Method for automatically segmenting inferior alveolar canal from three-dimensional volume data, and computer-readable recording medium in which program for executing same in computer is recorded

Abstract

A method for automatically segmenting an inferior alveolar canal from three-dimensional volume data comprises the steps of: determining a central feature point and both end feature points from three-dimensional volume data including an inferior alveolar canal; segmenting a central region of the inferior alveolar canal from the three-dimensional volume data on the basis of the central feature point; segmenting both end regions of the inferior alveolar canal from the three-dimensional volume data on the basis of the both end feature points; and reconstructing the inferior alveolar canal on the basis of the central region of the inferior alveolar canal and the both end regions of the inferior alveolar canal.

Description

A computer-readable recording medium having recorded thereon a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data and a program for executing the method on a computer.

[0001] The present invention relates to a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data and a computer-readable recording medium having recorded thereon a program for executing the same on a computer, and more particularly, to a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data, which is automatically performed through deep learning and can reduce the time and effort required for separating the inferior alveolar nerve canal from three-dimensional volume data, and a computer-readable recording medium having recorded thereon a program for executing the same on a computer.

[0002] 3D volume data refers to accumulated data of 3D image images (e.g., voxels) or 2D image images, such as CT (Computed Tomography), CBCT (Cone-Beam CT), and MRI (Magnetic Resonance Imaging). In dentistry, plastic surgery, etc., the 3D volume data is limited to the head and neck region and is utilized to diagnose and treat patients' maxillofacial and oral regions.

[0003] The inferior alveolar nerve canal, located within the mandible, is a large nerve branch responsible for sensation. Damage to the inferior alveolar nerve canal can lead to aftereffects such as paresthesia. Therefore, a three-dimensional analysis of the inferior alveolar nerve canal is necessary to establish diagnostic, treatment, and surgical plans for dental procedures such as wisdom tooth extraction, dental implant placement, and orthognathic surgery, or to compare pre- and post-operative results.

[0004] However, since the 3D volume data only has intensity information of a single channel, a process of segmenting the region or reconstructing the segmented data into a 3D model is required to analyze a specific region 3Dly. Since the inferior alveolar nerve canal exists inside the mandible, the location of the inferior alveolar nerve canal must be estimated through the cross-section of the mandible. In addition, metal materials such as maxillofacial surgery plates, metal dental prostheses, and orthodontic devices may cause metal artifacts in 3D volume data using X-rays (e.g., CT or CBCT). Therefore, it may be difficult to accurately separate the inferior alveolar nerve canal.

[0005] The purpose of the present invention is to provide a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data, which is performed automatically through deep learning, thereby reducing the time and effort required for separating the inferior alveolar nerve canal from three-dimensional volume data and improving accuracy.

[0006] Another object of the present invention is to provide a computer-readable recording medium having recorded thereon a program for executing a method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data on a computer.

[0007] According to one embodiment of the present invention, a method for automatically separating an inferior alveolar nerve canal from three-dimensional volume data includes the steps of determining a central feature point and end feature points in three-dimensional volume data including an inferior alveolar nerve canal, separating a central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point, separating end regions of the inferior alveolar nerve canal from the three-dimensional volume data based on the end feature points, and reconstructing the inferior alveolar nerve canal based on the central region of the inferior alveolar nerve canal and the end regions of the inferior alveolar nerve canal.

[0008] In one embodiment of the present invention, the three-dimensional volume data is input into a first artificial intelligence neural network, and the central feature point and the two end feature points can be determined from the first artificial intelligence neural network.

[0009] In one embodiment of the present invention, the central feature point may include at least three feature points.

[0010] In one embodiment of the present invention, the two-end feature points may include two feature points.

[0011] In one embodiment of the present invention, the step of separating the central region of the inferior alveolar nerve canal may include the step of generating a virtual curve based on the central feature point, the step of generating a cross-section for the central region of the inferior alveolar nerve canal based on the virtual curve, and the step of generating central separation data by separating the central region of the inferior alveolar nerve canal based on the cross-section for the central region of the inferior alveolar nerve canal.

[0012] In one embodiment of the present invention, the virtual curve may be a spline curve that passes directly through the central feature point.

[0013] In one embodiment of the present invention, the virtual curve may be a Bezier curve that does not directly pass through the central feature point.

