Intelligent surgical robotic system for crown lengthening

Abstract

This invention provides an intelligent surgical robot system for crown lengthening surgery, comprising: a data processing unit; and a biotype recognition and planning unit. The biotype recognition and planning unit is used by a gingival biotype classifier to identify the patient's gingival biotype and dynamically calculate the biological width based on the identified gingival biotype, thereby planning the gingival resection boundary and alveolar bone trimming path. The surgical robot execution unit and control unit, by identifying the patient's gingival biotype and dynamically calculating the biological width based on the identified gingival biotype, abandon the empirical assumptions of traditional fixed values, achieving personalized and refined planning of bone removal depth and gingival resection contour. This enables automated and precise resection, reduces the reliance on the surgeon's personal experience, and improves the reliability and predictability of the surgery.

Description

Technical Field

[0001] This invention belongs to the field of intelligent medical robot technology, and in particular relates to an intelligent surgical robot system for dental crown lengthening. Background Technology

[0002] Crown lengthening is a common pre-restoration procedure designed to expose more healthy tooth structure to meet the needs of restoration retention and aesthetics. Traditional methods rely on the dentist's experience and involve free hand manipulation, which can lead to inaccurate bone removal, easy invasion of the biological width (approximately 2mm), and uncontrollable post-operative gingival recession.

[0003] In the current biomedical engineering industry, physical guides are used to guide incisions through 3D-printed guides, which improves accuracy, but still require doctors to manually operate the instruments, which cannot avoid tremors and loss of depth control; moreover, the guides only provide static references and cannot cope with dynamic changes such as intraoperative bleeding and tissue deformation.

[0004] Specialized bone removal instruments control the depth of bone removal using graduated ball drills, but they cannot plan the overall resection boundary, and are still an experience-based operation.

[0005] Existing oral surgery robots (such as Yomi) are mainly used for implant preparation and do not yet support the combined treatment of periodontal soft and hard tissues. They also lack dedicated path planning and adaptive control algorithms for crown lengthening procedures.

[0006] In summary, the inventors discovered the following problems with the prior art during the implementation of this embodiment: Existing guides or instruments cannot achieve integrated, automated, and precise resection of soft and hard tissues. Ignoring individual differences in patients’ gingival biotypes and using a fixed biological width can lead to excessive postoperative recession in patients with thin gingiva or poor contour in patients with thick gingiva. Lacking the ability to perceive and dynamically correct during surgery, it is unable to cope with interference such as tissue displacement and bleeding; The surgical procedure relies on highly skilled doctors and is difficult to standardize and promote. Summary of the Invention

[0007] To address the problems existing in the prior art, the present invention provides an intelligent surgical robot system for crown lengthening surgery.

[0008] This disclosure provides an intelligent surgical robot system for crown lengthening surgery, including: The data processing unit is used to acquire the patient's CBCT images and intraoral scan data, and to configure the acquired CBCT images and intraoral scan data to perform soft and hard tissue spatial alignment and obtain a three-dimensional model in a unified coordinate system. The biotype identification and planning unit is used by the gingival biotype classifier to identify the patient's gingival biotype and dynamically calculate the biological width based on the identified gingival biotype, thereby planning the gingival resection boundary and alveolar bone trimming path. The gingival biotype classifier is trained based on the local point cloud features extracted from the three-dimensional model. The surgical robot execution unit is used to receive instructions from the biometric recognition planning unit and perform gingivectomy and alveolar bone trimming operations. The intraoperative sensing and feedback unit, integrated into the surgical robot execution unit, is used to scan the surgical area in real time during the operation, obtain actual tissue morphology data, and compare it with the planned target. The control unit is communicatively connected to the biometric identification and planning unit, the surgical robot execution unit, and the intraoperative perception and feedback unit, respectively, and is used to dynamically adjust the operation path of the surgical robot execution unit according to the comparison results.

[0009] Optionally, the data processing module also acquires facial 3D scan data for auxiliary spatial positioning, and configures CBCT images, intraoral scan data and facial 3D scan data to obtain a 3D model in a unified coordinate system.

