 layer, it may be intuitively felt that the image is of the layer closest to the foremost.

In an embodiment, a plurality of images may be set in one view. That is, one representative image and one or more auxiliary images may be set in one view. In this specification, the'auxiliary image' will be referred to as a'clinical reference image'. The representative image must be set, but the clinical reference image is not necessarily set. In addition, the clinical reference image and the representative image are obtained from different layers due to their properties. Hereinafter, some embodiments related to the clinical reference image will be described with reference to FIGS. 7 and 8.

When a representative image and a clinical reference image are set in a specific view, the clinical reference image may be additionally displayed in response to a predetermined user input. As illustrated in FIG. 7, when a user input 60 such as a mouse scroll is applied to an area of the specific view while the representative image 51 is displayed in a specific view area of the screen on which the FMX is displayed, the specific Instead of the representative image, the clinical reference image 51a may be displayed in the view area. To this end, it is preferable that the FMX data generated in step S112 include a representative image for each view and one or more clinical reference images.

There may be a plurality of clinical reference images. In this case, when the first user input is applied while the representative image is displayed, the first clinical reference image is displayed, and when the second user input is applied in that state, the second clinical reference image is displayed. Interface) could be provided. For example, if the user input is a scroll operation using a mouse scroll button, a representative image, a first clinical reference image, and a second clinical reference image will be sequentially displayed on the screen as the scroll is continuously input in one direction. .

In an embodiment, in a state where the representative image is displayed, in order for the user to recognize that the clinical reference image additionally exists, an icon indicating whether the clinical reference image is present may be overlaid on the representative image.

As will be described later, if the layer number of the clinical reference image of the specific view and the layer number of the representative image are compared, the tooth state of the specific view may be more clearly sensed.

This will be described with reference to FIG. 8. The operation of selecting a representative image described with reference to FIG. 3 may include an operation of selecting a clinical reference image in addition to selecting the representative image. To this end, in step S160, a comparison between the representative image and images of other layers is performed according to a predetermined criterion. For example, the representative image 51 of FIG. 7 is obtained from layer #6, but the images of the remaining layers (#1 to #5, #7 to #40; when the total number of layers is 40) and the representative image The comparison is performed according to the predetermined criterion of (51). In addition, as a result of the comparison, if there is an image of the representative image and the remaining layers for which a difference value greater than or equal to the reference value is calculated (S162), the image is selected as a clinical reference image of the representative image.

In one embodiment, the clinical reference image may be limited to one unconditionally. In this case, even if a plurality of images having the difference value exceeding the reference value exist, an image of one layer having the largest difference value among them may be selected as the clinical reference image.

In another embodiment, the clinical reference images may be selected as many as the number of images exceeding a reference value.

Hereinafter, various embodiments of a comparison criterion between a representative image and other images will be described.

In an embodiment, the comparison criterion may be based on a shape of a tooth outline. The tooth outline may refer to the outline of the entire tooth including a crown and a root. This is because FMX aims to understand not only the crown exposed outside the gum, but also the state of the root inside the gum. The tooth outline may be obtained based on a change in pixel density.

The comparison criterion may be based on the number of roots that may be determined according to the shape of the tooth outline. The tooth root has a mesial root, a distal root, and a palatal root, or two or more of the mesial root, distal root and palatal root are overlapping. Can exist. Even if one root is seen in the representative image, the number of roots may be divided into two in a layer different from the representative image. It is difficult to properly convey information on the shape of these teeth using only representative images. Accordingly, in order to more accurately provide information on different tooth shapes according to layers, an image showing the number of roots different from the number of roots of the representative image may be selected as the clinical reference image.

9 shows that in the representative image 70 obtained in layer X, the number of tooth roots 71 is one, and the image of layer Y 80 is layer Y when the number of roots 81 and 82 of each tooth is two. An example in which the image 80 of is selected as a clinical reference image is shown. The number of tooth roots may be determined by various algorithms for analyzing the shape of the tooth outline.

