Intraoral shape acquisition device and intraoral shape acquisition method

Abstract

An intraoral shape acquisition device (1) capable of correctly acquiring an intraoral shape of a region to which saliva or blood or the like is attached or a gingival margin region, includes a scanner (111) that takes an image of an intraoral region to acquire an intraoral shape, and an air blower (113) that ejects compressed air, the air blower (113) ejecting the compressed air toward a subject of the image taking when the scanner (111) takes the image.

Description

Technical Field

[0001] This invention relates to an intraoral shape acquisition device and a method for acquiring intraoral shape, and more specifically, to a technique for accurately acquiring intraoral shape data of areas covered with saliva, blood, etc., or gingival margin areas. Background Technology

[0002] In recent years, the development of digitalization (digital dentistry) in the dental industry has led to the emergence of instruments that can perform treatments more simply and with higher precision than before. For example, a device called an Intra Oral Scanner (IOS) can take pictures of the inside of a patient's mouth using a reader called a scanning pen, outputting the shape of the mouth as digital data (model). Typically, the scanning pen emits light towards the object (teeth or gums, etc.), and sensors detect the reflected light, thereby obtaining point group data representing the three-dimensional shape of the object.

[0003] On the other hand, the following issues were also pointed out regarding IOS. If the object is wetted by saliva, blood, etc., IOS cannot obtain adequate reflected light, thus sometimes failing to generate accurate models. Furthermore, IOS can only capture the visible area inside the oral cavity, and therefore usually cannot model the invisible areas located at the gum line. Technical products made based on inaccurate models generated due to such problems cannot be properly installed inside the oral cavity.

[0004] To address this issue, measures have been taken to continuously aspirate saliva, blood, etc., during the imaging process. Additionally, when imaging the gingival margin area, a procedure is performed to separate the abutment tooth from the gum (indentation). In cases where bleeding occurs due to indentation, aspiration is also necessary.

[0005] Patent documents 1 and 2 disclose an intraoral scanner that obtains the shape of the abutment tooth located at the gingival margin by using a needle-shaped measuring clamp to swipe across the surface of the tooth.

[0006] Existing technical documents

[0007] Patent documents

[0008] Patent Document 1: Japanese Patent Application Publication No. 2018-047299

[0009] Patent Document 2: Japanese Patent Application Publication No. 2016-508754 Summary of the Invention

[0010] The problem that the invention aims to solve

[0011] However, using suction or descaling methods during imaging requires a significant amount of time and effort from the dentist. Furthermore, it places a heavy physical burden on the patient. To employ the method described in Patent Document 1 or 2, the dentist needs to be familiar with the use of specialized measuring clamps.

[0012] The present invention was made to solve such problems, and its purpose is to provide an intraoral shape acquisition device and a method for accurately acquiring the intraoral shape of areas or gingival margins that are covered with saliva, blood, etc.

[0013] Methods for solving problems

[0014] An intraoral shape acquisition device according to one embodiment of the present invention includes: a scanner that takes pictures of the intraoral cavity to acquire the intraoral shape; and an air blower that sprays compressed air onto the subject being photographed while the scanner is taking the pictures.

[0015] In one embodiment of the oral cavity shape acquisition device of the present invention, the scanner and the air blower are built into the scanning pen.

[0016] In one embodiment of the oral cavity shape acquisition device of the present invention, the air blower can be attached to and detached from the scanning pen in which the scanner is built-in.

[0017] An intraoral shape acquisition device according to one embodiment of the present invention further includes an information processing device having: a sensing data acquisition unit that receives sensing data representing the intraoral shape from the scanner; and a model generation unit that generates a three-dimensional model based on the sensing data.

[0018] In an intraoral shape acquisition device according to one embodiment of the present invention, the scanner continuously acquires sensing data representing the intraoral shape while the air blower is spraying compressed air onto the subject, and the information processing device further has a feature for identifying abutment teeth of gingiva and abutment teeth included in the model based on the changes in the sensing data over time.

[0019] Invention Effects

[0020] According to the present invention, an intraoral shape acquisition device and a method for accurately acquiring the intraoral shape of areas or gingival margins covered with saliva, blood, etc. are provided. Attached Figure Description

[0021] Figure 1 This is a block diagram showing the structure of the intraoral shape acquisition device according to Embodiment 1.

[0022] Figure 2 It is a 3D diagram showing the appearance of the scanning pen.