[0010] Optionally, the CBCT images, intraoral scan data, and facial 3D scan data are configured to obtain a 3D model in a unified coordinate system. A multimodal dual-channel weighted ICP registration algorithm is then used, with the registration error function being: , in, To account for the registration error based on the feature points of the tooth cusp, This is based on cross-modal errors in facial soft tissue and CBCT bony landmarks. These are the weighting coefficients.

[0011] Optionally, the gingival biotype classifier is constructed based on a lightweight convolutional neural network and is used to distinguish whether the gingival biotype is thin or thick.

[0012] Optionally, the biological width can be dynamically calculated based on the identified gingival biotype, including: The calculation model for biological width is a piecewise function, which makes the biological width value change continuously with the thickness of the attached gingiva of an individual patient. The calculation model is as follows: , in, For gingival thickness, For biological width.

[0013] Optionally, when refining path planning, the biometric identification and planning unit defines a dynamic safety operation domain, the expression of which is: , in, For the rotation speed of the bone removal instrument, The root surface boundary, For a safe distance, For the set of real numbers, For the shortest Euclidean distance For points.

[0014] Optionally, when refining path planning, the biometric identification and planning unit constrains all trajectory points to be within the safe operating zone (SOZ) and automatically switches the end effector according to the tissue type to generate layered and collision-free robot motion commands.

[0015] Optionally, the intraoperative sensing and feedback unit calculates the local resection completion index. To detect surgical deviations, , in, For the actual model of the k-th scan, For the target model, As the initial model, Let Frobenius norm be used to represent the Frobenius norm.

[0016] Optionally, the system may also include: The postoperative learning unit is used to acquire intraoral scan data during postoperative follow-up and to build an actual healing model. ; The postoperative learning unit calculates the actual healing model. With preoperative planning model The multi-scale morphological deviation between the two is used to evaluate the surgical effect, and the gingival biotype classifier in the biotype identification and planning unit, the multimodal registration network of the data processing unit, and the safe operation domain prediction module of the biotype identification and planning unit are fine-tuned online based on the deviation. The multi-scale morphological deviation is Distance and Weighted sum of distances.

[0017] Optionally, the formula for calculating multi-scale morphological deviation is: , in, and These are the weighting coefficients. Distance reflects the worst-case deviation. Distance reflects the overall fit. This refers to multi-scale morphological deviations.

[0018] The intelligent surgical robot system for crown lengthening provided by this invention identifies the patient's gingival biotype and dynamically calculates the biological width based on the identified gingival biotype. It abandons the empirical assumptions of traditional fixed values ​​and realizes personalized and refined planning of bone removal depth and gingival resection contour, achieving automated and precise resection. This reduces the reliance of the surgery on the doctor's personal experience and improves the reliability and predictability of the surgery. Attached Figure Description

[0019] The above and other objects, features and advantages of this disclosure will become more apparent from the accompanying drawings, in which like reference numerals generally denote like parts.

[0020] Figure 1 This is a schematic diagram of the intelligent surgical robot system for crown lengthening provided in the embodiments of this disclosure; Figure 2 A schematic block diagram of the data processing unit provided in the embodiments of this disclosure; Figure 3 A schematic diagram of the biometric identification and planning unit provided in this embodiment of the disclosure; Figure 4 A schematic block diagram of the surgical robot execution unit provided in the embodiments of this disclosure; Figure 5 A schematic diagram of the intraoperative sensing and feedback unit provided in the embodiments of this disclosure; Figure 6 A schematic diagram of the postoperative learning unit provided in the embodiments of this disclosure; Figure 7 A schematic block diagram of the control unit provided in the embodiments of this disclosure; Figure 8 This is a flowchart illustrating the workflow of the intelligent surgical robot system for crown lengthening provided in this embodiment of the disclosure. Detailed Implementation The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0021] It should be understood that the following specific examples illustrate the implementation of this disclosure, and those skilled in the art can easily understand other advantages and effects of this disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. This disclosure can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this disclosure. It should be noted that, in the absence of conflict, the following embodiments and features in the embodiments can be combined with each other. Based on the embodiments in this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0022] It should be noted that various aspects of embodiments within the scope of the appended claims are described below. It will be apparent that the aspects described herein can be embodied in a wide variety of forms, and any particular structure and / or function described herein is merely illustrative. Based on this disclosure, those skilled in the art will understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects set forth herein can be used to implement the device and / or practice the method. Additionally, this device and / or method can be implemented using structures and / or functionalities other than one or more of the aspects set forth herein.

