Tooth segmentation method, device, equipment, medium and product based on oral scan data

Abstract

The present invention discloses a tooth segmentation method, device, electronic device, storage medium and program product based on oral scan data. The method comprises: downsampling the first oral scan data to obtain the second oral scan data, the first oral scan data being the scan data of the target oral cavity; performing tooth segmentation based on the second oral scan data to obtain the first tooth segmentation result; performing tooth segmentation based on the first oral scan data and the first tooth segmentation result to obtain the second tooth segmentation result; and determining the third tooth segmentation result of the first oral scan data based on the second tooth segmentation result. The technical solution solves the problems of low efficiency and poor accuracy of tooth segmentation by selecting sampling points in the oral scan data, thereby improving the efficiency of tooth segmentation while ensuring the segmentation accuracy, especially the accuracy of boundary segmentation.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and in particular to a tooth segmentation method, device, electronic device, storage medium and program product based on oral scan data. Background Art

[0002] Oral scan data is the three-dimensional point cloud data collected by intraoral scanner based on optical principles. For application scenarios such as dental implants, dental restorations, and orthodontics, oral scan data usually needs to be processed by tooth segmentation to separate the teeth from the oral scan data and analyze the morphological characteristics of the teeth in order to formulate a scientific treatment plan.

[0003] At present, the tooth segmentation method based on oral scan data usually involves first segmenting the entire jaw tooth model from the oral scan data, and then using the tooth segmentation model built based on the deep learning algorithm to segment individual teeth based on the entire jaw tooth model.

[0004] However, the number of point clouds in oral scan data is huge, generally ranging from tens of thousands to hundreds of thousands. Therefore, the efficiency of segmenting the whole jaw tooth model from oral scan data is low, and it is difficult to achieve accurate segmentation of the tooth boundary area. At the same time, the existing technology requires two stages to segment a single tooth, and the segmentation result of the second stage is completely dependent on the segmentation result of the first stage. Therefore, the final segmentation accuracy is difficult to guarantee. Summary of the invention

[0005] The present invention provides a tooth segmentation method, device, electronic device, storage medium and program product based on oral scan data to solve the problems of low efficiency and poor accuracy of tooth segmentation based on oral scan data. By selecting sampling points in the oral scan data, the tooth segmentation efficiency is improved while the segmentation accuracy, especially the segmentation accuracy of the boundary, is guaranteed.

[0006] According to one aspect of the present invention, a tooth segmentation method based on oral scan data is provided, the method comprising:

[0007] Downsampling the first mouth scan data to obtain second mouth scan data, where the first mouth scan data is scan data of the target oral cavity;

[0008] Performing tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result;

[0009] Performing tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result;

[0010] A third tooth segmentation result of the first oral scan data is determined according to the second tooth segmentation result.

[0011] According to another aspect of the present invention, a tooth segmentation device based on oral scan data is provided, the device comprising:

[0012] A downsampling module, used for downsampling the first mouth scan data to obtain second mouth scan data, wherein the first mouth scan data is scan data of a target oral cavity;

[0013] A first segmentation module, configured to perform tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result;

[0014] A second segmentation module, configured to perform tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result;

[0015] The segmentation result determination module is used to determine a third tooth segmentation result of the first oral scan data according to the second tooth segmentation result.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the tooth segmentation method based on oral scan data described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the tooth segmentation method based on oral scan data described in any embodiment of the present invention when executed.

[0019] According to another aspect of the present invention, a computer program product is provided, comprising a computer program, wherein when the computer program is executed by a processor, the method for teeth segmentation based on oral scan data according to any embodiment of the present invention is implemented.

[0020] The technical solution of the embodiment of the present invention is to downsample the first oral scan data to obtain the second oral scan data, wherein the first oral scan data is the scan data of the target oral cavity; perform tooth segmentation based on the second oral scan data to obtain a first tooth segmentation result; perform tooth segmentation based on the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result; and determine a third tooth segmentation result of the first oral scan data based on the second tooth segmentation result. This technical solution solves the problem of low efficiency and poor accuracy of tooth segmentation of oral scan data, and by selecting sampling points in the oral scan data, the efficiency of tooth segmentation is improved while ensuring segmentation accuracy, especially the accuracy of boundary segmentation.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a tooth segmentation method based on oral scan data provided according to the first embodiment of the present invention;

[0024] Figure 2 is a flow chart of a tooth segmentation method based on oral scan data provided according to the second embodiment of the present invention;

