Intelligent guiding system and method for facial beauty suture route

Abstract

The invention relates to the field of medical apparatuses and instruments and facial beauty operations, in particular to an intelligent guiding system and method for a facial beauty suture route. The method comprises the following steps: acquiring a facial wound image of a patient through high-definition camera equipment, and performing preprocessing and feature extraction in combination with data enhancement and deep learning technologies; automatically planning and dynamically optimizing a suture route by using a deep learning algorithm and a facial anatomical aesthetics model; in the operation process, the suturing route is displayed in real time in a three-dimensional highlight marking mode, visual operation guidance is provided, real-time feedback is collected, and the operation process is optimized; a high-precision mechanical device is used for executing sewing operation, and in combination with real-time feedback information, precise implementation of a sewing route is ensured. According to the invention, the suturing precision and the aesthetic degree in the facial cosmetic surgery can be improved, and postoperative scars and adverse reactions are reduced.

Description

Technical Field

[0001] The present invention relates to the field of medical devices and facial cosmetic surgery, and in particular to an intelligent guidance system and method for facial cosmetic suturing routes. Background Art

[0002] Existing facial cosmetic surgery suturing operations usually rely on the doctor's experience and feel, which to a certain extent leads to problems such as inaccurate suturing paths and uneven suturing tension. Due to the complex anatomical structure of the face and extremely high aesthetic requirements, the accuracy of the suturing route during surgery is crucial to the postoperative effect. However, manual operation often makes it difficult to ensure that the position and tension of all suture points meet the ideal standards, which may lead to problems such as obvious postoperative scars and unnatural facial contours. In order to solve the above problems, there is an urgent need for an intelligent system that can automatically plan and accurately guide suturing operations based on facial wound images, anatomical structure data and aesthetic principles, so as to improve suturing accuracy and aesthetics, and reduce the occurrence of postoperative scars and adverse reactions. Summary of the invention

[0003] The present invention provides an intelligent guidance system and method for facial cosmetic suturing routes, so as to solve the problem of how to automatically plan and accurately guide the suturing path in facial cosmetic surgery based on facial wound images, anatomical structure data and aesthetic principles, so as to improve suturing accuracy and aesthetics and reduce postoperative scars and adverse reactions.

[0004] In order to solve the above problems, the present invention provides an intelligent guidance system and method for facial beauty suture routes, including:

[0005] An intelligent guidance method for facial beauty suturing route, comprising:

[0006] The patient's facial wound images are collected using high-definition cameras, and preprocessed and feature extracted using data enhancement and deep learning techniques;

[0007] Using deep learning algorithms and facial anatomical aesthetic models, the suture route is automatically planned and dynamically optimized;

[0008] During the operation, the suture route is displayed in real time in the form of three-dimensional highlight marking, providing intuitive operation guidance, and collecting real-time feedback to optimize the surgical process;

[0009] The suturing operation is performed using a high-precision mechanical device, combined with real-time feedback information to ensure the precise implementation of the suturing route.

[0010] As a preferred solution, the intelligent guidance method for facial cosmetic suturing route also includes:

[0011] Use high-resolution camera equipment to collect images of patients' facial wounds in real time, capturing the fine structure of the wound and the texture characteristics of the surrounding skin;

[0012] Perform denoising, contrast enhancement and brightness adjustment on the collected images to ensure image clarity and stability;

[0013] The preprocessed images are analyzed using a deep learning model to automatically extract key features related to the surgery.

[0014] As a preferred solution, the intelligent guidance method for facial cosmetic suturing route also includes:

[0015] Use deep learning algorithms combined with facial anatomy and aesthetic models to automatically generate the optimal suture route;

[0016] Dynamically adjust the suturing path based on real-time feedback to adapt to changes in the environment during surgery;

[0017] A comprehensive optimal solution is generated through a multi-objective optimization algorithm to ensure that the suture path meets both medical requirements and aesthetic standards.