[0023] It should also be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of this disclosure. The illustrations only show the components related to this disclosure and are not drawn according to the number, shape and size of the components in actual implementation. In actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0024] Furthermore, specific details are provided in the following description to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0025] For ease of understanding, such as Figure 1 As shown, this embodiment discloses an intelligent surgical robot system for crown lengthening, including: The data processing unit is used to acquire the patient's CBCT images and intraoral scan data, and to configure the acquired CBCT images and intraoral scan data to perform soft and hard tissue spatial alignment and obtain a three-dimensional model in a unified coordinate system. Specifically, this implementation simultaneously acquires the patient's CBCT images and intraoral scan (IOS) data; it can also acquire facial 3D scans to assist in spatial localization, such as... Figure 2 As shown.

[0026] This implementation proposes a multimodal dual-channel weighted ICP registration algorithm, defining the total registration error function as: , in: Registration error based on tooth lip feature points; This represents the cross-modal error based on facial soft tissue and CBCT bony landmarks (such as the mandibular angle); Weight The settings are dynamically adjusted based on the image quality of each channel.

[0027] The ICP registration algorithm effectively overcomes the registration failure problem of a single modality when soft tissue or bone structure information is missing, and achieves high-precision soft and hard tissue fusion.

[0028] like Figure 3 As shown, the biotype identification and planning unit is used by the gingival biotype classifier to identify the patient's gingival biotype and dynamically calculate the biological width based on the identified gingival biotype, thereby planning the gingival resection boundary and alveolar bone trimming path. The gingival biotype classifier is trained based on the local point cloud features extracted from the three-dimensional model. Estimation of attached gingival thickness based on intraoral scan point cloud Furthermore, a lightweight convolutional neural network was used to identify gingival biotypes.

[0029] Constructing a biologically-wide adaptive computational model: , This model allows the biological width to vary continuously with individual anatomical features, avoiding postoperative complications caused by a "one-size-fits-all" approach.

[0030] Based on the restoration requirements, the system automatically outputs the gingival resection boundary line and the alveolar bone trimming surface.

[0031] Root protection-oriented personalized surgical approach generation: Define a dynamic safe operation zone (SOZ): , in The safe distance is adaptively increased based on the dynamic risk, which is the rotational speed of the bone removal instrument.

[0032] The path planner enforces all trajectory points to be within the SOZ and automatically switches the end effector (electric knife / ball drill) according to the tissue type, generating layered, collision-free robot motion commands.

[0033] After acquiring specific CBCT data, intraoral scans, and facial scans, a dual-channel weighted ICP registration algorithm is used to align the soft and hard tissues spatially, resulting in a high-fidelity 3D model in a unified coordinate system. In this aligned model, the intraoral scan data provides fine geometric information about the gingival surface (such as curvature and thickness variations). The system extracts local point cloud features (such as normal vector changes and probe-simulated depth) from the intraoral scan data region of the 3D model, using these features as input features for a gingival biotype classifier. A lightweight convolutional neural network (such as MobileNetV3) receives these features, outputs thin or thick gingival labels, and estimates continuous values. The biological width adaptive computation model outputs the target resection boundary, while the surgical path is generated by the path planning module based on this boundary, root safety constraints, and instrument dynamics.

