Preoperative planning for introducing a dental implant

EP4463090A1Pending Publication Date: 2024-11-20ALBERT LUDWIGS UNIV FREIBURG
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
EP2022844660
Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2022-01-10
Filing Date
2022-12-29
Publication Date
2024-11-20

AI Technical Summary

Technical Problem

Current dental implant planning methods require radiation-intensive CBCT scans, leading to high costs and increased radiation exposure, and lack precise prediction of tooth root axes and anatomical covariances, resulting in inaccuracies in implant placement.

Method used

A computer-aided method using statistical parametric 3D shape models to generate representations of tooth axes and implantation axes based on digital 3D surface representations, eliminating the need for CBCT scans by inferring invisible anatomical structures from surface scans, and integrating landmarks for precise calculations.

Benefits of technology

This approach reduces radiation exposure, lowers costs, and enhances the accuracy of implant placement by allowing precise calculation of tooth roots and axes without additional imaging, improving the precision of dental implant planning.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 1.1
    Figure 1.1
Patent Text Reader

Abstract

The invention relates to a computer-assisted method, a system and a computer-program product for assisting with preoperative planning for introducing a dental implant in a jaw of a patient. On the basis of a provided digital 3D surface reproduction, e.g. a digital plaster model, of at least part of the available dental crowns and / or the oral mucosa of the patient and statistical parametric 3D shape models (SSM), a tooth axis representation, a tooth crown representation and / or an implantation axis representation is generated. This takes place on the basis of the digital 3D surface reproduction and the corresponding statistical parametric 3D shape model. In addition, a corresponding statistical parametric 3D shape model can also be generated by means of the method, system and computer-program product. In order to check the plausibility, the determined representations for the tooth axis, tooth crown and / or implantation axis can be reproduced in an additionally taken 2D X-ray image, e.g. an orthopantomogram.
Need to check novelty before this filing date? Find Prior Art

Description

[0001] PREOPERATIVE PLANNING OF A DENTAL IMPLANT

[0002] Technical area

[0003] The invention relates to a computer-assisted method, a system and a computer program product for supporting preoperative planning of the insertion of a dental implant into a patient's jaw.

[0004] State of the art

[0005] Implant-supported prostheses are currently the gold standard in the treatment of partially edentulous patients, and their use is steadily increasing. Supported by the progressive development of digital workflows, surgical implant placement—the insertion of an implant into the jawbone—is becoming increasingly improved and more cost-effective.

[0006] Currently, the surgical insertion of dental implants is planned on the basis of 3-dimensional surface models or digital surface representations of the jaws (digitized plaster models or intraoral scans) as shown in Fig. 1 and 3-dimensional cone beam computed tomography (CBCT) images as shown in Fig. 2.

[0007] The surface model and the CBCT image are then superimposed in virtual space, as shown in Fig. 3, and the dental crown(s) to be replaced are virtually integrated into the tooth gap by a doctor / dentist (see Fig. 4, for example).

[0008] In addition, X-ray overview images (e.g. orthopantomograms, OPGs) are taken, since these, unlike CBCT images, allow the assessment of the worthiness of preserving individual teeth (see e.g. Fig. 5).

[0009] By examining the overlaid dataset (Fig. 4), anatomical and prosthetic factors are considered to determine the position and orientation of the implant. The anatomy of the surrounding structures is assessed using the CBCT scan. Neighboring teeth and surrounding nerves must not run too close to the implant, and the bone supply must be sufficient for firm anchorage of the implant. A suitable position and axis of an implant 601 are finally determined as shown in Fig. 6, taking into account the previously planned prosthesis and the surrounding anatomical structures.

[0010] Finally, a drilling template can be produced using 3D printing, for example, to enable precise transfer of the planned implant position / axis during the operation. The current state-of-the-art workflow described is a complex process that requires trained personnel to operate the appropriate planning software. In addition, expensive software licenses are required to carry out the planning and generation of a drilling template. Both factors lead to high costs. Above all, the process is associated with a not insignificant radiation exposure in a radiation-sensitive anatomical region. For example, the head and neck area, including the sensory organs and parts of the central nervous system, are regularly exposed to comparatively high radiation doses during CBCT scans. Compared to conventional radiography, 3-dimensional imaging using CBCT applies approximately 23 times the radiation dose, i.e. around 530 pSv (cf. OPG image approx.23pSv).

[0011] The US2018085201 Al or a related scientific publication ("Model-Based Teeth Reconstruction", Wu et al., describe a

[0012] A method and system for reconstructing individual teeth or entire rows of teeth based on a statistical shape model created using digitized plaster casts or plaster models. The focus of this approach is on generating realistic animations. However, the underlying 3D tooth models were designed with the artistic goal of achieving the best possible aesthetics. Therefore, an exact calculation of anatomical covariances, such as the precise prediction of the tooth root course, is not possible on the basis of this work. However, information as realistic as possible about the tooth roots, the tooth axes, and their anatomical covariance with the optically detectable tooth crowns is crucial for implant planning if no three-dimensional cross-sectional imaging technique is available.

[0013] In the article "Can we estimate root axis using a 3-dimensional tooth model via lingual-surface intraoral scanning?" (Lim et al., Am J Orthod Dentofacial Orthop. 2020 Nov;158(5):e99-el09. doi: 10.1016 / j.ajodo.2020.07.032), the authors discuss the estimation of the root axis using 3D tooth models. However, in the approaches discussed, a CBCT scan is taken for each patient to create a 3D tooth model using segmentation and to overlay this with a repeat CBCT scan during the course of therapy. The previously discussed problem of associated radiation therefore cannot be avoided by this workflow either.

[0014] The Ortho Insight 3D software (Motion View LLC, Chattanooga, Tennessee, USA) attempts to predict the shape of tooth roots based on standard tooth models. However, studies investigating the accuracy of this approach reported large deviations of 9.2–22.5° and 7.95–15°, respectively, between the actual and estimated root axes on average (Magkavali-Trikka et al., “Estimation of root inclination of anterior teeth from virtual study models: accuracy of a commercial software,” Prog Orthod. 2019;20. doi:10.1186 / s40510-019-0298-5; Dastoori et al., “Anterior teeth root inclination prediction derived from digital models: A comparative study of plaster study casts and CBCT images,” J Clin Exp Dent. 2018;10(ll):el069–el074. doi:10.4317 / jced.55180).

[0015] WO 2021 / 046147 A1 proposes determining a 3D shape of a restorative dental object using a machine learning system and a 3D representation of a 3D scan of at least part of a patient's dentition. However, this excludes automatic surgical planning.

[0016] WO 2020 / 227661 A1 discusses generating a three-dimensional anatomical model from medical image data and fitting a statistical shape model to it. Based on the fitted statistical shape model, quantitative measurements are performed to classify a defect related to the patient's anatomy.

[0017] Task and solution of the invention

[0018] Against this background, the object of the invention is to improve implant planning while simultaneously reducing radiation exposure.

[0019] The invention solves this problem by means of a computer-aided method according to claim 1, a system according to claim 12 and a computer program product according to claim 22.