[0018] As a preferred solution, the suture path generation includes:

[0019] Preliminary path planning is performed by combining the input key feature vector and facial anatomical matrix through the path generation formula;

[0020] The path is further optimized in combination with the aesthetic standard vector to meet the aesthetic requirements.

[0021] As a preferred solution, the intelligent guidance method for facial cosmetic suturing route also includes:

[0022] During the operation, the suture route is superimposed and displayed in the doctor's surgical field in a three-dimensional manner, and adjustments are made based on real-time feedback;

[0023] The key suture points and routes are highlighted in the surgical field through highlighting technology, and the display content is updated in real time;

[0024] Continuously collect data from the surgical site and feed it back to the path planning module to achieve real-time path adjustment.

[0025] As a preferred solution, the generation of the highlight mark relies on real-time data input of the surgical environment, including the position of surgical instruments, the progress of the operation, and slight changes in the patient's face.

[0026] As a preferred solution, the intelligent guidance method for facial cosmetic suturing route also includes:

[0027] Use high-precision mechanical devices to perform planned suturing operations to ensure the accuracy of suturing movements;

[0028] During complex or long suturing processes, the system can automatically take over part of the suturing operation, reducing the doctor's fatigue and operating pressure;

[0029] The suturing operation performed by the machine is monitored in real time through sensors and feedback mechanisms to ensure high consistency with the planned path.

[0030] As a preferred solution, the automatic suturing support system includes an automatic suturing device and a robotic arm, which can automatically adjust the suturing mode according to the complexity of the operation and the doctor's operating habits.

[0031] As a preferred solution, the real-time monitoring includes a displacement sensor and a pressure sensor, which monitors the position of the robot arm and the tension of the suture thread during the suturing process in real time, and immediately adjusts the suturing operation parameters when deviations or abnormalities are detected.

[0032] As a preferred option, after the operation is completed, the system will generate a detailed operation report and provide postoperative care and adjustment suggestions when necessary to ensure the patient's postoperative recovery is optimal.

[0033] The key innovative features of the present invention include:

[0034] (1) Integrate high-definition image acquisition and intelligent image preprocessing to achieve accurate extraction of wound features.

[0035] (2) Automatic suturing path planning based on facial anatomy and aesthetic models provides personalized optimal suturing solutions.

[0036] (3) Dynamic path optimization and real-time feedback mechanism to ensure precise adjustment and execution of the suturing path during surgery.

[0037] (4) High-precision mechanical assistance system that automatically performs or assists in suturing operations, reducing the surgeon’s surgical burden and improving surgical accuracy.

[0038] The following are its main beneficial effects:

[0039] The present invention automatically plans and accurately guides the suture path in facial cosmetic surgery by combining facial wound images, anatomical structure data and aesthetic principles, significantly improving the accuracy and aesthetics of sutures. Advanced image processing algorithms and deep learning models are used to analyze facial structures in real time, and multi-objective optimization algorithms and dynamic path adjustment formulas are used to ensure that the suture path meets individualized anatomical structures and aesthetic standards. Compared with traditional suturing methods that rely on the doctor's experience, the present invention can effectively reduce human operation errors, reduce the risk of postoperative scar formation, and improve the overall effect of the surgery and patient satisfaction. At the same time, through real-time monitoring and dynamic adjustment mechanisms, the system can adapt to changes during the operation, ensure the accuracy and consistency of each suture, and further improve the safety and stability of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 The present invention is a flowchart of an intelligent guidance method for a facial cosmetic suturing route provided by an embodiment of the present invention.

[0041] Figure 2 The present invention is a flowchart of the intelligent guidance system for facial beauty suturing routes. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0043] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present application. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0044] Reference Figure 1 , is a flow chart of an intelligent guidance system and method for a facial beauty suture route according to an embodiment of the present invention. The intelligent guidance system and method for a facial beauty suture route may at least include steps S100-S400:

[0045] S100, collects facial wound images of patients through high-definition cameras, and combines data enhancement and deep learning technology to perform preprocessing and feature extraction.

