Three-dimensional image processing device, three-dimensional image processing method, and program

Abstract

A three-dimensional image processing device for generating image data for analyzing a three-dimensional image of a diagnosis object, the three-dimensional image processing device being provided with: an image processing unit for performing alignment between a three-dimensional image of the analysis object captured at an existing first time point and a three-dimensional image of the analysis object captured at an existing second time point, the second time point being different from the first time point; the present invention relates to a method for aligning three-dimensional images in which a diagnostic object is present in a predetermined space containing an analysis object, the analysis object being a support, the method comprising: a first registration process in which one of the two three-dimensional images is subjected to rigid body transformation to reduce a difference from the other three-dimensional image, and a second registration process in which the other three-dimensional image is subjected to rigid body transformation to reduce a difference from the other three-dimensional image; and a second registration process for performing rigid body transformation on the one three-dimensional image after the first registration process is performed so as to reduce the difference between the image of the analysis object reflected in the other three-dimensional image and the image of the analysis object reflected in the one three-dimensional image.

Description

Technical Field

[0001] The present invention relates to a three-dimensional image processing device, a three-dimensional image processing method and a program. Background Art

[0002] Periodontal disease causes bone resorption (defects) in the alveolar bone that supports the teeth, and if it continues to progress, the teeth may eventually be lost. It is said that not only natural teeth, but also dental implants and plastic surgery implants are prone to bone resorption (defects) around the supporting parts.

[0003] In the past, the qualitative evaluation method for alveolar bone resorption was to measure the depth of the periodontal pocket (the groove between the tooth root and the gum) using a periodontal probe and check whether bleeding occurred due to its irritation. In addition, forceps were used to check the stability of the tooth.

[0004] However, it is difficult to accurately understand the state of alveolar bone loss due to periodontal disease based on the results of these examinations. In addition, these examination results do not make it easy for patients to understand the status of their periodontal disease. Therefore, X-rays of the teeth and their surroundings are used to visually capture the morphology of the alveolar bone.

[0005] Furthermore, in recent years, with the popularization of dental cone beam CT, it is also possible to capture the state of teeth and the surrounding alveolar bone in the form of three-dimensional images. This method has the effect of reducing the burden on the body, and because the results are provided in the form of images, it also has the effect of making the examination results easier for patients to understand.

[0006] Prior art literature

[0007] Patent Literature

[0008] Patent Document 1: Japanese Patent Application Publication No. 2015-116303

[0009] Non-patent literature

[0010] Non-patent literature 1: V Chappuis, O Engel, M Reyes, K Shahim, LP Nolte, D Buser, “Ridge alterations post-extraction in the esthetic zone: a 3D analysis with CBCT”, J. Dent. Res., Dec; 92(12 Suppl): 195S-201S. doi: 10.1177 / 0022034513506713. Epub 2013 Oct 24. PMID: 24158340; PMCID: PMC3860068. Summary of the invention

[0011] Problems to be solved by the invention

[0012] In such examinations using medical three-dimensional images, for example, there are cases where changes are compared with past results. By making such comparisons, bone resorption conditions in the area of ​​interest, such as the progression of periodontal disease, can be evaluated more colorfully and accurately than when evaluating based on the results of a single shot.

[0013] However, this comparison is usually a qualitative visual comparison, and accurate and quantitative comparison based on pixel units, which can be achieved by aligning the positions of the images, has not yet been performed. As a result, there are cases where the information required for diagnosis cannot be fully obtained, resulting in low diagnostic accuracy. In fact, there are reasons for this, and one of the reasons is that the morphological changes of teeth and periodontal tissues over time are often greater than those of hard tissues in other parts of the human body, so it is difficult to perform the precise alignment required to compare three-dimensional images taken at different times.

[0014] Although this situation exists, in order to reduce time, money and physical burden, it is hoped that more quantitative information can be obtained to further improve the accuracy of examination and diagnosis. In addition, this situation is not limited to humans, but also applies to animals. In addition, this situation also applies to dental implants or plastic surgery implants in addition to natural teeth.

[0015] In view of the above circumstances, an object of the present invention is to provide a technology for improving the accuracy of diagnosis using three-dimensional images.

[0016] Solutions for solving problems

[0017] One embodiment of the present invention relates to a three-dimensional image processing device, which generates image data for analyzing a three-dimensional image of a diagnostic object, and comprises: an image processing unit, which performs alignment on a three-dimensional image of the analytical object captured at a first moment and a three-dimensional image of the analytical object captured at a second moment, the second moment being different from the first moment, wherein the three-dimensional image projects an image of an object in a predetermined space including the analytical object, the diagnostic object being in the space, the analytical object being a support portion, the alignment comprising: a first registration process, which performs a rigid body transformation on one of the two three-dimensional images to reduce the difference between the three-dimensional image and the other three-dimensional image; and a second registration process, which performs a rigid body transformation on the one three-dimensional image after the first registration process is performed to reduce the difference between the image of the analytical object projected in the other three-dimensional image and the image of the analytical object projected in the one three-dimensional image.

[0018] One embodiment of the present invention relates to a three-dimensional image processing method, which generates image data for analyzing a three-dimensional image of a diagnostic object, and comprises: an image processing step, which performs alignment on a three-dimensional image of the analytical object captured at a first moment and a three-dimensional image of the analytical object captured at a second moment, the second moment being different from the first moment, the three-dimensional image projects an image of an object in a predetermined space including the analytical object, the diagnostic object being in the space, the analytical object being a support portion, the alignment comprising: a first registration process, which performs a rigid body transformation on one of the two three-dimensional images to reduce the difference between it and the other three-dimensional image; and a second registration process, which performs a rigid body transformation on the one three-dimensional image after the first registration process is performed to reduce the difference between the image of the analytical object projected in the other three-dimensional image and the image of the analytical object projected in the one three-dimensional image.

[0019] One embodiment of the present invention relates to a program for causing a computer to function as the three-dimensional image processing device described above.

[0020] Effects of the Invention

[0021] According to the present invention, it is possible to improve the accuracy of diagnosis using three-dimensional images. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is an explanatory diagram for explaining the outline of the three-dimensional image processing device according to the embodiment.

[0023] Figure 2 It is a diagram showing an example of mask data in the embodiment.

[0024] Figure 3 is a flowchart illustrating an example of a second registration process using mask data in an embodiment.

[0025] Figure 4 This is an example of experimental results of evaluating the three-dimensional alignment processing in the embodiment.

[0026] Figure 5 It is a diagram showing an example of the hardware configuration of the three-dimensional image processing device in the embodiment.

[0027] Figure 6 It is a diagram showing an example of the configuration of a control unit included in the three-dimensional image processing apparatus according to the embodiment.

[0028] Figure 7 This is a flowchart showing an example of the flow of processing executed by the three-dimensional image processing apparatus according to the embodiment.

[0029] Figure 8It is a diagram showing an example of experimental results in the embodiment. DETAILED DESCRIPTION

[0030] (Implementation Method)

[0031] Figure 1 This is an explanatory diagram for explaining the outline of a three-dimensional image processing device 1 according to an embodiment. The three-dimensional image processing device 1 generates image data for analyzing a three-dimensional image of a diagnostic object. The diagnostic object is, for example, tissue surrounding a root of a natural tooth. The diagnostic object is, for example, tissue surrounding a fixture and abutment of a dental implant. The diagnostic object is, for example, tissue surrounding a retaining portion of a plastic surgery implant.