[0014] In one embodiment of the present invention, the cross-section may be perpendicular to the virtual curve.

[0015] In one embodiment of the present invention, the cross-section may be a plane on which an intermediate cross-section plane perpendicular to the virtual curve is projected.

[0016] In one embodiment of the present invention, the cross-section may be parallel to the coronal plane.

[0017] In one embodiment of the present invention, the cross-section may be input into a second artificial intelligence neural network, and the central separation data may be generated from the second artificial intelligence neural network.

[0018] In one embodiment of the present invention, when the cross-section is one or more, the second artificial intelligence neural network may be a two-dimensional convolutional neural network.

[0019] In one embodiment of the present invention, when the cross-section is in the form of a stacked volume, the second artificial intelligence neural network may be a three-dimensional convolutional neural network.

[0020] In one embodiment of the present invention, the step of separating the two end regions of the inferior alveolar nerve canal may include the step of creating a region of interest based on the two end feature points, and the step of separating the two end regions of the inferior alveolar nerve canal in the region of interest to create two end separation data.

[0021] In one embodiment of the present invention, the region of interest is input to a third artificial intelligence neural network, and the two-end separation data can be generated from the third artificial intelligence neural network.

[0022] In one embodiment of the present invention, the two end regions of the inferior alveolar nerve canal may be regions including an anterior loop, and the central region of the inferior alveolar nerve canal may be a region excluding the region including the anterior loop.

[0023] In one embodiment of the present invention, the step of reconstructing the inferior alveolar nerve canal may include the step of mapping central separation data generated by separating the central region of the inferior alveolar nerve canal to the three-dimensional volume data, and the step of generating inferior alveolar nerve canal separation data by combining the mapped central separation data and end separation data generated by separating the end regions of the inferior alveolar nerve canal.

[0024] In one embodiment of the present invention, the inferior alveolar nerve canal separation data can be refined and interpolated.

[0025] In one embodiment of the present invention, the inferior alveolar nerve canal separation data may be the three-dimensional volume data or mesh data.

[0026] In one embodiment of the present invention, a program for executing the method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data on a computer can be recorded on a computer-readable recording medium.

[0027] According to a method for automatically separating an inferior alveolar nerve canal from three-dimensional volume data according to the present invention and a computer-readable recording medium having recorded thereon a program for executing the same on a computer, a central feature point and end feature points can be determined from three-dimensional volume data including an inferior alveolar nerve canal. A central region of the inferior alveolar nerve canal can be separated from the three-dimensional volume data based on the central feature point. End regions of the inferior alveolar nerve canal can be separated from the three-dimensional volume data based on the end feature points. The inferior alveolar nerve canal can be reconstructed based on the central region of the inferior alveolar nerve canal and the end regions of the inferior alveolar nerve canal. Accordingly, an operation processing operation can require less time and be accurate.

[0028] In addition, at least one of the steps of determining the central feature point and the two end feature points in the three-dimensional volume data including the inferior alveolar nerve canal, the step of separating the central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point, and the step of separating the two end regions of the inferior alveolar nerve canal from the three-dimensional volume data based on the two end feature points is performed using an artificial intelligence neural network, so the computational processing operation can require less time and be accurate.

[0029] FIG. 1 is a flowchart illustrating a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data according to one embodiment of the present invention.

[0030] Figures 2 to 7 are conceptual diagrams explaining feature points.

[0031] Figure 8 is a flowchart showing the steps of separating the central region of the inferior alveolar nerve canal from three-dimensional volume data based on the central feature point of Figure 1.

[0032] Figures 9 to 14 are drawings showing feature points, virtual curves, and cross sections.

[0033] Figures 15 and 16 are drawings illustrating cross-sections generated in various directions.

[0034] Figure 17 is a diagram illustrating the second artificial intelligence neural network.

[0035] Figure 18 is a flowchart showing the steps of separating the two-end regions of the inferior alveolar nerve canal from three-dimensional volume data based on the two-end feature points of Figure 1.

[0036] Figure 19 is a drawing showing an area of ​​interest.

[0037] Figure 20 is a diagram showing the third artificial intelligence neural network.

[0038] Figure 21 is a flowchart showing the steps for reconstructing the inferior alveolar nerve canal based on the central region of the inferior alveolar nerve canal and the two end regions of the inferior alveolar nerve canal of Figure 1.