[0020] One aspect of the invention relates to a computer-assisted method for supporting preoperative planning for the insertion of a dental implant into a patient's jaw. In a first step, a digital 3D surface representation of at least a portion of the existing dental crowns and / or the oral mucosa of the patient is provided. Such a digital 3D surface representation can, for example, be a surface scan that was or is generated directly using an intraoral scanner or using a plaster model scanned in 3D by a laboratory scanner. In a second step, a statistical parametric 3D shape model is provided that is suitable for generating representations of the tooth axes as well as the dental crowns and / or a portion of the oral mucosa. Statistical shape models are used, for example, to describe anatomical shapes, here e.g.of the tooth axes, and modeled in particular the probability of the presence of certain shapes. In a third step, a representation of the received digital 3D surface representation is generated by defining a plurality of landmarks on at least one tooth crown and / or parts of the oral mucosa that are visible in the provided digital 3D surface representation. These can be, for example, anatomical landmarks such as the tooth cusps. Finally, in a fourth step, a representation of the tooth axes of one or more of the teeth intended for the implant-supported dentures is determined based on the generated landmark-based representation of the digital 3D surface representation and the statistical parametric 3D shape model.This approach has the advantage that, using the statistical parametric shape model, it is possible to infer shapes that are not visible in the digital 3D surface representation, such as tooth axes or tooth roots, purely from the information of the digital 3D surface representation, i.e., without additional, radiation-intensive imaging. Radiation-intensive CBCT imaging is no longer necessary, and anatomical structures can be precisely calculated using the statistical parametric shape model based solely on a surface scan of at least part of the existing tooth crowns and / or the oral mucosa.

[0021] A further aspect of the invention relates to a system for supporting preoperative planning of the insertion of a dental implant into a patient's jaw. Such a system comprises several units. First, a data provision unit configured to provide a digital 3D surface representation. Second, a model provision unit configured to provide a statistical parametric 3D shape model. Third, an image processing unit configured to generate a representation of the digital 3D surface representation provided by the data provision unit by defining a plurality of landmarks located on the 3D surface representation. Fourth, an implant planning unit configured to determine a representation of the tooth axes of one or more of the teeth intended for the implant-supported dental prosthesis.The implant planning unit does this based on the landmark-based representation of the digital 3D surface representation generated by the image processing unit and a statistical parametric 3D shape model provided by the model provision unit.

[0022] A further aspect relates to a computer program product for supporting preoperative planning of the insertion of a dental implant into a jaw of a patient, which comprises computer-readable instructions for carrying out the methods according to the invention.

[0023] Embodiments of the invention are described below with reference to the figures.

[0024] The figures show:

[0025] FIG. 1 shows an example of a digital 3D surface representation of a patient;

[0026] FIG. 2 shows an example of a CBCT imaging dataset (3D imaging dataset) of the

[0027] patients;

[0028] FIG. 3 shows an example of an overlay of the 3D surface representation and the 3D

[0029] patient's imaging dataset;

[0030] FIG. 4 shows an example of a virtually inserted dental implant in the patient; FIG. 5 shows an example of a 2D X-ray image (orthopantomogram) of the patient;

[0031] FIG. 6 shows an example of a representation of an implant and its axis in an additional

[0032] imaging;

[0033] FIG. 7 shows an embodiment of a method for supporting a preoperative

[0034] Process for planning the insertion of a dental implant into a patient's jaw by means of which a tooth axis representation of one or more of the teeth intended for the implant-supported denture is determined;

[0035] FIG. 8 shows an example of an SSM-based reconstruction of the tooth crowns and tooth axes;

[0036] FIG. 9 shows an embodiment of a method for supporting a preoperative

[0037] Process for planning the insertion of a dental implant into a patient's jaw by means of which a tooth axis representation of one or more of the teeth intended for the implant-supported denture is determined and this is displayed in a 2D X-ray imaging set for plausibility check;

[0038] FIG. 10 shows an example of a projection of an SSM-based reconstruction of the tooth axes and a representation of the implants in an orthopantomogram;

[0039] FIG. 11 shows an embodiment of a method for supporting a preoperative process for planning the insertion of a dental implant into a patient's jaw, in which a statistical parametric shape model is generated for determining tooth axes;

[0040] FIG. 12 shows an example of annotation of anatomical landmarks on the surfaces of the tooth crowns and along the tooth roots;

[0041] FIG. 13 shows an example of determining a tooth axis in a multi-rooted tooth and annotating corresponding landmarks;

[0042] FIG. 14 shows an embodiment of a method for supporting a preoperative process for planning the insertion of a dental implant into a patient's jaw, in which a statistical parametric shape model is generated for determining dental crowns;

[0043] FIG. 15 shows an embodiment of a method for supporting a preoperative process for planning the insertion of a dental implant into a patient's jaw, in which a statistical parametric shape model is generated for determining implantation axes; FIG. 16 shows an embodiment of a system for supporting a preoperative process for planning the insertion of a dental implant into a patient's jaw;

[0044] FIG. 17 shows an example of a virtually positioned model of a drilling template.

[0045] All figures use the same reference symbols for identical or similar elements. Explanations of one figure also apply mutatis mutandis to the other figures.

[0046] Statistical parametric shape models (SSMs) are used within the scope of the invention. SSMs are a well-validated method for shape analysis and reconstruction of data sets. They contain shape-relevant information about an object as well as its variability. Such a model estimates the average shape of an object and accordingly specifies a range within which the shape may vary. It is assumed that the shape of an object can be represented by a set of n points, where the points can be given in any number of dimensions, but usually in two or three dimensions. The so-called "shape" in this case is defined as the quality of the point set that is invariant under certain transformations. In 2D or 3D, this is usually invariance under similarity transformations, i.e., rotation, translation, and scaling.

[0047] An SSM thus makes it possible to approximate shapes. This allows even incomplete shapes to be approximated to this shape using a fitting procedure of a corresponding SSM, thus generating a suggestion for the most likely addition of the missing elements.

[0048] In one embodiment of the invention, the SSM used later is first generated using a large number of training data sets. Each of these training data sets, in turn, consists of a large number of points in 2-, 3-, or even higher-dimensional space that are representative of a specific shape. A shape can also consist of several different anatomical structures, e.g., tooth crowns and tooth roots, or even more abstract characteristics such as tooth axes. This set of points can be generated, for example, by manual, semi-automatic, or fully automatic annotation of anatomical landmarks in image data of the corresponding dimensionality. Another possibility is to use the points of a surface mesh, which is used to represent the shape, as the above-mentioned set of points. The latter can be understood in a broader sense as mathematical landmarks.In any case, the multitude of training data sets consisting of points forms a point cloud. From this, an SSM is then generated by modeling the distribution of the points across all training data sets. For example, if n. T forms exist and will each form of n L 3-dimensional points, n T Training data sets consisting of n L 3D points. Each of these training data sets can be represented as a vector in a 3n t - dimensional space. The multitude of training data sets then forms a point cloud consisting of n T Points in 3-n t -dimensional space. A model of the distribution of these points can then be used to determine the mean shape and the distribution of possible shape variations of the training data sets.

[0049] The image data used within the scope of the invention comprise 3D surface representations of the dental crowns and / or the oral mucosa (e.g., Fig. 1, 100). These can be generated, for example, using a laboratory scanner that creates digital 3D scans of a plaster model previously produced from a corresponding impression, or using an intraoral scanner that directly scans the oral cavity. Furthermore, image data comprise 3D imaging data, e.g., from a CT scanner, in particular a CBCT scanner (e.g., Fig. 2, 200), an MR scanner, an X-ray system, in particular an orthopantomograph (e.g., Fig. 5, 500), or another imaging modality. Finally, combinations of two or more of the aforementioned image data are also possible as image data.

[0050] Landmarks are defined here as points that can be consistently found in different image data. These can generally be anatomical or mathematical landmarks. Anatomical landmarks refer to points that are anatomically distinguishable from other points and can therefore be consistently found; for example, tooth cusp tips or root tips. Mathematical landmarks, in turn, are points that can be mathematically distinguished from others, such as extremal points or points with a strong local curvature, or the previously mentioned points of a surface mesh. Further details on landmarks and their determination can be found, for example, in Section 4.1 in Cootes and Taylor, "Statistical Models of Appearance for Computer Vision Imaging Science and Biomedical Engineering" (University of Manchester, 2004, published online at: https: / / www.face- hereinafter referred to as COOTES.