[0046] S200 uses deep learning algorithms and facial anatomical aesthetic models to automatically plan and dynamically optimize suture routes.

[0047] During the operation, S300 displays the suture route in real time in the form of three-dimensional highlighted markings, provides intuitive operation guidance, and collects real-time feedback to optimize the surgical process.

[0048] S400 uses high-precision mechanical devices to perform suturing operations, combined with real-time feedback information to ensure the accurate implementation of the suturing route.

[0049] An intelligent guidance system and method for facial cosmetic suture routes provided in an embodiment of the present invention are mainly used to solve the technical problem solved by the present invention, which is "how to automatically plan and accurately guide the suture path in facial cosmetic surgery based on facial wound images, anatomical structure data and aesthetic principles, so as to improve suture accuracy and aesthetics, and reduce postoperative scars and adverse reactions."

[0050] The present invention relates to the field of medical devices and facial cosmetic surgery, and specifically to an intelligent guidance system and method for facial cosmetic suture routes; the method comprises: collecting facial wound images of patients through high-definition camera equipment, preprocessing and feature extraction in combination with data enhancement and deep learning technology; using deep learning algorithms and facial anatomical aesthetic models to automatically plan and dynamically optimize suture routes; during the operation, the suture routes are displayed in real time in a three-dimensional high-brightness marking manner, providing intuitive operation guidance, and collecting real-time feedback to optimize the operation process; using high-precision mechanical devices to perform suture operations, combined with real-time feedback information, to ensure the accurate implementation of suture routes. The present invention can improve the suture accuracy and aesthetics in facial cosmetic surgery, and reduce postoperative scars and adverse reactions.

[0051] S100, using a high-definition camera to collect the patient's facial wound image, and combining data enhancement and deep learning technology to perform preprocessing and feature extraction. Step S100 includes steps S110-S130:

[0052] S110, using the high-resolution camera to collect images of the patient's facial wound in real time, capturing the fine structure of the wound and the texture features of the surrounding skin. Specifically:

[0053] The system will capture high-definition images of the patient's face in real time according to the preset high-resolution standard. The image should not only show the overall facial contour, but also show the wound edge, depth, surrounding skin texture and other microscopic features in detail, ensuring that each frame of the image has enough details to support subsequent feature extraction and path planning.

[0054] Furthermore, during the acquisition process, the camera device maintains a stable frame rate to ensure the continuity and smoothness of image acquisition. During the operation, the dynamic changes of the wound are tracked in real time, the most subtle changes are captured, and timely data support is provided for real-time path planning.

[0055] Furthermore, in order to cope with the uneven lighting or reflection problems that may occur in the surgical environment, the system automatically adjusts the exposure of the camera and performs light correction. The adjustment process ensures that the camera can capture high-contrast and color-accurate images even in a surgical environment with complex lighting. In this way, the system can provide high-quality input data and eliminate image quality problems caused by insufficient light or overexposure.

[0056] S120: performing image preprocessing on the collected original image to enhance the clarity and stability of the image.

[0057] Specifically:

[0058] First, the system uses advanced denoising algorithms to remove noise that may exist in the image. The noise may come from the sensor of the camera device or interference in the environment, such as light changes in the operating room and electromagnetic interference of the equipment. The goal of the denoising process is to retain key details in the image (such as the edge and depth of the wound) while eliminating unnecessary random noise to ensure the clarity and accuracy of the image.

[0059] Furthermore, after the denoising process, the system performs contrast enhancement on the image to improve the visual difference between the wound and the surrounding skin in the image. Through techniques such as contrast stretching or histogram equalization, the system can improve the recognizability of the image and make the outline of the wound clearer. Contrast enhancement is particularly important for images captured under complex lighting conditions (shadow areas or reflective surfaces under surgical lights), which can significantly improve the overall quality of the image.

