Artificial intelligence-based implant position prediction method and device, terminal and medium

Abstract

The invention relates to the technical field of oral implantation. The invention discloses an artificial intelligence-based implant position prediction method and device, a terminal and a medium, which can improve the accuracy of a prediction result of an implant position. The artificial intelligence-based implant position prediction method comprises the following steps: acquiring first implant position information and a plurality of dental crown slice images of a dental crown area; and processing the first planting position information and all the dental crown slice images by adopting an artificial intelligence algorithm to obtain target planting position information of the implant in a tooth root area corresponding to the dental crown area.

Description

Technical Field

[0001] The present invention relates to the field of oral implant technology, and more specifically, to an artificial intelligence-based implant position prediction method, device, terminal and medium. Background Art

[0002] An implant is an artificial implant that is surgically implanted into the alveolar bone of a patient's toothless area to replace a lost or extracted tooth root. Implants are used to support restorations (also known as crowns).

[0003] The traditional AI-based implant position prediction method uses tooth root data (i.e., tooth root images) to train and infer the neural network, and finally obtains the target implant position information of the implant. However, the tooth root is the part of the tooth embedded in the alveolar bone, and the alveolar bone is surrounded by the gums. These oral tissues will lead to poor imaging quality of the tooth root image, resulting in inaccurate prediction results of the implant position. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide an artificial intelligence-based implant position prediction method, device, terminal and medium, which can improve the accuracy of the implant position prediction result. The embodiments of the present application are mainly implemented through the following technical solutions:

[0005] A first aspect of an embodiment of the present application provides an implant position prediction method based on artificial intelligence, comprising:

[0006] Acquire the first implantation position information of the crown area and multiple crown slice images;

[0007] The first implantation position information and all the crown slice images are processed using an artificial intelligence algorithm to obtain target implantation position information of the implant in the root area corresponding to the crown area.

[0008] According to an embodiment of the present application, the step of using an artificial intelligence algorithm to process the first implantation position information and all the crown slice images to obtain the target implantation position information of the implant in the root area corresponding to the crown area includes:

[0009] Inputting the first implant position information and all the crown slice images into the implant position prediction network of the artificial intelligence algorithm to obtain the second implant position information;

[0010] A three-dimensional space straight line fitting algorithm of an artificial intelligence algorithm is used to map the second implantation position information to the tooth root area to obtain the target implantation position information.

[0011] According to one embodiment of the present application, the training step of the implant position prediction network includes:

[0012] Acquire a training data set and a real implant position information set, wherein each training data in the training data set includes a dental crown training image and implant position training data corresponding to the dental crown training image, and each real implant position information in the real implant position information set has a one-to-one correspondence with the corresponding training data;

[0013] Inputting target training data into the Transformer model to obtain predicted planting position information, wherein the target training data is any training data in the training data set;

[0014] A loss function is calculated based on the predicted implant position information and the corresponding actual implant position information, and model parameters of the Transformer model are adjusted based on the loss function to form the implant position prediction network.

[0015] According to an embodiment of the present application, the three-dimensional space straight line fitting algorithm using an artificial intelligence algorithm maps the second implantation position information to the tooth root area, and the step of obtaining the target implantation position information includes:

[0016] constructing a first spatial transformation algorithm based on the second planting position information;

[0017] Obtaining a first residual sum of squares and a second residual sum of squares based on the first spatial transformation algorithm;

[0018] Calculate the first residual sum of squares and the second residual sum of squares based on the least squares method to obtain a first coefficient, a second coefficient, a third coefficient and a fourth coefficient of the spatial straight line;

[0019] The first coefficient, the second coefficient, the third coefficient, the fourth coefficient and all root slice images of the root area are input into the first space transformation algorithm to calculate the target implant position information.

[0020] According to one embodiment of the present application, the step of obtaining first implantation position information of the crown region includes:

[0021] Acquire third implantation position information of the implant in the tooth root area;

[0022] The third implantation position information is mapped to the tooth crown region through a three-dimensional space straight line fitting algorithm to obtain the first implantation position information.