[0025] Figure 3 is a flow chart of a tooth segmentation method based on oral scan data provided according to Embodiment 3 of the present invention;

[0026] Figure 4 is a structural schematic diagram of a tooth segmentation device based on oral scan data provided according to a fourth embodiment of the present invention;

[0027] Figure 5 It is a structural schematic diagram of an electronic device for implementing the tooth segmentation method based on oral scan data of embodiments 1 to 3 of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only embodiments of a part of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0030] Embodiment 1

[0031] Figure 1 A flowchart of a method for teeth segmentation based on oral scan data is provided for the first embodiment of the present invention. This embodiment can be applied to teeth segmentation in oral medical scenarios. The method can be performed by a teeth segmentation device based on oral scan data, which can be implemented in the form of hardware and / or software, and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0032] S110 . Down-sample the first mouth scan data to obtain second mouth scan data, where the first mouth scan data is scan data of a target oral cavity.

[0033] This solution can be executed by electronic devices such as computers and servers. The electronic device can obtain scanning data in the target oral cavity through scanning components such as intraoral scanners. The scanning data can be three-dimensional point cloud data, such as STL data. The electronic device can use the original scanning data obtained by the scanning component as the first mouth scan data. In order to avoid segmentation errors caused by scale differences, the electronic device can normalize each sampling point in the original scanning data and use the normalized original scanning data as the first mouth scan data. The electronic device can perform data processing on the first mouth scan data to output the tooth segmentation result.

[0034] The first mouth scan data has a huge amount of data, usually including tens of thousands to hundreds of thousands of sampling points. Directly using the first mouth scan data for tooth segmentation not only requires processing a huge amount of data, is time-consuming and labor-intensive, but also makes it difficult to achieve accurate segmentation at the level of a single tooth. Therefore, the electronic device can downsample the first mouth scan data, extract part of the data from the first mouth scan data for preliminary tooth segmentation, and based on the preliminary segmentation results, select key sampling points from the first mouth scan data for tooth segmentation in a targeted manner to obtain accurate and reliable tooth segmentation results.

[0035] It is understandable that the electronic device can extract sampling points from the first mouth scan data according to a preset sampling interval to obtain the second mouth scan data. Through downsampling processing, the electronic device can greatly reduce the amount of mouth scan data and effectively reduce the data processing complexity of tooth segmentation.

[0036] S120 , performing tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result.

[0037] The electronic device may pre-build a target segmentation model, and use the mouth scan samples with labels to train the target segmentation model to obtain a first tooth segmentation model. The labels of the mouth scan samples may be categories of each sampling point in the mouth scan samples, and the categories of the sampling points may include categories such as gums, tooth positions in teeth, and other oral targets. The first tooth segmentation model may be obtained by training based on target segmentation models such as pointnet++ and point transformer.

[0038] After obtaining the first tooth segmentation model, the electronic device can input the second mouth scan data into the first tooth segmentation model and use the output of the first tooth segmentation model as the first tooth segmentation result. It is easy to understand that the first tooth segmentation result includes each sampling point category in the second mouth scan data.

[0039] S130 , performing tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result.

[0040] In a feasible scheme, based on the first tooth segmentation result, the electronic device can obtain the category of each sampling point in the second mouth scan data. According to the category of each sampling point in the second mouth scan data, based on classification decision models such as K nearest neighbor, decision tree, support vector machine or naive Bayes, the electronic device can determine the category recognition result of each sampling point in the first mouth scan data. According to the category recognition result of each sampling point in the first mouth scan data, the electronic device can extract the target sampling point from the first mouth scan data according to the preset sampling point extraction principle to obtain the third mouth scan data. Among them, the category recognition result can be the predicted category of the sampling point, and can also include the confidence of the sampling point in each category. The third mouth scan data is input into the pre-trained second tooth segmentation model, and the electronic device can use the output result of the second tooth segmentation model as the second tooth segmentation result.

[0041] In order to reduce the amount of data processing for this tooth segmentation model, the electronic device can divide the first oral scan data into a boundary part and a non-boundary part according to the category recognition results of each sampling point in the first oral scan data, uniformly sample the sampling points of the boundary part to obtain boundary data, and sample the farthest point of the non-boundary part to obtain non-boundary data in order to maintain the shape of the oral scan data after sampling. The electronic device can merge the boundary data and the non-boundary data, and use the merged result as the third oral scan data. The third oral scan data is input into the pre-trained second tooth segmentation model, and the electronic device can use the output result of the second tooth segmentation model as the second tooth segmentation result.