[0039] Figure 22 is a drawing showing the inferior alveolar nerve canal separation data of Figure 21.

[0040] With respect to the embodiments of the present invention disclosed in the text, specific structural and functional descriptions are merely illustrative for the purpose of explaining the embodiments of the present invention, and the embodiments of the present invention may be implemented in various forms and should not be construed as being limited to the embodiments described in the text.

[0041] The present invention is susceptible to various modifications and takes various forms. Specific embodiments are illustrated in the drawings and described in detail herein. However, this is not intended to limit the present invention to specific disclosed forms, but rather to encompass all modifications, equivalents, and alternatives falling within the spirit and technical scope of the present invention.

[0042] While terms like "first" and "second" may be used to describe various components, these components should not be limited by these terms. These terms may be used to distinguish one component from another. For example, without departing from the scope of the present invention, a first component could be referred to as a "second component," and similarly, a second component could also be referred to as a "first component."

[0043] When a component is referred to as being "connected" or "connected" to another component, it should be understood that it may be directly connected or connected to that other component, but that there may be other components in between. Conversely, when a component is referred to as being "directly connected" or "directly connected" to another component, it should be understood that there are no other components in between. Other expressions that describe the relationship between components, such as "between" and "directly between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

[0044] The terminology used in this application is only used to describe specific embodiments and is not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly indicates otherwise. In this application, it should be understood that the terms "comprise" or "have" indicate the presence of a described feature, number, step, operation, component, part, or combination thereof, but do not preclude the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

[0045] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by those of ordinary skill in the art to which this invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and shall not be construed in an idealized or overly formal sense unless explicitly defined herein.

[0046] Meanwhile, if a particular embodiment can be implemented differently, the functions or operations specified within a particular block may occur in a different order than specified in the flowchart. For example, two consecutive blocks may actually be executed substantially simultaneously, or, depending on the related functions or operations, the blocks may be executed in reverse order.

[0047] Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the attached drawings. Identical components in the drawings are designated by the same reference numerals, and redundant descriptions of identical components are omitted.

[0048] FIG. 1 is a flowchart illustrating a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data according to one embodiment of the present invention.

[0049] Referring to FIG. 1, a method for automatically separating an inferior alveolar nerve from three-dimensional volume data according to the present embodiment may include a step (S100) of determining a central feature point and end feature points in three-dimensional volume data including an inferior alveolar nerve canal, a step (S200) of separating a central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point, a step (S300) of separating end regions of the inferior alveolar nerve canal from the three-dimensional volume data based on the end feature points, and a step (S400) of reconstructing the inferior alveolar nerve canal based on the central region of the inferior alveolar nerve canal and the end regions of the inferior alveolar nerve canal.

[0050] In one embodiment, the two end regions of the inferior alveolar nerve canal may be regions including an anterior loop, and the central region of the inferior alveolar nerve canal may be a region excluding the region including the anterior loop. The central region of the inferior alveolar nerve canal may have a simple shape, but the two end regions of the inferior alveolar nerve canal may have a complex shape. Therefore, in the three-dimensional volume data, the central region of the inferior alveolar nerve canal and the two end regions of the inferior alveolar nerve canal are separated separately, and then the central region of the inferior alveolar nerve canal and the two end regions of the inferior alveolar nerve canal are combined to reconstruct the inferior alveolar nerve canal.

[0051] The method for automatically separating the inferior alveolar nerve canal from the above three-dimensional volume data can be performed by a computing device.

[0052] According to the method for automatically segmenting the inferior alveolar nerve from 3D volume data according to the present embodiment, the inferior alveolar nerve canal can be completely automatically segmented from 3D volume data using deep learning. Fig. 1 illustrates the overall flowchart of the method for automatically segmenting the inferior alveolar nerve canal from 3D volume data. Each step is described in detail in Figs. 2 to 22.

[0053] Figures 2 to 7 are conceptual diagrams explaining feature points.

[0054] Referring to FIGS. 1 to 7, the method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data may include a step (S100) of determining the central feature point and the two end feature points in the three-dimensional volume data including the inferior alveolar nerve canal.