[0032] Hereinafter, the root of a natural tooth, the fixture of a dental implant, and the retaining part of a bridge base and a plastic surgery implant are collectively referred to as a support part. If the support part is used for explanation, the diagnostic object is, for example, the tissue surrounding the support part. The tissue surrounding the support part as the diagnostic object is, for example, a tissue that contributes to the support of the support part to a predetermined degree or more. Therefore, the tissue surrounding the support part is, for example, the periodontal tissue. The tissue surrounding the support part can be, for example, the alveolar bone or the femur.

[0033] In addition, natural teeth are composed of crowns and roots. Dental implants are composed of a superstructure equivalent to the crown of natural teeth, a fixture that supports the superstructure, and an abutment that connects the fixture and the superstructure. Plastic surgery implants are composed of a head that acts as a joint, a plate, and a holding part including a stem or screw that supports the head and plate.

[0034] Hereinafter, the crown of a natural tooth, the upper structure of a dental implant, and the head and plate of a plastic surgery implant are collectively referred to as a functional part.

[0035] A natural tooth can be a natural tooth of a human being or a natural tooth of an animal. A dental implant can be a dental implant of a human being or a dental implant of an animal. A plastic surgical implant can be a plastic surgical implant of a human being or a plastic surgical implant of an animal.

[0036] The three-dimensional image processing device 1 includes a control unit 11. The control unit 11 will be described in detail later, but includes a processor 91 such as a CPU (Central Processing Unit) and a memory 92, and executes various processes through the operation of the processor 91 and the memory 92.

[0037] The control unit 11 performs a three-dimensional alignment process on the analysis target image and the comparison target image. The three-dimensional alignment process is a process of aligning two three-dimensional images as execution targets. The execution targets are the analysis target image and the comparison target image.

[0038] The analysis target image is a three-dimensional image showing an image of the analysis target at a first time. The comparison target image is a three-dimensional image showing an image of the analysis target at a second time, and the second time is a time different from the first time. More specifically, the analysis target image is a three-dimensional image showing an analysis target captured at a first time, and the comparison target image is a three-dimensional image showing an analysis target captured at a second time, and the second time is different from the first time.

[0039] More specifically, a three-dimensional image showing the result of the analysis object photographed at the first moment being photographed at the second moment is a comparison object image, and a three-dimensional image showing the analysis object photographed at the first moment is an analysis object image. Conversely, a three-dimensional image showing the result of the analysis object photographed at the second moment being photographed at the first moment is an analysis object image, and a three-dimensional image showing the analysis object photographed at the second moment is a comparison object image.

[0040] In addition, the second time is, for example, a time earlier than the first time. The second time may also be a time later than the first time. In order to simplify the description, the following description is made by taking the case where the first time is later than the second time as an example.

[0041] It is explained that the analysis object image and the comparison object image are three-dimensional images that reflect the image of the existing analysis object. More specifically, the analysis object image and the comparison object image reflect the image of objects in a predetermined space (hereinafter referred to as the "photographed space") that includes the analysis object. In addition, there is a diagnostic object in the photographed space. Therefore, the image of the existing diagnostic object is reflected in the analysis object image and the comparison object image. In addition, more specifically, the analysis object is a supporting part. The image of the existing functional part can also be reflected in the analysis object image and the comparison object image. That is, the functional part can also exist in the photographed space. The photographed space is the so-called region of interest.

[0042] The imaged space may be a range determined according to a prescribed rule, or may be a range determined by a user, for example. The prescribed rule may be any rule as long as the analysis object and the diagnosis object are included in the imaged space. The prescribed rule may be, for example, a rule that a spherical space with a prescribed radius centered on the analysis object and including the diagnosis object is used as the imaged space.

[0043] In the case where there is a known deviation in the shape and positional relationship between the analysis object and the diagnosis object, an example of a prescribed rule is used to explain. In this case, the prescribed rule may be, for example, a rule that a rectangular parallelepiped having a prescribed height and containing the diagnosis object is used as the imaged space, and a square is used as the upper surface of the rectangular parallelepiped, the square being centered at a point located a prescribed distance above the upper end of the analysis object and consisting of sides of prescribed lengths.

[0044] As described above, the three-dimensional image showing the result of the analysis object photographed at the first time being photographed at the second time is the comparison target image, and the three-dimensional image showing the analysis object photographed at the first time is the analysis target image. Therefore, the person or animal having the analysis object shown in the analysis target image is the same as the person or animal having the analysis object shown in the comparison target image.

[0045] In order to simplify the description, the three-dimensional image processing device 1 is described below by taking a case where the analysis object is a tooth root as an example.

[0046] Specifically, the three-dimensional alignment process is a process of performing a rigid body transformation on the comparison target image of the two images to be executed so as to reduce the difference between the first root image and the second root image. The first root image is an image of the analysis target image that is projected in the analysis target image. The second root image is an image of the analysis target image that is projected in the comparison target image.

[0047] The process of performing rigid body transformation on the comparison target image so as to reduce the difference between the first tooth root image and the second tooth root image is, for example, a transformation that increases the sum of mutual information between pixel values ​​at the same coordinates on the two images to be executed.

[0048] As described above, the analysis object image and the comparison object image as the execution objects in the three-dimensional alignment process are both images showing the image of the teeth of the same person or animal, but they are taken at different times. One of the two three-dimensional images (i.e., the analysis object image and the comparison object image) is, for example, an image showing the image of the analysis object and its surrounding teeth and alveolar bones. In this case, the other three-dimensional image is, for example, an image showing the image of the analysis object of the same person or animal and its surrounding teeth and alveolar bones, and is an image in which a part of the surrounding teeth is missing due to tooth extraction. The other three-dimensional image can also be, for example, an image showing the image of the analysis object of the same person or animal and its surrounding teeth and an image of the alveolar bone that is partially absorbed and missing.

[0049] The analysis target image and the comparison target image are, for example, images representing a portion of an image obtained by photographing by an imaging device such as an X-ray device, and are also images of images that appear in a region of interest specified by a user. Hereinafter, the process of generating such an image representing a portion of an image obtained by photographing by an imaging device such as an X-ray device, and also an image that appears in a region of interest, based on an image obtained by photographing by an imaging device is referred to as a preliminary image forming process.

[0050] The preliminary image forming process may be performed by the user using another computer, for example, before the image data of the analysis target image and the image data of the comparison target image are input to the three-dimensional image processing device 1. The designation of the analysis target may be performed by the control unit 11 according to the user's instruction via the input unit 12 described later, after the image data of the analysis target image and the image data of the comparison target image are input to the three-dimensional image processing device 1.

[0051] In designating the analysis target, for example, processing is performed according to information input by the user. Specifically, the information input by the user used in designating the analysis target is information indicating a point in the image and a point between the crown and the root of the tooth to be analyzed.

[0052] Hereinafter, information used in designating the analysis object, i.e., information indicating a point in the image and between the tooth root of the analysis object and the tooth crown of the tooth having the analysis object, is referred to as first designation information. In addition, the point between the tooth root of the analysis object and the tooth crown of the tooth having the analysis object refers to a point at which the tooth root of the analysis object and the tooth crown of the tooth having the analysis object can be distinguished. The purpose is to input the following information to the analysis device: when the maxilla is designated, the tooth root position is above the designated point, and when the mandible is designated, the tooth root position is below the designated point.