[0023] Figure 3 It is a 3D diagram showing the appearance of the scanning pen.

[0024] Figure 4 This is a block diagram showing the structure of the intraoral shape acquisition device according to Embodiment 2.

[0025] Figure 5 This is a flowchart illustrating the operation of the intraoral shape acquisition device according to Embodiment 2. Detailed Implementation

[0026] Hereinafter, specific embodiments of the present invention will be described in detail with reference to the accompanying drawings.

[0027] (Implementation Method 1)

[0028] Figure 1 This is a block diagram illustrating the structure of an intraoral shape acquisition device 1 according to Embodiment 1 of the present invention. The intraoral shape acquisition device 1 includes a scanning pen 11 and an information processing device 13.

[0029] The scanning pen 11 is typically a cane-like device that a dentist can hold, used to photograph the shape inside a patient's mouth. Figure 2 This is a perspective view showing the appearance of the scanning pen 11 according to this embodiment. The scanning pen 11 includes a scanner 111 and an air blower 113. In this example, the scanner 111 and the air blower 113 are built into the housing of the scanning pen 11.

[0030] Scanner 111 includes a light source 1111 and a sensor 1113. The light source 1111 emits light to multiple points on the surface of the object. The reflected light from each point on the surface of the object is detected by the sensor 1113. Furthermore, in Figure 2 The image shows an example where the light source 1111 and sensor 1113 are arranged side-by-side near the front end of the housing of the scanning pen 11, but this arrangement can be modified accordingly. For example, the light source 1111 or sensor 1113 can also be arranged inside the housing of the scanning pen 11. In this case, it is possible to design an optical path for connecting the light source 1111 or sensor 1113 to the outside of the housing, allowing radiated or reflected light to pass through this optical path.

[0031] The information processing apparatus 13 includes a sensing data acquisition unit 131 and a model generation unit 133. The sensing data acquisition unit 131 acquires the detection results (sensing data) of the sensor 1113 for reflected light. The model generation unit 133 determines the distance from the scanner 111 to each point on the surface of the object based on the sensing data, for example, using known methods such as active wavefront sampling or confocal methods. Furthermore, based on these distances, it determines the coordinates of each point on the surface of the object. The model generation unit 133 outputs a model as a group of point data for each point on the surface of the object, or three-dimensional data (polygon data, etc.) generated based on this group of point data.

[0032] Furthermore, the information processing device 13 includes hardware such as a processing unit (CPU), a storage unit, an input / output unit, and a communication unit. Each of the aforementioned processing units (131, 133) is logically implemented by the CPU executing programs stored in the storage unit.

[0033] Air blower 113 injects compressed air from nozzle 1131. Figure 2 In this example, an air blower nozzle 1131 is provided near the front end of the housing of the scanner 111. The orientation of the nozzle 1131 is preferably variable, but it can also be fixed. In short, the orientation of the nozzle 1131 is set to efficiently spray compressed air onto the object. The air blower 113 sprays compressed air onto the object when the scanner 111 is photographing it (including before or during photographing). The sprayed compressed air disperses and removes saliva, blood, etc., present on the surface of the object. As a result, the scanner 111 can obtain the correct reflected light from the surface of the object. In addition, when compressed air is sprayed into the pocket-shaped area between the gum and the abutment tooth, the pocket is opened by the compressed air. As a result, the abutment tooth at the gum margin can be easily photographed without the need for pressure or other measures.

[0034] The air blower 113 can be configured to automatically start injecting compressed air in conjunction with the operation of the scanner 111. Alternatively, the air blower 113 may also have a button for manually starting the injection of compressed air.

[0035] In addition, Figure 2 In the example, scanner 111 and air blower 113 are integrated, but they can also be configured to be separable. For example, as... Figure 3 As shown, the scanning pen 11 can also be implemented by externally mounting an air blower 113 on the existing scanner 111 via accessory 1132.

[0036] According to this embodiment, the air blower 113 sprays compressed air onto the object when the scanner 111 takes a picture of the object. Therefore, even if the object is moistened with saliva, blood, or located at the gum line, there is no need for suction or decanting; an accurate model of the object can be obtained simply by one hand. This reduces the time and effort required by dentists compared to conventional methods. Furthermore, it also reduces the physical burden on patients.