Depending on the shape of the patient's teeth, there may be a plurality of images showing the number of roots different from the number of roots in the representative image. In this case, only a part of a plurality of images showing the number of roots different from the number of roots of the representative image may be selected as the clinical reference image. For example, only one image having the highest clarity among a plurality of images showing the number of roots different from the number of roots of the representative image may be selected as the clinical reference image. According to the present embodiment, it is possible to provide clinically necessary information through the minimum number of clinical reference images.

In one embodiment, one clinical reference image may be selected for each number of roots. For example, the representative image has one root per tooth, and if there is an image with two roots per tooth and an image with three roots per tooth in a different layer than the representative image, one root with two roots A clinical reference image and one clinical reference image with 3 roots may be selected. Accordingly, the most vivid representative image in the region of interest and another image of the anterior/posterior of the arch surface showing a different number of roots than the representative image may be included in the FMX.

Up to now, an embodiment in which the comparison criterion is based on the number of roots that can be determined according to the shape of the tooth outline has been described. According to the present embodiment, an effect of accurately grasping whether a target tooth of each view constituting the FMX has a normal apical root shape is provided. In addition, the location of the periapical lesion of a patient suspected of having apical apical disease can be prevented from being erroneously judged with only the representative image. In addition, for a patient suspected of periodontitis, it also provides an effect of preventing the location of periodontitis from being erroneously determined only with the representative image. In short, the FMX automatically generated according to this embodiment provides a clinical reference image showing a different root shape from the representative image even though the sharpest representative image is slightly inferior, so that a more accurate clinical judgment can be guided. do.

In another embodiment, the comparison criterion may be based on at least one of a shape and a location of a root canal. The shape of the root canal in the state where the nerve treatment has been completed is due to the artificial object (Gutta-percha) charged in the root canal position after the inflammation of the root canal has been removed according to endodontic treatment. The boundaries can be clearly grasped. For example, a contour of the root canal may be obtained based on the difference in brightness values of pixels, and an image in which at least one of the shape and position of the outline is different from the representative image by more than a reference value is different from the representative image. When present in the layer, the image may be selected as the clinical reference image. According to the present embodiment, there is an effect of providing clinical information meaningful for diagnosis and treatment after neurological treatment through FMX.

In another embodiment, an image in which the representative image and the root length differ by more than a reference value may be selected as the clinical reference image. The length of the root may be obtained through comparison of the tooth outline and the gingival bone boundary line. The gingival bone boundary line may be obtained by analyzing information such as a brightness value and a bone density value of each pixel included in the image of the region of interest. For example, the gingival bone boundary line may be obtained by connecting the center point of the gingival side of the closed curved surface formed between each tooth and between the gums.

In another embodiment, an image in which the representative image and the area of the inner tooth lesion differ by more than a reference value may be selected as the clinical reference image. The outline of the inner tooth lesion may be formed based on a brightness value of each pixel inside the tooth outline. For example, when the number of adjacent pixels whose brightness value is lower than the reference value is higher than the reference value, it may be determined that the corresponding pixels form a lesion inside the tooth.

In an embodiment, an FMX of a type most suitable for a multi-layer tooth panoramic image may be generated. The present embodiment will be described with reference to FIG. 10.

In steps S100 to S112, a specific type of FMX is automatically generated. Steps S100 to S112 have been described with reference to FIGS. 3 to 9. In this embodiment, steps S100 to S112 are repeatedly performed while changing the type of FMX (S114J and S116).

The type of FMX is FMX-18, which consists of a total of 18 photos including 14 periapical view and 4 bitewing view, 16 apical view and 4 bitewing view. The FMX-20 is composed of a total of 20 photos including the FMX-20, the FMX-16 is composed of a total of 16 photos including 14 apical view images and 2 bite wing view images, and the FMX- is composed of 14 apical view images. Types such as 14 are widely known. However, in the present invention, it has already been described that in addition to the widely known type of FMX, a modified type FMX in which at least part of the number of apical view images, the number of bite wing view images, and the order of each view arrangement may be considered. .

