Surgical planning method, device and program product for autogenous tooth transplantation

Abstract

The invention relates to the field of intelligent medical treatment, in particular to a surgical planning method and device for autogenous tooth transplantation and a program product. The method includes acquiring tooth images of a patient; the tooth image is segmented to obtain single tooth images, the single tooth images comprise acceptor teeth and N donor teeth, and N is a natural number larger than 1; performing three-dimensional reconstruction based on the image of the single tooth to obtain a three-dimensional single tooth; calculating the forms of the three-dimensional acceptor teeth and the three-dimensional donor teeth, and performing registration to obtain registered acceptor teeth; the registered acceptor teeth are subjected to angle and direction adjustment through virtual transplantation to obtain the planned angle and direction, the method is used for assisting autologous tooth transplantation, the operation difficulty is lowered, the operation time is shortened, and good clinical value is achieved.

Description

Technical Field

[0001] This application relates to the field of intelligent medicine, and specifically relates to a surgical planning method, device, program product and computer-readable storage medium for autologous tooth transplantation. Background Art

[0002] Autologous tooth transplantation (ATT) refers to the surgical process of transplanting a tooth from one position to another position in the same individual. Commonly, it is to transfer impacted, unerupted, malposed or ectopically erupted teeth into the alveolar sockets of other extraction sites or edentulous sites, or into the alveolar sockets prepared surgically. The relevant research results on the tissue healing theory after autologous tooth transplantation have promoted its further clinical application. As the best restorative method with biocompatibility, autologous tooth transplantation can restore tooth loss with natural teeth, maintain the bone mass of the alveolar bone, restore the normal periodontal tissue and dental proprioception in the recipient tooth area, achieving the goal of "turning waste into treasure". However, in the current traditional autologous tooth transplantation surgery, it is necessary to extract the donor tooth first and then perform implantation, there is a risk of repeated trial implantations, adjusting the angle and direction of the donor tooth, which will increase the surgical time and the ex vivo time of the donor tooth. Summary of the Invention

[0003] In view of the above problems, the present invention provides a surgical planning method for autologous tooth transplantation, specifically including: Obtain the dental image of the patient; Segment the dental image to obtain single-tooth images, including a recipient tooth and N donor teeth, where N is a natural number greater than 1; Perform three-dimensional reconstruction based on the single-tooth images to obtain three-dimensional single teeth; Calculate the morphology of the three-dimensional recipient tooth and the three-dimensional donor teeth and perform registration to obtain the registered recipient tooth; Adjust the angle and direction of the registered recipient tooth through virtual transplantation to obtain the planned angle and direction.

[0004] The registration is to perform rigid registration and angle adjustment on the morphology of the three-dimensional recipient tooth and the donor tooth through morphological calculation, and screen to obtain the registered recipient tooth.

[0005] Optionally, the process of the rigid registration and angle adjustment includes tooth center point positioning, tooth long axis positioning, and dental arch positioning. After sequentially determining the tooth center, tooth long axis, and dental arch, the three-dimensional recipient tooth and the three-dimensional donor teeth are registered.

[0006] The tooth center point positioning is to define a global coordinate system, calculate the translation matrix for moving the center point of the three-dimensional donor tooth to the center point of the three-dimensional recipient tooth in the global coordinate system, and obtain the tooth center point positioning result.

[0007] Optionally, the tooth long axis positioning is as follows: perform eigen decomposition on the matrix based on tooth center positioning to obtain eigenvectors, screen the eigenvectors to obtain the eigenvector corresponding to the maximum eigenvalue as the tooth long axis vector, including the tooth long axis vectors of the three-dimensional donor tooth and the three-dimensional recipient tooth; Adjust the direction of the tooth long axis vector, with the tooth long axis vector pointing from the tooth root to the tooth crown; Taking the tooth center point as the rotation center, calculate the rotation matrix for transforming the tooth long axis vector of the three-dimensional donor tooth to the tooth long axis vector of the three-dimensional recipient tooth to obtain the tooth long axis positioning result.

[0008] Optionally, the dental arch positioning is to fit the dental arch curve based on the tooth center point, including the dental arch curves of the three-dimensional donor tooth and the three-dimensional recipient tooth; Calculate the initial direction of the three-dimensional donor tooth through morphology, and calculate the initial direction of the three-dimensional recipient tooth based on the dental arch tangent direction; Taking the tooth long axis of the recipient tooth as the rotation axis, calculate the rotation matrix for transforming the initial direction of the three-dimensional donor tooth to the initial direction of the three-dimensional recipient tooth to obtain the dental arch positioning result.

[0009] Optionally, the angle adjustment calculates the registration data of the three-dimensional donor tooth through a minimum optimization function, and screens to obtain the registered three-dimensional donor tooth. The registration data is the tooth center positioning result, the tooth long axis positioning result, and the dental arch positioning result.

[0010] The angle and direction adjustment of the planned path includes the establishment of the occlusal plane, the establishment of the axial inclination, and the establishment of the torsion. The upper and lower positions of the recipient tooth are determined through the occlusal plane, the left and right positions are determined through the axial inclination and torque, and the connection of the teeth is determined through the torsion.