[0023] According to an embodiment of the present application, the step of mapping the third implantation position information to the crown region through a three-dimensional space straight line fitting algorithm to obtain the first implantation position information includes:

[0024] constructing a second spatial transformation algorithm based on the third planting position information;

[0025] Obtaining a third residual sum of squares and a fourth residual sum of squares based on the second spatial transformation algorithm;

[0026] Calculate the third residual sum of squares and the fourth residual sum of squares based on the least squares method to obtain a fifth coefficient, a sixth coefficient, a seventh coefficient and an eighth coefficient of the spatial straight line;

[0027] The fifth coefficient, the sixth coefficient, the seventh coefficient, the eighth coefficient and all the crown slice images are input into the second space transformation algorithm to calculate and obtain the first implant position information.

[0028] According to one embodiment of the present application, the calculation formula of the second space transformation algorithm is:

[0029]

[0030] in, represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the root slice image of the jth root area of ​​the pth patient on the x-axis; k1 represents the ninth coefficient of the space line; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; b1 represents the tenth coefficient of the space line; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th root slice image; k2 represents the eleventh coefficient of the spatial straight line; b2 represents the twelfth coefficient of the spatial straight line.

[0031] According to a second aspect of the embodiments of the present application, there is provided an implant position prediction device based on artificial intelligence, the device comprising:

[0032] A first implantation position information acquisition module, used to acquire first implantation position information of a crown region and a plurality of crown slice images;

[0033] The target implantation position information acquisition module is used to process the first implantation position information and all the crown slice images using an artificial intelligence algorithm to obtain the target implantation position information of the implant in the root area corresponding to the crown area.

[0034] The third aspect of the embodiments of the present application provides a terminal device, including: a processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory, and executing the steps of the artificial intelligence-based implant position prediction method provided in the first aspect of the embodiments of the present application.

[0035] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program enables a computer to execute the steps of the artificial intelligence-based implant position prediction method provided in the first aspect of the embodiment of the present application.

[0036] The beneficial effects of the embodiments of the present application include:

[0037] The embodiment of the present application uses all crown slice images of the crown area to complete the prediction of the implant position. Specifically, the embodiment of the present application uses an artificial intelligence algorithm to process the first implant position information and all crown slice images of the crown area to obtain the target implant position information of the implant in the root area corresponding to the crown area. Since the crown part of the tooth is not wrapped by various oral tissues such as alveolar bone or gums, the CBCT imaging of the crown part (that is, the crown slice image) will be clearer. Therefore, compared with the prior art, the embodiment of the present application can improve the accuracy of the prediction results of the implant position.

[0038] Moreover, in terms of the physical structure of the tooth, the cross-sectional area change of the crown part is much smaller than that of the root part. Therefore, the structural stability of the crown part is stronger than that of the root part, which is beneficial to improving the accuracy of the prediction results of the implant position. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0040] Figure 1 A flowchart of an artificial intelligence-based implant position prediction method of the present invention in some embodiments;

[0041] Figure 2 A tooth crown slice image in some embodiments of the present invention;

[0042] Figure 3 are tooth crown slice images in other embodiments of the present invention;

[0043] Figure 4 The tooth crown slice images in some other embodiments of the present invention;

[0044] Figure 5 A tooth root slice image in some embodiments of the present invention;

[0045] Figure 6 are tooth root slice images in other embodiments of the present invention;

[0046] Figure 7 Root slice images in some other embodiments of the present invention;

[0047] Figure 8 is a structural block diagram of an implant position prediction device based on artificial intelligence in some embodiments of the present invention;

[0048] Fig. 9 It is a principle block diagram of the terminal device of the present invention in some embodiments. DETAILED DESCRIPTION

[0049] In order to make the above-mentioned purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are described in detail below in conjunction with the accompanying drawings. In the following description, many specific details are set forth to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways different from those described herein, and those skilled in the art can make similar improvements without violating the connotation of the present application, so the present application is not limited by the specific embodiments disclosed below.

[0050] It should be noted that the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0051] The terms "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0052] The terms "comprises," "includes," or any other variations thereof are intended to cover a non-exclusive inclusion, for example, a process, method, system, product, or apparatus that comprises a series of steps or elements is not necessarily limited to those steps or elements explicitly listed but may include other steps or elements not explicitly listed or inherent to such process, method, product, or apparatus.

