Method, device, equipment and medium for determining tooth operation planning data

Abstract

The present disclosure relates to a method, device, equipment and medium for determining operation planning data of teeth. It includes: obtaining a three-dimensional scanning image of a target oral cavity and coordinate data of tooth feature points in the target oral cavity; based on the three-dimensional scanning image, performing pulp opening planning and root canal planning on the tooth to be repaired in the target oral cavity, and obtaining pulp opening planning image data and root canal planning image data of the tooth to be repaired; determining a first mapping relationship between tooth feature points and tooth pixel points according to the coordinate data of tooth feature points and the coordinate data of tooth pixel points contained in the three-dimensional scanning image; obtaining operation planning data of the tooth to be repaired based on the first mapping relationship, pulp opening planning image data and root canal planning image data. Thus, the operation planning data of the tooth to be repaired is determined by using the data at the image level of the target oral cavity and the coordinates of the actual feature points on the tooth, so as to guide the operation tool to accurately remove the infected part of the root canal in the tooth to be repaired based on the operation planning data.

Description

Technical Field

[0001] The present disclosure relates to the technical field of tooth restoration, and in particular to a method, device, equipment and medium for determining tooth operation planning data. Background Art

[0002] Dental pulp problems are common oral problems. If not treated promptly, they can cause severe tooth pain and tooth loss, which in turn can affect digestive function and even overall health.

[0003] At present, the dental pulp problem is generally solved by clearing the infected part of the root canal in the tooth to be repaired. However, the core of this method is how to determine the operation planning data of the tooth to be repaired. Therefore, a reliable method for determining the operation planning data of the tooth to be repaired is urgently needed to determine the operation planning data of the tooth to be repaired, so that the operation tool can accurately clear the infected part of the root canal in the tooth to be repaired based on the operation planning data of the tooth to be repaired. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides a method, device, equipment and medium for determining tooth operation planning data.

[0005] In a first aspect, the present disclosure provides a method for determining tooth operation planning data, comprising:

[0006] Acquire a three-dimensional scanned image of a target oral cavity and coordinate data of characteristic points of teeth in the target oral cavity;

[0007] Based on the three-dimensional scanning image, pulp access planning and root canal planning are performed on the tooth to be restored in the target oral cavity to obtain pulp access planning image data and root canal planning image data of the tooth to be restored;

[0008] Determine a first mapping relationship between the tooth feature points and the tooth pixel points according to the coordinate data of the tooth feature points and the coordinate data of the tooth pixel points included in the three-dimensional scanned image;

[0009] Based on the first mapping relationship, the pulp access planning image data and the root canal planning image data, the operation planning data of the tooth to be restored is acquired.

[0010] In a second aspect, the present disclosure provides a device for determining tooth operation planning data, comprising:

[0011] A first acquisition module is used to acquire a three-dimensional scanning image of a target oral cavity and coordinate data of tooth feature points in the target oral cavity;

[0012] A planning module, used for performing pulp opening planning and root canal planning on the tooth to be restored in the target oral cavity based on the three-dimensional scanning image, and obtaining pulp opening planning image data and root canal planning image data of the tooth to be restored;

[0013] A determination module, configured to determine a first mapping relationship between the tooth feature point and the tooth pixel point according to the coordinate data of the tooth feature point and the coordinate data of the tooth pixel point contained in the three-dimensional scanning image;

[0014] The second acquisition module is used to acquire the operation planning data of the tooth to be restored based on the first mapping relationship, the pulp opening planning image data and the root canal planning image data.

[0015] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the device comprising:

[0016] one or more processors;

[0017] a storage device for storing one or more programs,

[0018] When one or more programs are executed by one or more processors, the one or more processors implement the method provided in the first aspect.

[0019] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method provided in the first aspect is implemented.

[0020] Compared with the prior art, the technical solution provided by the embodiments of the present disclosure has the following advantages:

[0021] The present disclosure discloses a method, device, equipment and medium for determining operation planning data of a tooth, including: obtaining a three-dimensional scanning image of a target oral cavity and coordinate data of a tooth feature point in the target oral cavity; performing pulp opening planning and root canal planning on the tooth to be repaired in the target oral cavity based on the three-dimensional scanning image, and obtaining pulp opening planning image data and root canal planning image data of the tooth to be repaired; determining a first mapping relationship between the tooth feature point and the tooth pixel point according to the coordinate data of the tooth feature point and the coordinate data of the tooth pixel point contained in the three-dimensional scanning image; obtaining operation planning data of the tooth to be repaired based on the first mapping relationship, pulp opening planning image data and root canal planning image data. Thus, the pulp opening planning data and root canal planning data are determined at the image level by using the three-dimensional scanning image of the target oral cavity, and then the pulp opening planning data and root canal planning data determined from the image level are mapped to the actual tooth according to the conversion relationship determined by the coordinates of the actual tooth feature point and the coordinates of the tooth pixel point contained in the three-dimensional scanning image, so as to obtain the operation planning data of the tooth to be repaired, so as to guide the operation tool to accurately remove the infected part of the root canal in the tooth to be repaired based on the operation planning data of the tooth to be repaired. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0024] Figure 1 A schematic flow chart of a method for determining tooth operation planning data provided by an embodiment of the present disclosure;

[0025] Figure 2 A schematic diagram of the process of S120 provided in an embodiment of the present disclosure;

[0026] Figure 3 A schematic diagram of the internal structure of a tooth to be repaired provided in an embodiment of the present disclosure;

[0027] Figure 4 A schematic diagram of the structure of a device for determining tooth operation planning data provided by an embodiment of the present disclosure;

[0028] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] In order to more clearly understand the above-mentioned objectives, features and advantages of the present disclosure, the scheme of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0030] In the following description, many specific details are set forth to facilitate a full understanding of the present disclosure, but the present disclosure may also be implemented in other ways different from those described herein; it is obvious that the embodiments in the specification are only part of the embodiments of the present disclosure, rather than all of the embodiments.

[0031] In order to enable the operating tool to accurately remove the infected part of the root canal in the tooth to be repaired, the following Figure 1-Figure 3 The method for determining tooth operation planning data provided by the embodiment of the present disclosure is described. In the embodiment of the present disclosure, the method for determining tooth operation planning data can be executed by an electronic device. The electronic device can be a control device of a surgical robot.

[0032] Figure 1 A schematic flow chart of a method for determining tooth operation planning data provided by an embodiment of the present disclosure is shown.

[0033] like Figure 1 As shown, the method for determining tooth operation planning data may include the following steps.

[0034] S110, obtaining a three-dimensional scanning image of the target oral cavity and coordinate data of tooth feature points in the target oral cavity.

[0035] In this embodiment, before controlling the working tool to clear the infected part of the root canal in the tooth to be repaired, the electronic device obtains a three-dimensional scanning image of the target oral cavity where the tooth to be repaired is located, which is collected by a three-dimensional scanning device, and after the user uses a probe to select tooth feature points on the teeth in the target oral cavity, the electronic device locates the coordinate data of the tooth feature points through a tracking system, so that the electronic device combines the image data and the coordinate data of the tooth feature points to determine the working planning data of the tooth to be repaired.