[0051] Using the SSM for reconstruction

[0052] An SSM generated as described above captures the shape variability present in the training data sets. The landmarks, as shape-representing points, encode the shape relationship between the digital 3D surface representation and the information from the 3D imaging data. For example, shape relationships between tooth crowns and / or oral mucosa and the underlying tooth roots or associated tooth axes can be modeled in this way. It is therefore possible to infer the most probable position and axis of the tooth roots or tooth axes from a digital 3D surface representation alone using an SSM generated from the data of a sufficiently large number of training subjects. Ideally, this makes it possible to dispense with the information from an additional, possibly radiation-intensive, 3D imaging data set - even if one or more teeth are missing from the digital 3D surface scans. Therefore, based solely on one such asBased on the plaster model or surface model 100 shown in Fig. 1 of a patient who is missing one or more teeth, suggestions can be made for suitable implants and their implantation axes and / or suitable dental crowns (dentures) and, if necessary, even other non-visible anatomical structures.

[0053] Figure 7 shows a method according to a preferred embodiment of the invention.

[0054] In step 701, digital 3D surface representations of at least a portion of the existing dental crowns and / or oral mucosa of a patient are provided. Fig. 1 shows an example 100 of such a 3D surface representation. The 3D surface representations can be 3D scans of a plaster model using a digital scanner or image data from an intraoral scanner. They can therefore be digital representations of the surfaces of the dental crowns and / or oral mucosa that correspond to the plaster models known in the dental field.

[0055] In step 702, a statistical parametric 3D shape model is provided, which can be used to approximate the tooth axes and optionally the tooth crowns and / or part of the oral mucosa. Representations of these structures, e.g., using landmarks or surface meshes, can be generated using the SSM. The SSM can already exist and be retrieved from a corresponding database, or it can initially be generated using training data sets. The generation of a corresponding SSM will be discussed below.

[0056] In step 703, a representation is generated from the received digital 3D surface representation. For example, a plurality of landmarks located on the received digital 3D surface representation are defined for this purpose. In one embodiment of the invention, to generate such a point-based representation of the digital 3D surface representation, all or parts of the existing tooth crowns are annotated with landmarks specified by the respective SSM. For example, if the corresponding teeth are also present, the same landmarks can be annotated that were also annotated during the creation of the SSM to generate the representations of the overlaid data sets. For example, landmarks can be annotated on the tooth cusps, incisal edges, and / or central fissures using appropriate software. Additionally or alternatively, landmarks on the oral mucosa can be annotated.The representation(s) generated in this step can then be saved and / or forwarded in a format suitable for further processing. In step 704, based on the generated representation of the digital 3D surface representation and the SSM, an approximation of the digital 3D surface representation is created, i.e. a model based on the SSM that represents the digital 3D surface representation as closely as possible. This can be done, for example, by fitting the SSM to the digital 3D surface representation of the patient. The result is a representation of the approximation, for example again in the form of anatomical or mathematical landmarks. This representation then contains, in addition to the structures already recognizable from the digital 3D surface representation, structures that are not visible in the digital 3D surface representation but are contained in the SSM.Through approximation, one can also obtain representations of tooth roots that are not present in the patient dataset. This approximation of originally missing teeth or their tooth axes can then be used as suggestions for sensible implantation axes. For example, a representation of the tooth axes of one or more of the teeth intended for implant-supported dentures can be determined using the SSM and the digital 3D surface representation.

[0057] By an analogous procedure, alternative or additional suggestions for the design of the prospectively inserted dental prosthesis can be generated. In one embodiment of the invention, a second statistical parametric 3D shape model suitable for generating representations of dental crowns is provided in step 702. Based on a representation of the digital 3D surface representation and the second statistical parametric 3D shape model, a representation of the dental crowns and / or a portion of the oral mucosa of one or more of the teeth intended for the implant-supported dental prosthesis is also determined in step 704. The representations of the digital 3D surface representations can be generated in two different ways. If the 3D surface representations already exist as surface meshes, the points of the surface mesh are used as landmarks or points of the representation.The surface mesh thus corresponds to the representation. Another approach is to annotate landmarks in the digital 3D surface representation and use them as representations. For example, anatomical landmarks such as tooth cusps could be annotated here. Using a pure 3D surface representation, the position, shape, and size of missing teeth can also be calculated based on the SSM. This would replace the previously manual placement and editing of dental crowns in virtual space.

[0058] In a further embodiment of the invention, a third statistical parametric 3D shape model is provided in step 702, which is suitable for generating representations of implantation axes. The generation of such an SSM will also be discussed below. In step 703, representations of the digital 3D surface representations are then generated, analogous to the procedure for reconstructing the dental crowns. Based on the third statistical parametric 3D shape model and the representation of the digital 3D surface representation generated in step 703, a representation of the implantation axes of one or more of the teeth intended for the implant-supported dental prosthesis is then determined in step 704. Fig. 8 shows an example of this. If the 3D surface representations are already available as surface meshes, generating a representation is no longer necessary, and step 703 can be omitted.Generating implantation axes suggestions based on such empirical values ​​is particularly advantageous because tooth axes can deviate from the optimal implantation axes. For example, previously existing bone substance may be missing (atrophy), so that due to the lack of bone, the original tooth axes provide only limited guidance on the implantation axes to be used. By implementing existing planning data sets from implant insertions in an additional SSM (consisting of CBCT, 3D surface representation, and a defined implantation axis), not only the dental prosthesis but also the desired implantation axis(es) can be calculated for each situation.

[0059] The first, second, and third SSMs discussed here can, in principle, also be suitable for generating multiple representations of the aforementioned representations. For example, in some embodiments, the third SSM can be suitable for generating a representation of both the tooth axes and the implantation axes, allowing proposals for both types of axes to be generated using a single combined SSM. Likewise, in some embodiments, an SSM can be provided for generating representations of the tooth crowns and axes, and possibly even the implantation axes, and representations for tooth axes, crowns, and implantation axes can be generated based on this SSM and the provided 3D surface representation.

[0060] In any case, whether by using individual separate SSMs for tooth axes, tooth crowns, and implantation axes or by using individual combined SSMs, representations for tooth axes, tooth crowns, and implantation axes can be represented in a single combined representation. Fig. 8 shows such a representation 800 in which both a complete representation (e.g., as a surface mesh) of the proposed tooth axes 801 in the form of cylinders indicating direction and position, as well as a representation of the proposed tooth crowns 802, are visible.

[0061] In a further embodiment, in addition to or as an alternative to the previously described embodiments, the SSM used can model not only tooth crowns, tooth roots, and / or tooth axes, but also the bone structures near the teeth and the courses of nerves near the teeth (e.g., the mental nerve or inferior alveolar nerve). This way, predictions for existing bone structures and the course of nerves could be made based solely on digital surface representations, which is of key importance when planning and inserting an implant, e.g., to ensure secure anchoring of the implant and to avoid damage to the surrounding nerves. The described structures must therefore be taken into account when determining an implantation axis to guarantee long-term success.In such an embodiment of the invention, a statistical parametric 3D shape model is provided in step 702, which is also suitable for generating representations of bone structures near the teeth and / or the course of the nerves near the teeth. In step 704, based on this statistical parametric 3D shape model and the generated representation of the digital 3D surface representation, a representation of the bone structures near the teeth and / or the course of the nerves near the teeth is then additionally determined.