[0053] Unless otherwise defined, all technical and scientific terms used in the specification of this application have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application. The term "and / or" used in the specification of this application includes any and all combinations of one or more related listed items.

[0054] The specific implementation of the present application is further described below in conjunction with the accompanying drawings.

[0055] <Artificial intelligence-based implant position prediction method>

[0056] like Figure 1 FIG. 1 is a flowchart of an artificial intelligence-based implant position prediction method provided in the first aspect of the embodiment of the present application. Figure 1 In the method, the implant position prediction method based on artificial intelligence includes:

[0057] S1. Acquire first implantation position information of a crown region and a plurality of crown slice images.

[0058] The first planting position information is a three-dimensional coordinate, and the first planting position information is expressed as in, represents the coordinate information of the first implantation position information on the x-axis, that is, the coordinate information of the i-th tooth crown slice image of the p-th patient on the x-axis; represents the coordinate information of the first implantation position information on the y-axis, that is, the coordinate information of the i-th tooth crown slice image of the p-th patient on the y-axis; represents the coordinate information of the first implantation position information on the z-axis, that is, the i-th crown slice image of the p-th patient; represents the total number of crown slice images of the pth patient, and c represents the crown.

[0059] The crown slice image can be referenced Figure 2 , 3 and 4. Figure 2 In the figure, number 216 is Figure 2 The index number of the patient's mouth is "1.02 cm", which is the size of the crown area of ​​the edentulous part of the patient's mouth. Figure 3 In the figure, number 221 is Figure 3 The index number of the patient's mouth is "1.02 cm", which is the size of the crown area of ​​the edentulous part of the patient's mouth. Figure 4 In the figure, reference number 226 is Figure 4 The index number of "1.03cm" is the size of the crown area of ​​the edentulous part in the patient's mouth.

[0060] S2. Using an artificial intelligence algorithm to process the first implantation position information and all the crown slice images to obtain target implantation position information of the implant in the root area corresponding to the crown area.

[0061] Furthermore, the S2 step includes:

[0062] S21. Input the first implant position information and all the crown slice images into the implant position prediction network of the artificial intelligence algorithm to obtain the second implant position information.

[0063] Furthermore, the training steps of the implant position prediction network include:

[0064] S211. Obtain a training data set and a real implant position information set, wherein each training data in the training data set includes a crown training image and implant position training data corresponding to the crown training image, and each real implant position information in the real implant position information set has a one-to-one correspondence with the corresponding training data.

[0065] The implantation position training data and the actual implantation position information are both three-dimensional coordinates.

[0066] S212, inputting target training data into the Transformer model to obtain predicted planting position information, wherein the target training data is any training data in the training data set.

[0067] S213, calculating a loss function based on the predicted implant position information and the corresponding actual implant position information, and adjusting the model parameters of the Transformer model based on the loss function to form the implant position prediction network.

[0068] The training data set and the real implant position information set both use paired CBCT data of patients with successful implantation before and after the implantation.

[0069] The loss function can be implemented by existing technologies, and this application does not impose any further limitations on this.

[0070] It should also be noted that the second planting position information is a three-dimensional coordinate, and the second planting position information is expressed as in, Represents the predicted coordinate information of the second implant position information on the x-axis, that is, the predicted coordinate information of the p-th patient on the x-axis of the i-th crown slice image; Represents the predicted coordinate information of the second implant position information on the y-axis, that is, the predicted coordinate information of the p-th patient on the y-axis of the i-th crown slice image; Represents the predicted coordinate information of the second implant position information on the z-axis, that is, the i-th crown slice image of the p-th patient; represents the total number of crown slice images of the pth patient, and c represents the crown.

[0071] S22. Using a three-dimensional space straight line fitting algorithm of an artificial intelligence algorithm to map the second implantation position information to the tooth root area, to obtain the target implantation position information.

[0072] Furthermore, the step S22 includes:

[0073] S221. Construct a first space transformation algorithm based on the second planting position information.