[0036] The target oral cavity includes various types of teeth, especially teeth to be repaired that need to remove infected parts of the root canals, and each tooth has a unique number.

[0037] The three-dimensional scanned image may be a computed tomography (CT) image obtained by scanning various types of teeth in the target oral cavity using a three-dimensional scanning device. Optionally, the three-dimensional scanned image includes a tooth area, a gum area, and other areas.

[0038] Among them, tooth feature points can be some points selected on the teeth using a probe. In order to prevent the user from moving during the point selection process, we install a reference frame on the user's upper or lower teeth. When the user moves, the reference frame also moves, but the reference frame and the upper or lower teeth remain relatively stationary. By simultaneously acquiring the probe coordinates and the reference frame coordinates, we transform the probe coordinates into the reference frame coordinate system, thereby solving the problem of user movement.

[0039] S120, performing pulp access planning and root canal planning on the tooth to be restored in the target oral cavity based on the three-dimensional scanning image, and obtaining pulp access planning image data and root canal planning image data of the tooth to be restored.

[0040] In this embodiment, the electronic device analyzes the three-dimensional scanning image at the image level, so that according to the analysis results at the image level, pulp access planning and root canal planning are performed on the tooth to be repaired in the target mouth, and the pulp access planning results and root canal planning results of the tooth to be repaired at the image level are obtained.

[0041] The pulp access planning refers to planning an area on the tooth to be repaired that is convenient for the execution tool to enter the root canal, so as to guide the execution tool to enter the root canal to remove the infected part based on the area. Correspondingly, the pulp access planning image data of the tooth to be repaired is image data containing the pulp access planning area of ​​the tooth to be repaired.

[0042] Root canal planning refers to planning the position, angle, and length of the tool entering the root canal on the tooth to be repaired, so as to avoid damaging the tooth to be repaired after the tool enters the root canal, and at the same time, try to clean up the infected area. Correspondingly, the root canal planning image data of the tooth to be repaired is the image data that marks the root canal length of the tooth to be repaired, the position and angle of the tool entering the root canal.

[0043] S130, determining a first mapping relationship between the tooth feature points and the tooth pixel points according to the coordinate data of the tooth feature points and the coordinate data of the tooth pixel points included in the three-dimensional scanning image.

[0044] In this embodiment, after the electronic device uses the tracking system to locate the coordinate data of the tooth feature points (i.e., the actual coordinates of the tooth feature points), and after reading the coordinate data of the tooth pixel points from the three-dimensional scanning image (i.e., the coordinates of the tooth pixel points at the image level), the two are aligning to determine the conversion relationship between the coordinates of the actual tooth feature points and the coordinates of the tooth pixel points at the image level, and uses the conversion relationship as the first mapping relationship.

[0045] It is understandable that, considering the problem that the user is prone to movement during the point selection process, a reference frame is installed on the upper teeth or lower teeth of the target oral cavity, and then the probe is used to select feature points on the teeth, and the coordinate data of the tooth feature points of each tooth relative to the reference frame is obtained. For example, the coordinate data of the reference frame is expressed as [x0, y0], the probe coordinates are [x1, y1], and the coordinate data of the tooth feature points of each tooth relative to the reference frame is expressed as [x1-x0, y1-y0].

[0046] Among them, the coordinate data of the tooth feature points in the target oral cavity includes the coordinate data of the tooth feature points of each tooth relative to the reference frame; accordingly, the specific implementation method of S130 includes but is not limited to the following method: for the reference teeth to be repaired in the target oral cavity, the coordinate data of the tooth feature points of the reference teeth relative to the reference frame and the coordinate data of the tooth pixel points of the reference teeth contained in the three-dimensional scanning image are aligned to obtain a first coordinate transformation matrix; based on the first coordinate transformation matrix, the coordinate data of the tooth feature points of the teeth to be repaired relative to the reference frame are transformed to the three-dimensional scanning image to obtain the coordinate data of the tooth pixel points of the teeth to be repaired; the coordinate data of the tooth feature points of the teeth to be repaired relative to the reference frame and the coordinate data of the tooth pixel points of the teeth to be repaired are aligned to obtain a second coordinate transformation matrix; the first coordinate transformation matrix and the second coordinate transformation matrix are multiplied to obtain a first mapping relationship.

[0047] The reference tooth of the tooth to be restored may be an adjacent tooth of the tooth to be referenced.

[0048] The first mapping relationship refers to the coordinate conversion relationship between the coordinate data of the tooth feature point of each tooth in the target oral cavity relative to the coordinate data of the reference frame and the coordinate data of the tooth pixel point.

[0049] Specifically, the electronic device can adopt a rigid registration method to align the coordinate data of the tooth feature points of the reference tooth relative to the reference frame and the coordinate data of the tooth pixel points of the reference tooth contained in the three-dimensional scanned image to obtain a first coordinate transformation matrix, denoted as M1; since the first coordinate transformation matrix can be used as a conversion relationship between the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame and the coordinate data of the tooth pixel points in the three-dimensional scanned image, the electronic device transforms the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame to the three-dimensional scanned image based on the first coordinate transformation matrix to obtain the coordinate data of the tooth pixel points of the tooth to be repaired from the three-dimensional scanned image; further, the electronic device adopts a source-to-target registration algorithm (such as an icp algorithm) to continue to align the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame and the coordinate data of the tooth pixel points of the tooth to be repaired to obtain a second coordinate transformation matrix, denoted as M2, and finally multiply the first coordinate transformation matrix by the second coordinate transformation matrix to obtain a first mapping relationship, denoted as M1*M2.

[0050] Optionally, the first mapping relationship between the coordinate data of the tooth feature point of each tooth in the target oral cavity relative to the reference frame and the coordinate data of the tooth pixel point can be expressed as follows: reference->CT =M1*M2,M reference->CT =M -1 CT->reference .

[0051] S140, acquiring operation planning data of the tooth to be restored based on the first mapping relationship, the pulp opening planning image data and the root canal planning image data.

[0052] In this embodiment, the electronic device maps the pulp opening planning data and root canal planning data determined from the image level to the actual tooth based on the conversion relationship determined by the coordinates of the actual feature points on each tooth and the coordinates of the tooth pixel points contained in the three-dimensional scanning image, thereby obtaining the operation planning data of the tooth to be restored, so as to guide the operation tool to accurately clear the infected part of the root canal in the tooth to be restored based on the operation planning data of the tooth to be restored.