[0034] The biometric identification and planning unit outputs the gingival resection line (soft tissue boundary) and the alveolar bone trimming surface (hard tissue boundary). The position of this surface is determined by... Decision. The biotype recognition and planning unit outputs the target bone trimming surface; the three-dimensional model of the tooth root is extracted based on CBCT. The currently selected instrument type and rotation speed Construct a dynamic safe operating zone (SOZ) to ensure the path stays away from the tooth root; discretize the target surface into executable robot trajectory points; and generate layered, smooth, collision-free motion instructions (G-code or ROS trajectory).

[0035] like Figure 4 As shown, the surgical robot execution unit is used to receive instructions from the biometric recognition planning unit and perform gingivectomy and alveolar bone trimming operations. The robot is equipped with a six-dimensional force sensor, a high-definition endoscope, and a structured light scanner, and supports two operating modes: Fully automatic mode: The robot independently executes the preset path; Shared control mode: The doctor holds the robotic arm, and the system applies virtual wall force feedback.

[0036] Therefore, an impedance-controlled virtual wall interaction algorithm is designed: in: Allowed operating area (generated by biometric identification and planning unit); The nearest boundary point; It is the outer normal vector of the boundary; This is the stiffness coefficient, which is dynamically adjusted with the approach speed; For tactile feedback force vector, is the position vector of the end of the surgical instrument.

[0037] This algorithm ensures operational freedom while providing intuitive and safe tactile guidance to prevent accidental out-of-bounds operations.

[0038] like Figure 5 As shown, the intraoperative sensing and feedback unit is integrated into the surgical robot execution unit and is used to scan the surgical area in real time during the operation, obtain actual tissue morphology data, and compare it with the planned target. After each stage of bone removal is completed, a structured light scan is triggered to reconstruct the current surgical area.

[0039] Tissue types include: gingiva and alveolar bone. For soft tissue (gingiva): electrocautery, laser scalpels, or surgical scalpels are used. These tools are used to cut and shape the gingiva, characterized by precision and minimal bleeding. For hard tissue (alveolar bone): high-speed ball drills or ultrasonic bone cutters are used. These tools are used to grind away part of the alveolar bone to expose the tooth structure, requiring different rotation speeds, power, and cutting characteristics.

[0040] Introducing local excision completion index Perform deviation detection: , When an abnormal decrease or fluctuation exceeds a preset threshold, it is determined that there is tissue displacement or visual obstruction.

[0041] The system automatically pauses, re-registers, and partially replans subsequent paths to achieve closed-loop adaptive adjustment.

[0042] like Figure 7 As shown, the control unit is communicatively connected to the biometric identification and planning unit, the surgical robot execution unit, and the intraoperative perception and feedback unit, respectively, and is used to dynamically adjust the operation path of the surgical robot execution unit according to the comparison results.

[0043] like Figure 6 As shown, the system also includes: a postoperative learning unit. Postoperative intraoral scan data were obtained to construct an actual healing model. .

[0044] Design a multi-scale morphological deviation measurement function for performance evaluation: , in Distance reflects the worst-case deviation. Distance reflects the overall fit, weight Configurable.

[0045] Will Using its spatial distribution characteristics as a supervisory signal, the following model is updated through an online fine-tuning mechanism: Gingival biotype classifier, multimodal registration network, and safe operation domain prediction module.

[0046] This forms a continuous evolutionary closed loop of planning, execution, verification, and learning, enabling the system to be continuously optimized with clinical use. The working process of the intelligent surgical robot system for dental implant crown lengthening is as follows: Figure 8 As shown.

[0047] For the first time, attached gingival thickness was introduced as a continuous variable into the calculation of biological width, abandoning the traditional fixed value assumption. Individualized bone removal depth planning was achieved through piecewise nonlinear functions, which significantly improved the predictability and stability of postoperative gingival contour.

[0048] This embodiment integrates a multimodal dual-channel weighted ICP registration algorithm assisted by facial scanning: it introduces facial soft tissue as a cross-modal bridge between CBCT and intraoral scanning, constructs a dual-channel error function based on tooth features and skeletal landmarks, and realizes dynamic weight allocation, effectively solving the industry problem of insufficient registration information in local oral regions.