[0042] In another feasible solution, based on the first tooth segmentation result, the electronic device can locate the segmentation boundary, such as the boundary between teeth and the boundary between teeth and gums. The electronic device can extract the target sampling points from the first mouth scan data according to the segmentation boundary to form the third mouth scan data, so as to input the third mouth scan data into the second tooth segmentation model to obtain the second tooth segmentation result.

[0043] It should be noted that the first tooth segmentation model and the second tooth segmentation model can be the same tooth segmentation model or different tooth segmentation models. The second tooth segmentation result can include the categories of each sampling point in the third mouth scan data. In order to speed up the convergence speed of the tooth segmentation model during training, the electronic device can align the mouth scan samples according to a preset angle to obtain mouth scan samples at a similar angle. Using mouth scan samples at similar angles to train the tooth segmentation model can speed up the model convergence speed and greatly shorten the time consumed by model generalization.

[0044] S140: Determine a third tooth segmentation result of the first oral scan data according to the second tooth segmentation result.

[0045] It is easy to understand that the electronic device directly classifies the unknown category of sampling points in the first mouth scan data based on the classification decision model based on the categories of each sampling point in the second tooth segmentation result, thereby obtaining the recognition results of all the sampling point categories in the first mouth scan data, and using the recognition results of each sampling point category in the first mouth scan data as the third tooth segmentation result. The electronic device can also determine the third tooth segmentation result based on the first tooth segmentation result and the second tooth segmentation result. Specifically, the intraoral scanner can fuse the second tooth segmentation result with the first tooth segmentation result to obtain a segmentation fusion result. According to the categories of each sampling point in the segmentation fusion result, based on the classification decision model, the unknown category of sampling points in the first mouth scan data is classified, thereby obtaining the recognition results of all the sampling point categories in the first mouth scan data, and using the recognition results of each sampling point category in the first mouth scan data as the third tooth segmentation result.

[0046] The technical solution of the embodiment of the present invention is to downsample the first oral scan data to obtain the second oral scan data, wherein the first oral scan data is the scan data of the target oral cavity; perform tooth segmentation based on the second oral scan data to obtain a first tooth segmentation result; perform tooth segmentation based on the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result; and determine a third tooth segmentation result of the first oral scan data based on the second tooth segmentation result. This technical solution solves the problem of low efficiency and poor accuracy of tooth segmentation of oral scan data, and by selecting sampling points in the oral scan data, the efficiency of tooth segmentation is improved while ensuring segmentation accuracy, especially the accuracy of boundary segmentation.

[0047] Embodiment 2

[0048] Figure 2 This is a flowchart of a tooth segmentation method based on oral scan data provided by the second embodiment of the present invention. This embodiment is a refinement of the above embodiment. Figure 2 As shown, the method includes:

[0049] S201. Down-sample first mouth scan data to obtain second mouth scan data, where the first mouth scan data is scan data of a target oral cavity.

[0050] S202: Perform tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result.

[0051] S203 . Extract target sampling points from the first scan data according to the categories of the sampling points in the second scan data to obtain third scan data.

[0052] In this solution, the first tooth segmentation result includes the categories of each sampling point in the second mouth scan data. The second mouth scan data is obtained by downsampling the first mouth scan data, so the electronic device can map each sampling point in the second mouth scan data to the first mouth scan data, and determine the category recognition result of the sampling point of unknown category in the first mouth scan data according to the categories of each sampling point in the second mouth scan data.

[0053] After obtaining the category recognition results of each sampling point in the first mouth scan data, the electronic device can extract new mouth scan data, i.e., the third mouth scan data, from the first mouth scan data based on the category recognition results of each sampling point in the first mouth scan data for tooth segmentation in the subsequent stage.

[0054] In a feasible solution, extracting target sampling points from the first scan data according to the categories of the sampling points in the second scan data to obtain the third scan data includes:

[0055] Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data;

[0056] According to the category recognition result of each sampling point in the first scan data, the target sampling point is determined to obtain the third scan data; wherein the third scan data has the same amount of sampling point data as the second scan data.

[0057] The electronic device can determine the category recognition results of each sampling point in the first mouth scan data based on the categories of each sampling point in the second mouth scan data, based on classification decision models such as K nearest neighbor, decision tree, support vector machine or naive Bayes. The electronic device can extract target sampling points from the first mouth scan data according to the category recognition results of each sampling point in the first mouth scan data and according to the preset sampling point extraction principle to obtain the third mouth scan data. The category recognition result can be the predicted category of the sampling point, and can also include the confidence of the sampling point in each category. The amount of sampling point data of the third mouth scan data and the second mouth scan data can be the same. The third mouth scan data is input into the pre-trained second tooth segmentation model, and the electronic device can use the output result of the second tooth segmentation model as the second tooth segmentation result.