[0060] Furthermore, the system automatically adjusts the brightness level of the image to cope with the light changes in the surgical environment. By intelligently adjusting the brightness curve of the image, the system ensures that each part of the image is within the appropriate brightness range to avoid overexposure or underexposure. Brightness adjustment combines the data of exposure and light correction so that both bright and dark details of the image can be fully displayed, maximizing the use of useful information in the image.

[0061] S130, extracting features from the pre-processed image, identifying and marking key features such as wound boundary, depth, skin texture, etc. Specifically:

[0062] The system uses a deep learning model to analyze the preprocessed images and automatically identifies and extracts key features related to the surgery. The features include the edge contour of the wound, depth information, skin texture features, and the structure of the surrounding tissue. The data indicators at the input end, image resolution, and image details after contrast adjustment directly affect the accuracy of feature extraction. By accurately extracting the features, the system can provide reliable basic data for the path planning module to ensure the accurate design of the suture route.

[0063] Furthermore, in order to improve the generalization ability of the system, the system applies data enhancement technology to process the extracted feature images. Specific operations include rotating, flipping, scaling, random cropping and other enhancement operations on the image, thereby generating diverse image samples. The enhanced images are used to train and optimize the deep learning model, so that the system can still maintain a high degree of accuracy and stability when facing different surgical environments and patient characteristics.

[0064] Furthermore, based on data enhancement, the system generates a large number of diverse image sample libraries, which are not only used for real-time path planning optimization, but also improve the robustness of the model during system training and calibration. The steps ensure that the system can still accurately extract key features under different lighting conditions and different surgical environments, providing highly reliable basic data to support complex suture path planning.

[0065] S200, using deep learning algorithms and facial anatomical aesthetic models to automatically plan and dynamically optimize suture routes. Step S200 at least includes steps S210-S230:

[0066] S210, using deep learning algorithms and facial anatomy and aesthetic models to automatically generate the optimal suture route. Specifically:

[0067] Definition and input data

[0068] F i represents the i-th key feature vector obtained from the feature extraction and data enhancement module, F i =[f i1 ,f i2 ,…,f in ], where f ij represents the jth parameter associated with the i-th feature of the wound (wound edge, depth, skin texture, etc.).

[0069] A is the facial anatomical matrix, which represents the structural features of the face, including the coordinates and connection relationships of anatomical points. The matrix is ​​m×n, and each element a ij Represents the coordinates or relative distance of a specific point in the facial structure.

[0070] B is an aesthetic standard vector, which represents the facial aesthetic requirements after surgery, such as symmetry, curvature continuity, etc. The dimension is a vector of k, and each element b j The weight corresponding to an aesthetic criterion.

[0071] P is the parameterized representation of the stitching path, P(t) = [x(t), y(t), z(t)], which represents the change of the path over time t, and P(t) is the coordinate of the path in three-dimensional space.

[0072] ① Define the first formula as the path generation formula. When initially generating the stitching path, combine the input key feature vector F i and the facial anatomy matrix A, by solving the following optimization problem:

[0073]

[0074] Among them, the first It represents the optimization of the path P(t) in terms of matching degree with wound characteristics and anatomical structure. represents the constraint of path smoothness, and λ is the smoothness weight factor, which ensures the continuity and smoothness of the path.

[0075] ② Define the second formula as the aesthetic optimization formula. After the initial path is generated, the path is further optimized in combination with the aesthetic standard vector B to meet the aesthetic requirements. The optimization goal is:

[0076]

[0077] Among them, M j (P(t)) is a path-dependent aesthetic criterion function, the facial symmetry or curvature. The second term represents the difference between the path and the standard aesthetically guided path G(t), and μ is the aesthetic matching weight factor.