[0053] It is understandable that, since the first mapping relationship is the conversion relationship between the coordinate data of the tooth feature point of each tooth in the target oral cavity relative to the reference frame and the coordinate data of the tooth pixel point, the electronic device needs to consider the reference frame in the process of mapping the pulp access planning data and the root canal planning data determined from the image level to the actual tooth. For this reason, the specific implementation of S140 includes but is not limited to the following method: according to the first mapping relationship, the pulp access planning image data and the root canal planning image data are mapped to the reference frame; the second mapping relationship of the reference frame relative to the tooth feature point of the tooth to be repaired is obtained; according to the second mapping relationship, the pulp access planning image data and the root canal planning image data mapped to the reference frame are continued to be mapped to the tooth feature point of the tooth to be repaired, and the operation planning data of the tooth to be repaired is obtained.

[0054] Optionally, mapping the pulp opening planning image data and the root canal planning image data onto the reference frame can be achieved in the following manner: reference =M CT->reference *P ct

[0055] Among them, P reference is a characteristic point on the reference frame, P ct It is the pixel point in the pulp opening planning image data and the root canal planning image data.

[0056] Optionally, the second mapping relationship between the reference frame and the tooth feature points of the tooth to be restored can be achieved in the following manner: reference->patient

[0057] Optionally, according to the second mapping relationship, the pulp opening planning image data and the root canal planning image data mapped to the reference frame are further mapped to the tooth feature points of the tooth to be restored to obtain the operation planning data of the tooth to be restored, which can be achieved in the following manner: panteint =M reference->patient *P reference

[0058] Among them, P panteint It is the tooth characteristic point of the tooth to be restored.

[0059] A method for determining tooth operation planning data of an embodiment of the present disclosure includes: obtaining a three-dimensional scanning image of a target oral cavity and coordinate data of tooth feature points in the target oral cavity; performing pulp opening planning and root canal planning on the tooth to be repaired in the target oral cavity based on the three-dimensional scanning image, and obtaining pulp opening planning image data and root canal planning image data of the tooth to be repaired; determining a first mapping relationship between the tooth feature points of the tooth to be repaired and the tooth pixel points of the tooth to be repaired according to the coordinate data of the tooth feature points and the coordinate data of the tooth pixel points contained in the three-dimensional scanning image; obtaining operation planning data of the tooth to be repaired based on the first mapping relationship, pulp opening planning image data and root canal planning image data. Thus, by using the three-dimensional scanning image of the target oral cavity, pulp opening planning data and root canal planning data are determined at the image level, and then according to the conversion relationship determined by the coordinates of the actual tooth feature points and the coordinates of the tooth pixel points contained in the three-dimensional scanning image, the pulp opening planning data and root canal planning data determined from the image level are mapped to the actual tooth, thereby obtaining the operation planning data of the tooth to be repaired, so as to guide the operation tool to accurately remove the infected part of the root canal in the tooth to be repaired based on the operation planning data of the tooth to be repaired.

[0060] In another embodiment of the present disclosure, the specific implementation process of S120 is explained in detail.

[0061] Figure 2 A schematic diagram of the process of S120 is shown.

[0062] like Figure 2 As shown, S120 may include the following steps.

[0063] S210: Perform tooth segmentation processing on the three-dimensional scanned image to obtain tooth segmentation data of the tooth to be repaired.

[0064] Among them, the specific implementation method of S210 includes but is not limited to the following methods: segmenting tooth image data from a three-dimensional scanned image; performing single tooth segmentation on the tooth image data to obtain image data of a single tooth; performing tooth structure segmentation on the tooth to be repaired based on the image data of the tooth to be repaired contained in the image data of the single tooth, and obtaining tooth segmentation data of the tooth to be repaired, wherein the tooth segmentation data of the tooth to be repaired includes at least tooth structure data and root canal segmentation data.

[0065] Specifically, the three-dimensional scanned image includes the tooth area, gums and other areas. The electronic device first performs tooth area segmentation on the three-dimensional scanned image to obtain tooth image data, thereby reducing the image size. Since the tooth image data includes multiple teeth, the electronic device performs rough segmentation on the tooth image data to obtain image data of a single tooth. Then, the electronic device obtains the image data of the tooth to be repaired from the image data of the single tooth, and based on the image data of the tooth to be repaired, performs tooth structure segmentation on the tooth to be repaired to determine the tooth structure data and root canal segmentation data of the tooth to be repaired. The pulp cavity segmentation data can also be segmented to obtain the tooth segmentation data of the tooth to be repaired. In order to obtain richer information about the root canal, after obtaining the root canal segmentation data of the tooth to be repaired, the tooth structure data is encoded to obtain the tooth structure data in binary form, and then the binary tooth structure data and the root canal segmentation data are stacked to obtain the category of each root canal in the tooth to be repaired.

[0066] Optionally, the categories of root canals include but are not limited to distal category, mesial category, mesiobuccal category, mesiolingual category, distolingual category, etc.

[0067] In this way, by segmenting the three-dimensional scanned image from coarse to fine, the tooth segmentation data of the tooth to be repaired can be obtained in an orderly manner, and the accuracy of the tooth segmentation data can also be guaranteed.

[0068] S220: Detect the root canal orifice position and the apical foramen position of the tooth to be restored based on the three-dimensional scanning image and the tooth segmentation data of the tooth to be restored.

[0069] Among them, the specific implementation method of S220 includes but is not limited to the following methods: S2201, using a pre-trained detection network to detect the root canal orifice and apical foramen of the three-dimensional scanning image, and obtain root canal prediction data of different confidence levels of the tooth to be repaired; S2202, based on the root canal prediction data and tooth segmentation data with different confidence levels, determine the root canal orifice position and apical foramen position of the tooth to be repaired.

[0070] The root canal prediction data includes the predicted position of the root canal orifice, the offset corresponding to the predicted position of the root canal orifice, the predicted position of the apical foramen, and the offset corresponding to the predicted position of the apical foramen; accordingly, the specific implementation method of S2202 includes but is not limited to the following methods: S1, according to the root canal segmentation data contained in the tooth segmentation data, the number of root canals of the tooth to be repaired is obtained, and according to the tooth structure data contained in the tooth segmentation data, the distribution position of the tooth to be repaired is obtained; S2, based on the root canal orifice prediction position with the highest confidence and the apical foramen prediction position with the highest confidence, the first root canal prediction position with the closest distance to the current root canal orifice prediction position is obtained from the root canal segmentation data; The current root canal, and the second current root canal closest to the current predicted apical foramen position obtained from the root canal segmentation data; S3, determining the root canal orifice position of the tooth to be repaired according to the distribution position of the tooth to be repaired, the current predicted root canal orifice position, the center of gravity position of the first current root canal and the offset corresponding to the current predicted root canal orifice position, and, determining the apical foramen position of the tooth to be repaired according to the distribution position of the tooth to be repaired, the current predicted apical foramen position, the center of gravity position of the second current root canal and the offset corresponding to the current predicted apical foramen position, until the root canal orifice predicted position with the lowest confidence and the apical foramen predicted position with the lowest confidence are traversed.