[0074] Specifically, the calculation formula of the first space transformation algorithm is:

[0075]

[0076] in, Represents the predicted coordinate information of the second implant position information on the x-axis, that is, the predicted coordinate information of the p-th patient on the x-axis of the i-th crown slice image; The thirteenth coefficient represents the straight line in space; Represents the predicted coordinate information of the second implant position information on the z-axis, that is, the i-th tooth root slice image of the p-th patient; The fourteenth coefficient represents the straight line in space; Represents the predicted coordinate information of the second implant position information on the y-axis, that is, the predicted coordinate information of the p-th patient on the y-axis of the i-th tooth root slice image; represents the fifteenth coefficient of the space line; Represents the sixteenth coefficient of the space line.

[0077] S222. Obtain a first residual sum of squares and a second residual sum of squares based on the first spatial transformation algorithm.

[0078] Specifically, the calculation formula of the first residual sum of squares is:

[0079]

[0080] in, Represents the predicted coordinate information of the second implant position information on the x-axis, that is, the predicted coordinate information of the p-th patient on the x-axis of the i-th crown slice image; The thirteenth coefficient represents the straight line in space; Represents the predicted coordinate information of the second implant position information on the z-axis, that is, the i-th crown slice image of the p-th patient; The fourteenth coefficient represents the straight line in space; represents the total number of crown slice images of the pth patient, and c represents the crown.

[0081] The calculation formula of the second residual sum of squares is:

[0082]

[0083] in, Represents the predicted coordinate information of the second implant position information on the z-axis, that is, the i-th crown slice image of the p-th patient; represents the coordinate information of the second implant position information on the y-axis, that is, the predicted coordinate information of the p-th patient on the y-axis of the i-th crown slice image; represents the fifteenth coefficient of the space line; represents the sixteenth coefficient of the space line, represents the total number of crown slice images of the pth patient, and c represents the crown.

[0084] S223. Calculate the first residual sum of squares and the second residual sum of squares based on the least squares method to obtain a first coefficient, a second coefficient, a third coefficient and a fourth coefficient of the spatial straight line.

[0085] The calculation method for calculating the first residual sum of squares and the second residual sum of squares based on the least squares method is:

[0086]

[0087] in, represents the first residual sum of squares, represents the total number of crown slice images of the pth patient, c represents the crown; i represents the i-th crown slice image; Represents the predicted coordinate information of the second implant position information on the x-axis, that is, the predicted coordinate information of the p-th patient on the x-axis of the i-th crown slice image; The thirteenth coefficient represents the straight line in space; Represents the predicted coordinate information of the second implant position information on the z-axis, that is, the i-th crown slice image of the p-th patient; The fourteenth coefficient represents the straight line in space; Represents the predicted coordinate information of the second implant position information on the y-axis, that is, the predicted coordinate information of the p-th patient on the y-axis of the i-th crown slice image; represents the fifteenth coefficient of the space line; The sixteenth coefficient represents the straight line in space; represents the second residual sum of squares.

[0088] Further, the second planting position information is brought into the least squares method to solve the first coefficient The second coefficient The third coefficient and the fourth coefficient

[0089] The first coefficient for

[0090] in, i. and The meaning is the same as above, so it will not be repeated here.

[0091] The second coefficient for:

[0092] in, i. and The meaning is the same as above, so it will not be repeated. is the first coefficient.

[0093] The third coefficient for:

[0094] in, i. and The meaning is the same as above, so it will not be repeated here.

[0095] The fourth coefficient for:

[0096] in, i. and The meaning is the same as above, so it will not be repeated. is the third coefficient.

[0097] S224, inputting the first coefficient, the second coefficient, the third coefficient, the fourth coefficient and all root slice images of the root area into the first spatial transformation algorithm to calculate the target implant position information.

[0098] The target planting position information is a three-dimensional coordinate, and the target planting position information is expressed as in, represents the coordinate information of the target implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; represents the coordinate information of the target implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th tooth root slice image; represents the coordinate information of the target implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; represents the total number of tooth root slice images of the pth patient, and r represents the tooth root.