[0058] This solution can provide a basis for tooth segmentation in subsequent stages by mapping the first tooth segmentation result to the first mouth scan data. The electronic device can extract sampling points with low segmentation accuracy from the first mouth scan data and apply them to subsequent tooth segmentation to obtain high-precision tooth segmentation results while reducing the amount of data processing.

[0059] S204 , performing tooth segmentation based on the third oral scan data to obtain a second tooth segmentation result.

[0060] After obtaining the third mouth scan data, the electronic device may input the third mouth scan data into the second tooth segmentation model, and use the output of the second tooth segmentation model as the second tooth segmentation result. The second tooth segmentation result may include the categories of each sampling point in the third mouth scan data.

[0061] In a preferred embodiment, performing tooth segmentation based on the third oral scan data to obtain a second tooth segmentation result includes:

[0062] Performing tooth segmentation based on the third oral scan data to obtain a tooth segmentation result of this iteration;

[0063] Determine the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration; wherein, if this iteration is the first iteration, the reference segmentation result matched in this iteration is the tooth segmentation result of the first mouth scan data determined based on the first tooth segmentation result; if this iteration is not the first iteration, the reference segmentation result matched in this iteration is the tooth segmentation result of the first mouth scan data determined based on the tooth segmentation result of the previous iteration;

[0064] If the overlap rate is greater than or equal to a preset overlap threshold, the tooth segmentation result of this iteration is used as the second tooth segmentation result;

[0065] If the overlap rate is less than the preset overlap threshold, the third mouth scan data is updated according to the tooth segmentation result of this iteration, and the tooth segmentation based on the third mouth scan data is returned to be executed until the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration is greater than or equal to the preset overlap threshold, and the second tooth segmentation result is output.

[0066] In order to meet the requirements of different segmentation accuracies, the electronic device can perform tooth segmentation step by step to obtain tooth segmentation results that meet the segmentation accuracy requirements. Specifically, after the third mouth scan data is input into the second tooth segmentation model and the first iteration tooth segmentation results are obtained, the electronic device can compare the first iteration tooth segmentation results with the first iteration matching reference segmentation results, and calculate the overlap rate of the two tooth segmentation results. Among them, the first iteration matching reference segmentation results can be the category recognition results of all sampling points in the first mouth scan data determined based on the categories of each sampling point in the second mouth scan data.

[0067] The electronic device may extract the same sampling points from the teeth segmentation result of the first iteration and the reference segmentation result matched in the first iteration to form a first sampling point set. Each target sampling point in the first sampling point set has two category recognition results, one from the reference segmentation result matched in the first iteration, and the other from the teeth segmentation result matched in the first iteration. The electronic device may use the category recognition result of the target sampling point in the reference segmentation result matched in the first iteration as the first category recognition result, and the category recognition result of the target sampling point in the teeth segmentation result matched in the first iteration as the second category recognition result. The electronic device may compare the first category recognition result and the second category recognition result of each target sampling point in the first sampling point set, and calculate the number of target sampling points in the first sampling point set that have the same first category recognition result and the second category recognition result. The electronic device may use the ratio of the number of target sampling points that have the same first category recognition result and the second category recognition result to the total number of target sampling points in the first sampling point set as the overlap rate of the teeth segmentation result of the first iteration and the reference segmentation result matched in the first iteration.

[0068] If the overlap rate is greater than or equal to a preset overlap threshold, the electronic device can use the tooth segmentation result of the first iteration as the second tooth segmentation result; if the overlap rate is less than the preset overlap threshold, the electronic device can determine the category recognition result of each sampling point in the first mouth scan data based on the tooth segmentation result of the first iteration, extract new third mouth scan data from the first mouth scan data based on the category recognition result of each sampling point in the first mouth scan data, return to execute tooth segmentation based on the third mouth scan data, and perform tooth segmentation again until the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration is greater than or equal to the preset overlap threshold, and output the second tooth segmentation result.

[0069] This scheme realizes accurate boundary recognition by successively updating the sampling points in the third mouth scan data, which can meet the tooth segmentation requirements of different precisions and is conducive to obtaining high-precision tooth segmentation results.

[0070] S205 : Determine the categories of the sampling points in the first scan data according to the categories of the sampling points in the third scan data and based on a predetermined classification decision model.