[0078] ③ The third formula is defined as a multi-objective optimization formula. The system combines the solution P(t) of the path with the medical standard and the aesthetic standard for multi-objective optimization. The final path is determined by the following formula:

[0079]

[0080] Among them, M i represents the medical standard path point, α, β, and γ are the medical, aesthetic, and path smoothness weights, respectively.

[0081] The first formula, the second formula and the third formula combine medical standards, aesthetic requirements and path smoothness, and ultimately optimize a suture path that meets both medical functions and aesthetic requirements.

[0082] The running process is described, and the dynamic suture route planning is as follows:

[0083] ① Feature input and analysis: The system first obtains the key feature vector F from the feature extraction module i Combined with the facial anatomical matrix A, the path generation formula is used for preliminary path planning. The process generates a suture path P(t) that is adapted to the facial structure and wound characteristics through the first formula.

[0084] ② Aesthetic optimization: After generating the preliminary path, the system introduces the aesthetic standard vector B to further optimize the path so that it not only meets the medical requirements but also meets the aesthetic standards of the patient's face. This optimization is achieved through the second formula to ensure that the path can preserve the natural beauty of the face.

[0085] ③Multi-objective optimization: Finally, the system further adjusts the path through the multi-objective third formula, taking into account multiple factors such as medicine, aesthetics and path smoothness, and generates the optimal suturing route. The final path not only guarantees the suturing effect, but also ensures that the postoperative effect meets the highest aesthetic standards.

[0086] S220: After generating the preliminary suturing route, the system can automatically optimize the route according to the real-time feedback of the dynamically changing surgical scene. Specifically:

[0087] Input data definition and symbol description

[0088] R t It is the real-time feedback data matrix of the surgery, the input data at time t, including the changes in wound morphology, the position of surgical instruments, the distribution of tension, etc. The dimension is p×q, and each element Represents a specific feedback parameter.

[0089] P t is the current stitching path vector, the parameterized representation of the path at time t, P t =[x(t), y(t), z(t)], which represents the coordinates of the path in three-dimensional space.

[0090] δP t is the path adjustment vector, the adjustment amount of the stitching path at time t.

[0091] G t is the surgical aesthetic and anatomical standard vector, representing the standard that the path should meet at time t.

[0092] M t Real-time optimization functions for surgery include multiple objective functions such as medical standards, aesthetic requirements, and path smoothness.

[0093] ① Define the fourth formula as real-time path feedback and adjustment, based on the real-time feedback data R during the operation t , the system calculates the current stitching path Pt If a deviation is detected or adjustment is required, the system will calculate the adjustment amount δP of the path t :

[0094]

[0095] Among them, λ is the adjustment coefficient, which controls the sensitivity of path adjustment. It represents the time derivative of real-time feedback data, reflecting the speed and trend of dynamic changes during surgery. Denotes the objective function M t The gradient of the path indicates the direction in which the current path needs to be optimized. μ is the optimization coefficient, which controls the degree of path optimization.

[0096] When generating a preliminary suturing route, the system uses the first formula, the second formula, and the third formula to calculate the edge features, depth information, and surrounding skin texture of the patient's facial wound. The first formula is used to calculate the curvature of the wound edge, the second formula is used to evaluate the change in wound depth, the third formula is used to capture the complexity of the skin texture, and the fourth formula is used to combine the features to generate the key nodes of the preliminary path.

[0097] ② Define the fifth formula as dynamic path optimization, and get the path adjustment value δP t After that, the system updates the stitching path P by solving the following optimization problem: t+1 :

[0098]

[0099] Among them, P t+1 is the update path at time t+1. t ×δP t It represents the spinor term that combines anatomical and aesthetic standards in path adjustment, ensuring that the path meets aesthetic standards without deviating from medical requirements. Represents the acceleration term of the path, ensuring that the path remains smooth during the adjustment process.