[0049] Dynamic Safety Operation Zone (SOZ) path constraint mechanism in the context of tooth root proximity: Integrating dynamic parameters such as the rotation speed of the bone removal instrument into the safety distance calculation, constructing a three-dimensional safety zone that adapts to the operational risk, and forcing the robot trajectory to be located within it, thus preventing accidental tooth root injury from the algorithm level.

[0050] A virtual wall human-computer collaborative interaction algorithm based on impedance control: In the shared control mode, a position-force coupled tactile feedback strategy is designed. When the operating end approaches a non-target area, a reverse force is dynamically generated according to distance and speed, which not only ensures the doctor's degree of freedom of operation, but also provides intuitive and reliable safety boundary protection.

[0051] An intraoperative incremental path correction strategy centered on local resection completion: a completion index based on relative morphological changes is proposed to replace the absolute error threshold, which more robustly detects unexpected interferences such as tissue displacement and bleeding obstruction, and triggers local replanning to achieve highly adaptive closed-loop surgical execution.

[0052] Support for a continuously evolving postoperative assessment and online learning closed-loop system: Construct a multi-scale morphological deviation measurement function that integrates Hausdorff distance and Chamfer distance, and use this as a supervisory signal to fine-tune core modules such as biotype recognition, registration, and path generation online, so that the system has the clinical evolution capability of becoming more accurate with use.

[0053] Compared with the prior art, this embodiment has the following advantages: It has higher precision, with robot execution and real-time feedback, and the error is controlled within ±0.1mm, which is better than the guide plate (±0.3mm). For the first time, an AI classification system for gingival biotypes was introduced to dynamically adjust surgical parameters and reduce the risk of complications. Enhanced safety: Triple protection with force control, vision, and virtual walls to prevent accidental damage to tooth roots or adjacent teeth; More efficient: The entire process is automated, reducing surgery time by more than 30%; It has wider applicability: it supports both fully automatic and shared control modes, catering to both high-end and teaching scenarios; It has the ability to continuously evolve: through the digital twin closed loop, the system becomes more and more accurate the more it is used.

[0054] The basic principles of this disclosure have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this disclosure are merely examples and not limitations, and should not be considered as essential features of each embodiment of this disclosure. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the scope of this disclosure to the necessity of employing the aforementioned specific details for implementation.

[0055] In this disclosure, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The block diagrams of devices, apparatuses, devices, and systems involved in this disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as "comprising," "including," "having," etc., are open-ended terms meaning "including but not limited to," and are used interchangeably with them. The terms "or" and "and" as used herein refer to the terms "and / or," and are used interchangeably with them unless the context clearly indicates otherwise. The term "such as" as used herein refers to the phrase "such as but not limited to," and is used interchangeably with it.

[0056] Additionally, as used herein, the "or" used in a list of items beginning with "at least one" indicates a separate list, such that a list of, for example, "at least one of A, B, or C" means A or B or C, or AB or AC or BC, or ABC (i.e., A and B and C). Furthermore, the word "exemplary" does not imply that the described example is preferred or better than other examples.

[0057] It should also be noted that in the systems and methods of this disclosure, the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered as equivalent solutions to this disclosure.

[0058] Various changes, substitutions, and modifications can be made to the technology described herein without departing from the teachings defined by the appended claims. Furthermore, the scope of the claims of this disclosure is not limited to the specific aspects of the processes, machines, manufactures, events, means, methods, and actions described above. Currently existing or later-developed processes, machines, manufactures, events, means, methods, or actions that perform substantially the same function or achieve substantially the same result as the corresponding aspects described herein can be utilized. Therefore, the appended claims include such processes, machines, manufactures, events, means, methods, or actions within their scope.

[0059] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this disclosure. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of this disclosure. Therefore, this disclosure is not intended to be limited to the aspects shown herein, but rather to be carried out within the widest scope consistent with the principles and novel features disclosed herein.

[0060] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this disclosure to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations therein.