[0071] It is understandable that the classification decision model can be constructed by algorithms such as K-nearest neighbor, decision tree, support vector machine or naive Bayes, and is used to classify unknown samples according to known sample types. After obtaining the second tooth segmentation result, the electronic device can use the categories of each sampling point in the second tooth segmentation result as known samples, and classify the sampling points of unknown categories in the first mouth scan data based on the segmentation decision model, and determine the category recognition results of the sampling points of unknown categories in the first mouth scan data according to the classification results, thereby obtaining the categories of all sampling points in the first mouth scan data.

[0072] The technical solution of the embodiment of the present invention is to downsample the first oral scan data to obtain the second oral scan data, wherein the first oral scan data is the scan data of the target oral cavity; perform tooth segmentation based on the second oral scan data to obtain the first tooth segmentation result; extract the target sampling points from the first oral scan data according to the categories of each sampling point in the second oral scan data to obtain the third oral scan data; perform tooth segmentation based on the third oral scan data to obtain the second tooth segmentation result; determine the categories of each sampling point in the first oral scan data based on a predetermined classification decision model according to the categories of each sampling point in the third oral scan data. This technical solution solves the problem of low efficiency and poor accuracy of tooth segmentation of oral scan data, and by selecting sampling points in the oral scan data, it improves the efficiency of tooth segmentation while ensuring segmentation accuracy, especially the accuracy of boundary segmentation.

[0073] Embodiment 3

[0074] Figure 3This is a flowchart of a method for teeth segmentation based on oral scan data provided by Embodiment 3 of the present invention. This embodiment refines the above embodiment. Figure 3 As shown, the method includes:

[0075] S310 . Downsample the first mouth scan data to obtain second mouth scan data, where the first mouth scan data is scan data of a target oral cavity.

[0076] S320: Perform tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result.

[0077] It is easy to understand that the distinction between teeth in different tooth positions is significantly smaller than the distinction between teeth and gums. To achieve the same segmentation accuracy, the segmentation of the tooth-to-tooth boundary is more difficult than the segmentation of the tooth-to-gingiva boundary. Using a tooth segmentation model with the same segmentation capability is likely to lead to a waste of resources. Therefore, electronic devices can use tooth segmentation models with different capabilities to segment the tooth-to-tooth boundary and the tooth-to-gingiva boundary respectively, so as to maximize the use of computing resources.

[0078] S330: Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data.

[0079] In this solution, the first tooth segmentation result includes the categories of each sampling point in the second mouth scan data. The second mouth scan data is obtained by downsampling the first mouth scan data, so the electronic device can map each sampling point in the second mouth scan data to the first mouth scan data, and determine the category recognition result of the sampling point of unknown category in the first mouth scan data according to the categories of each sampling point in the second mouth scan data.

[0080] S340. Determine fourth mouth scan data and fifth mouth scan data based on the category recognition results of each sampling point in the first mouth scan data; wherein the fourth mouth scan data is extracted from the first mouth scan data based on the sampling point extraction principle of first segmentation boundary matching; the fifth mouth scan data is extracted from the first mouth scan data based on the sampling point extraction principle of second segmentation boundary matching; the first segmentation boundary is the boundary between teeth; and the second segmentation boundary is the boundary between teeth and gums.

[0081] The electronic device may locate the segmentation boundary according to the category recognition result of each sampling point in the first oral scan data. The category recognition result may include categories such as gums, tooth positions in teeth, and other oral targets; the segmentation boundary may include a first segmentation boundary and a second segmentation boundary; the first segmentation boundary is the boundary between teeth; the second segmentation boundary is the boundary between teeth and gums. The electronic device may set the same sampling point extraction principle for the first segmentation boundary and the second segmentation boundary, and the fourth oral scan data and the fifth oral scan data may be the same oral scan data.

[0082] Due to the difference in segmentation difficulty between the first segmentation boundary and the second segmentation boundary, the electronic device may also set different sampling point extraction principles for the first segmentation boundary and the second segmentation boundary, respectively, so as to obtain different oral scan data. For example, the sampling point extraction interval corresponding to the first segmentation boundary is smaller than the sampling point extraction interval corresponding to the second segmentation boundary, that is, the sampling points in the fourth oral scan data are denser than the sampling points in the fifth oral scan data.

[0083] S350: Perform tooth segmentation according to the fourth oral scan data to obtain a fourth tooth segmentation result.