[0062] In a further embodiment, in step 703, in addition to or alternatively to the annotation of anatomical landmarks on the dental crowns, landmarks on the oral mucosa of a patient can also be annotated. This may be necessary, for example, because all or a large portion of the teeth are missing. Since the bone in the jaw region lies directly beneath the mucosa, there is a correlation between the optically detectable intraoral situation and the bony situation of the jaws. The shape of the mucosa-covered jaw sections therefore usually allows conclusions to be drawn about the bone supply and the course of important anatomical structures. Since each tooth has characteristic crown and root features, the position and course of tooth roots can also be deduced based on a surface scan.Based on an SSM of the upper and lower jaw after implementing a large amount of training data, statements can also be made about the course and shape of the maxillary sinus floor and the inferior alveolar nerve (mandibular nerve). If the SSM to be used describes possible shapes of the oral mucosa as well as the tooth axes and / or crowns, and possibly even the bone structures near the teeth and / or the course of the nerves near the teeth, suggestions for implants and superstructures / dentures can be generated solely from surface models of the oral mucosa, using a procedure analogous to the previous embodiments. For example, this method could support the creation and insertion of implant-supported superstructures for completely edentulous patients.In one embodiment of the invention, such an SSM is provided in step 702, and in step 704, based on the representation of the digital 3D surface representation thus generated and the statistical parametric 3D shape model, a representation of the tooth axes of one or more of the teeth intended for the implant-supported dental prosthesis is determined. Additionally, in step 704, based on the representation of the digital 3D surface representation thus generated and the statistical parametric 3D shape model, representations of the tooth crowns, tooth axes, and / or implantation axes of one or more of the teeth intended for the implant-supported dental prosthesis, as well as optionally the bone structures near the teeth and / or the course of the nerves near the teeth, can optionally be determined.

[0063] In some embodiments, an additional, imaging-based plausibility check of the generated suggestions can be provided. For example, the suggested dental crowns, dental axes and / or implantation axes as well as the estimated bone structures and / or nerve courses can be represented in further imaging data, e.g., by projection. Figure 9 shows such an embodiment. There, in step 901, further imaging data of the bony situation of parts of the patient's mouth, jaw and face that are relevant for the insertion of the dental implant are provided, and the determined representation of the dental crowns, dental axes and / or implantation axes as well as optionally the bone structures near the teeth and / or the course of the nerves near the teeth are represented in this further imaging data for plausibility check. For example, based on further imaging data, e.g.,make the actually existing bone structures visible, it is checked whether the implant axes lead into the bone and whether there is sufficient substance there for fixation or whether they run within soft tissue that is unsuitable for fixation. In a particularly preferred embodiment, the additional imaging data is 2D X-ray imaging data, in particular OPG imaging data. The aim is that the automatically generated implantation proposal, which is calculated by the SSM, is transferred to the OPG for the purpose of plausibility checks and for the purpose of adjustment. Only in the OPG is the bony situation and the course of neighboring structures (e.g. tooth roots, nerve canal) visible. In a preferred embodiment, a single-tooth fusion of the OPGs with the SSMs is carried out for this purpose. The landmarks in the SSM serve as a reference for the automatically calculated regions in the OPG.A projection is achieved using a 2D-3D registration approach based on the contours of the tooth crown in the OPG with the surface geometry of the SSM. This projection allows the axes from the SSM to be transferred to the OPG representation. If the user notices, when reviewing the overlaid data, that a change to the implantation proposal needs to be made, they can shift or rotate the implantation axis, for example to maintain minimum distances to neighboring structures. In a particularly preferred embodiment, the OPG, which exhibits distortion effects due to the image acquisition, is scaled using the known dimensions in the surface model. This scaling of the OPG enables the measurement of metric distances in the OPG. By measuring the dimensions in the region of the implant, the practitioner can determine the desired implant length and diameter after adjusting the implantation axis.In a further preferred embodiment, after the steps described above have been completed, all changes made, as well as the selected implant, are transferred back to the 3D model. For this purpose, the two-dimensional changes made are recalculated into the three-dimensional data set. Since corrections can only be made in the plane of the x-ray image in the OPG, the three-dimensional representation in the surface model offers a new opportunity to view all three spatial planes. In particular, the oro-lingual axis is not visible in the OPG due to the projection method. By subsequently viewing the generated implantation proposal in three dimensions, it can be determined whether the selected implant has an oral or vestibular perforation, for example, or whether a sufficient distance to the mucosa and the underlying bone has been maintained.An example of a plausibility check based on an OPG image is shown in Fig. 10, in which the tooth axes 1001 and also implants 1002 are shown in a stylized manner in OPG imaging data 1000.

[0064] Generation of the SSM

[0065] In some embodiments of the invention, the SSM used later is generated from training data sets. Each of these training data sets can consist of a single data set or a fusion of different data sets. In one embodiment, the training data set consists of a digital 3D surface representation fused with 3D CBCT image data. For this purpose, numerous existing CBCT images were overlaid with the corresponding 3D surface representations. This creates a link between the optically detectable intraoral scan and the three-dimensional volume tomography. Based on the fused data sets as training data, the correlations between the surface and the underlying structures can now be mapped in an SSM.In a further embodiment, each training data set consists of a fusion of 3D surface representations of 3D CBCT image data and a suitable representation of at least one implantation axis used for the respective patient. In a further embodiment, each training data set consists only of a 3D surface representation. In these embodiments, shape models can be created for calculating the tooth crowns, the tooth root course, the nerve and bone course, and also implantation axes.

[0066] Fig. 11 shows the steps of a first such embodiment of the invention for generating a first SSM.

[0067] In step 1101, several digital 3D surface representations of at least a portion of the dental crowns and / or at least a portion of the oral mucosa are provided, each originating from different training subjects. The digital 3D surface representations 100, shown, for example, in Fig. 1, correspond to those already described and can be obtained or generated in the same way. In a preferred embodiment, the training subjects are orthognathic, i.e., they have a full set of teeth and a standard tooth arrangement.

[0068] In step 1102, 3D imaging data sets are also provided from the same training subjects. The specific imaging modality is arbitrary, as long as the tooth axes can be determined from the resulting 3D imaging data sets and image registration with the digital 3D surface representation of the corresponding training subject is possible. For example, if both the course of the tooth roots and the tooth crowns are recognizable in the 3D imaging data, these are suitable for the method. Based on the course of the root(s), the course of the tooth axis can in principle be determined (more on this below). Furthermore, registration of both data sets can be performed using points that can be determined in both data sets and correspond to one another, e.g., on the tooth crowns. In a preferred embodiment, the 3D imaging data originate from a CBCT. An example of 3-dimensionally segmented CBCT imaging data 200 is shown in Fig. 2.

[0069] In step 1103, a plurality of training data sets is generated by aligning the digital 3D surface representation and the 3D imaging data of each of the training subjects using image registration so that structures detectable in both image data overlap as closely as possible. An example of such an overlay 300 is shown in Fig. 3. The 3D surface representation can serve as the reference image and the 3D imaging data as the object image, or vice versa. The object image is then optimally adapted to the reference image using a compensating transformation. The software solutions and image registration algorithms commonly used in medical image processing can be used here. The result of the image registration is then a combined or overlaid training data set for each training subject. For example, this then contains detailed information about the tooth crown and the tooth root.

[0070] In a preferred embodiment of the invention, prior to image registration in a step 1112, corresponding registration landmarks are defined on the digital 3D surface representation and the 3D imaging data. In a particularly preferred embodiment, these registration landmarks are annotated on the surfaces of the tooth crowns. During the registration step, an attempt is then made to bring the corresponding landmarks into the best possible agreement with one another. For registration based on registration landmarks, an iterative closest point (ICP) method can be used, for example, which iteratively reduces the distance between the landmarks and thus the tooth surfaces, resulting in an overlay with a minimal distance. In step 1104, a representation is now generated for each of the generated training data sets.The representation must be suitable for sufficiently reproducing the shapes to be observed so that a statistical parametric shape model can be generated based on it. Typically, the respective representation is carried out using a specific number of shape-defining points, in particular the landmarks already mentioned. In one embodiment of the invention, for example, as shown in Fig. 12, training landmarks 1201 and 1202 are placed at specific locations on the tooth crowns and / or the oral mucosa as well as along the tooth axes. For example, reliably recognizable positions such as tooth cusps, incisal edges, and central fissures can be used here. The tooth axes can be determined, for example, using the component of the superimposed training data sets that consists of the 3D imaging data. The courses of the tooth roots can usually be recognized from this data. Landmarks can be, for example,the root canals can be used. In the case of a tooth with a single root, the tooth axis can be determined using the root canal. When placing landmarks, teeth with multiple roots are treated as if they had a single large root that runs along the center of the multiple real roots. The center can be determined, for example, by determining the center point of the roots in a horizontal section through multiple roots of the same tooth. This is repeated for multiple horizontal sections to produce a regression line of the center points determined in this way. This procedure is illustrated in Fig. 13, where the landmarks 1301 - 1305 are determined using cross-sectional images as described above.