[0011] The establishment of the occlusal plane is determined by the centroid and tooth long axis of the three-dimensional donor tooth. First, calculate the centroid of the three-dimensional donor tooth to obtain the centroid coordinates, then calculate the tooth long axis of the three-dimensional donor tooth, and based on the centroid coordinates and tooth long axis, obtain the occlusal-gingival position of the donor tooth in three-dimensional space, and adjust the occlusal-gingival position to establish the occlusal plane.

[0012] The establishment of the axial inclination is to change the axial inclination by rotating L° along the buccolingual direction mesially or distally, compare the axial inclinations at different rotation angles, and screen to obtain the axial inclination. L is a natural number greater than 1.

[0013] Optionally, the axial inclination is changed by rotating 5° along the buccolingual direction mesially or distally.

[0014] Optionally, the establishment of the axial inclination also includes the establishment of the root movement angle. The root movement direction is precisely controlled by rotating S° along the mesiodistal direction buccally or lingually. S is a natural number greater than 1.

[0015] Optionally, for establishing the root movement angle, the root movement direction is precisely controlled by rotating 5° along the mesiodistal radial buccal or lingual side each time.

[0016] For establishing the torsion degree, a cross quadrant is first created. In each quadrant, the three-dimensional donor tooth is rotated 45° - 75° along the tooth long axis N times, where N is a natural number greater than 1, and the selected quadrants are obtained through screening. In the selected quadrants, the three-dimensional donor tooth is rotated 5° - 10° counterclockwise or clockwise to obtain the rotation angle, and by comparing the rotation angles, the torsion degree is obtained through screening.

[0017] The segmentation is performed through a segmentation model to obtain the image of a single tooth. The segmentation model includes one or more of the following: U-Net, V-Net, FCN, DeepLab v1, v2, v3, v3 +, Mask R-CNN.

[0018] The three-dimensional reconstruction of the recipient tooth is obtained by reconstructing through the tooth socket and crown space of the donor tooth.

[0019] Optionally, the three-dimensional reconstruction of the recipient tooth further includes recipient tooth optimization. When there are defects in the recipient tooth, during the reconstruction process of the recipient tooth, repairs are made based on the surrounding parts of the defects to obtain a complete three-dimensional recipient tooth.

[0020] The method further includes the selection of the donor tooth. Based on the tooth image, the position of the tooth socket of the recipient tooth is obtained, the depth and width of the tooth socket are calculated, and the donor tooth is obtained through screening based on the depth and width of the tooth socket of the recipient tooth.

[0021] Optionally, the screening of the donor tooth is performed by calculating the depth and width of other teeth in the tooth image, and a tooth that is 1 - 2 mm wider and 1 - 2 mm deeper than the tooth socket of the recipient tooth is selected as the donor tooth.

[0022] The purpose of the present invention is to provide a computer program product, which includes a computer program or instruction, and the computer program or instruction is executed by a processor to implement the above-mentioned surgical planning method for autologous tooth transplantation.

[0023] The purpose of the present invention is to provide a computer device, which includes a memory, a processor, and a computer program or instruction stored on the memory, and the computer program or instruction is executed by the processor to implement the above-mentioned surgical planning method for autologous tooth transplantation.

[0024] The purpose of the present invention is to provide a computer-readable storage medium, which stores a computer program or instruction, and the computer program or instruction is executed by a processor to implement the above-mentioned surgical planning method for autologous tooth transplantation.

[0025] Advantages of the present invention: 1. For the risk of long ex vivo time of the donor tooth, the present invention uses artificial intelligence-assisted autologous tooth transplantation for preoperative planning, planning the angle and direction of the donor tooth before surgery, and directly transplanting it based on the planned angle and direction when the donor tooth is extracted, greatly reducing the operation time and the ex vivo time of the donor tooth, and avoiding the problem of donor tooth failure.

[0026] 2. The present invention proposes the registration of the donor tooth and the recipient tooth, calculates the adaptability degree of the donor tooth and the recipient tooth through tooth center positioning, tooth long axis positioning, and dental arch positioning, which helps to screen the donor tooth and reduce the mismatch degree of the donor tooth.

[0027] 3. The present invention proposes a planned path during the donor tooth transplantation process, adjusts the direction and angle of the donor tooth by establishing the occlusal plane, axial inclination, and torsion degree, and then obtains the planned direction and angle, which helps the doctor to assist in implantation during clinical actual transplantation, reduces the operation difficulty, and improves the operation success rate. In addition, there are often tooth gaps and the transplanted tooth is in a low occlusal position relationship after traditional autologous tooth transplantation. After autologous tooth transplantation, orthodontics is carried out to restore the occlusal relationship. Based on this problem, when planning the virtual transplantation operation of autologous tooth transplantation, the up and down position relationship of the autologous tooth is planned, the occlusal plane is determined, the left and right position relationship is planned, the axial inclination is established, the connection of the teeth is planned, and the torsion degree is established, avoiding the orthodontic surgery in the later stage of autologous tooth transplantation, reducing the secondary treatment of patients, and saving the treatment cost.