[0084] It is understandable that the fourth mouth scan data is input into the pre-trained third tooth segmentation model, and the electronic device can use the output result of the third tooth segmentation model as the fourth tooth segmentation result. The fourth tooth segmentation result can include the categories of each sampling point in the fourth mouth scan data.

[0085] S360: Perform tooth segmentation according to the fifth oral scan data to obtain a fifth tooth segmentation result.

[0086] The fifth mouth scan data is input into a pre-trained fourth teeth segmentation model, and the electronic device can use the output result of the fourth teeth segmentation model as the fifth teeth segmentation result.

[0087] It should be noted that the third tooth segmentation model and the fourth tooth segmentation model can be different tooth segmentation models. The complexity of the network structure of the third tooth segmentation model can be higher than that of the fourth tooth segmentation model to complete a more difficult segmentation task. For example, the third tooth segmentation model can be a multi-classification target segmentation model, that is, to achieve the distinction between different tooth positions, and the fourth tooth segmentation model can be a two-classification target segmentation model, that is, to achieve the distinction between teeth and gums. The fifth tooth segmentation result can include the categories of each sampling point in the fifth mouth scan data.

[0088] S370: Determine a second tooth segmentation result according to the fourth tooth segmentation result and the fifth tooth segmentation result.

[0089] After obtaining the fourth tooth segmentation result and the fifth tooth segmentation result, the electronic device may use the data fusion result of the fourth tooth segmentation result and the fifth tooth segmentation result as the second tooth segmentation result.

[0090] Specifically, for the sampling points that do not overlap in the fourth tooth segmentation result and the fifth tooth segmentation result, and the overlapping sampling points with the same category recognition results in the fourth tooth segmentation result and the fifth tooth segmentation result, their category recognition results are directly retained. For the overlapping sampling points with different category recognition results in the fourth tooth segmentation result and the fifth tooth segmentation result, the intraoral scanner can remove them to obtain the second tooth segmentation result.

[0091] S380: Determine a third tooth segmentation result of the first oral scan data according to the second tooth segmentation result.

[0092] According to the technical solution of the embodiment of the present invention, first mouth scan data is downsampled to obtain second mouth scan data, wherein the first mouth scan data is scanning data of a target oral cavity; teeth segmentation is performed based on the second mouth scan data to obtain a first teeth segmentation result; according to the categories of each sampling point in the second mouth scan data, the category recognition result of each sampling point in the first mouth scan data is determined; according to the category recognition result of each sampling point in the first mouth scan data, fourth mouth scan data and fifth mouth scan data are determined; wherein the fourth mouth scan data is mouth scan data extracted from the first mouth scan data based on the sampling point extraction principle of matching the first segmentation boundary; the fifth mouth scan data is mouth scan data extracted from the first mouth scan data based on the sampling point extraction principle of matching the second segmentation boundary; the first segmentation boundary is the boundary between teeth; the second segmentation boundary is the boundary between teeth and gums; teeth segmentation is performed based on the fourth mouth scan data to obtain a fourth teeth segmentation result; teeth segmentation is performed based on the fifth mouth scan data to obtain a fifth teeth segmentation result; and a third teeth segmentation result of the first mouth scan data is determined based on the second teeth segmentation result. This technical solution solves the problem of low efficiency and poor accuracy of tooth segmentation in oral scan data. By selecting sampling points in the oral scan data, it improves the efficiency of tooth segmentation while ensuring the segmentation accuracy, especially the accuracy of boundary segmentation. By distinguishing the types of segmentation boundaries, it achieves efficient utilization of the tooth segmentation model, which is conducive to reducing the overall complexity of the tooth segmentation task.

[0093] Embodiment 4

[0094] Figure 4 This is a schematic diagram of the structure of a tooth segmentation device based on oral scan data provided by the fourth embodiment of the present invention. Figure 4 As shown, the device comprises:

[0095] A downsampling module 410 is used to downsample the first mouth scan data to obtain second mouth scan data, where the first mouth scan data is scan data of a target oral cavity;

[0096] A first segmentation module 420, configured to perform tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result;

[0097] A second segmentation module 430, configured to perform tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result;

[0098] The segmentation result determination module 440 is used to determine a third tooth segmentation result of the first oral scan data according to the second tooth segmentation result.

[0099] In this solution, the first tooth segmentation result includes each sampling point category in the second oral scan data; the second segmentation module 430 includes:

[0100] a third data generating unit, configured to extract target sampling points from the first scan data according to the categories of the sampling points in the second scan data, to obtain third scan data;

[0101] The second segmentation unit is used to perform tooth segmentation based on the third oral scan data to obtain a second tooth segmentation result.