[0053] In designating the analysis object, a region having a predetermined shape and size based on a point indicated by the first designation information is set as the region of interest. Therefore, in designating the analysis object, for example, a region having a predetermined shape and size centered on a point indicated by the first designation information is set as the region of interest.

[0054] The image data of the two images to be executed in the three-dimensional alignment process, that is, the image data of the analysis target image and the comparison target image, are, for example, image data of images obtained by such a prior image shaping process. In addition, it is not necessary to perform a prior image shaping process, and an image obtained by shooting with a shooting device can be directly used as an execution object of the three-dimensional alignment process.

[0055] Hereinafter, a set of two three-dimensional images to be executed in the three-dimensional alignment process is referred to as a target image set. In other words, the target image set is a set of an analysis target image and a comparison target image.

[0056] In the following, for the sake of simplicity, the three-dimensional image processing device 1 is described by taking as an example a case where the analysis target image and the comparison target image included in the target image group are images of the same person taken at different times, that is, the comparison target image is an image before tooth extraction, and the analysis target image is an image after tooth extraction.

[0057] Furthermore, there may not be a drastic change between two three-dimensional images in the target image group, such as the loss of surrounding teeth due to tooth extraction. Regardless of whether or not there is tooth extraction, as long as the analysis object is included in the two images in the target image group, diagnosis can be performed using the three-dimensional image obtained by the three-dimensional image processing device 1. The diagnosis is, for example, analysis of morphological changes in the surrounding alveolar bone of the analysis object.

[0058] Furthermore, the image data representing the analysis target image and the image data representing the comparison target image satisfy the same size condition before the three-dimensional highlighted image is generated. The same size condition is a condition that the size of the analysis target image in each dimension is the same as the size of the comparison target image in each corresponding dimension.

[0059] That is, the same size condition is a condition that the size (x, y, z) of the analysis target image and the size (x', y', z') of the comparison target image have the relationship x=x', y=y', z=z'. Thus, the same size condition is a condition that each dimension in three dimensions is the same size as the corresponding dimension of the three-dimensional image of the comparison target.

[0060] In addition, x represents the size of the first dimension of the image to be analyzed as a three-dimensional image. y represents the size of the second dimension of the image to be analyzed as a three-dimensional image. z represents the size of the third dimension of the image to be analyzed as a three-dimensional image. x′ represents the size of the first dimension of the image to be compared as a three-dimensional image. y′ represents the size of the second dimension of the image to be compared as a three-dimensional image. z represents the size of the third dimension of the image to be compared as a three-dimensional image.

[0061] When the above-mentioned preliminary image forming process is performed, the analysis target image and the comparison target image to be performed in the three-dimensional alignment process meet the same size condition. This is because the shape and size of the interest region are predetermined as described above, and the interest region having the same shape and size is set in the preliminary image forming process regardless of the image.

[0062] In addition, regarding the size of the entire image in the XYZ direction, the size of the analysis target image is made consistent with the region of interest, and the comparison target image is slightly larger than the analysis target image and is cropped after the first registration to be consistent with the analysis target image. In this case, it is possible to further suppress the generation of a defective portion in the comparison target image after the first registration. This is because if the sizes are the same, the portion that was originally outside the image is included in the transformed image due to the angle transformation.

[0063] The three-dimensional alignment process includes a first registration process and a second registration process. The first registration process is a process of performing a rigid body transformation on the comparison target image so as to reduce the overall difference between each image included in the target image group. That is, the first registration process is a process of performing a rigid body transformation on one of the two three-dimensional images, the analysis target image and the comparison target image, so as to reduce the difference between it and the other three-dimensional image. Hereinafter, the comparison target image transformed by the first registration process is referred to as the first transformed image.

[0064] In the first registration process, a point on the comparison target image and a point on the analysis target image may be specified. In this case, starting from a state where the specified point in each image is consistent, a rigid body transformation is performed on the comparison target image to reduce the difference between the comparison target image and the analysis target image.

[0065] Furthermore, in the first registration, when the sizes of the images are different, a process of aligning the points between the crown and the root respectively designated by the user with each other may be performed.

[0066] Hereinafter, information used in the first registration process, that is, information specifying a point on the comparison target image and a point on the analysis target image, is referred to as second specifying information. The point indicated by the second specifying information is, for example, a point between a tooth root as an analysis target and a tooth crown having the analysis target.

[0067] The second designation information is inputted by the user into the three-dimensional image processing apparatus 1 via, for example, the input unit 12 described later. The control unit 11 obtains the second designation information inputted by the user, and performs a rigid body transformation so as to reduce the difference between the comparison target image and the analysis target image while aligning the points indicated by the obtained second designation information.

[0068] In addition, the point indicated by the second designation information may be the same as the point indicated by the first designation information. In the case where the control unit 11 performs the prior image shaping process, the first designation information is input to the three-dimensional image processing device 1 before the first registration process is performed. Therefore, in this case, the first designation information may also be used as the second designation information.

[0069] The second registration process is a process of performing a rigid body transformation on the first transformed image so as to reduce the difference between the image of the analysis target shown in the first transformed image and the image of the analysis target shown in the analysis target image.

[0070] The second registration process is, for example, a process of transforming the first transformed image based on information representing the image of the analyzed object shown in each image to reduce the difference in the image morphology of the analyzed object shown in the information. The second registration process may be, for example, a process of performing a rigid body transformation obtained according to a prescribed rule on the first transformed image. An example of such a process according to a prescribed rule is, for example, a process using mask data described later. An example of the second registration process using mask data will be described later.

[0071] <Significance of reducing differences in tooth root morphology shown in images>

[0072] The morphological changes of teeth and periodontal tissues over time are more dramatic than those of other parts of the human body. However, among teeth and periodontal tissues, the root is a tissue that undergoes relatively little morphological change over time. In dental implants, the functional part may also be replaced, the morphological changes of the surrounding bone are greater, and the morphological changes of the supporting part are less. In plastic surgery implants, the morphological changes of the supporting part are less likely to be compared with the morphological changes of the surrounding bone.

[0073] Therefore, if the change of the tooth or periodontal tissue is estimated based on the position of the tooth root, the change of the tooth or periodontal tissue can be estimated with high accuracy compared with the case where other parts are used as the reference. Therefore, by performing a process to reduce the deviation in the image morphology of the tooth root reflected in the analysis target image and the image morphology of the tooth root reflected in the comparison target image, the control unit 11 can estimate the change of the tooth or periodontal tissue with higher accuracy. Even for dental implants or plastic surgery implants, as long as the change of the surrounding tissue is estimated based on the position of the support part, the change of the surrounding tissue can be estimated with high accuracy.

[0074] <Significance of Executing the First Registration Process>

[0075] Performing the first registration process before performing the second registration process suppresses the occurrence of over-learning in machine learning. Specifically, performing the first registration process before performing the second registration process suppresses the occurrence of a situation where the degree of consistency between the two images is high only around the root image represented by the root designation information but low for the entire image.

[0076] <Details of Second Registration Processing Using Mask Data>

[0077] In the second registration process, mask data may be used. Mask data is data representing pixels of the unchanged tooth root inclusion region (hereinafter referred to as "tooth root inclusion pixels") in the pixels of the analysis target image. The unchanged tooth root inclusion region is a region on the analysis target image, and is a region including the image of the analysis target.

[0078] The mask data is, for example, image data of a binary image (hereinafter referred to as a "mask image") that satisfies a mask image condition. The mask image condition is a condition in which the pixel value of the unchanged tooth root inclusion area is one of two predetermined pixel values, and the pixel value of the area outside the unchanged tooth root inclusion area is the other of the two predetermined pixel values.