[0028] 4. Regarding the selection of the donor tooth, when the donor tooth is extracted using the principle of proximity, it is easy to have the problem of insufficient adaptability. A detailed donor tooth screening path is proposed to screen out more suitable donor teeth, reduce the operation difficulty, and improve the postoperative survival rate of the donor tooth. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those skilled in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0030] Figure 1 It is a schematic flow chart of the surgical planning method for autologous tooth transplantation provided by the embodiment of the present invention; Figure 2 It is a schematic diagram of the surgical planning system for autologous tooth transplantation provided by the embodiment of the present invention; Figure 3 It is a schematic diagram of the surgical planning device for autologous tooth transplantation provided by the embodiment of the present invention; Figure 4 It is a schematic diagram of the segmentation process provided by the embodiment of the present invention; Figure 5Schematic diagrams of virtual transplantation of two donor teeth provided by embodiments of the present invention into a recipient tooth; Figure 6 Schematic diagram of registration of the recipient tooth and the donor tooth provided by embodiments of the present invention; Figure 7 Visualization process of virtual transplantation planning for Case 1 provided by embodiments of the present invention; Figure 8 Relevant indicators of two donor teeth for Case 1 provided by embodiments of the present invention; Figure 9 Postoperative imaging results for Case 1 provided by embodiments of the present invention; Figure 10 Donor teeth provided by the AI preoperative reference platform for Case 2 provided by embodiments of the present invention; Figure 11 Postoperative imaging results for Case 2 provided by embodiments of the present invention. Detailed implementation manners

[0031] In order to enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0032] In some processes described in the specification, claims and above-mentioned drawings of the present invention, a plurality of operations appear in a specific order. However, it should be clearly understood that these operations may not be executed in the order in which they appear herein or may be executed in parallel. The serial numbers of the operations, such as S101, S102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions such as "first" and "second" in this article are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, nor do they limit that "first" and "second" are of different types.

[0033] Figure 1 Schematic diagram of the surgical planning method for autologous tooth transplantation provided by embodiments of the present invention, specifically including: S101: Obtain dental images of the patient; In one embodiment, the dental images include CBCT images.

[0034] In a specific embodiment, the present invention collects the original CBCT images, and then through a graphics image preprocessing module, a tooth ROI, that is, the region of interest of the teeth, is obtained through a feature extraction network. We do this to increase the proportion of teeth in the overall data and lay a foundation for the subsequent segmentation network. Finally, a multi-class tooth segmentation network needs to be performed on the tooth ROI, and finally the segmentation results of single teeth will be obtained. The U-Net convolutional neural network is used to process the segmentation tasks of teeth and jaws, and the network structure and training strategy are optimized to improve the segmentation accuracy. As Figure 4 shown, after the tooth image passes through the image preprocessing module, the region of interest of the teeth is obtained through the feature extraction network, and then the region of interest of the teeth is input into the multi-task segmentation network to obtain the segmentation results of single tooth images.

[0035] S102: Segment the tooth image to obtain single tooth images, including the recipient tooth and N donor teeth, where N is a natural number greater than 1; In one embodiment, the segmentation is performed by a segmentation model to obtain the images of single teeth. The segmentation model includes one or more of the following: U-Net, V-Net, FCN, DeepLab v1, v2, v3, v3 +, Mask R-CNN.

[0036] In a specific embodiment, 100 cases of CBCT image data are respectively imported into the interactive image editing software, a MASK is newly created to cover the teeth in the region of interest, the target region is gradually separated layer by layer in the image segmentation, the training model database is trained, and the CBCT image segmentation model is trained to obtain a trained segmentation model.

[0037] In one embodiment, the method further includes the selection of donor teeth. Based on the tooth image, the alveolar socket position of the recipient tooth is obtained, the depth and width of the alveolar socket are calculated, and the donor teeth are screened through the depth and width of the alveolar socket of the recipient tooth.

[0038] In one embodiment, the screening of the donor teeth is performed by calculating the depth and width of other teeth in the tooth image, and selecting those that are 1-2 mm wider and 1-2 mm deeper than the alveolar socket of the recipient tooth as the donor teeth.

[0039] In another embodiment, the donor tooth is screened by one or several of the screening indicators such as root morphology, tooth integrity, impaction position, tooth position, and tooth function. Multiple rounds of screening are carried out based on the previous round (or independently screened based on different screening indicators, and the intersection of the donor teeth obtained by independent screening is taken to obtain the donor teeth). After obtaining the donor teeth, the width and depth are calculated, and the matching degree is calculated with the depth and width of the tooth socket of the recipient tooth. When the matching degree is met, the donor tooth is the candidate donor tooth. When the matching degree is not met, one screening indicator is reduced to obtain the donor teeth and the matching degree is calculated and compared. Repeat this step until the appropriate candidate donor teeth are obtained or the number of donor teeth is zero. Among them, when the depth of the donor tooth is 2-3 mm smaller than the tooth socket and the width is 1-2 mm smaller than the tooth socket, it is determined to be a match. In addition, the functions of the teeth include caries-free, caries, no apical region, apical region, no periodontal inflammation, and periodontal inflammation. The donor teeth are screened with caries-free prior to caries, apical region prior to no apical region, and no periodontal inflammation prior to periodontal inflammation; the tooth positions include ipsilateral, contralateral, same jaw, and opposite jaw. The donor teeth are screened with ipsilateral prior to contralateral and same jaw prior to opposite jaw; the impaction position is screened with vertical impaction prior to mesial impaction, distal impaction prior to buccal impaction, and lingual impaction prior to inverted impaction to obtain the donor teeth; the root morphology is with fused root prior to double root, and double root prior to triple root; the tooth integrity is with fully erupted prior to partially erupted, and partially erupted prior to completely impacted.