[0071] Specifically, the electronic device calls a target detection network (such as CenterNet) as a pre-trained detection network, and the target detection network has a position prediction branch, a detection box size prediction branch and an offset prediction branch. The detection box size prediction branch is removed during the training stage, and only the position prediction branch and the offset prediction branch are retained. The electronic device inputs the three-dimensional scanning image into the target detection network, and outputs root canal orifice prediction positions with different confidences and apical foramen prediction positions with different confidences through the position prediction branch, and outputs the offset corresponding to the root canal orifice prediction position and the offset corresponding to the apical foramen prediction position through the offset prediction branch, thereby obtaining root canal prediction data with different confidences.

[0072] In order to improve the accuracy of the prediction of the root canal orifice position and the apical foramen position of the tooth to be restored, this embodiment also combines the tooth segmentation data to optimize the root canal prediction data with different confidence levels. Figure 3The schematic diagram of the internal structure of the tooth to be repaired is shown. The root canal segmentation data contained in the tooth segmentation data has detailed root canal information. The electronic device reads the root canal segmentation data to determine the number of root canals of the tooth to be repaired. Since the tooth structure data contained in the tooth segmentation data can characterize the distribution range of each voxel point in the tooth to be repaired, the distribution position of the tooth to be repaired can be determined by analyzing the tooth structure data; then, the electronic device sorts the root canal orifice predicted position and the apical foramen predicted position in order of confidence from high to low, and traverses from the root canal orifice predicted position with the highest confidence and the apical foramen predicted position with the highest confidence. When traversing to the current root canal orifice predicted position and the current apical foramen predicted position, a preset distance calculation method (such as the K nearest neighbor algorithm) is used to calculate the distance between the current root canal orifice predicted position and each root canal in the root canal segmentation data, and calculates the current The distance between the predicted position of the apical foramen and each root canal in the root canal segmentation data, and the first current root canal and the second current root canal are determined; further, the root canal orifice position of the tooth to be repaired is determined in combination with the distribution position of the tooth to be repaired, the current predicted position of the root canal orifice, the center of gravity position of the first current root canal and the offset corresponding to the current predicted position of the root canal orifice. Similarly, the apical foramen position of the tooth to be repaired is determined in combination with the distribution position of the tooth to be repaired, the current predicted position of the apical foramen, the center of gravity position of the second current root canal and the offset corresponding to the current predicted position of the apical foramen; finally, determine whether the confidence corresponding to the current predicted position of the root canal orifice is the minimum confidence. If so, stop traversing the predicted position of the root canal orifice, otherwise, continue traversing. Similarly, determine whether the confidence corresponding to the current predicted position of the apical foramen is the minimum confidence. If so, stop traversing the predicted position of the apical foramen, otherwise, continue traversing.

[0073] The first current root canal may be considered as the root canal where the current predicted position of the root canal orifice is located, and the second current root canal may be considered as the root canal where the current predicted position of the apical foramen is located.

[0074] Among them, the distribution positions of the teeth to be repaired include the upper teeth position and the lower teeth position.

[0075] Among them, the specific implementation method of "determining the root canal orifice position of the tooth to be repaired according to the distribution position of the tooth to be repaired, the current predicted root canal orifice position, the center of gravity position of the first current root canal and the offset corresponding to the current predicted root canal orifice position" in S3 includes but is not limited to the following methods: if the distribution position of the tooth to be repaired is the upper tooth position, and the current predicted root canal orifice position is below the center of gravity position of the first current root canal, then the current predicted root canal orifice position is retained; if the distribution position of the tooth to be repaired is the lower tooth position, and the current predicted root canal orifice position is above the center of gravity position of the first current root canal, then the current predicted root canal orifice position is retained; the retained current predicted root canal orifice position is added to the corresponding offset to obtain the root canal orifice position of the tooth to be repaired.

[0076] Among them, the specific implementation method of "determining the apical foramen position of the tooth to be repaired according to the distribution position of the tooth to be repaired, the current predicted apical foramen position, the center of gravity position of the second current root canal and the offset corresponding to the current predicted apical foramen position" in S3 includes but is not limited to the following methods: if the distribution position of the tooth to be repaired is the upper tooth position, and the current predicted apical foramen position is above the center of gravity position of the second current root canal, then the current predicted apical foramen position is retained; if the distribution position of the tooth to be repaired is the lower tooth position, and the current predicted apical foramen position is below the center of gravity position of the second current root canal, then the current predicted apical foramen position is retained; the retained current predicted apical foramen position is added to the corresponding offset to obtain the apical foramen position of the tooth to be repaired.

[0077] In this way, first, the root canal prediction data of different confidence levels of the tooth to be restored is predicted through the pre-trained detection network, and then the root canal orifice position and apical foramen position of the tooth to be restored are detected in combination with the tooth segmentation data of the tooth to be restored, thereby improving the accuracy of root canal orifice and apical foramen detection.

[0078] S230: Predicting the tooth principal axis of the tooth to be restored based on the tooth segmentation data of the tooth to be restored.

[0079] Among them, the specific implementation method of S230 includes but is not limited to the following methods: using a pre-trained rotation angle prediction model to process the tooth segmentation data to obtain the predicted rotation angle of the tooth to be repaired; rotating the tooth segmentation data around a preset origin according to the predicted rotation angle, and using the vertical axis of the rotated tooth segmentation data as the tooth principal axis of the tooth to be repaired.

[0080] Specifically, the electronic device calls the posture network as a pre-trained rotation angle prediction model, and inputs the tooth segmentation data of the tooth to be repaired into the model for rotation angle prediction, to obtain the predicted rotation angle of the tooth to be repaired, the predicted rotation angle including the rotation angle of the x-axis, the rotation angle of the y-axis and the rotation angle of the z-axis. Then, the electronic device obtains a preset origin, rotates the tooth segmentation data of the tooth to be repaired around the rotation angle of the x-axis, the rotation angle of the y-axis and the rotation angle of the z-axis respectively, and uses the vertical axis after rotation (i.e., the z-axis) as the tooth principal axis of the tooth to be repaired.

[0081] Optionally, the pose network is the same as the ResNet classification network, with the classification head of the ResNet classification network removed and replaced with three regression heads to predict the rotation angle of the x-axis, the rotation angle of the y-axis, and the rotation angle of the z-axis.

[0082] Since the tooth principal axis is the coordinate axis used for performing pulp access planning on the tooth to be restored, predicting the tooth principal axis is helpful to ensure the normal execution of the pulp access planning process.

[0083] S240: Perform pulp access planning on the tooth to be restored based on the tooth segmentation data and the tooth main axis of the tooth to be restored, and obtain pulp access planning image data of the tooth to be restored.

[0084] Among them, the specific implementation method of S240 includes but is not limited to the following methods: performing surface fitting on the root canal segmentation data contained in the tooth segmentation data along a direction perpendicular to the main axis of the tooth to obtain a target surface containing all the root canals of the tooth to be repaired; obtaining intersection pixel points from the pixel points contained in the target surface and the pixel points in the tooth structure data contained in the tooth segmentation data; performing region generation processing on the intersection pixel points to obtain pulp opening planning image data of the tooth to be repaired.