[0037] (Implementation Method 2)

[0038] According to Embodiment 1, it is possible to easily photograph the abutment tooth at the gingival margin. In Embodiment 2, a means for automatically identifying the abutment tooth and gingiva is further provided.

[0039] When compressed air is injected into the pocket-shaped area between the gum and the abutment tooth, the compressed air causes the pocket to open. The objects subjected to the compressed air injection (the abutment tooth and gum) vibrate, but the characteristics of the vibration vary greatly depending on the location. That is, the amplitude and period of the vibration should be different between the relatively soft gum and the abutment tooth, which is firmly fixed to the bone.

[0040] Therefore, in this embodiment, firstly, compressed air is injected while continuously photographing the state around the abutment tooth at the gingival margin. In other words, "moving images" are captured at a predetermined frame rate. Next, the captured moving images are analyzed to detect differences in the vibration characteristics of the object. Thus, the abutment tooth and gingiva included in the model are identified.

[0041] Figure 4 This is a block diagram showing the structure of the intraoral shape acquisition device 1 according to Embodiment 2. The information processing device 13 has abutment tooth recognition unit 135, which performs processing for recognizing abutment teeth and gingiva. Other components of the intraoral shape acquisition device 1 are the same as those in Embodiment 1.

[0042] use Figure 5 The flowchart below illustrates an example of the operation of the intraoral shape acquisition device 1. Here, the explanation focuses on the differences from Embodiment 1, and descriptions of structures and operations already described in Embodiment 1 are omitted as appropriate.

[0043] Step 1: Capturing moving images

[0044] The dentist points the scanning pen 11 toward the abutment tooth at the gum line to begin taking pictures. The air blower 113 starts operating, using compressed air to open the pocket between the gum and the abutment tooth. The scanner 111 begins taking pictures, continuously capturing the intraoral shape around the abutment tooth at predetermined intervals (frame rate). The model generation unit 133 then outputs multiple models sequentially over time. This is what is called a three-dimensional "dynamic image." This "dynamic image" is stored in the storage device within the information processing unit 13.

[0045] Step 2: Feature point extraction

[0046] The abutment tooth recognition unit 135 extracts feature points from each model contained in the "dynamic image". Typically, it can use all or a portion of the point groups contained in the model as feature points.

[0047] Step 3: Calculation of the motion of feature points

[0048] The tooth recognition unit 135 compares multiple models that are consecutively defined in time, identifies the corresponding feature points, and records the coordinates of these feature points in each frame. This process is performed on all frames. That is, the coordinates n1 of feature point N in the model at time t1, n2 of feature point N in the model at time t2, n3 of feature point N in the model at time t3, and so on, are determined sequentially. Then, a dataset {n1, n2, n3, ...} representing the motion of feature point N is generated. The same process is performed for other feature points O, P, Q, ...

[0049] Step 4: Discrimination of abutment teeth and gingiva based on the motion characteristics of feature points

[0050] The abutment tooth recognition unit 135 detects differences in the motion characteristics of feature points. Typically, there are threshold-based discrimination methods and machine learning-based discrimination methods.

[0051] (Threshold-based discrimination)

[0052] The tooth abutment recognition unit 135 calculates an index for evaluating the motion of feature point N based on a dataset {n1, n2, n3…} representing the motion of feature point N. For example, if feature point N is vibrating, its amplitude and period can be calculated as indices. Indices are calculated similarly for other feature points O, P, Q…

[0053] The abutment tooth identification unit 135 distinguishes feature points by applying a predefined threshold to the calculated index. For example, feature points with amplitudes exceeding the threshold X are labeled as representing gingiva, while feature points with amplitudes below the threshold X are labeled as representing abutment teeth. Here, the threshold can be a value pre-determined through experiments or the like.

[0054] (Discrimination based on machine learning)

[0055] The abutment tooth recognition unit 135 uses a dataset {n1, n2, n3…} representing the motion of feature points N as learning data, and can classify the feature points into abutment teeth and gingiva through machine learning. For example, the abutment tooth recognition unit 135 has a machine learning unit 1351 that performs unsupervised learning. When the machine learning unit 1351 is given a dataset representing the motion of multiple feature points as learning data, it automatically identifies the differences in their characteristics and forms a set (cluster) of feature points with the same characteristics. The machine learning unit 1351 assigns a label representing gingiva to the feature points contained in one cluster and a label representing abutment teeth to the feature points contained in the other cluster.