[0100] ③ Define the sixth formula as multi-objective functional optimization, and perform global optimization on the path through functional analysis to meet multiple objectives of the surgery. The optimization objective function is:

[0101]

[0102] Among them, ||R t -P t || 2 is the difference between the path and the feedback data, ensuring that the path keeps up with the changes in the surgical site. t ,G t) is the Lagrangian multiplier term between the path and the anatomical and aesthetic criteria, γ is the weight, and L is the Lagrangian multiplier function. It is the smoothness constraint of the path, ensuring the smoothness and operability of the path after adjustment.

[0103] The operation process is described as follows:

[0104] ① Real-time path feedback and adjustment: The system receives feedback data R in real time during the operation. t , and combined with the current path P t Calculate the path adjustment δP t This adjustment is calculated by the fourth formula, which reflects the dynamic changes of the current surgical status and provides precise direction for real-time adjustment of the path.

[0105] ② Dynamic path optimization: Through the fifth formula, the system further optimizes the path based on the calculated path adjustment amount. This process not only takes into account the changes in the surgical site, but also incorporates aesthetic and anatomical standards into the optimization process to ensure that the path meets medical requirements and maintains the best aesthetic effect after surgery.

[0106] ③ Multi-objective functional optimization: Through the sixth formula, the system performs global optimization on the path. This optimization takes into account the multi-objective requirements (such as accuracy, smoothness, aesthetics, etc.) during the operation to ensure that the path always remains in the best state during the operation.

[0107] S230, during the path planning process, the system not only considers suture accuracy and aesthetics, but also comprehensively considers multiple objectives such as operation time, wound healing characteristics and individual differences, and generates a comprehensive optimal solution through a multi-objective optimization algorithm. Specifically:

[0108] Input data definition and symbol description

[0109] T i is the operation time parameter, indicating the completion of each suture path segment P i The time required.

[0110] D i is the patient individual difference parameter matrix, covering individual differences related to suturing, such as skin elasticity, age, wound depth, etc. The dimension is p×q, where D i The element d ij represents the relationship between the i-th path and the j-th patient feature.

[0111] R i It is the postoperative recovery prediction data, which means that in the path segment P i The quality of recovery after completion, including the likelihood of scarring, speed of recovery, etc.

[0112] P i The suture path vector represents a certain path during the surgical process.

[0113] S i It is a path smoothness index that reflects the geometric continuity and smoothness of the path.

[0114] λ j ,α j ,β j ,γ j is the weight coefficient, which is used to balance the contribution of different objective functions in the overall optimization.

[0115] Formula design and algorithm process

[0116] ① Define the seventh formula as the operation time optimization model, optimize the suture path to minimize the operation time, and the objective function is:

[0117]

[0118] Wherein, T(P) is the surgical time objective function of the path planning. i is the weight coefficient of surgical time, which adjusts the contribution of each path segment to the total time. i ) is the completed path segment P i The time required.

[0119] ② Define the eighth formula as the adaptive optimization model for individual differences of patients, optimize the suture path to adapt to the individual differences of patients, and the objective function is:

[0120]

[0121] Where D(P) is the individual difference adaptability objective function of the path planning. i is the individual difference fitness weight coefficient, which adjusts the importance of the path segment in fitness optimization. ij is the path segment P i Relationship parameters with individual patient characteristics.

[0122] During the operation, the system receives sensor data in real time and dynamically adjusts the preliminary path through the fifth to eighth formulas. The fifth formula is used to calculate the impact of real-time environmental changes on the suturing path, the sixth formula is used to fine-tune the suturing path according to the position of the surgical instrument, the seventh formula evaluates the impact of skin tension on the path, and the eighth formula is used to optimize the smoothness of the path curve by combining the above factors.

[0123] ③ Define the ninth formula as the postoperative recovery optimization model to optimize the suture path to improve the postoperative recovery effect. The objective function is:

[0124]

[0125] Wherein, R(P) is the postoperative recovery objective function of the path planning. i is the postoperative recovery weight coefficient, which adjusts the effect of the path segment on postoperative recovery. i ) is the path segment P i Prediction function for postoperative recovery.