[0099] The calculation formula of the target planting position information is:

[0100]

[0101] in, The meanings of and j are the same as above, so they are not repeated here. is the first coefficient, is the second coefficient, is the third coefficient, is the fourth coefficient.

[0102] The tooth root slice image can be referred to Figure 5 , 6 and 7. Figure 5 In the figure, number 261 is Figure 5 The index number of "1.39cm" is the size of the root area of ​​the edentulous part of the patient's mouth. Figure 6 In the figure, number 266 is Figure 6 The index number is "1.45 cm" which is the size of the root area of ​​the edentulous part of the patient's mouth. Figure 7 In the figure, number 271 is Figure 7 The index number of "1.50 cm" is the size of the root area of ​​the edentulous part in the patient's mouth.

[0103] Depend on Figure 2-7 The attached figures shown can determine that the change in cross-sectional area (size) of the crown region of the toothless part in the patient's mouth is smaller than the change in cross-sectional area (size) of the root region. Therefore, the structural stability of the crown region is stronger. The present application uses the data of the crown region to predict the implantation position of the implant more accurately.

[0104] In some embodiments, the step of obtaining first implantation position information of the crown region includes:

[0105] S3. Acquire the third implantation position information of the implant in the tooth root area.

[0106] In the embodiment of the present application, the third implant position information is derived from the patient's CBCT data. Specifically, multiple root slice images of the root area are extracted from the CBCT data, and the third implant position information is obtained from the root slice images.

[0107] S4. Mapping the third implantation position information to the tooth crown region through a three-dimensional space straight line fitting algorithm to obtain the first implantation position information.

[0108] Furthermore, the S4 step includes:

[0109] S41. Constructing a second space transformation algorithm based on the third planting position information.

[0110] In the embodiment of the present application, the third planting position information is a three-dimensional coordinate, and the third planting position information is expressed as in, represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th tooth root slice image; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; represents the total number of tooth root slice images of the pth patient, and r represents the tooth root.

[0111] In the embodiment of the present application, the third planting position information is combined with the coefficient of the spatial straight line to construct the second spatial transformation algorithm.

[0112] Specifically, the calculation formula of the second space transformation algorithm is:

[0113]

[0114] in, represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; k1 represents the ninth coefficient of the space line; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; b1 represents the tenth coefficient of the space line; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the j-th root slice image of the p-th patient on the y-axis; k2 represents the eleventh coefficient of the spatial straight line; b2 represents the twelfth coefficient of the spatial straight line.

[0115] S42: Obtain a third residual sum of squares and a fourth residual sum of squares based on the second spatial transformation algorithm.

[0116] The calculation formula of the third residual sum of squares is:

[0117]

[0118] in, represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; k1 represents the ninth coefficient; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; b1 represents the tenth coefficient.

[0119] The calculation formula of the fourth residual sum of squares is:

[0120]

[0121] in, represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th tooth root slice image; k2 represents the eleventh coefficient; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th root slice image of the p-th patient; b2 represents the twelfth coefficient.

[0122] S43. Calculate the third residual sum of squares and the fourth residual sum of squares based on the least squares method to obtain the fifth coefficient, the sixth coefficient, the seventh coefficient and the eighth coefficient of the spatial straight line.

[0123] The calculation method for calculating the third residual sum of squares and the fourth residual sum of squares based on the least squares method is:

[0124]

[0125] Wherein, Q1 represents the third residual sum of squares; represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; k1 represents the ninth coefficient; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; b1 represents the tenth coefficient; Q2 represents the fourth residual sum of squares; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th tooth root slice image; k2 represents the eleventh coefficient; b2 represents the twelfth coefficient.

[0126] Further, the third planting position information is substituted into the least square method to solve the fifth coefficient k1, the sixth coefficient b1, the seventh coefficient k2 and the eighth coefficient b2.

[0127] The fifth coefficient k1 is

[0128] in, represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; Represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient.

[0129] The sixth coefficient b1 is

[0130] in, represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the p-th patient on the x-axis of the j-th tooth root slice image; k1 is the fifth coefficient; Represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient.