[0079] The two predetermined pixel values ​​are, for example, 0 and 1. The size of the mask image is the same as that of the analysis target image and the first transformed image. Therefore, the mask image is a three-dimensional image. The mask data may be, for example, information indicating the boundary of the region containing the unchanged tooth root.

[0080] The mask data is, for example, image data of a binary image in which the image of an object in a predetermined space containing the analysis object has different pixel values ​​from other images. The predetermined space containing the analysis object is, for example, a space extending in all directions by a predetermined width in accordance with the image of the analysis object.

[0081] Figure 2 is a diagram showing an example of mask data in an embodiment. More specifically, Figure 2 FIG. 1 is a diagram showing an example of a mask image in a case where the mask data in the embodiment is image data of a mask image. Figure 2 Indicates image M1, image M2, and image M3.

[0082] Image M1 is a diagram of the mask image observed from the direction of one of the three mutually orthogonal axes (hereinafter referred to as the "first axis direction"). Image M2 is a diagram of the mask image observed from the direction of another of the three mutually orthogonal axes (hereinafter referred to as the "second axis direction"). Image M3 is a diagram of the mask image observed from the direction of one of the three mutually orthogonal axes and in the direction in which a vector orthogonal to the vector parallel to the first axis direction and the vector parallel to the second axis direction points (hereinafter referred to as the "third axis direction").

[0083] Figure 2 The point P in is an example of a point in the three-dimensional image indicated by the second specification information.

[0084] Thus, the mask data can be said to be information indicating whether each pixel is an unchanged tooth root containing region. Therefore, for example, when the value of the tooth root containing pixel in the mask data is 1 and the value of the other pixels is 0, if the value of each pixel indicated by the mask data is multiplied by each pixel of the analysis target image, an image containing the image of the analysis target is obtained. In addition, if the value of each pixel indicated by the same mask data is multiplied by each pixel of the first transformed image, an image with a high probability of containing the image of the analysis target is obtained, that is, an image with a high degree of consistency with the image obtained from the analysis target image is obtained.

[0085] However, since the mask data is data obtained based on the analysis target image, such an image may not necessarily be obtained for the first transformed image. Therefore, if an appropriate rigid body transformation is performed on the first transformed image, the first transformed image includes the image of the analysis target, and thus an image with a high degree of consistency with the image obtained from the analysis target image is obtained.

[0086] In this way, the process of transforming the first transformed image so as to reduce the difference in the morphology of the image of the analysis object is the second registration process using the mask data. The second registration process using the mask data will be further described.

[0087] In the second registration process using the mask data, a rigid body transformation is performed on the first transformed image to improve the consistency between the partial analyzed object image and the partial compared object image. The partial analyzed object image is an image of the unchanged tooth root inclusion area in the analyzed object image. More specifically, the partial analyzed object image is an image of a portion of the analyzed object image obtained based on the image data of the analyzed object image and the mask data, and is an image of the unchanged tooth root inclusion area.

[0088] The partial comparison target image is an image obtained based on the image data and mask data of the first transformed image, and is an area on the image of the first transformed image, and is an image of an image reflected in the candidate image extraction. The candidate image extraction area is an area that satisfies the following condition: assuming that the image existing in the area is not the first transformed image but the analysis target image, the area is a tooth root inclusion area.

[0089] Figure 3 1 is a flowchart illustrating an example of the second registration process using mask data in the embodiment. Figure 3 The processes shown.

[0090] In the second registration process using the mask data, first, only the mask region is extracted from the analysis target image to obtain a partial analysis target image (step S101). In the second registration process using the mask data, a rigid body transformation is then performed on the first transformed image (step S102).

[0091] In the second registration process using the mask data, next, a partial comparison object image is obtained from the first transformed image after the rigid body transformation is performed (step S103). In the second registration process using the mask data, next, a difference between the obtained partial resolution object image and the partial comparison object image is obtained (step S104).

[0092] In the second registration process using the mask data, next, it is determined whether a predetermined end condition related to the size of the difference obtained in step S104 is satisfied (step S105). The predetermined end condition may be, for example, a condition that the difference is smaller than a predetermined difference. The predetermined end condition may be, for example, a condition that the difference converges to be smaller than a predetermined difference.

[0093] The predetermined termination condition may be, for example, a condition that the mutual information between the partial analysis target image and the partial comparison target image converges. The mutual information between the partial analysis target image and the partial comparison target image is a quantity indicating the degree of consistency between the partial analysis target image and the partial comparison target image, and therefore the convergence of the mutual information between the partial analysis target image and the partial comparison target image means the convergence of the difference.

[0094] When the end condition is not satisfied (step S105: No), the content of the rigid body transformation is updated according to a predetermined rule so as to reduce the difference between part of the analysis target image and part of the comparison target image (step S107).

[0095] Specifically, the parameter values ​​that determine the content of the rigid body transformation are updated according to a predetermined rule so as to reduce the difference between part of the analysis target image and part of the comparison target image. After step S107, the process returns to step S102.

[0096] On the other hand, if the end condition is satisfied (step S105: Yes), the first transformed image after the transformation based on the process of the previous step S102 is obtained as the result of the second registration process (step S106). After executing step S106, the process ends.

[0097] Thus, in the second registration process, a first transformed image is obtained that satisfies the following condition: the difference between the image of the analysis object shown in the second transformed image and the image of the analysis object shown in the analysis object image is smaller than the difference before the second registration process is performed. More specifically, in the second registration process, a first transformed image is obtained in which the difference between the position or slope of the image of the analysis object shown in the first transformed image and the position or slope of the image of the analysis object shown in the analysis object image is smaller than the difference before the second registration process is performed.

[0098] Hereinafter, the first transformed image transformed by performing the second registration process is referred to as a second transformed image. Therefore, the image obtained as a result of the second registration process is the second transformed image.

[0099] The difference in morphology between the image of the object to be analyzed shown in the image to be analyzed and the image to be analyzed shown in the second transformed image is smaller than the difference in morphology between the image to be analyzed shown in the image to be analyzed and the image to be analyzed shown in the first transformed image. The morphology of the supporting part such as the root of a tooth changes less with age than that of other periodontal tissues, and therefore, by using the image to be analyzed and the second transformed image, the morphological change of the state of the tooth or periodontal tissue that occurs between the image to be analyzed and the second transformed image can be estimated with higher accuracy.

[0100] <Experimental Results>

[0101] Figure 4 This is an example of experimental results for evaluating the three-dimensional alignment process in the embodiment. Figure 4 The images G1-1, G1-2, G1-3, G2-1, G2-2, G2-3, G3-1, G3-2, G3-3, G4-1, G4-2, and G4-3 are shown.

[0102] Image G1-1 is a diagram of the object image before transformation observed from the first axis direction. The object image before transformation is a comparison object image before the three-dimensional alignment process is performed. Image G1-2 is a diagram of the object image before transformation observed from the second axis direction. Image G1-3 is a diagram of the object image before transformation observed from the third axis direction.

[0103] Image G2-1 is a diagram of the first transformed image observed from the first axis direction. Image G2-2 is a diagram of the first transformed image observed from the second axis direction. Image G2-3 is a diagram of the first transformed image observed from the third axis direction. Image G3-1 is a diagram of the second transformed image observed from the first axis direction. Image G3-2 is a diagram of the second transformed image observed from the second axis direction. Image G3-3 is a diagram of the second transformed image observed from the third axis direction.