[0040] In a specific embodiment, the root morphologies of each tooth in the oral cavity are different, the sizes are different, and the number of roots is also different. The root is located in the alveolar socket, and the socket seen after extracting the root is the alveolar socket, that is, the position occupied by the original root. Therefore, after transplanting a tooth in the mouth into the alveolar socket of another tooth, the problem of alveolar socket incompatibility will inevitably occur. Unfortunately, currently in clinical practice, only the preoperative CBCT is used as a reference for alveolar socket preparation. When the shapes of the donor tooth and the recipient tooth are quite different, the predictability of alveolar socket preparation is extremely low and the surgical difficulty is high.

[0041] When preparing the alveolar socket during the operation, the alveolar socket should not be too wide or too deep. If it is too small, it is easy to cause extrusion of the periodontal membrane. If it is too large, the initial stability is not good. It is most appropriate to be 1 mm wider and 2 mm deeper than the donor tooth.

[0042] In a specific embodiment, compared with the digital 3D printed donor tooth model, the AI surgical reference platform saves the workflow of printing the donor tooth model, reduces surgical consumables, reduces surgical costs, and presents a more digital, visual, and diversified preoperative plan. When there are multiple donor teeth, the AI preoperative planning system can pre-screen the transplantation plans with higher failure rates and lower matching degrees, enabling the surgeon to explore the surgical plans for different approaches and achieve the optimal arrangement and combination during the operation, reaching the surgical consensus of "starting from the end".

[0043] When it comes to artificial intelligence, every time data annotation or data replication is added, errors are inevitably generated. For example, there are already errors in tooth data annotation, and there will also be errors in the 3D model printed according to the data after the error during the printing and production process. Then, using the model with two layers of errors to try the matching degree of the alveolar socket will increase the preparation risk of over-grinding or under-grinding. If the amount of grinding is too large or too small, when the real donor tooth is extracted and tried, the alveolar socket needs to be prepared again, which increases the damage to the periodontal ligament of the periodontal tissue and prolongs the operation time.

[0044] S103: Perform three-dimensional reconstruction based on the single-tooth image to obtain a three-dimensional single tooth; In one embodiment, the three-dimensional reconstruction of the recipient tooth is obtained by reconstructing through the alveolar socket and crown space of the donor tooth.

[0045] In one embodiment, the three-dimensional reconstruction of the recipient tooth further includes recipient tooth optimization. When the recipient tooth has defects, during the reconstruction of the recipient tooth, repairs are made based on the surrounding parts of the defects to obtain a complete three-dimensional recipient tooth.

[0046] S104: Calculate the morphology of the three-dimensional recipient tooth and the three-dimensional donor tooth and perform registration to obtain the registered recipient tooth; In one embodiment, the registration is to perform rigid registration and angle adjustment on the morphology of the three-dimensional recipient tooth and the donor tooth through morphological calculation, and the registered recipient tooth is screened out.

[0047] In one embodiment, the process of rigid registration and angle adjustment includes tooth center point positioning, tooth long axis positioning, and dental arch positioning. After sequentially determining the tooth center, tooth long axis, and dental arch, the three-dimensional recipient tooth and the three-dimensional donor tooth are registered.

[0048] In one embodiment, the tooth center point positioning is to define a global coordinate system, calculate the translation matrix for moving the center point of the three-dimensional donor tooth to the center point of the three-dimensional recipient tooth in the global coordinate system, and obtain the tooth center point positioning result.

[0049] Optionally, the tooth long axis positioning is: performing eigenvalue decomposition on the matrix based on the tooth center positioning to obtain eigenvectors, screening the eigenvectors to obtain the eigenvector corresponding to the largest eigenvalue as the tooth long axis vector, including the tooth long axis vector of the three-dimensional donor tooth and the tooth long axis vector of the three-dimensional recipient tooth; Adjust the direction of the tooth long axis vector, and the tooth long axis vector points from the tooth root to the tooth crown; Taking the tooth center point as the rotation center, calculate the rotation matrix for transforming the tooth long axis vector of the three-dimensional donor tooth to the tooth long axis vector of the three-dimensional recipient tooth, and obtain the tooth long axis positioning result.

[0050] Optionally, the dental arch positioning is to fit the dental arch curve according to the dental center points, including the dental arch curve of the three-dimensional donor tooth and the dental arch curve of the three-dimensional recipient tooth; Calculate the initial direction of the three-dimensional donor tooth through morphology, and calculate the initial direction of the three-dimensional recipient tooth in the dental arch tangent direction; Taking the tooth long axis of the recipient tooth as the rotation axis, calculate the rotation matrix from the initial direction of the three-dimensional donor tooth to the initial direction of the three-dimensional recipient tooth to obtain the dental arch positioning result.

[0051] Optionally, the angle adjustment calculates the registration data of the three-dimensional donor tooth through a minimum optimization function, and filters to obtain the registered three-dimensional donor tooth. The registration data is the tooth center positioning result, the tooth long axis positioning result, and the dental arch positioning result.