[0131] The seventh coefficient k2 is

[0132] in, represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th tooth root slice image; Represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient.

[0133] The eighth coefficient b2 is

[0134] in, represents the total number of tooth root slice images of the pth patient, r represents the tooth root; j represents the jth tooth root slice image; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th tooth root slice image; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; k2 represents the seventh coefficient.

[0135] S44, inputting the fifth coefficient, the sixth coefficient, the seventh coefficient, the eighth coefficient and all the crown slice images into the second space transformation algorithm to calculate and obtain the first implant position information.

[0136] The calculation formula of the first planting position information is:

[0137]

[0138] Wherein, k1 is the fifth coefficient, b1 is the sixth coefficient, k2 is the seventh coefficient, b2 is the eighth coefficient, Represents the coordinate information of the first implant position information on the z-axis, that is, the i-th crown slice image of the p-th patient.

[0139] Through the above technical solution, the embodiment of the present application uses all the crown slice images of the crown area to complete the prediction of the implant position. Specifically, the embodiment of the present application uses an artificial intelligence algorithm to process the first implant position information and all the crown slice images of the crown area to obtain the target implant position information of the implant in the root area corresponding to the crown area. Since the crown part of the tooth is not wrapped by various oral tissues such as alveolar bone or gums, the CBCT imaging of the crown part (that is, the crown slice image) will be clearer. Therefore, compared with the prior art, the embodiment of the present application can improve the accuracy of the prediction results of the implant position.

[0140] Moreover, in terms of the physical structure of the tooth, the cross-sectional area change of the crown part is much smaller than that of the root part. Therefore, the structural stability of the crown part is stronger than that of the root part, which is beneficial to improving the accuracy of the prediction results of the implant position.

[0141] <Artificial intelligence-based implant position prediction device>

[0142] like Figure 8FIG. 1 is a block diagram of an artificial intelligence-based implant position prediction device according to the second aspect of the present application. Figure 8 In the embodiment, the implant position prediction device 500 based on artificial intelligence comprises:

[0143] A first implantation position information acquisition module 501, used to acquire first implantation position information of a crown region and a plurality of crown slice images;

[0144] The target implantation position information obtaining module 502 is used to process the first implantation position information and all the crown slice images using an artificial intelligence algorithm to obtain the target implantation position information of the implant in the root area corresponding to the crown area.

[0145] <Terminal Equipment>

[0146] In a third aspect of the embodiments of the present application, a terminal device is provided, wherein the principle block diagram of the terminal device can be as follows: Fig. 9 As shown. The terminal device includes a processor, a memory, a network interface, a display screen and a temperature sensor connected via a system bus. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the terminal device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, an artificial intelligence-based implant position prediction method is implemented. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor is pre-set inside the terminal device to detect the operating temperature of the internal device.

[0147] Those skilled in the art will understand that Fig. 9 The principle block diagram shown in the figure is only a block diagram of a partial structure related to the scheme of the present invention, and does not constitute a limitation on the terminal device to which the scheme of the present invention is applied. The specific terminal device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0148] In some embodiments, the terminal device includes a processor and a memory, the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the steps of the artificial intelligence-based implant position prediction method provided in the first aspect of the above-mentioned embodiment of the present application.

[0149] <Computer Readable Storage Medium>

[0150] According to a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium is used to store a computer program, wherein the computer program enables a computer to execute the steps of the artificial intelligence-based implant position prediction method provided in the first aspect of the embodiment of the present application.

[0151] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided by the present invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0152] The technical features of the above embodiments can be combined without changing the basic principles of the present invention. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the scope of patent protection of the present application shall be subject to the attached claims.

Claims

1. An artificial intelligence-based implant position prediction method, characterized in that: include: Acquire the first implantation position information of the crown area and multiple crown slice images; The first implantation position information and all the crown slice images are processed using an artificial intelligence algorithm to obtain target implantation position information of the implant in the root area corresponding to the crown area.