[0104] Image G4-1 is a diagram of the analysis target image viewed from the first axis direction, Image G4-2 is a diagram of the analysis target image viewed from the second axis direction, and Image G4-3 is a diagram of the analysis target image viewed from the third axis direction.

[0105] Figure 4 It means that compared with the object image before transformation, the first transformed object image has smaller differences in the position and slope of the analyzed object, and compared with the first transformed image, the second transformed image has smaller differences in the position and slope of the analyzed object. Figure 4 This indicates a comparison target image obtained by three-dimensional alignment processing, which has a smaller difference from the analysis target image in terms of the position and slope of the analysis target.

[0106] In this way, the three-dimensional alignment process is a process of aligning two three-dimensional images.

[0107] The image to be analyzed and the second transformed image are both three-dimensional images. Therefore, a three-dimensional image (hereinafter referred to as a "three-dimensional highlighted image") can be generated that represents the difference between the image to be analyzed and the second transformed image by highlighting such as coloring. Such a three-dimensional highlighted image generation process (hereinafter referred to as a "three-dimensional highlighted image generation process") is executed, for example, by the control unit 11.

[0108] When a three-dimensional highlighted image is generated, the user can visually understand the difference between the state of the tooth or periodontal tissue shown in the analysis target image and the state of the tooth or periodontal tissue shown in the comparison target image.

[0109] The generation of three-dimensional highlighted images is beneficial not only to medical professionals but also to patients who are not medical professionals. This is because the periodontal tissue examination chart is a list of numerical values, so it is necessary to have knowledge of what each numerical value refers to, but with a three-dimensional image, this knowledge is not so much required, so it is easier to understand the examination results.

[0110] Furthermore, the three-dimensional highlighted image may be, for example, a three-dimensional image that shows the difference in different colors depending on whether the difference is positive or negative.

[0111] In addition, the three-dimensional highlighted image may be, for example, an image indicating whether the tooth root belongs to the first root part, the second root part, or the third root part. The first root part is a part of the tooth root that is not covered by the bone at the first moment. The second root part is a part of the tooth root that is covered by the bone at the first moment but is not covered by the bone at the second moment, which is a moment later than the first moment. The third root part is a part of the tooth root that is covered by the bone at the second moment as well as at the first moment.

[0112] In such a three-dimensional highlighted image, the first tooth root part is indicated in white, for example, the second tooth root part is indicated in red, for example, and the third tooth root part is indicated in green, for example.

[0113] Hereinafter, the tooth or periodontal tissue shown in the comparison target image is referred to as the first photographed tissue. Hereinafter, the tooth or periodontal tissue shown in the analysis target image is referred to as the second photographed tissue.

[0114] The analyzed object image and the second transformed image are both three-dimensional images. Therefore, the analyzed object image and the second transformed image are both sets of pixel values. Since the pixels are an ordered set, quantitative information related to the analyzed object image and the second transformed image can also be obtained based on the analyzed object image and the second transformed image. Hereinafter, the process of obtaining quantitative information related to the analyzed object image and the second transformed image (hereinafter referred to as "quantitative information") is referred to as quantitative information acquisition processing. The quantitative information acquisition processing is performed, for example, by the control unit 11.

[0115] The quantitative information related to the analysis target image and the second transformed image is, for example, information that numerically represents the difference between the analysis target image and the second transformed image. The information that numerically represents the difference between the analysis target image and the second transformed image is, for example, information that represents the amount of bone absorption of the second tissue relative to the first tissue. The information that numerically represents the difference between the analysis target image and the second transformed image is, for example, information that represents the amount of bone proliferation of the second tissue relative to the first tissue.

[0116] The information that numerically expresses the difference between the analysis target image and the second transformed image may be, for example, information that expresses the three-dimensional volume of each of the first tooth root site, the second tooth root site, and the third tooth root site.

[0117] Thus, if the second transformed image is used, quantitative information can be obtained with higher accuracy than that obtained by using the comparison target image before the three-dimensional alignment process. Therefore, the three-dimensional image processing device 1 that obtains the second transformed image can improve the diagnostic accuracy of the state of the tooth or periodontal tissue.

[0118] <About Generation of Mask Data>

[0119] Here, a specific example of generating mask data is described. Specifically, the mask data is generated by a computer. The mask data is generated, for example, by the control unit 11. In addition, the generation of mask data does not necessarily have to be performed by the three-dimensional image processing device 1, and may be performed by other devices.

[0120] In this case, the three-dimensional image processing device 1 obtains mask data generated by another device that generates mask data before executing the three-dimensional alignment process, and uses the mask data for the three-dimensional alignment process.

[0121] In order to simplify the description, an example of mask data generation processing (hereinafter referred to as “mask data generation processing”) will be described below by taking the case where the control unit 11 performs the processing as an example.

[0122] As described above, the image to be analyzed is a three-dimensional image. Therefore, the control unit 11 can perform processing on the three-dimensional image in the form of a set of two-dimensional images. In the mask data generation process, the control unit 11 processes the image to be analyzed in the form of an ordered set with slice images of the object to be analyzed as elements, that is, an ordered set in which the order of the elements is sorted in the direction from the object to be analyzed toward the crown of the tooth having the object to be analyzed (hereinafter referred to as the "ordered set of the object to be analyzed"). In the following, in order to simplify the description, the direction from the object to be analyzed toward the crown of the tooth having the object to be analyzed is referred to as the direction from the root of the object to be analyzed toward the crown.

[0123] The analysis target slice images are two-dimensional images generated by slicing the analysis target image in the direction from the root of the tooth to the crown of the tooth. Therefore, the analysis target slice images are a kind of so-called slice images.

[0124] In addition, the order of the ordered set may be ascending from the root of the analyzed object toward the crown, or may be descending from the crown of the analyzed object toward the root, but any rule is acceptable. In addition, for example, information on the direction from the root of the analyzed object toward the crown in mask data processing is obtained based on the point position information and the jaw designation information. The point position information is information indicating a point in the image and a point between the crown and the root of the analyzed object. The above-mentioned first designation information and the second designation information are both examples of point position information.

[0125] The jaw designation information is information indicating that the analysis object is either the upper jaw or the lower jaw in the three-dimensional image. The jaw designation information is input to the three-dimensional image processing device 1 by the user via the input unit 12, for example. In this case, the control unit 11 obtains the input jaw designation information. The point position information is input to the three-dimensional image processing device 1 by the user via the input unit 12, for example. In this case, the control unit 11 obtains the input point position information.

[0126] The control unit 11 selects whether each analysis target slice image is a two-dimensional image for mask data generation in the mask data generation process. The two-dimensional image for mask data generation is an analysis target slice image whose first order difference is greater than the second order difference, and whose first order difference is greater than the absolute value of the order difference between the slice image including the point indicated by the point designation information and the tooth crown boundary image.

[0127] The first order difference is the absolute value of the order difference between the crown boundary image and the tooth root inclusion boundary image. The second order difference is the absolute value of the order difference between the root inclusion boundary image and the tooth crown boundary image.

[0128] The tooth crown boundary image is an analysis target slice image that satisfies a predetermined condition in the analysis target slice image of the image showing the tooth crown (hereinafter referred to as the "tooth crown image"). The tooth root inclusion boundary image is an analysis target slice image that satisfies a predetermined condition in the analysis target slice image of the image showing the tooth root (hereinafter referred to as the "tooth root inclusion image").