[0056] Furthermore, the machine learning unit 1351 can also classify feature points into abutment teeth and gingiva using other well-known machine learning methods such as supervised learning and deep learning. For example, in supervised learning, during the learning phase, the machine learning unit 1351 is provided with multiple known training data sets that combine a dataset representing the motion of a feature point with labels indicating whether the feature point is an abutment tooth or gingiva. Thus, the machine learning unit 1351 gradually learns the correlation between the dataset representing the motion of the feature point and the labels indicating whether the feature point is an abutment tooth or gingiva. As learning progresses, the machine learning unit 1351 takes an unknown dataset representing the motion of a feature point as input and outputs an inferrer with labels highly correlated with that feature point.

[0057] Step 5: Determining the Boundary Line

[0058] The abutment tooth identification unit 135 determines the boundary between the feature points identified as abutment teeth in step 4 and the feature points identified as gingiva. This boundary is called the boundary line. The abutment tooth identification unit 135 generates a line (reflection) object representing the boundary line.

[0059] Step 6: Output of the model, etc.

[0060] The abutment tooth recognition unit 135 outputs the desired content from the model of the abutment tooth, the boundary line, and the model of the gingiva.

[0061] According to this embodiment, the intraoral shape acquisition device 1 can distinguish the abutment tooth and gingiva based on differences in their movement by analyzing continuous model data over time. Furthermore, it can automatically generate a model reflecting the accurate shape of the abutment tooth and a boundary line corresponding to the boundary between the abutment tooth and the gingiva. Therefore, it is possible to manufacture a technical product with excellent fit.

[0062] Furthermore, the present invention is not limited to the embodiments described above, and appropriate modifications can be made without departing from the spirit of the invention. For example, in the above embodiments, the intraoral shape acquisition device 1 acquires three-dimensional point group data, but two-dimensional image data may also be acquired. In this case, the model generation unit 133 can construct a three-dimensional model based on multiple two-dimensional image data. In addition, the method for constructing a three-dimensional model from two-dimensional images is a known technique, so detailed description is omitted.

[0063] In addition to acquiring three-dimensional point group data, the intraoral shape acquisition device 1 can also acquire additional information related to the color, temperature, etc., of each feature point. In this case, for example, if the machine learning unit 1351 uses this additional information as learning data, the discrimination accuracy can be improved.

[0064] Explanation of reference numerals in the attached figures

[0065] 1. Intraoral shape acquisition device

[0066] 11 Scanning Pen

[0067] 111 Scanner

[0068] 1111 Light Source

[0069] 1113 sensor

[0070] 113 Air Blower

[0071] 1131 jet nozzle

[0072] Attachment 1132

[0073] 13 Information Processing Devices

[0074] 131 Sensor Data Acquisition Unit

[0075] Model Generation Department 133

[0076] 135 abutment tooth identification section

[0077] 1351 Machine Learning Department.

Claims

1. An intraoral shape acquisition device, characterized in that, The intraoral shape acquisition device includes: A scanner that continuously captures images of the intraoral shape around the abutment tooth at a predetermined frame rate at the gingival margin; An air blower that injects compressed air; as well as Information processing device The air blower sprays compressed air onto the object being photographed during the scanning process. The scanner continuously acquires sensor data representing the shape inside the oral cavity while the air blower is spraying compressed air onto the subject. The information processing device has: A sensing data acquisition unit receives sensing data representing the shape inside the oral cavity from the scanner; The model generation unit outputs multiple three-dimensional dynamic images in a time sequence based on the sensed data; as well as The abutment tooth recognition unit analyzes multiple consecutive three-dimensional dynamic images in a time sequence, identifies corresponding feature points, detects differences in the motion characteristics of these feature points, and determines the abutment teeth and gingiva contained in the dynamic images based on these differences in motion characteristics. The abutment tooth recognition unit outputs at least one of the following: a three-dimensional model of the abutment tooth, a boundary line representing the boundary between the gingiva and the abutment tooth, and a three-dimensional model of the gingiva.

2. The intraoral shape acquisition device according to claim 1, characterized in that, The scanner and the air blower are built into the scanning pen.

3. The intraoral shape acquisition device according to claim 1, characterized in that, The air blower can be attached to and detached from the scanning pen that has the built-in scanner.

4. The intraoral shape acquisition device according to claim 1, characterized in that, The abutment tooth recognition unit has a machine learning unit that distinguishes between the abutment tooth and the gingiva.

Images