[0126] ④ Define the tenth formula as the path smoothness constraint model, and constrain the path smoothness through the high-order function partial derivative formula to ensure the continuity and operability of the path during surgery. The constraint function is:

[0127]

[0128] Wherein, S(P) is the path smoothness constraint function. i is the smoothness weight coefficient, which adjusts the importance of the smoothness of the path segment in the optimization. is the path segment P i The second derivative of represents the change in curvature of the path.

[0129] ⑤ Define the eleventh formula as a multi-objective comprehensive optimization formula, combine the objective function, construct a multi-objective comprehensive optimization formula, and solve the global optimal path P through functional analysis * :

[0130]

[0131] Among them, P * is the optimal suture path, taking into account the operation time, individual differences of patients, postoperative recovery and path smoothness. δ is the adjustment coefficient of the path smoothness constraint.

[0132] When generating the final suture path, the system applies formulas 9 to 11 to perform multi-objective optimization on the path. The ninth formula is used to balance medical needs and aesthetic standards, the tenth formula is used to adjust the path to reduce the risk of postoperative scars, and the eleventh formula integrates the operation time and the patient's recovery speed to ensure that the final path is not only accurate but also meets clinical needs.

[0133] The operation process description, multi-objective comprehensive optimization:

[0134] ① Operation time optimization: The system first optimizes the preliminary path based on the operation time objective function T(P) of path planning to ensure that the operation time is minimized.

[0135] ② Patient individual difference adaptability optimization: Further, the system is based on the patient individual difference parameter matrix D iOptimization is performed and the path is adjusted using the individual difference adaptive objective function D(P) to ensure that it adapts to the individual characteristics of the patient.

[0136] ③ Postoperative recovery optimization: Furthermore, the system further optimizes the path through the postoperative recovery objective function R(P) to improve the postoperative recovery effect and reduce the risk of scar formation and other complications.

[0137] ④ Path smoothness constraint: Furthermore, the system ensures the geometric continuity and smoothness of the path through the path smoothness constraint function S(P), making the surgical operation smoother and more precise.

[0138] ⑤ Comprehensive solution and feedback adjustment: Through functional analysis, the multi-objective comprehensive optimization formula is solved, and the system generates the global optimal path P * If unsatisfactory surgical results are found during the evaluation process, the system will adjust the weight coefficients based on the feedback and re-optimize until the global optimal solution is obtained.

[0139] The multi-objective optimization algorithm in S230 is used to generate the final suture path, which needs to meet medical and aesthetic standards. The key output of this step is the optimized suture path data, which includes the three-dimensional coordinate information of the path, the smoothness of the path, the tension distribution, etc.

[0140] S300: During the operation, the suture route is displayed in real time in a three-dimensional highlighted manner to provide intuitive operation guidance, and real-time feedback is collected to optimize the operation process. Step S300 at least includes steps S310-S330:

[0141] S310: During the operation, the suture route is displayed in a three-dimensional manner in the doctor's surgical field of view, providing intuitive operation guidance. Specifically:

[0142] The three-dimensional path display in S310 depends on the final optimized path data obtained from step S230. In S230, the path data (the three-dimensional coordinates and tension distribution of the path) generated by the multi-objective optimization algorithm will be directly used as input data for the three-dimensional display in S310. The data will be used to overlay the path in the doctor's field of view during the operation.

[0143] After the pre-processing module of the system (including image pre-processing and path planning) is completed, the system will receive detailed stitching path data P i =[x i (t),y i (t),z i(t)], the data represents the three-dimensional coordinates of each time point in the surgical area. The coordinates are processed and mapped to the three-dimensional model of the patient's face. Three-dimensional coordinate input: P i It is generated by facial image data collected by high-precision camera equipment. After feature extraction and path planning, the system determines the three-dimensional coordinates of each suture point. Three-dimensional model generation: The system integrates the coordinates into the patient's real-time three-dimensional facial model, which also includes facial anatomy and other surgical reference points.