[0129] The prescribed condition satisfied by the crown boundary image is, for example, a condition that the position difference with the root inclusion boundary image is smaller than that of other crown images. The prescribed condition satisfied by the root inclusion boundary image is, for example, a condition that the position difference with the crown boundary image is smaller than that of other root inclusion images. Therefore, the crown image can be, for example, an analysis object slice image that shows an image of the crown but not an image of the root. The root inclusion image can be, for example, an analysis object slice image that shows an image of the root but not an image of the crown.

[0130] In this way, the control unit 11 obtains a three-dimensional image including the tooth root of the analysis object but not including the tooth crown of the analysis object (hereinafter referred to as "three-dimensional image for mask data generation") in the form of a set of two-dimensional images for mask data generation. Next, the control unit 11 performs a binarization process to convert the three-dimensional image for mask data generation into a binary image in which the pixel values ​​of the tooth image and other images are different.

[0131] Binarization processing includes, for example, arc connection point determination processing. The arc connection point determination processing is a process of determining the set of the other ends of the curve satisfying the arc connection condition among the other ends of the curve in the three-dimensional image for mask data generation and the point indicated by the point position information as one end (hereinafter referred to as the "mask curve") as the image of the tooth. In other words, the arc connection point determination processing is a process of determining the pixels located at the other end of the curve satisfying the arc connection condition among the pixels in the image as the execution object (hereinafter referred to as the "arc connection pixel").

[0132] The arc connection condition is a condition that the difference between the pixel value of all points on the mask curve and the pixel value of the point indicated by the point position information is within a predetermined range.

[0133] The binarization process including the arc connection determination process includes a setting process. The setting process is a process of setting one of two predetermined pixel values ​​as the pixel value of the arc connection pixel and setting the other as the pixel value of the non-arc connection pixel. In addition, the control unit 11 performs the arc connection determination process in a manner that satisfies the secondary condition, thereby reducing the possibility that the arc connection pixel includes an area other than the tooth root, such as a bone area.

[0134] The secondary condition is that the range of the arc-shaped connected pixels is smaller than the actual tooth root. The control unit 11 may also perform a process of expanding the range of the arc-shaped connected pixels by morphological transformation after the binarization process. By performing a process of expanding the range of the arc-shaped connected pixels by morphological transformation after the binarization process, the control unit 11 can generate mask data that includes a safety margin around the tooth root.

[0135] By such binarization processing, the three-dimensional image for mask data generation is converted into a binary image in which the pixel values ​​of the tooth image and other images are different. The image data of the three-dimensional image for mask data generation after the conversion and binarization is an example of mask data.

[0136] Figure 5 1 is a diagram showing an example of the hardware configuration of the three-dimensional image processing device 1 in the embodiment. The three-dimensional image processing device 1 includes a control unit 11, which includes a processor 91 such as a CPU (Central Processing Unit) and a memory 92 connected via a bus, and executes a program. The three-dimensional image processing device 1 functions as a device including the control unit 11, the input unit 12, the communication unit 13, the storage unit 14, and the output unit 15 by executing the program.

[0137] More specifically, the processor 91 reads out a program stored in the storage unit 14 and stores the read program in the memory 92. As the processor 91 executes the program stored in the memory 92, the three-dimensional image processing device 1 functions as a device including the control unit 11, the input unit 12, the communication unit 13, the storage unit 14, and the output unit 15.

[0138] The control unit 11 controls the operation of various functional units of the three-dimensional image processing device 1. The control unit 11 may, for example, perform a three-dimensional alignment process. The control unit 11 may, for example, perform a mask data generation process. The control unit 11 may, for example, perform a three-dimensional highlighted image generation process. The control unit 11 may, for example, perform a quantitative information acquisition process. The control unit 11 may, for example, perform a pre-image forming process.

[0139] The input unit 12 includes input devices such as a mouse, a keyboard, and a touch panel. The input unit 12 may be configured as an interface for connecting these input devices to the three-dimensional image processing device 1. The input unit 12 receives input of various information to the three-dimensional image processing device 1.

[0140] For example, the user inputs information such as instructions to the control unit 11 to the input unit 12. For example, the first designation information may be input to the input unit 12. For example, the second designation information may be input to the input unit 12. For example, the jaw designation information may be input to the input unit 12. For example, the point position information may be input to the input unit 12.

[0141] The communication unit 13 is configured to include a communication interface for connecting the three-dimensional image processing device 1 to an external device. The communication unit 13 communicates with the external device via wired or wireless communication. The external device is, for example, a device that is a transmission source of the analysis target image. The communication unit 13 obtains the analysis target image by communicating with the device that is a transmission source of the analysis target image. The external device is, for example, a device that is a transmission source of the comparison target image. The communication unit 13 obtains the comparison target image by communicating with the device that is a transmission source of the comparison target image.

[0142] The devices that are the transmission sources of the analysis target image and the comparison target image may be the same. In this case, the devices that are the transmission sources of the analysis target image and the comparison target image may also perform a prior image forming process, for example. In this case, the analysis target image and the comparison target image transmitted by the devices that are the transmission sources of the analysis target image and the comparison target image are the analysis target image and the comparison target image obtained by the prior image forming process.

[0143] The external device may be, for example, a device that is an output destination of the image data of the second transformed image. In this case, the communication unit 13 outputs the image data of the second transformed image to the device that is an output destination of the image data of the second transformed image by communicating with the device that is an output destination of the image data of the second transformed image.

[0144] The external device may be, for example, a device that is an output destination of the image data of the three-dimensional highlighted image. In this case, the communication unit 13 outputs the image data of the three-dimensional highlighted image to the device that is an output destination of the image data of the three-dimensional highlighted image by communicating with the device that is an output destination of the image data of the three-dimensional highlighted image.

[0145] The external device may be, for example, a device as an output destination of the quantitative information. In this case, the communication unit 13 outputs the quantitative information to the device as an output destination of the quantitative information by communicating with the device as an output destination of the quantitative information.

[0146] The external device may be, for example, a device that is a source of mask data generation. In this case, the communication unit 13 obtains the mask data by communicating with the device that is a source of mask data generation. The device that is a source of mask data generation is a device that obtains an analysis target image that is an execution target in the three-dimensional alignment process, and performs mask data generation processing based on the obtained analysis target image to generate mask data.

[0147] The storage unit 14 is configured using a computer-readable storage medium device such as a magnetic hard disk device or a semiconductor storage device. The storage unit 14 stores various information related to the three-dimensional image processing device 1. The storage unit 14 stores, for example, information input via the input unit 12 or the communication unit 13. The storage unit 14 stores, for example, a comparison target image. The comparison target image may be obtained from an external device or the like, or may be pre-stored in the storage unit 14. The storage unit 14 may also store mask data.

[0148] The output unit 15 outputs various information. The output unit 15 is configured to include display devices such as a CRT (Cathode Ray Tube) display, a liquid crystal display, and an organic EL (Electro-Luminescence) display. The output unit 15 can also be configured as an interface for connecting these display devices to the three-dimensional image processing device 1. The output unit 15 outputs information input to the input unit 12 or the communication unit 13, for example.

[0149] The output unit 15 may display, for example, the second transformed image. The output unit 15 may display, for example, the analysis target image. The output unit 15 may display, for example, the three-dimensional highlighted image. The output unit 15 may display, for example, the quantitative information.