[0055] The step (S100) of determining the central feature point and the two end feature points in the three-dimensional volume data including the inferior alveolar nerve canal may be manually processed by a user or may be automatically processed by the deep learning. For example, the step (S100) of determining the central feature point and the two end feature points in the three-dimensional volume data including the inferior alveolar nerve canal may be performed using a first artificial intelligence neural network. That is, the three-dimensional volume data may be input into the first artificial intelligence neural network and the feature points may be output. The first artificial intelligence neural network is disclosed in Republic of Korea Registration No. 10-2373500, Republic of Korea Registration No. 10-2334480, etc., and the contents disclosed in the above patent registration documents may be incorporated by reference as if fully disclosed in the present specification.

[0056] Figures 2 to 7 illustrate examples of the above-described feature points. For example, the feature points may be maxillofacial feature points existing on the skin surface. Figure 2 illustrates maxillofacial feature points existing on the skin surface. The feature points of Figure 2 may include Soft Tissue Glabella (Soft_Glabella), Soft Tissue Nasion (Soft_N), Pronasale (Pn), Soft Tissue A-point (Sls), Right Alar Base (Ala_R), Left Alar Base (Ala_L), Stomion Superior (Sts), Stomion Inferius (Sti), Mentolabial Sulcus (Si), and Soft Tissue Pogonion (Soft_Pog). For example, the feature points may be feature points associated with the maxillofacial bone. Figures 3 to 6 illustrate feature points associated with the maxillofacial bone. The characteristic points of FIGS. 3 to 6 can be expressed according to the frontal portion (A), the cross-section of the side portion (B), the side portion (C), and the bottom portion (D).The characteristic points in Figures 3 to 6 are Sella (S), Nasion (N), Anterior Nasal Spine (ANS), Point-A (A), Posterior Nasal Spine (PNS), Point-B (B), Pogonion (Pg), Gnathion (Gn), Right / Left of Orbitale Superius (OrSR / OrSL), Right / Left of Orbitale Inferius (OriR / OriL), Right / Left of Sutura Zygomaticofrontale(ZyFrR / ZyFrL), Right / Left of Foramen Mentale(FoMR / FoML), Basion(Ba), Right Porion(PoR), Right / Left of Condylus Medialis(CmR / CmL), Right / Left of Condylus Lateralis(ClR / ClL), Right / Left of Areus Zygomatieus (ArZyR / ArZyL), Right / Left of Inferior It may include Gonion (IGoR / IGoL), Right / Left of Posterior Gonion (PGoR / PGoL), Right of Processus Coronoideus (PrCor), Right / Left of Gonion (GoR / GoL). Fig. 7 shows characteristic points associated with teeth. The characteristic points of Fig. 7 may include Central Incisor Root, Mid Point of Central Incisors, First Molar Distal Root, Canine Root, Distal Point of First Molar crown, Cusp Tip, Distal Point of Canine Crown, Canine Root. However, the characteristic points of the present invention are not limited to the characteristic points of Figs. 2 to 7.

[0057] Fig. 8 is a flowchart illustrating a step (S200) of separating the central region of the inferior alveolar nerve canal from three-dimensional volume data based on the central feature point of Fig. 1. Figs. 9 to 14 are drawings illustrating feature points, virtual curves, and cross-sections. Figs. 15 and 16 are drawings illustrating cross-sections generated in various directions. Fig. 17 is a drawing illustrating a second artificial intelligence neural network.

[0058] Referring to FIGS. 1 to 17, the method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data may include the step (S200) of separating the central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point.

[0059] The step (S200) of separating the central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point may include a step (S210) of generating a virtual curve based on the central feature point, a step (S220) of generating a cross-section for the central region of the inferior alveolar nerve canal based on the virtual curve, and a step (S230) of separating the central region of the inferior alveolar nerve canal based on the cross-section for the central region of the inferior alveolar nerve canal to generate central separation data.

[0060] The virtual curve may be generated based on the central feature point. The central feature point may include at least three feature points. In one embodiment, the virtual curve may be a spline curve that directly passes through the central feature point. In one embodiment, the virtual curve may be a Bezier curve that does not directly pass through the central feature point. The Bezier curve is a curve that uses linear interpolation. In addition, the cross-section may be generated based on the virtual curve. However, the present invention is not limited thereto. The angular curve may be any curve other than the spline curve and the Bezier curve.