[0071] By annotating such training landmarks, a multitude of representations are generated, with each representation representing the tooth crowns and / or the oral mucosa as well as the tooth axes of the respective training subject in whole or in part.

[0072] Finally, in step 1105, an SSM is generated from the training data sets. In a preferred embodiment, the generation of the SSM is based on the previously set training landmarks.

[0073] Fig. 14 shows the steps of another embodiment of the invention for generating a second SSM.

[0074] The steps of this embodiment may be additional to or separate from the steps discussed in connection with Fig. 11.

[0075] Step 1401 corresponds to step 1101 of Fig. 11.

[0076] In step 1403, the provided 3D surface representations are provided as training data sets for the second SSM. The 3D surface representations thus serve directly as training data sets. In step 1404, a plurality of point-based representations of the 3D training data sets are generated from them. This can be done in two ways.

[0077] First, by providing an existing point-based representation for each provided 3D training dataset. As discussed above, an existing point-based representation can be in the form of the surface mesh or its points. If the 3D surface representations are already available as surface meshes, e.g., as standard tessellation language (STL) files, these can be used directly as representations of training datasets.

[0078] Second, by generating a landmark-based representation for each provided 3D training dataset by defining a plurality of training landmarks on the dental crowns of the respective training subject. This can be done, for example, analogously to the method discussed in connection with Fig. 11.

[0079] In step 1405, the second statistical parametric 3D shape model is then generated based on the plurality of generated representations of the 3D training data sets. Using an SSM generated in this way, surface meshes of missing tooth crowns, for example, can be modeled.

[0080] In some embodiments, the SSM is supplemented with possible implantation axes in addition to the tooth crowns and tooth axes. This is advantageous because the tooth axes do not always coincide with the desired implantation axes, i.e., the axis along which the implant is inserted into the jaw. Based on such an SSM, predictions or recommendations for optimal implantation axes can be made.

[0081] Fig. 15 shows the steps of another embodiment of the invention for generating a third SSM. The steps of this embodiment can be performed in addition to or separately from the steps discussed in connection with Figs. 11 and 14.

[0082] In step 1501, a plurality of digital superimposed 3D data sets originating from the various training subjects are provided. Each of the digital superimposed 3D data sets comprises an overlay of a digital 3D surface representation 100 and a 3D imaging data set 200 of at least a portion of the existing dental crowns and / or oral mucosa of the respective training subject. Additionally, a digital superimposed 3D data set comprises at least one implantation axis used in a previous insertion of a dental implant in the respective training subject. Furthermore, in this embodiment (implant axis SSM), it would be possible to implement the length and diameter of the selected implant.For example, each 3D dataset is an overlay of the respective 3D surface representation and the 3D imaging dataset, into which the practitioner has positioned a 3D model of the desired implant, taking into account all patient-specific factors and at their own discretion. The resulting datasets can, for example, be in the form of surface meshes in which the practitioner has annotated landmarks for the implantation axes used. However, datasets consisting purely of anatomical landmarks and datasets consisting purely of surface meshes are also possible.

[0083] In step 1503, the provided plurality of digital overlaid 3D datasets are provided as a plurality of 3D training datasets. The digital overlaid 3D datasets thus serve directly as training datasets.

[0084] In step 1504, a plurality of landmark-based representations of the 3D training data sets are generated. This can be done in two ways.

[0085] First, by providing an existing point-based representation for each provided 3D training data set. An existing point-based representation can, as already discussed in connection with step 1404 of Fig. 14, be in the form of the surface mesh. Thus, if the digitally superimposed 3D data sets are already available as surface meshes, as mixtures of a surface mesh and a set of landmarks representing the implantation axes, e.g., landmarks at the occlusal and apical ends of the implant, or as sets of landmarks representing the entire digitally superimposed 3D data sets, these can be used directly as representations of training data sets.

[0086] Second, by generating a landmark-based representation for each provided 3D training data set by defining a plurality of training landmarks on tooth axes and the at least one implantation axis, as well as on tooth crowns and / or parts of the oral mucosa of the respective training subject. This can be done, for example, analogously to the manner discussed in connection with Fig. 11.

[0087] In step 1505, the third statistical 3D shape model is then generated based on the plurality of landmark-based representations of the third 3D training data sets.

[0088] In principle, the digital superimposed 3D data sets used to generate the SSM described here can also be generated in an additional step analogous to step 1103 from provided 3D surface representations, 3D imaging data and additionally provided position, direction and length data of previously used implantation axes by appropriate superposition. In practice, however, the data will usually already be present in a superimposed form following a previous insertion of a dental implant. The practitioner has, for example, inserted landmarks for the implantation axes into surface networks that represent the superposition of 3D surface representations and 3D imaging data. Such already existing point-based representations for the provided third 3D training data set can therefore contain annotated landmarks that represent the at least one implantation axis.

[0089] In addition to the steps discussed in connection with Figs. 11, 12 and 13, preferred embodiments contain the optional step 1114 or 1414 or 1514. In this step, all training data sets are aligned in a uniform coordinate system with regard to their translation, rotation and optionally also their scaling in space. For example, the training data sets can be aligned to one another based on their landmarks in a common coordinate system such that corresponding landmarks in different training data sets are as close to one another as possible. In particular, the training data sets can be aligned to one another using known optimization methods. In this case, linear transformations are sought that minimize the distance between corresponding landmarks of the respective training data set and an average training data set.This average training data set can be a specific reference training data set or the mean of the already aligned training data sets. For example, an ICP algorithm can be used here to eliminate irrelevant information about the shape, such as the position, size, and rotation of this training data, and to bring all training data sets into a coordinate system. As already mentioned, the scaling of the data sets can optionally be adjusted, e.g., to a standardized size. In a particularly preferred embodiment of the invention, however, it is assumed that the shape of a large jaw does not correspond to the enlargement of a smaller one, and vice versa, so that in this embodiment the scaling of the individual data sets is not changed.

[0090] To generate the respective SSMs discussed above, the distributions of the point cloud representing the multitude of representations of the training data sets are modeled, as explained at the beginning. In particular, their expected values ​​and variances are determined. In a particularly preferred embodiment, a principal component analysis (PCA) is applied to the training data sets. This calculates the principal axes of the point cloud and yields the eigenvectors and corresponding eigenvalues ​​of the covariance of the data. Using the eigenvectors corresponding to the largest eigenvalues, the training data sets can then be approximated and new shapes generated. The PCA thus provides a linear model of the shape variability of the training data and averages the shapes of all training data. Details on generating an SSM, particularly using PCA, are described, for example, in COOTES, Section 4.3.In a further embodiment, the training data also includes imaging data from which the near-tooth bone structures and / or courses of near-tooth nerves can be determined. These can be determined, for example, from the CBCT data received in step 1102 or step 1501 or from additionally received x-ray images. Their existing or to-be-generated representations are also incorporated into the SSM in a manner analogous to the procedure already discussed. For example, said structures and courses are also annotated with training landmarks in step 1104 or step 1504, so that the generation of the SSM is also based on these shapes.