[0102] Based on the above solution, the third data generating unit is specifically used to:

[0103] Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data;

[0104] According to the category recognition result of each sampling point in the first scan data, the target sampling point is determined to obtain the third scan data; wherein the third scan data has the same amount of sampling point data as the second scan data.

[0105] In a feasible solution, the second segmentation unit is specifically used to:

[0106] Performing tooth segmentation based on the third oral scan data to obtain a tooth segmentation result of this iteration;

[0107] Determine the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration; wherein, if this iteration is the first iteration, the reference segmentation result matched in this iteration is the tooth segmentation result of the first mouth scan data determined based on the first tooth segmentation result; if this iteration is not the first iteration, the reference segmentation result matched in this iteration is the tooth segmentation result of the first mouth scan data determined based on the tooth segmentation result of the previous iteration;

[0108] If the overlap rate is greater than or equal to a preset overlap threshold, the tooth segmentation result of this iteration is used as the second tooth segmentation result;

[0109] If the overlap rate is less than the preset overlap threshold, the third mouth scan data is updated according to the tooth segmentation result of this iteration, and the tooth segmentation based on the third mouth scan data is returned to be executed until the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration is greater than or equal to the preset overlap threshold, and the second tooth segmentation result is output.

[0110] In a preferred embodiment, the first tooth segmentation result includes each sampling point category in the second mouth scan data;

[0111] The second segmentation module 430 is specifically configured to:

[0112] Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data;

[0113] Determine fourth mouth scan data and fifth mouth scan data according to the category recognition result of each sampling point in the first mouth scan data; wherein the fourth mouth scan data is mouth scan data extracted from the first mouth scan data based on the sampling point extraction principle of first segmentation boundary matching; the fifth mouth scan data is mouth scan data extracted from the first mouth scan data based on the sampling point extraction principle of second segmentation boundary matching; the first segmentation boundary is a boundary between teeth; and the second segmentation boundary is a boundary between teeth and gums;

[0114] Performing tooth segmentation according to the fourth oral scan data to obtain a fourth tooth segmentation result;

[0115] Performing tooth segmentation according to the fifth oral scan data to obtain a fifth tooth segmentation result;

[0116] A second tooth segmentation result is determined according to the fourth tooth segmentation result and the fifth tooth segmentation result.

[0117] In this embodiment, the second tooth segmentation result includes each sampling point category in the third oral scan data;

[0118] The segmentation result determination module 440 is specifically used for:

[0119] According to the categories of the sampling points in the third oral scan data, based on a predetermined classification decision model, the categories of the sampling points in the first oral scan data are determined.

[0120] The tooth segmentation device based on oral scan data provided in the embodiment of the present invention can execute the tooth segmentation method based on oral scan data provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0121] Embodiment 5

[0122] Figure 5 A schematic diagram of an electronic device 510 that can be used to implement embodiments one to three of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0123] like Figure 5 As shown, the electronic device 510 includes at least one processor 511, and a memory connected to the at least one processor 511 in communication, such as a read-only memory (ROM) 512, a random access memory (RAM) 513, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 511 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 512 or the computer program loaded from the storage unit 518 to the random access memory (RAM) 513. In the RAM 513, various programs and data required for the operation of the electronic device 510 can also be stored. The processor 511, the ROM 512, and the RAM 513 are connected to each other via a bus 514. An input / output (I / O) interface 515 is also connected to the bus 514.

[0124] A number of components in the electronic device 510 are connected to the I / O interface 515, including: an input unit 516, such as a keyboard, a mouse, etc.; an output unit 517, such as various types of displays, speakers, etc.; a storage unit 518, such as a disk, an optical disk, etc.; and a communication unit 519, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 519 allows the electronic device 510 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0125] The processor 511 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 511 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 511 executes the various methods and processes described above, such as a tooth segmentation method based on oral scan data.

[0126] In some embodiments, the tooth segmentation method based on oral scan data can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 518. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 510 via the ROM 512 and / or the communication unit 519. When the computer program is loaded into the RAM 513 and executed by the processor 511, one or more steps of the tooth segmentation method based on oral scan data described above can be performed. Alternatively, in other embodiments, the processor 511 can be configured to perform the tooth segmentation method based on oral scan data in any other appropriate manner (for example, by means of firmware).

[0127] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0128] The computer program for implementing the method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable dental segmentation device based on oral scan data, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program can be executed completely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or completely on a remote machine or server.