[0150] Figure 6 1 is a diagram showing an example of the configuration of the control unit 11 included in the three-dimensional image processing apparatus 1 according to the embodiment. The control unit 11 includes an image processing unit 111 , an input control unit 112 , a communication control unit 113 , a storage control unit 114 , and an output control unit 115 .

[0151] The image processing unit 111 performs at least a three-dimensional alignment process. The image processing unit 111 may also perform, for example, a three-dimensional highlighted image generation process. The image processing unit 111 may also perform, for example, a quantitative information acquisition process. The image processing unit 111 may also perform, for example, a preliminary image shaping process. The image processing unit 111 may also perform, for example, a mask data generation process.

[0152] The image processing unit 111 may, for example, control the operation of the communication control unit 113 so that the communication unit 113 outputs the image data of the second transformed image to a device that is an output destination of the image data of the second transformed image. In this case, the image processing unit 111 outputs the image data of the second transformed image to the communication control unit 113. The communication control unit 113 causes the communication unit 113 to output the obtained image data.

[0153] The image processing unit 111 may control the operation of the output control unit 115, for example, so that the output unit 115 outputs the image data of the second transformed image. In this case, the image processing unit 111 outputs the image data of the second transformed image to the output control unit 115. The output control unit 115 causes the output unit 15 to output the obtained image data.

[0154] The input control unit 112 controls the operation of the input unit 12. The communication control unit 113 controls the operation of the communication unit 13. The storage control unit 114 controls the operation of the storage unit 14.

[0155] The output control unit 115 controls the operation of the output unit 15. For example, the output control unit 115 controls the operation of the output unit 15 so that the output unit 15 displays the analysis target image. For example, the output control unit 115 controls the operation of the output unit 15 so that the output unit 15 displays the second transformed image obtained by the image processing unit 111.

[0156] For example, when the image processing unit 111 performs the three-dimensional highlighted image generation process, the output control unit 115 may control the operation of the output unit 15 so that the output unit 15 displays the three-dimensional highlighted image obtained by the image processing unit 111. For example, when the image processing unit 111 performs the quantitative information acquisition process, the output control unit 115 may control the operation of the output unit 15 so that the output unit 15 displays the quantitative information obtained by the image processing unit 111.

[0157] Use the following Figure 7 An example of the flow of processing performed by the three-dimensional image processing device 1 is described below. Figure 7 In the description, for simplicity, an example of the process is described by taking as an example a case where the second designation information is input in advance by the user and an analysis target image and a comparison target image on which a preliminary image forming process has been performed in advance are used.

[0158] Figure 7 1 is a flowchart showing an example of the process flow performed by the three-dimensional image processing device 1 of the embodiment. The target image group is input to the input unit 12 or the communication unit 13 (step S201). Next, the image processing unit 111 performs a first registration process on the image of the input target image group (step S202). Next, the image processing unit 111 performs a second registration process (step S203).

[0159] Next, the image processing unit 111 controls the operation of the communication control unit 113 or the output control unit 115, and outputs the image data of the second transformed image to the output destination corresponding to each control object (step S204). Therefore, in step S204, the image processing unit 111 controls the operation of the communication unit 13 by controlling the operation of the communication control unit 113, and outputs the image data of the second transformed image to the device as the output destination. In this case, as described above, the image processing unit 111 outputs the image data of the second transformed image to the communication control unit 113.

[0160] In step S204, the image processing unit 111 controls the operation of the output control unit 115 so that the output unit 15 outputs the image data of the second transformed image. In this case, the image processing unit 111 outputs the image data of the second transformed image to the output control unit 115 as described above.

[0161] (Experimental results)

[0162] An example of the result of an experiment using the three-dimensional image processing apparatus 1 is shown. Figure 8 is a diagram showing an example of an experimental result in an embodiment. In the experiment, an image showing changes in the alveolar bone of a patient is obtained by a three-dimensional image processing device 1. In the experiment, an image showing changes in the alveolar bone is obtained based on an image of the patient's teeth taken in 2018 and an image of the patient's teeth taken in 2020. Image G5-1 shows changes in the alveolar bone by highlighting. For example, area A1 in image G5-1 shows changes in the alveolar bone. The upper left, upper right, and lower left images of image G5-2 are examples of cross-sections of three-dimensional images taken in 2018, respectively.

[0163] Image G5-3 is an example of a three-dimensional image taken in 2018. The upper left, upper right, and lower left images of image G5-4 are examples of cross sections of a three-dimensional image taken in 2020, respectively. Image G5-5 is an example of a three-dimensional image taken in 2020. The difference between the image of area A2 in image G5-3 and the image of area A3 in image G5-5 is area A1. More specifically, area A1 indicates that there is absorption of alveolar bone between 2018 and 2020. According to image G5-1, the amount of absorption of alveolar bone in area A1 between 2018 and 2020 is 6.9 cubic millimeters.

[0164] The three-dimensional image processing device 1 of the embodiment configured in this way performs a rigid body transformation on one of the three-dimensional images so as to reduce the difference between the images of the analysis object shown in the two three-dimensional images taken at different times. As described above, the tooth root is less likely to undergo morphological changes over time than the tooth or other periodontal tissues. Therefore, such a three-dimensional image processing device 1 can improve the diagnostic accuracy of the state of the tooth or periodontal tissue.

[0165] (Variation Example)

[0166] In addition, when the point position information and the jaw information are input to the three-dimensional image processing device 1, the image processing unit 111 may also perform a separation-improved image generation process. The separation-improved image generation process is a process for generating an image in which the degree of separation between the image of the tooth and the image of the alveolar bone shown in the analysis target image and the second transformed image is improved. Hereinafter, for the sake of simplicity, the image to be executed in the separation-improved image generation process is referred to as a separation target image. The separation target image is the analysis target image or the second transformed image.

[0167] <Regarding Separation Improvement Image Generation Processing>

[0168] The separability-enhanced image generation process is an example of the mask data generation process.

[0169] In the separation-enhanced image generation process, the first secondary separation process is performed. The first secondary separation process is a process of selecting a slice on the root side of the position indicated by the point position information from the sliced ​​image obtained by slicing the separation target image from the direction of the root of the tooth to be analyzed toward the crown based on the jaw information. As described above, whether it is a slice image on the root side is determined based on the point position information and the jaw information.

[0170] The process of selecting a slice closer to the tooth root than the position indicated by the point position information in the resolution-enhanced image generation process is, for example, the above-mentioned process of selecting whether each analysis target slice image is a two-dimensional image for mask data generation.

[0171] In addition, when the image to be separated is a CT image, the image to be separated is a so-called axial image. Therefore, in this case, the long axis of the tooth is approximately orthogonal to the slice image. When analyzing a greatly tilted tooth, the slice image may be a slice image in which the user specifies the tooth axis or tooth neck line and re-cuts the slices orthogonal to the tooth axis.

[0172] In the separation-improved image generation process, the second secondary separation process is performed next. The second secondary separation process is a process of binarizing the separation target image by a threshold value greater than a predetermined value. The predetermined value is a value that satisfies the following condition: the area on the separation target image determined by the image processing unit 111 as pixels representing teeth is smaller than the threshold value and smaller than the predetermined value. Through the second secondary separation process, a binary image is obtained in which, for example, the pixel values ​​of teeth and alveolar bones are 1 and the pixel values ​​of other pixels are 0.

[0173] In the separation-enhanced image generation process, the third sub-separation process is performed next. The third sub-separation process is an arc connection point determination process.