[0061] For example, as illustrated in FIG. 9, the central feature points may be the Right Mandibular Foramen (MdF_R), Gnathion (Gn), and Left Mental Foramen (MdF_L). The virtual curve of FIG. 9 may be a spline curve passing through the central feature points of FIG. 9. The cross-section of FIG. 9 may be generated based on the virtual curve of FIG. 9. The right drawing of FIG. 9 shows an example of the cross-section of FIG. 9.

[0062] For example, as illustrated in Fig. 10, the central feature points may be Right Mandibular Foramen (MdF_R), Right Antegonion (Ag_R), Menton (Me), Left Antegonion (Ag_L), and Left Mental Foramen (MdF_L). The virtual curve in Fig. 10 may be a spline curve passing through the central feature points in Fig. 10. The right drawing in Fig. 10 shows an example of a cross-section in Fig. 10.

[0063] For example, as illustrated in Fig. 11, the central feature points may be Right Porian (Po_R), Right Mandibular Foramen (MdF_R), Menton (Me), Left Mandibular Foramen (MdF_L), and Left Porian (Po_L). The virtual curve in Fig. 11 may be a spline curve passing through the central feature points in Fig. 11. The right drawing in Fig. 11 shows an example of a cross-section in Fig. 11.

[0064] Meanwhile, the cross-section can be generated in various directions based on the virtual curve. As illustrated in FIG. 12, in one embodiment, the cross-section can be perpendicular to the virtual curve. As illustrated in FIG. 13, in one embodiment, the intermediate cross-section perpendicular to the virtual curve can be a projected surface. As illustrated in FIG. 14, in one embodiment, the cross-section can be parallel to the coronal plane.

[0065] For example, Fig. 15 illustrates an example of the cross-section plane perpendicular to the virtual curve. For example, Fig. 16 illustrates an example of a surface onto which the intermediate cross-section plane perpendicular to the virtual curve is projected.

[0066] Meanwhile, the coronal plane is one of the planes representing the human body. For example, the planes representing the human body may include the sagittal plane, the coronal plane, and the transverse plane. The sagittal plane is a plane that divides the human body into left and right sides. The coronal plane is a plane that divides the human body into front and back sides. The transverse plane is a plane that divides the human body into upper and lower sides.

[0067] The step (S230) of generating the central separation data by separating the central region of the inferior alveolar nerve canal based on the cross-section of the central region of the inferior alveolar nerve canal may be performed using a second artificial intelligence neural network. That is, the cross-section may be input to the second artificial intelligence neural network and the central separation data may be output. The second artificial intelligence neural network may be a convolutional neural network (CNN).

[0068] In one embodiment, the second artificial intelligence neural network may be a two-dimensional convolutional neural network. The cross-section may be one or more. In this case, the cross-section may be a two-dimensional image image. Therefore, the two-dimensional convolutional neural network may be utilized.

[0069] In one embodiment, the second artificial intelligence neural network may be a three-dimensional convolutional neural network. The cross-section may be in the form of a stacked volume. In this case, the cross-section may be a three-dimensional image image. Therefore, the three-dimensional convolutional neural network may be utilized.

[0070] Figure 18 is a flowchart illustrating a step (S300) of separating the two-end regions of the inferior alveolar nerve canal from the three-dimensional volume data based on the two-end feature points of Figure 1. Figure 19 is a diagram illustrating a region of interest (VOI). Figure 20 is a diagram illustrating a third artificial intelligence neural network.

[0071] Referring to FIGS. 1 to 20, the method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data may include a step (S300) of separating the two-end regions of the inferior alveolar nerve canal from the three-dimensional volume data based on the two-end feature points (FP_BE).

[0072] The step (S300) of separating the two end regions of the inferior alveolar nerve canal from the three-dimensional volume data based on the two end feature points (FP_BE) may include the step (S310) of generating a region of interest (VOI) based on the two end feature points (FP_BE) and the step (S320) of separating the two end regions of the inferior alveolar nerve canal in the region of interest (VOI) to generate two end separation data.

[0073] The above region of interest (VOI) can be generated based on the double-ended feature points (FP_BE). Specifically, the double-ended feature points (FP_BE) can be points located around the anterior loop. Therefore, the region of interest (VOI) can be an area including the anterior loop. In Fig. 19, the double-ended feature points (FP_BE) are depicted as dots, and the region of interest (VOI) is depicted as a rectangular parallelepiped (or cube) including the dots.