[0091] Fig. 16 shows an example of an embodiment of a system 1600 according to the invention. Such a system comprises a data provision unit 1601 which is configured to provide a digital 3D surface representation. This can be, for example, a database, such as a PACS or a system for generating image data. The latter can in particular be an intraoral scanner or a laboratory scanner, i.e. a 3D scanner for scanning 3D objects and in particular plaster models. Furthermore, it can also be one or more imaging systems such as a CT, in particular a cone beam CT (CBCT), an MRI or an X-ray system, in particular an orthopantomograph. The data provision unit can therefore comprise individual or a plurality of such systems and databases.

[0092] Furthermore, the system 1600 includes a model provisioning unit 1602 for providing an SSM. This may be a pure database, but the model provisioning unit 1602 may also be configured to generate an SSM.

[0093] In addition, the system 1600 comprises an image processing unit 1603. This is configured to generate a representation of the digital 3D surface representation provided by the data provision unit 1601. The image processing unit 1603 can enable manual, semi-automatic, or fully automatic generation of the representation. In particular, this can be a corresponding environment for manual, semi-automatic, or fully automatic annotation of image data, which is also configured to forward or export the generated representations in a suitable data format. In a preferred embodiment, this is done by annotating a plurality of landmarks on the 3D surface representation. For example, these can be the anatomical landmarks discussed above. In a further preferred embodiment, as already discussed above, the points of a surface network can be used as landmarks orPoints of a point-based representation are used.

[0094] Finally, the system 1600 includes an implant planning unit 1604. This is configured to determine a representation of the tooth axes of one or more of the teeth intended for the implant-supported dental prosthesis based on the representation of the digital 3D surface representation generated by the image processing unit 1603 and a statistical parametric 3D shape model provided by the model provision unit 1602. The implant planning unit 1604 can be configured to determine the representation in the manner already explained above, in particular by adapting / fitting the SSM provided by the model provision unit 1602 to the representation of the digital 3D surface representation provided by the image processing unit 1603.

[0095] In a further embodiment, the image processing unit 1603 can also be configured to generate a point-based representation of the digital 3D surface representation provided by the data provision unit by providing an already existing point-based representation of the provided digital 3D surface representation (100). The implant planning unit 1604 is then configured to determine a representation of the tooth crowns and / or a part of the oral mucosa based on the representation of the digital 3D surface representation generated by the image processing unit 1603 and a further statistical parametric 3D shape model provided by the model provision unit 1602.

[0096] In a further embodiment, the image processing unit 1603 can also be configured to generate a point-based representation of the digital 3D surface representation provided by the data provision unit by providing an already existing point-based representation of the provided digital 3D surface representation (100). The implant planning unit 1604 is then configured to determine a representation of at least one implantation axis based on the representation of the digital 3D surface representation generated by the image processing unit 1603 and a further statistical parametric 3D shape model provided by the model provision unit 1602.

[0097] In further embodiments, the implant planning unit 1604 can be configured to determine a representation of the bone structures near the teeth and / or the course of the nerves near the teeth based on the representation of the digital 3D surface representation generated by the image processing unit 1603 and further statistical parametric 3D shape models provided by the model provision unit 1602.

[0098] In one embodiment, the model provision unit 1602 can also be configured to generate an SSM in the manner already described above. Depending on the training data, this SSM can include representations of the tooth crowns, tooth axes, and / or implant axes, as well as the bone structures near the teeth and / or the course of the nerves near the teeth. Thus, in a preferred embodiment, the data provision unit 1601 is configured to provide a plurality of digital 3D surface representations of at least part of the tooth crowns and / or at least part of the oral mucosa of the respective training subject, originating from various training subjects.Furthermore, it is configured to additionally provide a plurality of 3D imaging data sets originating from the various training subjects, from which tooth axes can be determined and which can each be registered with the provided digital 3D surface representations belonging to the same training subject. The image processing unit 1603 of this embodiment is configured to generate a plurality of 3D training data sets by registering the provided 3D surface representations and 3D imaging data sets belonging to each of the training subjects with one another. Furthermore, the image processing unit 1603 generates a plurality of representations of the 3D training data by generating a representation for each of the generated 3D training data sets, specifically by defining a plurality of training landmarks on tooth axes as well as on tooth crowns and / or parts of the oral mucosa of the respective training subject.Finally, the model providing unit 1602 is configured to generate a statistical parametric 3D shape model based on training landmarks of the plurality of representations of the 3D training data.

[0099] In a further embodiment, the image processing unit 1603 is also configured to provide the plurality of digital 3D surface representations provided by the data provision unit 1601 as a plurality of 3D training data sets and, as described in connection with Fig. 14, to generate a plurality of landmark-based representations of the second 3D training data sets. In this embodiment, the model provision unit 1602 is configured to generate a statistical parametric 3D shape model based on training landmarks from the generated plurality of representations of the 3D training data. Representations of the dental crowns, for example, can be generated from this SSM.

[0100] In a further embodiment, the data provision unit 1601 is also configured to provide the plurality of digital superimposed 3D data sets originating from the various training subjects, as described in connection with Fig. 15. The image processing unit 1603 is also configured to provide the plurality of digital superimposed 3D data sets provided by the data provision unit 1601 as a plurality of 3D training data sets and, as described in connection with Fig. 15, to generate a plurality of landmark-based representations of the second 3D training data sets. The model provision unit 1602 is configured in this embodiment to generate a statistical parametric 3D shape model based on training landmarks of the generated plurality of representations of the 3D training data. From this SSM, for example,

[0101] Representations of the implantation axes are generated.

[0102] In further embodiments that can be combined with all those described above, the image processing unit 1603 can also be configured to align the individual, respective 3D training data sets with one another in a common coordinate system before generating the respective statistical parametric 3D shape model. In a preferred embodiment derived therefrom, the model provision unit 1602 is configured to perform a principal component analysis of the plurality of mutually aligned respective 3D training data sets or their representations to generate the respective statistical parametric 3D shape model.

[0103] In a further embodiment, the data provision unit 1601 is configured to provide additional imaging data in addition to the digital 3D surface representations and the 3D imaging data sets. In a preferred embodiment, these are 2D X-ray images, in particular OPG imaging data. The implant planning unit 1604 is configured to display the already determined representation of the tooth crowns, tooth axes, and / or implantation axes, as well as optionally the bone structures near the teeth and / or the course of the nerves near the teeth, in the additional imaging data, in particular to project them into the additional imaging data. An example of this is shown in Fig. 10.In particular, in some embodiments, the implant planning unit 1604 can be configured to perform the plausibility check steps already described in detail above, in particular the transfer of the implantation axes into a 2D X-ray image and, if necessary, back into the 3D model. This allows the implanter to perform a plausibility check. For example, using additional imaging data that, for example, reveal the actual bone structures, it can be checked whether the implant axes lead into bony tissue and whether sufficient substance is present there for attachment, or whether they run within soft tissue that is completely unsuitable for attachment.

[0104] Finally, an embodiment of the system 1600 may include an additional drill guide unit 1605 configured to generate a drilling template and / or control instructions for an automated drilling device based on the generated implant planning data for the insertion of the implant-supported dental prosthesis. An example of a model of such a drilling template 1701 is shown in Fig. 17. This may be a unit for generating control instructions for a 3D printer and an associated 3D printer. Additionally or alternatively, it may be a unit that generates control commands for a robot and / or a corresponding surgical robot suitable for performing the necessary drilling.A computer program product for supporting a preoperative process for planning the insertion of a dental implant into a patient's jaw contains control instructions for the previously described procedure for generating representations of the tooth axes and optionally the tooth crowns, tooth axes, and / or implantation axes of one or more of the teeth intended for the implant-supported dental prosthesis, as well as the bone structures near the teeth and / or the course of the nerves near the teeth, based on the digital 3D surface representation and the statistical parametric 3D shape model. In particular, some embodiments of the computer program product comprise control instructions for generating SSMs as described above. Such a computer program product can be stored on one of the conventional non-volatile storage media.