In step S118, quality is scored for each type of FMX generated. The FMX quality scoring may be performed based on at least one of a total score of sharpness of each view image and a concentration of layer distribution of a representative image for each view. In this case, the higher the concentration, the higher the scoring result. If a certain type of FMX has a different layer of the representative image for each view, that type of FMX is negative in terms of reliability, and there is a concern that the representative image for each view obtained from different layers may cause confusion about the tooth state information. Because there is.

In step S120, the FMX of the type selected based on the score according to the scoring is output. The output may mean that the FMX image is displayed, the FMX data is exported in the form of a file, but the FMX data is transmitted to an external device such as an insurance company server.

The methods according to the embodiments of the present invention described so far can be performed by executing a computer program implemented in computer-readable code. The computer program may be transmitted from a first electronic device to a second electronic device through a network such as the Internet and installed in the second electronic device, thereby being used in the second electronic device. The first electronic device and the second electronic device include all of a server device, a physical server belonging to a server pool for a cloud service, and a fixed electronic device such as a desktop PC.

Hereinafter, the configuration and operation of the automatic FMX generation apparatus 100 according to another embodiment of the present invention will be described with reference to FIG. 11. As shown in FIG. 11, the FMX automatic generation apparatus 100 according to the present embodiment includes a memory 103, a processor 102 that executes instructions loaded in the memory, a storage 104, and a network interface 105. Include.

The network interface 105 receives data of a multi-layer dental panoramic image from an external device such as a panoramic image capturing device. The received data is loaded 132 into the memory 103 so that FMX automatic generation using the received multi-layer tooth panorama image is performed.

In an embodiment, the automatic FMX generation device 100 may include a photographing device that generates data of the multi-layer tooth panorama image. Of course, it may be understood that the photographing device incorporates the automatic FMX generation device 100.

The storage 104 stores the binary 143, which is an executable file of FMX automatic generation software. The binary 143 is stored in the storage 104 at the time of manufacture of the FMX automatic generating device 100, or after the manufacture of the FMX automatic generating device 100, after the installation of an application program by a user, the storage 104 ) Can be stored.

The storage 104 may store the exported file 142 of the FMX generated as a result of the execution of the FMX automatic generation software.

The memory 103 may store FMX automatic generation instructions 133 that are loaded as the FMX automatic generation software is executed.

The FMX automatic generation instructions 133 include an instruction for automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality standard. , An instruction for further selecting a clinical reference image in which a difference value according to a predetermined criterion with the representative image exceeds a reference value among images of a plurality of layers of the first ROI, and a first corresponding to the first ROI. It may include at least one of an instruction for automatically generating an FMX in which the representative image of the first ROI is set as an image of one view, and an instruction for outputting the automatically generated FMX.

In the memory 103, the FMX data 132 generated according to the execution result of the FMX automatic generation instruction 133 is temporarily stored, and the FMX data 132 is recognized by the user through an output device such as a display (not shown). It may be displayed as information in a form that can be used.

The embodiments of the present invention have been described above with reference to the accompanying drawings, but those of ordinary skill in the art to which the present invention pertains can be implemented in other specific forms without changing the technical spirit or essential features. You can understand. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not limiting.

Claims (15)