[0174] In the improved-separability image generation process, a fourth sub-separation process is performed next. The fourth sub-separation process is a process of replacing the pixel values ​​of pixels surrounded by the arc-connected pixels and not being arc-connected pixels with the pixel values ​​of the arc-connected pixels.

[0175] In the separation-enhanced image generation process, the fifth sub-separation process is performed next. The fifth sub-separation process is a process of enlarging the area of ​​arc-shaped connected pixels to be larger than the actual root shape through morphological transformation, wherein the area of ​​the arc-shaped connected pixels is generated to be smaller than the actual root shape in order to reliably separate the tooth root and the alveolar bone in the second sub-separation process.

[0176] In the separation-enhanced image generation process, the sixth sub-separation process is executed next. The sixth sub-separation process is a process of setting all pixel values ​​of the slice images not selected in the first sub-separation process to 0.

[0177] In this way, the separation-improved image generation process is to perform arc-shaped connection point determination processing with a setting smaller than the actual tooth root based on the position of the point, and then perform an enlargement process. As a result, the second registration can be performed, and a mask can be automatically generated based only on the first designated information and the jaw designated information. Therefore, by performing the separation-improved image generation process, an image is generated in which the degree of separation between the tooth and the alveolar bone reflected in the separation object image is improved.

[0178] In addition, the case where the user inputs the first designation information, the second designation information, the point position information, and the jaw designation information has been described above as an example. However, the first designation information, the second designation information, the point position information, and the jaw designation information may be pre-stored in the storage unit 14. For example, if the user selects an analysis target image and a comparison target image, and the position indicated by the first designation information is substantially the same regardless of the image, the user does not need to input the first designation information.

[0179] In addition, even if the user does not make a selection, an image with substantially the same position indicated by the first designation information can be obtained regardless of the image due to limitations of the shooting environment, and in this case, the user does not need to input the first designation information. The same applies to the second designation information, point position information, and jaw designation information.

[0180] In addition, in the generation of mask data, range position information may be used instead of point position information. The range position information may also be information indicating the tooth neck. Since the tooth neck is below the tooth root, mask data will be generated even if range position information is used instead of point position information.

[0181] In addition, the three-dimensional image processing device 1 does not necessarily need to be composed of a single housing. The three-dimensional image processing device 1 may also be implemented using a plurality of information processing devices that are communicably connected via a network. In this case, the functional units of the three-dimensional image processing device 1 may also be dispersed and installed in a plurality of information processing devices.

[0182] In addition, the output unit 15 is an example of a prescribed display destination. In addition, the first transformed image is an example of one three-dimensional image after the first registration process is performed.

[0183] In addition, all or part of the functions of the three-dimensional image processing device 1 can also be implemented using hardware such as ASIC (Application Specific Integrated Circuit), PLD (Programmable Logic Device), FPGA (Field Programmable Gate Array). The program can also be recorded in a computer-readable recording medium. In addition, "computer-readable recording medium" refers to removable media such as floppy disks, optical magnetic disks, ROMs, CD-ROMs, and storage devices such as hard disks built into computer systems. The program can also be sent via telecommunication lines.

[0184] As mentioned above, although the embodiment of this invention is demonstrated in detail with reference to drawings, the specific structure is not limited to these embodiments, and also includes the design etc. within the range which does not deviate from the summary of this invention.

[0185] Description of Reference Numerals

[0186] 1: Three-dimensional image processing device

[0187] 11: Control Department

[0188] 12: Input section

[0189] 13: Ministry of Communications

[0190] 14: Storage

[0191] 15: Output section

[0192] 111: Image processing department

[0193] 112: Input control unit

[0194] 113: Communication Control Department

[0195] 114: Storage control unit

[0196] 115: Output control unit

[0197] 91: Processor

[0198] 92: Memory.

Claims

1. A three-dimensional image processing device that generates image data for analyzing a three-dimensional image of a diagnostic object, comprising: an image processing unit that performs alignment on a three-dimensional image of an analysis object captured at a first time and a three-dimensional image of the analysis object captured at a second time, the second time being different from the first time, in, The three-dimensional image shows an image of an object in a predetermined space including the analysis target. The diagnosis object exists in the space, The object of analysis is a support part, The alignment includes: A first registration process is performed to perform a rigid body transformation on one of the two three-dimensional images to reduce the difference between the one three-dimensional image and the other three-dimensional image; and The second registration process performs a rigid body transformation on the one three-dimensional image after the first registration process to reduce the difference between the image of the analysis object projected in the other three-dimensional image and the image of the analysis object projected in the one three-dimensional image.

2. The three-dimensional image processing device according to claim 1, wherein: In the second registration process, mask data is used, the mask data indicating pixels of a region among pixels of the other three-dimensional image, the region being on the other three-dimensional image and including the image of the analysis object.

3. The three-dimensional image processing device according to claim 2, wherein: The mask data is image data including a binary image in which the image of an object in a predetermined space to be analyzed and other images have different pixel values.

4. The three-dimensional image processing device according to claim 3, wherein: The binary image is a binary image in which the pixel value of the arc-shaped connected pixels is one of the two predetermined pixel values, and the pixel value of the pixel not connected in the arc-shaped is the other of the two predetermined pixel values, the arc-shaped connected pixels are pixels located at the other end of the curve, and the other end of the curve is: the other end of the curve located in the three-dimensional image and having one end as a specified point, and the other end of the curve satisfies the condition that the difference between the pixel value of all points on the curve and the pixel value of the point is within a predetermined range, wherein the three-dimensional image includes the image of the support part of the analysis object, but does not include the image of the functional part of the tooth having the analysis object, and the specified point is located between the image of the support part and the image of the functional part. The functional part is a crown of a natural tooth, a superstructure of a dental implant, a head or a plate of an orthopedic implant.

5. The three-dimensional image processing device according to claim 1, comprising: an output control unit that controls the operation of a predetermined display destination, in, the image processing unit generates a three-dimensional highlight image based on the other three-dimensional image and the one three-dimensional image transformed by the alignment, the three-dimensional highlight image being a three-dimensional image showing a difference between the other three-dimensional image and the one three-dimensional image in a highlighted manner, The output control unit displays the three-dimensional highlighted image on the display destination.

6. The three-dimensional image processing device according to claim 1, comprising: an output control unit that controls the operation of a predetermined display destination, in, the image processing unit obtains quantitative information indicating a difference between the other three-dimensional image and the one three-dimensional image using numerical values, based on the other three-dimensional image and the one three-dimensional image transformed by the alignment, The output control unit displays the quantitative information on the display destination.

7. A three-dimensional image processing method, which generates image data for analyzing a three-dimensional image of a diagnostic object, comprising: an image processing step of aligning a three-dimensional image of the analysis object captured at a first moment and a three-dimensional image of the analysis object captured at a second moment, the second moment being different from the first moment, in, The three-dimensional image shows an image of an object in a predetermined space including the analysis target. The diagnosis object exists in the space, The analysis object is a support part, The alignment includes: A first registration process is performed to perform a rigid body transformation on one of the two three-dimensional images to reduce the difference between the one three-dimensional image and the other three-dimensional image; and The second registration process performs a rigid body transformation on the one three-dimensional image after the first registration process to reduce the difference between the image of the support portion projected in the other three-dimensional image and the image of the support portion projected in the one three-dimensional image. 8 . A program for causing a computer to function as the three-dimensional image processing device according to claim 1 .

Images