[0105] A particularly preferred embodiment is described below. If not already available, an SSM is first created using digitized plaster models or intraoral scans and CBCT scans of various training subjects.

[0106] The plaster models are fabricated using commercially available materials, such as alginates, silicones, or polyethers. Digitization is performed using an optical scanner, such as an E3 3-shape laboratory scanner (3shape, Copenhagen, Denmark), and exported as Standard Tessellation Language (STL) files.

[0107] The CBCT scans are performed using a commercially available CBCT scanner, e.g., the 3D Accuitomo 170 CBCT scanner (Morita Corporation, Osaka, Japan), with a slice thickness of 0.25 mm and a field of view of 17 x 12 cm. The data sets are exported as DICOM (Digital Imaging and Communications in Medicine) files from the local picture archiving and communication system.

[0108] CBCT scans can contain artifacts due to fixed dentures or fillings, which may lead to inadequate visualization of the tooth crown. To enable the accurate representation of the tooth crown morphology and root shape in a single dataset, the CBCT is fused with the surface scan. Using appropriate software, all bony structures and teeth are segmented from the DICOM datasets. To fuse the segmented model of the CBCT scan with the digitized plaster model, five corresponding landmarks are defined on both datasets, and an iterative procedure is performed to determine the nearest point on the lingual surface of the teeth. Specifically, the ICP method described above can be used here.The ICP method iteratively reduces the distance between tooth surfaces, resulting in an overlay with a maximum distance of less than 0.5 mm. The result is a combined training dataset containing detailed information about the tooth crown and root.

[0109] Anatomical landmarks are now used to parameterize the complex morphology of the tooth crowns and roots and to create a landmark-based SSM of the tooth shape. To establish consistent and reproducible landmarks on the tooth crown, cusps, incisal edges, and central fissures are annotated. The landmark-based description of tooth root anatomy, however, is performed differently, since there are no clearly identifiable anatomical landmarks along tooth roots. Five landmarks are defined for each tooth root. A first landmark is placed in the center of the root canal at the level of the cementoenamel junction (CEJL). Three further landmarks are placed at intervals of two millimeters each along the tooth root in an apical direction in the center of the root canal. A fifth landmark is placed at the apical end of the root.As previously described, multi-rooted teeth are treated as if they had a single large root when placing landmarks. If multiple roots of the same tooth were cut horizontally, a landmark was placed at their center. Finally, a landmark-based model is created for each dataset, which contains information about the shape of the tooth crown and root. Figure 13 shows examples of landmarks 1301–1305 for an individual in the CBCT dataset.

[0110] To determine the root alignment, an idealized root axis is calculated for each tooth using a regression line based on the landmarks 1301–1305 shown, for example, in Fig. 13. This method can compensate for minor errors in the subjective positioning of the root landmarks in the CBCT scan, as multiple landmarks represent the axis. Even if one landmark is incorrectly positioned, this effect is mitigated by the remaining three landmarks.

[0111] Common software packages (e.g., R software) can be used to create the SSM. All datasets contained in this training dataset are aligned with respect to their translation and rotation in space within a single coordinate system. Based on the previously described landmarks, all available surface models are overlaid using the ICP algorithm. Using the ICP algorithm, non-form-relevant information such as the position and rotation of the surface scans is eliminated, and all models are brought into a single coordinate system. Finally, the SSM is generated using a subsequent principal component analysis.