[0129] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0130] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0131] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0132] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0133] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0134] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A tooth segmentation method based on oral scan data, characterized in that: The method comprises: Downsampling the first mouth scan data to obtain second mouth scan data, where the first mouth scan data is scan data of the target oral cavity; Performing tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result; the first tooth segmentation result includes each sampling point category in the second mouth scan data; Performing tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result; According to the categories of the sampling points in the second tooth segmentation result, based on a predetermined classification decision model, determining the categories of the sampling points in the first oral scan data; The step of performing tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result includes: Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data; Determine the target sampling point according to the category recognition result of each sampling point in the first scan data to obtain the third scan data; Teeth segmentation is performed based on the third oral scan data to obtain a second teeth segmentation result.

2. The tooth segmentation method based on oral scan data according to claim 1, characterized in that: The third scan data has the same amount of sampling point data as the second scan data.

3. The tooth segmentation method based on oral scan data according to claim 1, characterized in that: The performing teeth segmentation based on the third oral scan data to obtain a second teeth segmentation result includes: Performing tooth segmentation based on the third oral scan data to obtain a tooth segmentation result of this iteration; Determine the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration; wherein, if this iteration is the first iteration, the reference segmentation result matched in this iteration is the tooth segmentation result of the first mouth scan data determined based on the first tooth segmentation result; if this iteration is not the first iteration, the reference segmentation result matched in this iteration is the tooth segmentation result of the first mouth scan data determined based on the tooth segmentation result of the previous iteration; If the overlap rate is greater than or equal to a preset overlap threshold, the tooth segmentation result of this iteration is used as the second tooth segmentation result; If the overlap rate is less than the preset overlap threshold, the third mouth scan data is updated according to the tooth segmentation result of this iteration, and the tooth segmentation based on the third mouth scan data is returned to be executed until the overlap rate between the reference segmentation result matched in this iteration and the tooth segmentation result of this iteration is greater than or equal to the preset overlap threshold, and the second tooth segmentation result is output.

4. The tooth segmentation method based on oral scan data according to claim 1, characterized in that: The performing tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result also includes: Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data; Determine fourth mouth scan data and fifth mouth scan data according to the category recognition result of each sampling point in the first mouth scan data; wherein the fourth mouth scan data is mouth scan data extracted from the first mouth scan data based on the sampling point extraction principle of first segmentation boundary matching; the fifth mouth scan data is mouth scan data extracted from the first mouth scan data based on the sampling point extraction principle of second segmentation boundary matching; the first segmentation boundary is a boundary between teeth; and the second segmentation boundary is a boundary between teeth and gums; Performing tooth segmentation according to the fourth oral scan data to obtain a fourth tooth segmentation result; Performing tooth segmentation according to the fifth oral scan data to obtain a fifth tooth segmentation result; A second tooth segmentation result is determined according to the fourth tooth segmentation result and the fifth tooth segmentation result.

5. The tooth segmentation method based on oral scan data according to claim 1, characterized in that: The second tooth segmentation result includes each sampling point category in the third oral scan data; According to the categories of the sampling points in the third oral scan data, based on a predetermined classification decision model, the categories of the sampling points in the first oral scan data are determined.

6. A tooth segmentation device based on oral scan data, characterized in that: The device comprises: A downsampling module, used for downsampling the first mouth scan data to obtain second mouth scan data, wherein the first mouth scan data is scan data of a target oral cavity; A first segmentation module, configured to perform tooth segmentation based on the second mouth scan data to obtain a first tooth segmentation result; the first tooth segmentation result includes categories of each sampling point in the second mouth scan data; A second segmentation module, configured to perform tooth segmentation according to the first oral scan data and the first tooth segmentation result to obtain a second tooth segmentation result; A segmentation result determination module, configured to determine the category of each sampling point in the first oral scan data according to the category of each sampling point in the second tooth segmentation result and based on a predetermined classification decision model; Wherein, the second segmentation module is specifically used for: Determine a category recognition result of each sampling point in the first scan data according to the category of each sampling point in the second scan data; Determine the target sampling point according to the category recognition result of each sampling point in the first scan data to obtain the third scan data; Teeth segmentation is performed based on the third oral scan data to obtain a second teeth segmentation result.

7. An electronic device, characterized in that: The electronic device comprises: At least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the tooth segmentation method based on oral scan data as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the tooth segmentation method based on oral scan data according to any one of claims 1 to 5 when executed.

9. A computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for tooth segmentation based on oral scan data according to any one of claims 1 to 5 is implemented.

Images