Claims

1. A crown lengthening intelligent surgical robotic system, characterized in that, include: The data processing unit is used to acquire the patient's CBCT images and intraoral scan data, and to configure the acquired CBCT images and intraoral scan data to perform soft and hard tissue spatial alignment and obtain a three-dimensional model in a unified coordinate system. The biotype identification and planning unit is used by the gingival biotype classifier to identify the patient's gingival biotype and dynamically calculate the biological width based on the identified gingival biotype, thereby planning the gingival resection boundary and alveolar bone trimming path. The gingival biotype classifier is trained based on the local point cloud features extracted from the three-dimensional model. The surgical robot execution unit receives instructions from the biometric recognition planning unit and performs gingivectomy and alveolar bone trimming operations. The intraoperative sensing and feedback unit, integrated into the surgical robot execution unit, is used to scan the surgical area in real time during the operation, obtain actual tissue morphology data, and compare it with the planned target. The control unit is communicatively connected to the biometric identification and planning unit, the surgical robot execution unit, and the intraoperative perception and feedback unit, respectively, and is used to dynamically adjust the operation path of the surgical robot execution unit according to the comparison results.

2. The crown lengthening intelligent surgical robotic system of claim 1, wherein, The data processing module also acquires facial 3D scan data for auxiliary spatial positioning, and configures CBCT images, intraoral scan data and facial 3D scan data to obtain a 3D model in a unified coordinate system.

3. The intelligent surgical robot system for crown lengthening according to claim 2, characterized in that, The CBCT image, intraoral scanning data and facial three-dimensional scanning data are configured to obtain a three-dimensional model in a unified coordinate system, and a sampling multi-modal double-channel weighted ICP registration algorithm is used, and the registration error function is: , wherein, is a registration error based on dental surface feature points, is a cross-modality error based on facial soft tissue and CBCT bony landmarks, is a weight coefficient.

4. The crown lengthening intelligent surgical robotic system of claim 1, wherein, The gingival biotype classifier is built on a lightweight convolutional neural network and is used to distinguish whether the gingival biotype is thin or thick.

5. The crown lengthening intelligent surgical robotic system of claim 1, wherein, Biological width is dynamically calculated based on the identified gingival biotype, including: The calculation model for biological width is a piecewise function, which makes the biological width value change continuously with the thickness of the attached gingiva of an individual patient. The calculation model is as follows: ， wherein, is the gingival thickness, is the biological width.

6. The crown lengthening intelligent surgical robotic system of claim 1, wherein, When refining path planning, the biometric identification and planning unit defines a dynamic safety operation domain, the expression of which is: ， wherein, is the speed of the bone removal instrument, is the root surface boundary, is the safety distance, is the set of real numbers, is the shortest Euclidean distance, is the point.

7. The crown lengthening intelligent surgical robotic system of claim 6, wherein, When refining path planning, the biometric identification and planning unit constrains all trajectory points to be within the safe operating zone (SOZ) and automatically switches end-effectors according to tissue type, generating layered and collision-free robot motion commands.

8. The intelligent surgical robot system for crown lengthening according to claim 1, characterized in that, The intraoperative perception and feedback unit detects a surgical deviation by calculating a local resection completeness indicator ​ ， in, For the actual model of the k-th scan, For the target model, As the initial model, Let Frobenius norm be used to represent the Frobenius norm.

9. The intelligent surgical robot system for crown lengthening according to claim 1, characterized in that, Also includes: The postoperative learning unit is used to acquire intraoral scan data during postoperative follow-up and to build an actual healing model. ; The postoperative learning unit calculates the actual healing model. With preoperative planning model The multi-scale morphological deviation between the two is used to evaluate the surgical effect, and the gingival biotype classifier in the biotype identification and planning unit, the multimodal registration network of the data processing unit, and the safe operation domain prediction module of the biotype identification and planning unit are fine-tuned online based on the deviation. The multi-scale morphological deviation is Distance and Weighted sum of distances.

10. The intelligent surgical robot system for crown lengthening according to claim 9, characterized in that, The formula for calculating multi-scale morphological deviation is: ， in, and These are the weighting coefficients. Distance reflects the worst-case deviation. Distance reflects the overall fit. This refers to multi-scale morphological deviations.

Images