[0052] In a specific embodiment, a surgical planning design is proposed through rigid registration and angle optimization. The present invention reconstructs a three-dimensional tooth model through two-dimensional imaging, and realizes three-stage tasks of regional detection, target positioning, and instance segmentation of the three-dimensional tooth model based on the V-Net network, providing pre-data for surgical planning and scheme display. According to the existing segmentation results, the present invention uses the principal component analysis method to analyze the morphology of the donor tooth and the recipient tooth. First, calculate the center points of the recipient tooth and the alternative donor tooth. Define a global coordinate system, calculate the translation matrix for moving the center point of the donor tooth to the center point of the recipient tooth in the global coordinate system, and apply the transformation to the donor tooth to obtain the point positioning result. Calculate the covariance matrix after decentralizing the translation matrix X_(𝑚×𝑛), and perform eigen-decomposition. Finally, select the eigenvector corresponding to the largest eigenvalue as the tooth long axis vector. Determine the upper and lower teeth according to the FDI number, and update the direction of the tooth long axis vector to ensure that the tooth long axis direction always points from the tooth root to the tooth crown. Taking the tooth center point as the rotation center, calculate the rotation matrix for transforming the donor tooth long axis vector to the recipient tooth axis vector, and apply the transformation to the donor tooth to obtain the axis positioning result. Fit the upper / lower tooth arch curve according to the upper / lower tooth center points, and calculate the initial direction of the donor tooth according to morphology; calculate the initial direction of the recipient tooth in the dental arch tangent direction. Taking the tooth long axis as the rotation axis, calculate the rotation matrix from the initial direction of the donor tooth to the initial direction of the recipient tooth, and apply the transformation to the donor tooth to obtain the dental arch positioning result. On the premise of ensuring the feasibility of the scheme, in order to quantify the effectiveness and robustness of the recommendation algorithm, the present invention proposes an optimization function, and realizes an ATT intelligent surgical recommendation with a high similarity between the alternative donor tooth and the recipient tooth and a small surgical trauma by minimizing the optimization function. As Figure 5 shown, remove the damaged left mandibular second molar (tooth 37) for virtual simulation of a non-invasive tooth extraction socket. Subsequently, the left mandibular third molar (tooth 38) and the right mandibular third molar (tooth 48) are respectively placed as donor teeth at the planned position of the left mandibular second molar extraction socket, demonstrating the direct virtual superposition rehearsal of ATT.

[0053] In a specific embodiment, the donor tooth and the recipient tooth through rigid registration are as follows Figure 6 As shown, the green part is the donor tooth, and the brownish-yellow part is the recipient tooth. By adjusting the transparency of the two images, the three-dimensional structural differences between the two regions of interest are found.

[0054] S105: Adjust the angle and direction of the registered recipient tooth through virtual transplantation to obtain the planned angle and direction.

[0055] In one embodiment, the adjustment of the angle and direction of the planned path includes the establishment of the occlusal plane, the establishment of the axial inclination, and the establishment of the torsion. The upper and lower positions of the recipient tooth are determined by the occlusal plane, the left and right positions are determined by the axial inclination and torque, and the connection of the teeth is determined by the torsion.

[0056] In one embodiment, the establishment of the occlusal plane is determined by the centroid and the long axis of the tooth of the three-dimensional donor tooth. First, calculate the centroid of the three-dimensional donor tooth to obtain the centroid coordinates, then calculate the long axis of the tooth of the three-dimensional donor tooth, and based on the centroid coordinates and the long axis, obtain the occlusogingival position of the donor tooth in three-dimensional space, and adjust the occlusogingival position to establish the occlusal plane.

[0057] In one embodiment, the establishment of the axial inclination is to change the axial inclination by rotating L° along the buccolingual direction mesially or distally each time, compare the axial inclinations at different rotation angles, and screen to obtain the axial inclination. L is a natural number greater than 1.

[0058] Optionally, the axial inclination is changed by rotating 5° along the buccolingual direction mesially or distally each time; Optionally, the establishment of the axial inclination further includes the establishment of the root movement angle. The root movement direction is precisely controlled by rotating S° along the mesiodistal direction buccally or lingually each time. S is a natural number greater than 1.

[0059] Optionally, for the establishment of the root movement angle, the root movement direction is precisely controlled by rotating 5° along the mesiodistal direction buccally or lingually each time.

[0060] In one embodiment, for the establishment of the torsion, a cross quadrant is first created. In each quadrant, the three-dimensional donor tooth is rotated 45° - 75° along the long axis of the tooth N times. N is a natural number greater than 1, and the selected quadrant is screened.

[0061] In one embodiment, in the selected quadrant, the three-dimensional donor tooth is rotated 5° - 10° counterclockwise or clockwise to obtain the rotation angle, and the rotation angles are compared to screen to obtain the torsion.

[0062] In a specific embodiment, the present invention uses an AI pre-operative planning reference platform to assist in autologous tooth transplantation. The AI pre-operative planning includes a series of processes such as image segmentation, three-dimensional reconstruction, model registration, virtual transplantation, donor tooth screening, and pre-operative planning. In the functional architecture of the final plan visualization, it includes two parts: quantitative indicators and result visualization. The quantitative indicators provide clinicians with plan data analysis in the form of TXT files. The result visualization needs to convert the format through the MITK image processing software and present the autologous tooth virtual transplantation plan through 3-matics.