Claims

Claims: Computer-aided method for supporting preoperative planning of the insertion of a dental implant (601) into a patient's jaw, comprising the following steps: - Providing (701) a digital 3D surface representation (100) of at least a portion of the patient's existing dental crowns and / or oral mucosa; - Providing (702) a first statistical parametric 3D shape model for generating representations of tooth axes (801; 1001); - Generating (703) a representation of the provided digital 3D surface representation (100) by specifying a plurality of landmarks (1201, 1202; 1301-1305) on at least one tooth crown and / or parts of the oral mucosa that are visible in the provided digital 3D surface representation (100); and - Determining (704) a tooth axis representation (801; 1001) of one or more of the teeth intended for the implant-supported dental prosthesis based on the generated landmark-based representation of the digital 3D surface representation (100) and the first statistical parametric 3D shape model. Method according to claim 1, further comprising: - Providing (702) a second statistical parametric 3D shape model to generate representations of tooth crowns and / or part of the oral mucosa; - Providing (703) a representation of the provided digital 3D surface representation (100) by providing an existing point-based representation of the provided digital 3D surface representation (100) or generating a landmark-based representation of the provided digital 3D surface representation (100) by specifying a variety of landmarks (1201, 1202; 1301-1305) on dental crowns and / or a portion of the oral mucosa of the respective training subject; and 25 - Determining (704) a crown representation of one or more of the teeth intended for the implant-supported dental prosthesis and / or a representation of a part of the oral mucosa based on the generated representation of the digital 3D surface rendering (100) and the second statistical parametric 3D shape model. Method according to claim 1 or 1, further comprising: - Providing (702) a third statistical parametric 3D shape model for generating representations of implantation axes; - Providing (703) a representation of the provided digital 3D surface representation (100) by providing an existing point-based representation of the provided digital 3D surface representation (100) or generating a landmark-based representation of the provided digital 3D surface representation (100) by specifying a variety of landmarks (1201, 1202; 1301-1305) on dental crowns and / or a portion of the oral mucosa of the respective training subject; and - Determining (704) an implant axis representation for one or more of the teeth intended for the implant-supported dental prosthesis based on the generated representation of the provided digital 3D surface representation (100) and the third statistical parametric 3D shape model. A method according to any of the preceding claims, wherein additionally 2D radiographic imaging data (500, 1000), preferably panoramic radiographic imaging data, of the bony situation of parts of the patient's mouth, jaw, and face relevant to the insertion of the dental implant are provided, and the determined tooth axis representation (801; 1001) and / or the determined implant axis representation is displayed in the 2D radiographic imaging data (500, 1000) for plausibility control (901). A method according to any of the preceding claims, comprising the generation of the first statistical 3D shape model according to the following steps: Providing (1101) a sample of training subjects A large number of digital 3D surface representations (100) of at least a part of the tooth crowns and / or at least a part of the oral mucosa; - Providing (1102) a variety of 3D imaging datasets (200) originating from the various training subjects, from which tooth axes (801; 1001) can be determined and which can each be registered with the provided digital 3D surface representations belonging to the same training subject; - Generating (1103) a plurality of first 3D training datasets (300) by registering the provided 3D surface representations and 3D imaging datasets belonging to each of the training subjects; - Generating (1104) a plurality of representations of the first 3D training datasets (300) by generating one representation for each generated first 3D training dataset (300) by defining a plurality of training landmarks (1201, 1202; 1301-1305) on tooth axes (801; 1001) as well as on tooth crowns and / or parts of the oral mucosa of the respective training subject; and - Generating (1105) the first statistical parametric 3D shape model based on the training landmarks (1201, 1202; 1301-1305) of the plurality of landmark-based representations of the first 3D training datasets (300). A method according to claim 5, wherein the registration of 3D surface representations (100) and 3D imaging datasets (200) belonging to a training subject is performed by matching (1112) a previously defined plurality of corresponding registration landmarks on the 3D surface representations (100) and 3D imaging datasets (200) to each other. A method according to any of the preceding claims, further comprising generating the second statistical 3D shape model by the following additional steps: - Providing (1403) the provided multitude of digital 3D surface representations (100) as a multitude of second 3D training datasets; - Generating (1404) a plurality of point-based representations of the second 3D training datasets by providing one pre-existing point-based representation for each second 3D training dataset provided, or by generating one landmark-based representation for each second 3D training dataset provided, by Numerous training landmarks (1201) on the crowns of the respective teeth training subject is determined; and - Generating (1405) the second statistical parametric 3D shape model based on the plurality of generated representations of the second 3D training datasets. A method according to any of the preceding claims, further comprising generating the third statistical 3D shape model by the following steps: - Providing (1501) a plurality of digital superimposed 3D datasets originating from the various training subjects, wherein each of the digital superimposed 3D datasets comprises a superimposition of a digital 3D surface representation (100) of at least a portion of the existing dental crowns and / or oral mucosa of the respective training subject and an associated 3D imaging dataset (200) and at least one implantation axis used in a previous placement of a dental implant in the respective training subject; - Providing (1503) the provided multitude of digital superimposed 3D datasets as a multitude of third 3D training datasets; - Generating (1504) a plurality of point-based representations of the third 3D training datasets by providing one pre-existing point-based representation for each third 3D training dataset provided, or by generating one landmark-based representation for each third 3D training dataset provided by defining a plurality of training landmarks (1201, 1202; 1301-1305) on tooth axes (801; 1001) and the at least one implantation axis, as well as on tooth crowns and / or parts of the oral mucosa of the respective training subject; and - Generating (1505) the third statistical 3D shape model based on the plurality of generated representations of the third 3D training datasets. Method according to claim 8, wherein the already existing point-based representation contains annotated landmarks for each provided third 3D training dataset, representing the at least one implantation axis. 28 A method according to any one of claims 5 to 9, comprising aligning the individual 3D training datasets (300) or their representations in a common coordinate system (1114; 1414; 1514) before generating the statistical parametric 3D shape model. A method according to claim 10, wherein generating the statistical parametric 3D shape model (1105; 1405; 1505) comprises performing a principal component analysis on the plurality of respective 3D training datasets (300) or their representations aligned in a common coordinate system. A system for supporting preoperative planning of the insertion of a dental implant into a patient's jaw, comprising a data provisioning unit (1601) configured to provide a digital 3D surface representation (100). a model provisioning unit (1602) that is set up to provide a statistical parametric 3D shape model;an image processing unit (1603) configured to generate a representation of the digital 3D surface representation (100) provided by the data provision unit (1601) by defining a plurality of landmarks (1201, 1202; 1301-1305) located on the 3D surface representation (100); an implant planning unit (1604) configured to determine a tooth axis representation (801;1001) for one or more of the teeth intended for the implant-supported dental prosthesis based on the landmark-based representation of the digital 3D surface representation (100) generated by the image processing unit (1603) and a statistical parametric 3D shape model provided by the model provisioning unit (1602). System according to claim 12, wherein the image processing unit (1603) is further configured to generate a point-based representation of the digital 3D surface representation (100) provided by the data provisioning unit (1601) by providing a pre-existing point-based representation of the provided digital 3D surface representation (100); and; 29 The implant planning unit (1604) is also equipped to determine a crown representation of one or more of the teeth intended for the implant-supported dental prosthesis and / or a representation of a part of the oral mucosa based on the representation of the digital 3D surface display (100) generated by the image processing unit (1603) and a statistical parametric 3D shape model provided by the model provisioning unit (1602).System according to claim 12 or 13, wherein the image processing unit (1603) is further configured to generate a point-based representation of the digital 3D surface representation (100) provided by the data provision unit (1601) by providing an existing point-based representation of the provided digital 3D surface representation (100); and the implant planning unit (1604) is further configured to determine a representation of the implant axes of one or more of the teeth intended for the implant-supported dental prosthesis based on the representation of the digital 3D surface representation (100) generated by the image processing unit (1603) and a statistical parametric 3D shape model provided by the model provision unit (1602).A system according to any one of claims 12 to 14, wherein the data provision unit (1601) is further configured to provide 2D radiographic imaging data (500, 1000), preferably panoramic radiographic imaging data, of the bony situation of parts of the patient's mouth, jaw, and face relevant to the placement of the dental implant; and wherein the implant planning unit (1604) is further configured to display the specific tooth axis representation (801; 1001) and / or implant axis reconstruction for plausibility checks in the further imaging data. A system according to any one of claims 12 to 15, which is configured to generate a first statistical parametric 3D shape model, wherein the data provision unit (1601) is further configured to provide a plurality of digital 3D surface representations (100) of at least a part of the tooth crowns, originating from different training subjects. 30 and / or at least a part of the oral mucosa of the respective training subject; a plurality of 3D imaging datasets (200) originating from the various training subjects, from which tooth axes (801; 1001) can be determined and which can each be registered with the provided digital 3D surface representations belonging to the same training subject; and the image processing unit (1603) is also configured to generate a plurality of 3D training datasets (300) by registering the provided 3D surface representations and 3D imaging datasets belonging to each of the training subjects; and a plurality of representations of the 3D training data by generating one representation for each of the generated 3D training datasets by placing a plurality of training landmarks (1201, 1202; 1301-1305) on tooth axes (801;1001) as well as on dental crowns and / or parts of the oral mucosa of the respective training subject; the model provisioning unit (1602) is further configured to generate a first statistical parametric 3D shape model based on the training landmarks (1201, 1202; 1301-1305) of the plurality of representations of the 3D training data. System according to one of claims 12 to 16, which is configured to generate a second statistical parametric 3D shape model, wherein the image processing unit (1603) is further configured to; Providing the multitude of digital 3D surface representations (100) as a multitude of 3D training datasets; and Generating a multitude of point-based representations of the multitude of provided 3D training datasets by providing one pre-existing point-based representation for each provided 3D training dataset, or by generating one landmark-based representation for each provided 3D training dataset by using a multitude of 31 training landmarks (1201) are set on the dental crowns of the respective training subject; the model provisioning unit (1602) is also set up to generate a second statistical parametric 3D shape model based on the multitude of generated representations of the 3D training data.System according to one of claims 12 to 17, which is configured to generate a third statistical parametric 3D shape model, wherein the data provisioning unit (1601) is further configured to provide a plurality of digital superimposed 3D datasets originating from different training subjects, wherein each of the digital superimposed 3D datasets comprises a superimposition of a digital 3D surface representation (100) of at least a part of the existing dental crowns and / or the oral mucosa of the respective training subject and an associated 3D imaging dataset (200) as well as at least one implantation axis that was used in a previous insertion of a dental implant in the respective training subject; the image processing unit (1603) is further configured to. Providing the multitude of digitally superimposed 3D datasets as a multitude of 3D training datasets; and Generating a multitude of point-based representations of the third 3D training datasets by providing one pre-existing point-based representation for each provided third 3D training dataset, or by generating one landmark-based representation for each provided third 3D training dataset by defining a multitude of training landmarks (1201, 1202; 1301-1305) on tooth axes (801; 1001) and the at least one implantation axis, as well as on tooth crowns and / or parts of the oral mucosa of the respective training subject; the model delivery unit (1602) is also configured to generate 32 a third statistical parametric 3D shape model based on the A multitude of generated representations of the 3D training data. A system according to any one of claims 1 to 18, wherein the data provision unit (1601) comprises an intraoral scanner and / or a laboratory scanner. A system according to any one of claims 12 to 19, wherein the data provision unit (1601) comprises a magnetic resonance imaging (MRI) scanner, a computed tomography (CT) scanner, a cone-beam computed tomography (CBCT) scanner, an X-ray system, and / or an orthopantomograph (OPG). A system according to any one of claims 12 to 20, further comprising a drilling guidance unit (1605) configured to generate a drilling template (1701) and / or control instructions for an automated drilling device based on the generated implant planning data for the insertion of the implant-supported dental prosthesis.Computer program product for supporting preoperative planning of the insertion of a dental implant into a patient's jaw, comprising computer-readable instructions for carrying out the method according to one of claims 1-11. 33