2. The artificial intelligence-based implant position prediction method according to claim 1, characterized in that: The step of using an artificial intelligence algorithm to process the first implantation position information and all the crown slice images to obtain the target implantation position information of the implant in the root area corresponding to the crown area includes: Inputting the first implant position information and all the crown slice images into the implant position prediction network of the artificial intelligence algorithm to obtain the second implant position information; A three-dimensional space straight line fitting algorithm of an artificial intelligence algorithm is used to map the second implantation position information to the tooth root area to obtain the target implantation position information.

3. The artificial intelligence-based implant position prediction method according to claim 2, characterized in that: The training steps of the implant position prediction network include: Acquire a training data set and a real implant position information set, wherein each training data in the training data set includes a dental crown training image and implant position training data corresponding to the dental crown training image, and each real implant position information in the real implant position information set has a one-to-one correspondence with the corresponding training data; Inputting target training data into the Transformer model to obtain predicted planting position information, wherein the target training data is any training data in the training data set; A loss function is calculated based on the predicted implant position information and the corresponding actual implant position information, and model parameters of the Transformer model are adjusted based on the loss function to form the implant position prediction network.

4. The artificial intelligence-based implant position prediction method according to claim 2, characterized in that: The step of mapping the second implantation position information to the tooth root area using a three-dimensional space straight line fitting algorithm using an artificial intelligence algorithm to obtain the target implantation position information comprises: constructing a first spatial transformation algorithm based on the second planting position information; Obtaining a first residual sum of squares and a second residual sum of squares based on the first spatial transformation algorithm; Calculate the first residual sum of squares and the second residual sum of squares based on the least squares method to obtain a first coefficient, a second coefficient, a third coefficient and a fourth coefficient of the spatial straight line; The first coefficient, the second coefficient, the third coefficient, the fourth coefficient and all root slice images of the root area are input into the first space transformation algorithm to calculate the target implant position information.

5. The artificial intelligence-based implant position prediction method according to claim 1, characterized in that: The step of obtaining the first implantation position information of the crown area comprises: Acquire third implantation position information of the implant in the tooth root area; The third implantation position information is mapped to the tooth crown region through a three-dimensional space straight line fitting algorithm to obtain the first implantation position information.

6. The artificial intelligence-based implant position prediction method according to claim 5, characterized in that: The step of mapping the third implantation position information to the tooth crown region through a three-dimensional space straight line fitting algorithm to obtain the first implantation position information comprises: constructing a second spatial transformation algorithm based on the third planting position information; Obtaining a third residual sum of squares and a fourth residual sum of squares based on the second spatial transformation algorithm; Calculate the third residual sum of squares and the fourth residual sum of squares based on the least squares method to obtain a fifth coefficient, a sixth coefficient, a seventh coefficient and an eighth coefficient of the spatial straight line; The fifth coefficient, the sixth coefficient, the seventh coefficient, the eighth coefficient and all the crown slice images are input into the second space transformation algorithm to calculate and obtain the first implant position information.

7. The artificial intelligence-based implant position prediction method according to claim 6, characterized in that: The calculation formula of the second space transformation algorithm is: in, represents the coordinate information of the third implant position information on the x-axis, that is, the coordinate information of the root slice image of the jth root area of ​​the pth patient on the x-axis; k1 represents the ninth coefficient of the space line; represents the coordinate information of the third implant position information on the z-axis, that is, the j-th tooth root slice image of the p-th patient; b1 represents the tenth coefficient of the space line; represents the coordinate information of the third implant position information on the y-axis, that is, the coordinate information of the p-th patient on the y-axis of the j-th root slice image; k2 represents the eleventh coefficient of the spatial straight line; b2 represents the twelfth coefficient of the spatial straight line.

8. An artificial intelligence-based implant position prediction device, characterized in that: include: A first implantation position information acquisition module, used to acquire first implantation position information of a crown region and a plurality of crown slice images; The target implantation position information acquisition module is used to process the first implantation position information and all the crown slice images using an artificial intelligence algorithm to obtain the target implantation position information of the implant in the root area corresponding to the crown area.

9. A terminal device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the steps of the artificial intelligence-based implant position prediction method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein the computer program enables a computer to execute the steps of the implant position prediction method based on artificial intelligence as described in any one of claims 1 to 7.

Images