[0085] Specifically, the electronic device makes cross sections of different radii along a direction perpendicular to the main axis of the tooth, and then obtains a target surface containing all the root canals of the tooth to be repaired from the cross sections of different radii. The target surface can cover all the root canals of the tooth to be repaired. Then, the target surface is moved upward or downward along a direction perpendicular to the main axis of the tooth. The purpose is to obtain intersection pixels from the pixels contained in the target surface and the pixels in the tooth structure data contained in the tooth segmentation data. Finally, the intersection pixels are subjected to region generation processing to obtain pulp opening planning image data of the tooth to be repaired.

[0086] In this way, the tooth segmentation data and the tooth main axis of the tooth to be restored are combined to accurately plan an area on the tooth to be restored, thereby obtaining pulp opening planning image data, which facilitates the execution tool to enter the root canal based on the pulp opening planning image data to clear the infected part of the root canal.

[0087] S250, performing root canal planning on the tooth to be repaired based on the root canal opening position of the tooth to be repaired, the apical foramen position of the tooth to be repaired, and the tooth segmentation data of the tooth to be repaired, and obtaining root canal planning image data of the tooth to be repaired.

[0088] Among them, the specific implementation method of S250 includes but is not limited to the following methods: extracting the root canal centerline of the target root canal in the tooth to be repaired based on the root canal orifice position, the apical foramen position and the root canal segmentation data contained in the tooth segmentation data; calculating the curve length of the root canal centerline based on the distance between adjacent points on the root canal centerline; obtaining the planned operating angle and planned operating position of the target root canal based on the root canal orifice position and the root canal centerline; using the root canal centerline of the target root canal, the curve length of the root canal centerline, the planned operating angle of the target root canal and the planned operating position of the target root canal as root canal planning image data.

[0089] Specifically, the electronic device extracts the centerline of the target root canal where the root canal orifice position and the apical foramen position are located based on the root canal orifice position, the apical foramen position and the root canal segmentation data included in the tooth segmentation data to obtain the root canal centerline of the target root canal, and then adds the root canal orifice position and the apical foramen position to the root canal centerline accordingly, so that the root canal centerline includes multiple adjacent points from the root canal orifice position to the apical foramen position, and then calculates the distances between adjacent points on the root canal centerline, and superimposes these distances to obtain the curve length of the root canal centerline; at the same time, the two points closest to the root canal orifice position are obtained from the root canal centerline, and the operating angle of the target root canal in the tooth to be repaired is determined based on these two points, and the root canal orifice position is used as the planned operating position of the target root canal in the tooth to be repaired.

[0090] The target root canal refers to the root canal on which work needs to be performed in the tooth to be restored.

[0091] In this way, the root canal orifice position, the apical foramen position and the tooth segmentation data are combined to determine the curve length of the root canal centerline of the target root canal, so as to control the operating distance of the execution tool based on the root canal centerline and its corresponding curve length. At the same time, based on the root canal orifice position and the root canal centerline, the planned operating angle and the planned operating position of the target root canal are determined, and the planned operating angle is used as the angle for the execution tool to enter the target root canal, and the planned operating position is used as the position for the execution tool to enter the target root canal, which is conducive to the execution tool to perform precise operations on the target root canal of the tooth to be restored based on these data.

[0092] The embodiment of the present disclosure also provides a tooth operation planning data determination device for implementing the above-mentioned tooth operation planning data determination method. Figure 4 In the disclosed embodiment, the tooth operation planning data determination device may be an electronic device, wherein the electronic device may be a control device of a surgical robot.

[0093] Figure 4 A schematic structural diagram of a device for determining tooth operation planning data provided by an embodiment of the present disclosure is shown.

[0094] like Figure 4 As shown, the tooth operation planning data determination device 400 may include:

[0095] A first acquisition module 410 is used to acquire a three-dimensional scanning image of a target oral cavity and coordinate data of tooth feature points in the target oral cavity;

[0096] A planning module 420 is used to perform pulp opening planning and root canal planning on the tooth to be restored in the target oral cavity based on the three-dimensional scanning image, and obtain pulp opening planning image data and root canal planning image data of the tooth to be restored;

[0097] A determination module 430, configured to determine a first mapping relationship between the tooth feature point and the tooth pixel point according to the coordinate data of the tooth feature point and the coordinate data of the tooth pixel point included in the three-dimensional scanned image;

[0098] The second acquisition module 440 is used to acquire the operation planning data of the tooth to be restored based on the first mapping relationship, the pulp opening planning image data and the root canal planning image data.

[0099] A device for determining operation planning data of a tooth according to an embodiment of the present disclosure includes: obtaining a three-dimensional scanning image of a target oral cavity and coordinate data of a tooth feature point in the target oral cavity; performing pulp opening planning and root canal planning on a tooth to be repaired in the target oral cavity based on the three-dimensional scanning image, and obtaining pulp opening planning image data and root canal planning image data of the tooth to be repaired; determining a first mapping relationship between tooth feature points and tooth pixels according to the coordinate data of the tooth feature points and the coordinate data of tooth pixels contained in the three-dimensional scanning image; obtaining operation planning data of the tooth to be repaired based on the first mapping relationship, pulp opening planning image data and root canal planning image data. Thus, the pulp opening planning data and root canal planning data are determined at the image level by using the three-dimensional scanning image of the target oral cavity, and then the pulp opening planning data and root canal planning data determined from the image level are mapped to the actual tooth according to the conversion relationship determined by the coordinates of the actual tooth feature points and the coordinates of the tooth pixels contained in the three-dimensional scanning image, so as to obtain the operation planning data of the tooth to be repaired, so as to guide the operation tool to accurately remove the infected part of the root canal in the tooth to be repaired based on the operation planning data of the tooth to be repaired.

[0100] In some embodiments of the present disclosure, the planning module 420 includes:

[0101] A tooth segmentation unit, used for performing tooth segmentation processing on the three-dimensional scanned image to obtain tooth segmentation data of the tooth to be repaired;

[0102] A detection unit, configured to detect a root canal orifice position and a root apex foramen position of the tooth to be restored based on the three-dimensional scanning image and the tooth segmentation data of the tooth to be restored;

[0103] A prediction unit, configured to predict the tooth principal axis of the tooth to be restored based on the tooth segmentation data of the tooth to be restored;

[0104] A pulp opening planning unit, used for performing pulp opening planning on the tooth to be restored based on the tooth segmentation data and the tooth main axis of the tooth to be restored, and obtaining pulp opening planning image data of the tooth to be restored;

[0105] The root canal planning unit is used to perform root canal planning on the tooth to be repaired based on the root canal opening position of the tooth to be repaired, the apical foramen position of the tooth to be repaired and the tooth segmentation data of the tooth to be repaired, so as to obtain the root canal planning image data of the tooth to be repaired.