[0063] The surgical operations of the experimental group and the blank control group were both completed by a dentist. The difference is that the experimental group also required an assistant to convert the surgical plan into a three-dimensional stereoscopic image (STL), and perform the calculate part operation on all the masks of the automatically segmented CBCT in Mimics research 21.0, export 3D objects to 3-matics, copy the surgical plan in STL mode to 3-matics to synchronously visualize the transplantation effect, provide more intuitive and accurate surgical guidance for the surgeon, and record the main evaluation indicators during the operation - the ex vivo time of the donor tooth and the number of trial implantations.

[0064] In a specific embodiment, Case 1, as Figure 7 shown, the patient's tooth 37 needs to be extracted, and there are two donor teeth 38 / 48 in the mouth at the same time. The AI surgical planning reference platform (based on the segmentation, three-dimensional reconstruction, registration, and virtual transplantation planning methods of the present invention) gave the visualization results of the above transplantation plan. The reference platform simultaneously performed virtual transplantation on the two teeth. The results showed that the alveolar socket preparation area of tooth 37 was smaller, mainly concentrated in a strip-shaped preparation point on the lingual side. The difficulty was smaller. Therefore, the surgical plan with tooth 38 as the donor tooth was more preferred. Secondly, the AI surgical planning platform generated 72 surgical plans for each of the two types of transplanted teeth respectively, as Figure 8As shown, the optimal bone grinding volume for the 48-tooth is 317 voxels, and the optimal bone grinding volume for the corresponding tooth is 147 voxels. This set of data confirms the selection of the 38-tooth as the donor tooth. According to the preparation points given by the AI surgical planning reference platform, a side-cutting drill was used to prepare the lingual cord, and a round bur was used to prepare the buccal punctate preparation points, completing the preparation of the alveolar socket quickly and accurately. After extracting the 38-tooth, it was successfully implanted in one attempt. Since the initial stability of the transplanted tooth was good, a simple fixation method of suspension suture was selected. At 3 months after surgery, the mobility of the transplanted tooth was I°. At the 1-year follow-up after surgery, the tooth was stable, the mobility returned to normal, the periodontal health was good, the pulp vitality test showed vital pulp, and the current intensity causing the reaction was 43 (the current intensity causing the reaction in the control tooth was 39). The percussion sound was normal, there were no signs of attachment loss, no periodontal pocket, no signs of inflammation, no discomfort, and the masticatory function was normal. Imaging changes showed that the periapical low-density image of the transplanted tooth showed a gradually shrinking trend, and there were no signs of progressive root resorption. At 1 year after surgery, the periapical periodontal ligament width of the transplanted tooth was normal, and the widened range did not exceed 2 times the periodontal ligament space in the area not affected by the root. There were only fine and sparse images in the alveolar bone, and complete bone repair was achieved in the apical area, as Figure 9 shown.

[0065] In another specific embodiment, Case 2, as Figure 10As shown, the 26th tooth of the patient needs to be extracted, and there are three donor teeth, namely the 18th / 38th / 48th teeth, in the oral cavity at the same time. The AI surgical planning reference platform gives the visualization results of the above transplantation plan. The reference platform also virtually transplants two teeth. The best surgical plan given by the reference platform is to transplant the 38th tooth to the 26th tooth. The visualization results show that the alveolar socket preparation work mainly focuses on the palatal side and the mesial area of the alveolar socket, and the bone grinding volume is 6160 voxels. In terms of data, the bone grinding volume in this case is larger than that in the previous case. Therefore, the side cutting drill or ball drill of the high-speed handpiece can no longer meet the bone grinding volume. Therefore, an implant handpiece is used for the preparation of the alveolar socket in this case. After extracting the 26th tooth, the implant machine is equipped with the corresponding trephine bur, and the cavity is prepared in the mesial and palatal areas of the alveolar socket at a speed of 1000 r / min, while cooling with 0.9% sodium chloride solution at 4°C. After reaching the predetermined depth, the preparation of the alveolar socket is completed. The alveolar cavity is repeatedly rinsed with 0.9% sodium chloride solution to thoroughly remove the bone chips and granulation tissue in the cavity. Then, the donor tooth is extracted by the minimally invasive extraction method and implanted into the alveolar socket according to the virtual transplantation direction of the surgical planning reference platform. Then, it is sutured with silk thread suspension, and the transplanted tooth is fixed to the adjacent teeth with stainless steel wire, periodontal fiber fixation band and light-cured resin. Finally, the necessary occlusal adjustment is performed on the donor tooth to ensure no occlusal interference, and the autologous tooth transplantation surgery of Case 2 is completed. At 6 months after the operation, the mobility of the transplanted tooth is 0. When reviewed 1 year after the operation, the tooth is stable, the mobility has returned to normal, the periodontal health is good, the pulp vitality test shows vital pulp, and there is no sinus tract in the gingiva. The percussion sound is normal, there is no sign of attachment loss, no periodontal pocket, no sign of inflammation, no discomfort, and the chewing function has been restored. The prognosis of this case is very rapid among all cases. First of all, the original dentition occlusion relationship of this patient is normal, without smoking habit and periodontal disease, and the teeth are cleaned regularly every six months. This patient has very good compliance. The imaging changes in the review film half a year after the operation are as follows Figure 11 As shown, the low-density image around the apex of the transplanted tooth shows a gradually shrinking trend, without signs of progressive root resorption. There is still a sparse area in the mesial apical area, but there is a manifestation of bone healing around the apical sparse area.