[0074] The step (S320) of generating the two-end separation data by separating the two-end regions of the inferior alveolar nerve canal in the region of interest (VOI) may be performed using a third artificial intelligence neural network. That is, the region of interest (VOI) may be input to the third artificial intelligence neural network, and the two-end separation data may be output. The third artificial intelligence neural network may be the convolutional neural network.

[0075] In one embodiment, the third artificial intelligence neural network may be a three-dimensional convolutional neural network. The region of interest (VOI) may be a three-dimensional image. Therefore, the three-dimensional convolutional neural network may be utilized.

[0076] Fig. 21 is a flowchart illustrating a step (S400) of reconstructing the inferior alveolar nerve canal based on the central region of the inferior alveolar nerve canal and the two end regions of the inferior alveolar nerve canal of Fig. 1. Fig. 22 is a diagram illustrating inferior alveolar nerve canal separation data of Fig. 21.

[0077] Referring to FIGS. 1 to 22, the method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data may include the step (S400) of reconstructing the inferior alveolar nerve canal based on the central region of the inferior alveolar nerve canal and the two end regions of the inferior alveolar nerve canal.

[0078] The step (S400) of reconstructing the inferior alveolar nerve canal based on the central region of the inferior alveolar nerve canal and the two end regions of the inferior alveolar nerve canal may include a step (S410) of mapping the central separation data generated by separating the central region of the inferior alveolar nerve canal to the three-dimensional volume data, and a step (S420) of generating inferior alveolar nerve canal separation data by combining the mapped central separation data and the two end separation data generated by separating the two end regions of the inferior alveolar nerve canal.

[0079] As described in FIGS. 8 to 17, the central separation data can be generated. The central separation data can be mapped to the three-dimensional volume data. As described in FIGS. 18 to 20, the two-end separation data can be generated. As shown in the left drawing of FIG. 22, the inferior alveolar nerve canal separation data can be generated by combining the mapped central separation data and the two-end separation data. The inferior alveolar nerve canal separation data included in the left drawing of FIG. 22 can be converted into mesh data through a method such as a marching cube. In one embodiment, the inferior alveolar nerve canal separation data can be the three-dimensional volume data or the mesh data. The mesh data can include three-dimensional points (Vertex) and a triangular face (Triangle) or a rectangular face (Rectangle) generated by connecting the points. However, the present invention is not limited thereto. The mesh data can be any polygon excluding the triangular face and the rectangular face.

[0080] Meanwhile, the inferior alveolar nerve separation data can be refined and interpolated. In particular, the interpolation can be performed on the central separation data or between the central separation data and the bilateral separation data.

[0081] According to the present embodiment, the central feature point and the end feature points (FP_BE) can be determined from the three-dimensional volume data including the inferior alveolar nerve canal. The central region of the inferior alveolar nerve canal can be separated from the three-dimensional volume data based on the central feature point. The end regions of the inferior alveolar nerve canal can be separated from the three-dimensional volume data based on the end feature points (FP_BE). The inferior alveolar nerve canal can be reconstructed based on the central region of the inferior alveolar nerve canal and the end regions of the inferior alveolar nerve canal. Accordingly, the computational processing operation can require less time and be accurate.

[0082] In addition, at least one of the step (S100) of determining the central feature point and the two-end feature points (FP_BE) in the three-dimensional volume data including the inferior alveolar nerve canal, the step (S200) of separating the central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point, and the step (S300) of separating the two-end feature points (FP_BE) in the three-dimensional volume data is performed using an artificial intelligence neural network, so the computational processing operation can require less time and be accurate.

[0083] According to one embodiment of the present invention, a computer-readable recording medium having recorded thereon a program for executing a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data according to the above embodiments on a computer may be provided. The above-described method can be written as a program that can be executed on a computer, and can be implemented on a general-purpose digital computer that executes the program using the computer-readable medium. In addition, the structure of data used in the above-described method can be recorded on a computer-readable medium through various means. The computer-readable medium may include program commands, data files, data structures, etc., either singly or in combination. The program commands recorded on the medium may be those specially designed and configured for the present invention, or may be known and usable by those skilled in the art in the field of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program instructions include not only machine language codes, such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the present invention.

[0084] In addition, the method for automatically separating the inferior alveolar nerve canal from the three-dimensional volume data described above can also be implemented in the form of a computer program or application executed by a computer and stored in a recording medium.