[0106] In some embodiments of the present disclosure, the tooth segmentation unit is specifically used to:

[0107] Segmenting tooth image data from the three-dimensional scanned image;

[0108] Performing single tooth segmentation on the tooth image data to obtain single tooth image data;

[0109] Based on the image data of the tooth to be restored contained in the image data of the single tooth, tooth structure segmentation is performed on the tooth to be restored to obtain tooth segmentation data of the tooth to be restored, wherein the tooth segmentation data of the tooth to be restored includes at least tooth structure data and root canal segmentation data.

[0110] In some embodiments of the present disclosure, the detection unit includes:

[0111] A root canal orifice apical foramen detection subunit, used to detect the root canal orifice apical foramen of the three-dimensional scanned image using a pre-trained detection network, and obtain root canal prediction data of different confidence levels of the tooth to be repaired;

[0112] The position determination subunit is used to determine the root canal orifice position and the apical foramen position of the tooth to be restored based on the root canal prediction data with different confidence levels and the tooth segmentation data.

[0113] In some embodiments of the present disclosure, the root canal prediction data includes a predicted position of a root canal orifice, an offset corresponding to the predicted position of the root canal orifice, a predicted position of an apical foramen, and an offset corresponding to the predicted position of the apical foramen;

[0114] Accordingly, the position determination subunit is specifically used for:

[0115] According to the root canal segmentation data included in the tooth segmentation data, the number of root canals of the tooth to be repaired is obtained, and according to the tooth structure data included in the tooth segmentation data, the distribution position of the tooth to be repaired is obtained;

[0116] Starting traversal based on the root canal orifice predicted position with the highest confidence and the apical foramen predicted position with the highest confidence, obtaining a first current root canal closest to the current root canal orifice predicted position from the root canal segmentation data, and obtaining a second current root canal closest to the current apical foramen predicted position from the root canal segmentation data;

[0117] The root canal orifice position of the tooth to be repaired is determined according to the distribution position of the tooth to be repaired, the current predicted root canal orifice position, the center of gravity position of the first current root canal and the offset corresponding to the current predicted root canal orifice position, and the apical foramen position of the tooth to be repaired is determined according to the distribution position of the tooth to be repaired, the current predicted apical foramen position, the center of gravity position of the second current root canal and the offset corresponding to the current predicted apical foramen position, until the root canal orifice predicted position with the lowest confidence and the apical foramen predicted position with the lowest confidence are traversed.

[0118] In some embodiments of the present disclosure, the position determination subunit is specifically used to:

[0119] If the distribution position of the tooth to be repaired is the upper tooth position, and the current predicted position of the root canal orifice is below the center of gravity of the first current root canal, then retain the current predicted position of the root canal orifice;

[0120] If the distribution position of the tooth to be repaired is the lower tooth position, and the current predicted position of the root canal orifice is above the center of gravity of the first current root canal, then retain the current predicted position of the root canal orifice;

[0121] The retained current predicted root canal orifice position is added to the corresponding offset to obtain the root canal orifice position of the tooth to be repaired.

[0122] In some embodiments of the present disclosure, the position determination subunit is further specifically used for:

[0123] If the distribution position of the tooth to be repaired is the upper tooth position, and the current predicted position of the apical foramen is above the center of gravity of the second current root canal, then the current predicted position of the apical foramen is retained;

[0124] If the distribution position of the tooth to be repaired is the lower tooth position, and the current predicted position of the apical foramen is below the center of gravity of the second current root canal, then the current predicted position of the apical foramen is retained;

[0125] The retained current predicted apical foramen position is added to the corresponding offset to obtain the apical foramen position of the tooth to be repaired.

[0126] In some embodiments of the present disclosure, the prediction unit is specifically configured to:

[0127] Using a pre-trained rotation angle prediction model, the tooth segmentation data is processed to obtain a predicted rotation angle of the tooth to be repaired;

[0128] The tooth segmentation data is rotated around a preset origin according to the predicted rotation angle, and the vertical axis of the tooth segmentation data after rotation is used as the tooth main axis of the tooth to be restored.

[0129] In some embodiments of the present disclosure, the medullary opening planning unit is specifically used to:

[0130] Performing surface fitting on the root canal segmentation data included in the tooth segmentation data along a direction perpendicular to the main axis of the tooth, to obtain a target surface including all the root canals of the tooth to be repaired;

[0131] Obtaining intersection pixel points from the pixel points included in the target curved surface and the pixel points in the tooth structure data included in the tooth segmentation data;

[0132] The intersection pixel points are processed for region generation to obtain the pulp opening planning image data of the tooth to be repaired.

[0133] In some embodiments of the present disclosure, the root canal planning unit is specifically used to:

[0134] Extracting a root canal centerline of a target root canal in the tooth to be repaired according to the root canal orifice position, the apical foramen position, and the root canal segmentation data included in the tooth segmentation data;

[0135] Calculating the curve length of the root canal centerline based on the distance between adjacent points on the root canal centerline;

[0136] Based on the root canal orifice position and the root canal centerline, obtaining a planned operating angle and a planned operating position of the target root canal;

[0137] The root canal centerline of the target root canal, the curve length of the root canal centerline, the planned operation angle of the target root canal and the planned operation position of the target root canal are used as the root canal planning image data.

[0138] In some embodiments of the present disclosure, the coordinate data of the tooth feature points in the target oral cavity includes the coordinate data of the tooth feature points of each tooth relative to the reference frame;

[0139] Accordingly, the determination module 430 is specifically configured to:

[0140] For the reference tooth of the tooth to be restored in the target oral cavity, coordinate data of the tooth feature points of the reference tooth relative to the reference frame and coordinate data of the tooth pixel points of the reference tooth contained in the three-dimensional scanned image are registered to obtain a first coordinate transformation matrix;

[0141] Based on the coordinate transformation matrix, the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame are transformed to the three-dimensional scanned image to obtain the coordinate data of the tooth pixel points of the tooth to be repaired;

[0142] Registering the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame and the coordinate data of the tooth pixel points of the tooth to be repaired to obtain a second coordinate transformation matrix;

[0143] The first coordinate transformation matrix and the second coordinate transformation matrix are multiplied to obtain the first mapping relationship.

[0144] In some embodiments of the present disclosure, the second acquisition module 440 is specifically configured to:

[0145] According to the first mapping relationship, mapping the pulp opening planning image data and the root canal planning image data onto a reference frame;

[0146] Acquire a second mapping relationship between the reference frame and the tooth feature points of the tooth to be restored;

[0147] According to the second mapping relationship, the pulp opening planning image data and the root canal planning image data mapped to the reference frame are further mapped to the tooth feature points of the tooth to be restored, so as to obtain the operation planning data of the tooth to be restored.

[0148] It should be noted that Figure 4 The tooth operation planning data determination device 400 shown can execute Figure 1 to Figure 3 The various steps in the method embodiment shown in the figure are implemented Figure 1 to Figure 3 The various processes and effects in the method embodiment shown are not described in detail here.