[0066] In another specific embodiment, the preoperative CBCT of the 37th tooth of the patient shows a history of post and core crown treatment several years ago, and a large area of low density in the apical area. After CBCT analysis, the AI surgical planning reference platform directly excludes the plan of using the 38th tooth as the donor tooth. The 28th tooth is too large. Therefore, according to the surgical planning reference platform, the 28th tooth is selected as the donor tooth for the 35th tooth. At 3 months after the operation, the mobility of the transplanted tooth is I°. When reviewed 1 year after the operation, it returns to the normal physiological mobility. The percussion sound is normal, there is no sign of attachment loss, no periodontal pocket, no sign of inflammation, no discomfort, the occlusion is in a crossbite relationship, but there is occlusal contact between the upper and lower teeth, and the chewing function can be exercised. The electric vitality test is normal and the temperature test is normal.

[0067] In a specific embodiment, when the matching degree between the recipient tooth and the alveolar socket of the donor tooth is relatively high and the ex vivo time of the donor tooth is less than 1 minute, the transplanted tooth has a high survival rate and even the possibility of vital pulp survival. Therefore, in autologous tooth transplantation, the conventional root canal treatment should be postponed, and the pulp condition of the affected tooth should be closely observed regularly, and timely root canal treatment should be carried out when necessary.

[0068] The AI surgical planning reference platform can assist in the alveolar socket preparation for autologous tooth transplantation, effectively shorten the ex vivo time of the donor tooth, improve the preservation rate of vital pulp of the donor tooth and the survival rate of autologous tooth transplantation, facilitate new attachment for periodontal healing, and achieve excellent prognostic effects.

[0069] In a specific embodiment, by comparing the control group (traditional autologous tooth transplantation) and the experimental group's surgical procedures (autologous tooth transplantation assisted by the AI surgical planning reference platform), it can be found that the main difference between the experimental group and the control group lies in changing the sequence of donor tooth extraction in the surgery. The control group still maintains the traditional method of extracting the tooth first and then preparing, while the experimental group adopts the surgical method of preparing first and then extracting, minimizing the ex vivo time of the donor tooth to the greatest extent.

[0070] The disclosed embodiment of the present invention also provides a computer program product or system, including a computer program, which when executed by a processor implements the steps of the surgical planning method for autologous tooth transplantation described above.

[0071] Figure 2 The schematic diagram of the surgical planning system for autologous tooth transplantation provided by the embodiment of the present invention specifically includes: Acquisition module: Acquire the dental images of the patient; Segmentation module: Segment the dental images to obtain single-tooth images, including the recipient tooth and N donor teeth, where N is a natural number greater than 1; Reconstruction module: Perform three-dimensional reconstruction based on the single-tooth images to obtain three-dimensional single teeth; Registration module: Calculate the morphology of the three-dimensional recipient tooth and the three-dimensional donor tooth and perform registration to obtain the registered recipient tooth; Planning module: Adjust the angle and direction of the registered recipient tooth through virtual transplantation to obtain the planned angle and direction.

[0072] Figure 3 The schematic diagram of the surgical planning device for autologous tooth transplantation provided by the embodiment of the present invention specifically includes: A memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, any one of the above-described surgical planning methods for autologous tooth transplantation is implemented.

[0073] The disclosed embodiments of the present invention also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements any of the above-described surgical planning methods for autologous tooth transplantation.

[0074] The verification results of this verification embodiment show that assigning a fixed weight to the indication can improve the performance of this method compared to the default settings. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described systems, devices, and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein. In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in each embodiment of the present invention, the functional units can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units. Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium can include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk, or optical disc, etc.

[0075] Those of ordinary skill in the art can understand that all or part of the steps in implementing the methods of the above embodiments can be completed by instructing relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be read-only memory, magnetic disk, or optical disc, etc.

[0076] The above has introduced in detail a computer device provided by the present invention. For those of ordinary skill in the art, according to the idea of the embodiments of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A surgical planning method for autologous tooth transplantation, characterized in that: include: Obtain dental images of the patient; Segmenting the tooth image to obtain a single tooth image, including a recipient tooth and N donor teeth, where N is a natural number greater than 1; A three-dimensional single tooth is obtained by three-dimensional reconstruction based on a single tooth image; Calculating the morphology of the three-dimensional recipient tooth and the three-dimensional donor tooth and registering them to obtain a registered recipient tooth; The angle and direction of the registered recipient tooth are adjusted through virtual transplantation to obtain the planned angle and direction.

2. The method for planning the operation of autologous tooth transplantation according to claim 1, characterized in that: The registration is to perform rigid registration and angle adjustment on the morphology of the three-dimensional recipient tooth and the donor tooth through morphological calculation, and screen the registered recipient tooth; Optionally, the rigid alignment and angle adjustment process includes tooth center point positioning, tooth long axis positioning, and dental arch positioning, and the three-dimensional recipient tooth and the three-dimensional donor tooth are aligned after sequentially determining the tooth center, tooth long axis, and dental arch.