In the method performed by the computing device,
Obtaining a multi-layered tooth panorama image including image data for each of a plurality of layers on the arch surface;
Obtaining a tooth outline by applying tooth segmentation to the multi-layer tooth panoramic image;
Partitioning a first region of interest defined by a type of FMX based on the tooth outline;
Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest according to a predetermined quality criterion; And
Including the step of automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest,
FMX automatic generation method. The method of claim 1,
The step of automatically selecting the representative image,
Including the step of selecting the representative image based on the sharpness of each of the images of the plurality of layers of the first region of interest,
FMX automatic generation method. In the method performed by the computing device,
Obtaining a multi-layered tooth panorama image including image data for each of a plurality of layers on the arch surface;
Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion; And
Including the step of automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest,
The step of automatically generating the FMX,
Including the step of automatically generating an FMX including the layer identification information of the representative image,
FMX automatic generation method. In the method performed by the computing device,
Obtaining a multi-layered tooth panorama image including image data for each of a plurality of layers on the arch surface;
Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion; And
Including the step of automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest,
Automatically selecting the representative image of the first region of interest,
In accordance with the predetermined quality criterion, selecting a representative image of the second region of interest from among images of a plurality of layers of the second region of interest of the multi-layer tooth panorama image,
The step of automatically generating the FMX,
Generating the FMX in which the representative image of the second region of interest is set as an image of a second view corresponding to the second region of interest,
The representative image of the first region of interest and the representative image of the second region of interest are obtained from different layers,
FMX automatic generation method. In the method performed by the computing device,
Obtaining a multi-layered tooth panorama image including image data for each of a plurality of layers on the arch surface;
Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion; And
Including the step of automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest,
The step of selecting the representative image,
Including the step of further selecting a clinical reference image from among images of a plurality of layers of the first region of interest in which a difference value according to a predetermined criterion with the representative image exceeds a reference value,
The step of automatically generating the FMX,
Including the step of generating an FMX in which the representative image and the clinical reference image are set as the image of the first view,
FMX automatic generation method. The method of claim 5,
The default image of the first view is the representative image, and the clinical reference image is additionally displayed in response to a predetermined user input,
FMX automatic generation method. The method of claim 5,
The step of further selecting the clinical reference image,
Including the step of selecting an image having a different number of roots than the representative image among images of a plurality of layers of the first region of interest as the clinical reference image,
FMX automatic generation method. The method of claim 7,
Selecting an image having a different number of roots than the representative image as the clinical reference image,
Including the step of selecting some of the plurality of images having different numbers of roots and the representative image as the clinical reference image based on the sharpness,
FMX automatic generation method. The method of claim 5,
The step of further selecting the clinical reference image,
Including the step of selecting an image from among images of a plurality of layers of the first region of interest, as the clinical reference image, an image having a length of the representative image and a tooth root different from a reference value or more,
FMX automatic generation method. delete The method of claim 1,
The first region of interest is a region including a plurality of teeth corresponding to the first view,
The step of partitioning the first ROI defined by the type of the FMX,
Comprising the step of forming an outline of the first region of interest by merging squares formed by tooth outlines of each of the plurality of teeth corresponding to the first view,
FMX automatic generation method. In the method performed by the computing device,
Obtaining a multi-layered tooth panorama image including image data for each of a plurality of layers on the arch surface;
Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion; And
Including the step of automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest,
Repeating the steps of automatically generating the representative image and automatically generating the FMX while changing the type of the FMX;
Scoring each FMX generated for each FMX type;
Determining a type of an output target FMX based on the score for each FMX according to the scoring; And
Further comprising the step of outputting the determined type of FMX,
FMX automatic generation method. The method of claim 12,
The step of scoring each FMX generated for each FMX type,
Including the step of scoring each FMX using the concentration of the layer distribution of the representative image for each view included in the FMX,
FMX automatic generation method. A network interface for receiving data of a multi-layered tooth panorama image including image data of a plurality of layers on the arch surface;
Storage for storing software for automatic generation of FMX templates;
A memory in which a plurality of instructions are loaded according to the execution of the software;
Including a processor that executes the plurality of instructions,
The plurality of instructions,
Instructions for automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion; And
Including an instruction for automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest,
FMX auto-generated device. Combined with a computing device,
Obtaining a multi-layered tooth panorama image including image data for each of a plurality of layers on the arch surface;
Obtaining a tooth outline by applying tooth segmentation to the multi-layer tooth panoramic image;
Partitioning a first region of interest defined by a type of FMX based on the tooth outline;
Automatically selecting a representative image of the first region of interest from among images of a plurality of layers of the first region of interest of the multi-layer tooth panorama image according to a predetermined quality criterion; And
The step of automatically generating an FMX (Full Mouth Series) in which a representative image of the first region of interest is set as an image of a first view corresponding to the first region of interest is executed,
FMX automatically generated computer program recorded on a computer-readable recording medium.

Images