[0149] Figure 5 A schematic structural diagram of an electronic device provided by an embodiment of the present disclosure is shown.

[0150] like Figure 5 As shown, the electronic device may include a processor 501 and a memory 502 storing computer program instructions.

[0151] Specifically, the processor 501 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0152] The memory 502 may include a large capacity memory for information or instructions. By way of example and not limitation, the memory 502 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive or a combination of two or more of these. Where appropriate, the memory 502 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 502 may be inside or outside the integrated gateway device. In a particular embodiment, the memory 502 is a non-volatile solid-state memory. In a particular embodiment, the memory 502 includes a read-only memory (ROM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (Electrically Erasable Programmable ROM, EEPROM), an electrically rewritable ROM (EAROM) or a flash memory, or a combination of two or more of these.

[0153] The processor 501 reads and executes the computer program instructions stored in the memory 502 to perform the steps of the method for determining tooth operation planning data provided in the embodiment of the present disclosure.

[0154] In one example, the electronic device may further include a transceiver 503 and a bus 504. Figure 5 As shown, the processor 501, the memory 502 and the transceiver 503 are connected via a bus 504 and communicate with each other.

[0155] The bus 504 includes hardware, software, or both. For example, but not limitation, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industrial Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a MicroChannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, the bus 504 may include one or more buses. Although embodiments of the present application describe and illustrate a particular bus, the present application contemplates any suitable bus or interconnect.

[0156] The following is an embodiment of a computer-readable storage medium provided in an embodiment of the present disclosure. The computer-readable storage medium and the method for determining tooth operation planning data in the above-mentioned embodiments belong to the same inventive concept. For details not described in detail in the embodiment of the computer-readable storage medium, reference can be made to the embodiment of the method for determining tooth operation planning data in the above-mentioned embodiments.

[0157] This embodiment provides a storage medium containing computer executable instructions. When the computer executable instructions are executed by a computer processor, they are used to perform a method for determining tooth operation planning data. The method includes:

[0158] Acquire a three-dimensional scanned image of a target oral cavity and coordinate data of characteristic points of teeth in the target oral cavity;

[0159] Based on the three-dimensional scanning image, pulp access planning and root canal planning are performed on the tooth to be restored in the target oral cavity to obtain pulp access planning image data and root canal planning image data of the tooth to be restored;

[0160] Determine a first mapping relationship between the tooth feature points and the tooth pixel points according to the coordinate data of the tooth feature points and the coordinate data of the tooth pixel points included in the three-dimensional scanned image;

[0161] Based on the first mapping relationship, the pulp opening planning image data and the root canal planning image data, the operation planning data of the tooth to be restored is acquired.

[0162] Of course, the computer executable instructions of a storage medium containing computer executable instructions provided in an embodiment of the present disclosure are not limited to the above method operations, and can also execute related operations in the method for determining tooth operation planning data provided in any embodiment of the present disclosure.

[0163] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present disclosure can be implemented with the help of software and necessary general hardware, and of course it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present disclosure can be essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer cloud platform (which can be a personal computer, server, or network cloud platform, etc.) to execute the tooth operation planning data determination method provided by each embodiment of the present disclosure.

[0164] Note that the above are only preferred embodiments of the present disclosure and the technical principles used. Those skilled in the art will understand that the present disclosure is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present disclosure. Therefore, although the present disclosure is described in more detail through the above embodiments, the present disclosure is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present disclosure, and the scope of the present disclosure is determined by the scope of the appended claims.

Claims

1. A method for determining tooth operation planning data, characterized in that: include: Acquire a three-dimensional scanned image of a target oral cavity and coordinate data of characteristic points of teeth in the target oral cavity; Based on the three-dimensional scanning image, pulp access planning and root canal planning are performed on the tooth to be restored in the target oral cavity to obtain pulp access planning image data and root canal planning image data of the tooth to be restored; Determine a first mapping relationship between the tooth feature points and the tooth pixel points according to the coordinate data of the tooth feature points and the coordinate data of the tooth pixel points included in the three-dimensional scanned image; Based on the first mapping relationship, the pulp access planning image data and the root canal planning image data, the operation planning data of the tooth to be restored is acquired.

2. The method according to claim 1, characterized in that Based on the three-dimensional scanning image, performing pulp access planning and root canal planning on the tooth to be restored in the target oral cavity to obtain pulp access planning image data and root canal planning image data of the tooth to be restored, including: Performing tooth segmentation processing on the three-dimensional scanned image to obtain tooth segmentation data of the tooth to be repaired; Detecting the root canal orifice position and the apical foramen position of the tooth to be restored based on the three-dimensional scanning image and the tooth segmentation data of the tooth to be restored; Predicting the tooth principal axis of the tooth to be restored based on the tooth segmentation data of the tooth to be restored; Based on the tooth segmentation data of the tooth to be restored and the tooth main axis, performing pulp opening planning on the tooth to be restored, and obtaining pulp opening planning image data of the tooth to be restored; Based on the root canal opening position of the tooth to be repaired, the apical foramen position of the tooth to be repaired and the tooth segmentation data of the tooth to be repaired, root canal planning is performed on the tooth to be repaired to obtain root canal planning image data of the tooth to be repaired.

3. The method according to claim 2, characterized in that The step of performing tooth segmentation processing on the three-dimensional scanned image to obtain tooth segmentation data of the tooth to be repaired includes: Segmenting tooth image data from the three-dimensional scanned image; Performing single tooth segmentation on the tooth image data to obtain single tooth image data; Based on the image data of the tooth to be repaired contained in the image data of the single tooth, tooth structure segmentation is performed on the tooth to be repaired to obtain tooth segmentation data of the tooth to be repaired, wherein the tooth segmentation data of the tooth to be repaired includes at least tooth structure data and root canal segmentation data.

4. The method according to claim 2, characterized in that: The detecting the root canal orifice position and the apical foramen position of the tooth to be restored based on the three-dimensional scanning image and the tooth segmentation data of the tooth to be restored comprises: Using a pre-trained detection network, the root canal orifice apex foramen detection is performed on the three-dimensional scanned image to obtain root canal prediction data of different confidence levels of the tooth to be repaired; Based on the root canal prediction data with different confidence levels and the tooth segmentation data, the root canal orifice position and the apical foramen position of the tooth to be restored are determined.