3. The method for planning the surgery of autologous tooth transplantation according to claim 2, characterized in that: The tooth center point positioning is to define a global coordinate system, calculate the translation matrix of the three-dimensional donor tooth center point to the three-dimensional recipient tooth center point in the global coordinate system, and obtain the tooth center point positioning result; Optionally, the tooth long axis positioning is: performing eigendecomposition based on the matrix of tooth center positioning to obtain eigenvectors, screening the eigenvectors to obtain the eigenvector corresponding to the maximum eigenvalue as the tooth long axis vector, including the tooth long axis vector of the three-dimensional donor tooth and the tooth long axis vector of the three-dimensional recipient tooth; Adjusting the direction of the tooth long axis vector so that the tooth long axis vector points from the tooth root to the tooth crown; Taking the tooth center point as the rotation center, calculate the rotation matrix of the three-dimensional donor tooth's long axis vector transformed to the three-dimensional recipient tooth's long axis vector, and obtain the tooth long axis positioning result; Optionally, the dental arch positioning is to fit a dental arch curve according to the center point of the tooth, including a dental arch curve of a three-dimensional donor tooth and a dental arch curve of a three-dimensional recipient tooth; The initial orientation of the three-dimensional donor tooth was calculated by morphology, and the initial orientation of the three-dimensional recipient tooth was calculated by the tangent direction of the dental arch; Taking the long axis of the recipient tooth as the rotation axis, the rotation matrix from the initial direction of the three-dimensional donor tooth to the initial direction of the three-dimensional recipient tooth is calculated to obtain the dental arch positioning result; Optionally, the angle adjustment is performed by calculating the registration data of the three-dimensional donor tooth through a minimum optimization function, and the registered three-dimensional donor tooth is screened and obtained, wherein the registration data includes the tooth center positioning result, the tooth long axis positioning result, and the dental arch positioning result.

4. The method for planning the surgery of autologous tooth transplantation according to claim 1, characterized in that: The planned angle and direction adjustment includes the establishment of the occlusal plane, the establishment of the axial inclination, and the establishment of the torsion. The upper and lower positions of the recipient teeth are determined by the occlusal plane, the left and right positions are determined by the axial inclination and torque, and the connection of the teeth is determined by the torsion.

5. The method for planning the surgery of autologous tooth transplantation according to claim 4, characterized in that: The establishment of the occlusal plane is determined by the centroid and long axis of the three-dimensional donor tooth. The centroid of the three-dimensional donor tooth is first calculated to obtain the centroid coordinates, and then the long axis of the three-dimensional donor tooth is calculated. The gingival position of the donor tooth in the three-dimensional space is obtained based on the centroid coordinates and the long axis of the tooth, and the gingival position is adjusted to establish the occlusal plane; The axis inclination is established by changing the axis inclination by rotating L° along the buccolingual radial direction mesial or distal, comparing the axis inclinations at different rotation angles, and screening to obtain the axis inclination, where L is a natural number greater than 1; Optionally, the axis inclination is changed by rotating the axis inclination by 5° along the buccolingual radial direction mesial or distal; Optionally, the establishment of the axial inclination also includes the establishment of the root movement angle, and the root movement direction is precisely controlled every S° rotation along the buccal or lingual side of the mesiodistal radial direction, where S is a natural number greater than 1; Optionally, the root movement angle is established to accurately control the root movement direction every 5° rotation along the mesiodistal radial buccal or lingual side; The twist degree is established by first creating a cross quadrant, and in each quadrant, the three-dimensional donor tooth is rotated 45°-75° along the long axis of the tooth N times, where N is a natural number greater than 1, and the selected quadrant is obtained by screening; The three-dimensional donor tooth is rotated 5°-10° counterclockwise or clockwise in the screened quadrant to obtain the rotation angle, and the torsion degree is obtained by comparing the rotation angle.

6. The method for planning an autologous tooth transplantation according to claim 1, characterized in that: The segmentation is performed by segmenting a segmentation model to obtain an image of a single tooth, and the segmentation model includes one or more of the following: U-Net, V-Net, FCN, DeepLab v1, v2, v3, v3 +, Mask R-CNN; Optionally, the three-dimensional reconstruction of the recipient tooth is obtained by reconstructing the socket and crown space of the donor tooth; Optionally, the three-dimensional reconstruction of the recipient tooth also includes recipient tooth optimization. When there is a defect in the recipient tooth, the surrounding area of ​​the defect is repaired during the reconstruction of the recipient tooth to obtain a complete three-dimensional recipient tooth.

7. The method for planning an autologous tooth transplantation according to claim 1, characterized in that: The method further includes selecting a donor tooth, obtaining the tooth socket position of the recipient tooth based on the tooth image, calculating the depth and width of the tooth socket, and selecting the donor tooth by the depth and width of the tooth socket of the recipient tooth; Optionally, the donor tooth is screened by calculating the depth and width of other teeth in the dental image, and selecting a donor tooth that is 1-2 mm wider and 1-2 mm deeper than the socket of the recipient tooth.

8. A computer program product comprising a computer program or instructions, characterized in that: The computer program or instructions are executed by a processor to implement the surgical planning method for autologous tooth transplantation as described in any one of claims 1-7.

9. A computer device comprising a memory, a processor and a computer program or instruction stored in the memory, characterized in that: The computer program or instructions are executed by a processor to implement the surgical planning method for autologous tooth transplantation as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program or instruction stored thereon, characterized in that: The computer program or instructions are executed by a processor to implement the surgical planning method for autologous tooth transplantation as described in any one of claims 1-7.

Images