[0085] The present invention relates to a method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data and a computer-readable recording medium having recorded thereon a program for executing the method on a computer, which can reduce the effort and time for computational processing operations and improve accuracy and productivity.

[0086] Although the present invention has been described above with reference to preferred embodiments thereof, it will be understood by those skilled in the art that various modifications and changes may be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below.

Claims

1. A step of determining a central feature point and two end feature points in three-dimensional volume data including the inferior alveolar nerve canal; A step of separating the central region of the inferior alveolar nerve canal from the three-dimensional volume data based on the central feature point; A step of separating the two-end region of the inferior alveolar nerve canal from the three-dimensional volume data based on the two-end feature points; and A method for automatically separating the inferior alveolar nerve from three-dimensional volume data, characterized by comprising a step of reconstructing the inferior alveolar nerve based on the central region of the inferior alveolar nerve and the two end regions of the inferior alveolar nerve.

2. A method for automatically separating the inferior alveolar nerve canal of 3D volume data, characterized in that in the first paragraph, the 3D volume data is input into a first artificial intelligence neural network, and the central feature point and the two end feature points are determined from the first artificial intelligence neural network.

3. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the first paragraph, the central feature point includes at least three feature points.

4. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the first paragraph, the two-end feature points include two feature points.

5. In the first paragraph, the step of separating the central region of the inferior alveolar nerve canal is, A step of generating a virtual curve based on the above central feature points; A step of creating a cross-section for the central region of the inferior alveolar nerve canal based on the virtual curve; A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized by comprising a step of generating central separation data by separating the central region of the inferior alveolar nerve canal based on the cross-section of the central region of the inferior alveolar nerve canal.

6. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the fifth paragraph, the virtual curve is a spline curve that directly passes through the central feature point.

7. A method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data, characterized in that in the fifth paragraph, the virtual curve is a Bezier curve that does not directly pass through the central feature point.

8. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the fifth paragraph, the cross-section is perpendicular to the virtual curve.

9. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the fifth paragraph, the cross-section is a plane on which an intermediate cross-section plane perpendicular to the virtual curve is projected.

10. A method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data, characterized in that in the fifth paragraph, the cross-section plane is parallel to the coronal plane.

11. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the fifth paragraph, the cross-section is input into a second artificial intelligence neural network, and the central separation data is generated from the second artificial intelligence neural network.

12. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the 11th paragraph, when the cross-section is one or more, the second artificial intelligence neural network is a two-dimensional convolutional neural network.

13. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the 11th paragraph, when the cross-section is in the form of a stacked volume, the second artificial intelligence neural network is a three-dimensional convolutional neural network.

14. In the first paragraph, the step of separating the two end regions of the inferior alveolar nerve canal is, A step of creating a region of interest based on the above two-end feature points; and A method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data, characterized in that it comprises a step of separating the two end regions of the inferior alveolar nerve canal in the above region of interest to generate two end separation data.

15. A method for automatically separating the inferior alveolar nerve canal of three-dimensional volume data, characterized in that in the 14th paragraph, the region of interest is input into a third artificial intelligence neural network, and the two-end separation data is generated from the third artificial intelligence neural network.

16. A method for automatically separating the inferior alveolar nerve canal from three-dimensional volume data, characterized in that in the first paragraph, the two end regions of the inferior alveolar nerve canal are regions including an anterior loop, and the central region of the inferior alveolar nerve canal is a region excluding the region including the anterior loop.

17. In the first paragraph, the step of reconstructing the inferior alveolar nerve canal is as follows: A step of mapping the central separation data generated by separating the central region of the inferior alveolar nerve canal to the three-dimensional volume data; and A method for automatically separating the inferior alveolar nerve of three-dimensional volume data, characterized by comprising a step of generating inferior alveolar nerve separation data by combining the mapped central separation data and the two-end separation data generated by separating the two-end regions of the inferior alveolar nerve.

18. A method for automatically separating the inferior alveolar nerve from three-dimensional volume data, characterized in that in the 17th paragraph, the inferior alveolar nerve separation data is refined and interpolated.

19. A method for automatically separating the inferior alveolar nerve using three-dimensional volume data, characterized in that in the 17th paragraph, the inferior alveolar nerve separation data is three-dimensional volume data or mesh data.

20. A computer-readable recording medium having recorded thereon a program for executing the method of any one of claims 1 to 19 on a computer.

Images