5. The method according to claim 4, characterized in that The root canal prediction data includes a predicted position of a root canal orifice, an offset corresponding to the predicted position of the root canal orifice, a predicted position of an apical foramen, and an offset corresponding to the predicted position of the apical foramen; Accordingly, determining the root canal orifice position and the apical foramen position of the tooth to be restored based on the root canal prediction data with different confidence levels and the tooth segmentation data includes: According to the root canal segmentation data included in the tooth segmentation data, the number of root canals of the tooth to be repaired is obtained, and according to the tooth structure data included in the tooth segmentation data, the distribution position of the tooth to be repaired is obtained; Starting traversal based on the root canal orifice predicted position with the highest confidence and the apical foramen predicted position with the highest confidence, obtaining a first current root canal closest to the current root canal orifice predicted position from the root canal segmentation data, and obtaining a second current root canal closest to the current apical foramen predicted position from the root canal segmentation data; The root canal orifice position of the tooth to be repaired is determined according to the distribution position of the tooth to be repaired, the current predicted root canal orifice position, the center of gravity position of the first current root canal and the offset corresponding to the current predicted root canal orifice position, and the apical foramen position of the tooth to be repaired is determined according to the distribution position of the tooth to be repaired, the current predicted apical foramen position, the center of gravity position of the second current root canal and the offset corresponding to the current predicted apical foramen position, until the root canal orifice predicted position with the lowest confidence and the apical foramen predicted position with the lowest confidence are traversed.

6. The method according to claim 5, characterized in that The determining the position of the root canal orifice of the tooth to be restored according to the distribution position of the tooth to be restored, the current predicted position of the root canal orifice, the center of gravity position of the first current root canal and the offset corresponding to the current predicted position of the root canal orifice comprises: If the distribution position of the tooth to be repaired is the upper tooth position, and the current predicted position of the root canal orifice is below the center of gravity of the first current root canal, then retain the current predicted position of the root canal orifice; If the distribution position of the tooth to be repaired is the lower tooth position, and the current predicted position of the root canal orifice is above the center of gravity of the first current root canal, then retain the current predicted position of the root canal orifice; The retained current predicted root canal orifice position is added to the corresponding offset to obtain the root canal orifice position of the tooth to be repaired.

7. The method according to claim 5, characterized in that The step of determining the position of the apical foramen of the tooth to be repaired according to the distribution position of the tooth to be repaired, the current predicted position of the apical foramen, the center of gravity position of the second current root canal and the offset corresponding to the current predicted position of the apical foramen comprises: If the distribution position of the tooth to be repaired is the upper tooth position, and the current predicted position of the apical foramen is above the center of gravity of the second current root canal, then the current predicted position of the apical foramen is retained; If the distribution position of the tooth to be repaired is the lower tooth position, and the current predicted position of the apical foramen is below the center of gravity of the second current root canal, then the current predicted position of the apical foramen is retained; The retained current predicted apical foramen position is added to the corresponding offset to obtain the apical foramen position of the tooth to be repaired.

8. The method according to claim 2, characterized in that: The step of predicting the tooth principal axis of the tooth to be restored based on the tooth segmentation data of the tooth to be restored comprises: Using a pre-trained rotation angle prediction model, the tooth segmentation data is processed to obtain a predicted rotation angle of the tooth to be repaired; The tooth segmentation data is rotated around a preset origin according to the predicted rotation angle, and the vertical axis of the tooth segmentation data after rotation is used as the tooth main axis of the tooth to be restored.

9. The method according to claim 2, characterized in that: The method of performing pulp access planning on the tooth to be restored based on the tooth segmentation data and the tooth main axis of the tooth to be restored to obtain pulp access planning image data of the tooth to be restored includes: Performing surface fitting on the root canal segmentation data included in the tooth segmentation data along a direction perpendicular to the main axis of the tooth, to obtain a target surface including all the root canals of the tooth to be repaired; Obtaining intersection pixel points from the pixel points included in the target curved surface and the pixel points in the tooth structure data included in the tooth segmentation data; The intersection pixel points are processed for region generation to obtain the pulp opening planning image data of the tooth to be repaired.

10. The method according to claim 2, characterized in that The method of performing root canal planning on the tooth to be repaired based on the root canal opening position of the tooth to be repaired, the apical foramen position of the tooth to be repaired and the tooth segmentation data of the tooth to be repaired to obtain the root canal planning image data of the tooth to be repaired includes: Extracting a root canal centerline of a target root canal in the tooth to be repaired according to the root canal orifice position, the apical foramen position, and the root canal segmentation data included in the tooth segmentation data; Calculating the curve length of the root canal centerline based on the distance between adjacent points on the root canal centerline; Based on the root canal orifice position and the root canal centerline, obtaining a planned operating angle and a planned operating position of the target root canal; The root canal centerline of the target root canal, the curve length of the root canal centerline, the planned operation angle of the target root canal and the planned operation position of the target root canal are used as the root canal planning image data.

11. The method according to claim 1, characterized in that: The coordinate data of the tooth feature points in the target oral cavity include the coordinate data of the tooth feature points of each tooth relative to the reference frame; Correspondingly, determining the first mapping relationship between the tooth feature points and the tooth pixel points according to the coordinate data of the tooth feature points and the coordinate data of the tooth pixel points included in the three-dimensional scanned image includes: For the reference tooth of the tooth to be restored in the target oral cavity, coordinate data of the tooth feature points of the reference tooth relative to the reference frame and coordinate data of the tooth pixel points of the reference tooth contained in the three-dimensional scanned image are registered to obtain a first coordinate transformation matrix; Based on the first coordinate transformation matrix, the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame are transformed to the three-dimensional scanned image to obtain the coordinate data of the tooth pixel points of the tooth to be repaired; Registering the coordinate data of the tooth feature points of the tooth to be repaired relative to the reference frame and the coordinate data of the tooth pixel points of the tooth to be repaired to obtain a second coordinate transformation matrix; The first coordinate transformation matrix and the second coordinate transformation matrix are multiplied to obtain the first mapping relationship.

12. The method according to claim 1, characterized in that The step of acquiring operation planning data of the tooth to be restored based on the first mapping relationship, the pulp opening planning image data and the root canal planning image data comprises: According to the first mapping relationship, mapping the pulp opening planning image data and the root canal planning image data onto a reference frame; Acquire a second mapping relationship between the reference frame and the tooth feature points of the tooth to be restored; According to the second mapping relationship, the pulp opening planning image data and the root canal planning image data mapped to the reference frame are further mapped to the tooth feature points of the tooth to be restored, so as to obtain the operation planning data of the tooth to be restored.

13. A device for determining tooth operation planning data, characterized in that: include: A first acquisition module is used to acquire a three-dimensional scanning image of a target oral cavity and coordinate data of tooth feature points in the target oral cavity; A planning module, used for performing pulp opening planning and root canal planning on the tooth to be restored in the target oral cavity based on the three-dimensional scanning image, and obtaining pulp opening planning image data and root canal planning image data of the tooth to be restored; A determination module, configured to determine a first mapping relationship between the tooth feature point and the tooth pixel point according to the coordinate data of the tooth feature point and the coordinate data of the tooth pixel point contained in the three-dimensional scanning image; The second acquisition module is used to acquire the operation planning data of the tooth to be restored based on the first mapping relationship, the pulp opening planning image data and the root canal planning image data.

14. An electronic device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the method described in any one of claims 1 to 12.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the method according to any one of claims 1 to 12.

Images