[0144] Furthermore, the system superimposes the generated three-dimensional path onto the doctor's surgical field of view through augmented reality (AR). The process includes accurately aligning the digital three-dimensional path to the real surgical scene and ensuring that the displayed path can be dynamically updated as the surgical instruments and patient positions change. Path alignment and calibration: Before display, the system uses a calibration algorithm to ensure that the three-dimensional path is accurately aligned with the actual patient's face. The input real-time data (such as the position of the surgical instrument, micro-movement of the patient's head, etc.) will dynamically adjust the position and angle of the path display to keep the path consistent with the actual operating environment. Real-time update and feedback: During the operation, the system will monitor the changes in the surgical environment in real time and adjust the path display based on the feedback data. If the doctor's operation causes the path to deviate from the actual surgical position, the system will automatically correct the displayed path to ensure that the doctor's visual guidance is always consistent with the surgical position.

[0145] Furthermore, the display path not only provides static visual guidance, but also provides doctors with dynamic operation prompts and adjustment suggestions through real-time interaction with surgical operations. Multi-view adjustment: Doctors can adjust the display viewing angle through surgical equipment or voice commands, view the suturing path from different angles, and ensure that the position and angle of each needle can be accurately judged. Real-time feedback prompts: The system can provide prompts based on the doctor's operation feedback (position deviation or operation speed of the surgical instrument), and suggest adjusting the operation to optimize the suturing effect.

[0146] S320: Using the highlight marking technology, key suturing points and routes are highlighted in the surgical field of view, and the displayed content is updated in real time as the surgery progresses. Specifically:

[0147] The system first receives data transmitted from the image preprocessing and path planning module, wherein the data includes the three-dimensional coordinates P of the stitching path. i =[x i (t),y i (t),z i (t)] and the key points K identified during the operation j , the anatomical structure that needs special attention or the area that needs to be sutured. Key point input: Key point Kj It is determined by the system through image analysis and path planning, and usually includes the starting point of the wound, the turning point, and the parts on the path that may involve higher risks. Path input: The path data P i Through high-precision imaging and deep learning model generation, the patient's facial anatomical structure and aesthetic model are combined to ensure that every path point is carefully planned.

[0148] Furthermore, the system generates highlight mark information based on the input key point and path data. The generation of highlight marks depends on the real-time data input R(t) of the surgical environment, including the position of surgical instruments, the progress of the operation, and slight changes in the patient's face. Dynamic highlight marks: The system superimposes highlight marks on the doctor's surgical field of view through augmented reality (AR) technology. The color, brightness, and size of the mark are dynamically adjusted according to the real-time data of the operation to ensure that the doctor can clearly identify the key points and paths at any time. Real-time adjustment and update: During the operation, the system will continuously monitor the position of the surgical instruments and the progress of the operation, and update the position and display intensity of the highlight mark in real time. As described above, when the surgical instrument approaches a key point, the system will automatically increase the brightness and color saturation of the point to alert the doctor.

[0149] Furthermore, the system not only provides static highlight marks during surgery, but also helps doctors optimize the operation path through a real-time feedback mechanism. Based on the input data R(t) from sensors and cameras, the system can detect possible operation deviations during surgery and prompt doctors to make adjustments through real-time guidance. Operation deviation detection: If the system detects that the doctor's operation deviates from the planned path or key points, the system will remind the doctor to adjust through visual and audio feedback. The system may emit a prompt sound or flash a highlight mark to attract the doctor's attention. Guidance information update: As the operation progresses, the system will continuously update the guidance information. During the suturing process, the path display is adjusted according to the real-time monitoring data to ensure that each step of the operation is accurate and correct.

[0150] S330: During the operation, the system continuously collects data from the operation site and feeds the data back to the path planning module to achieve real-time path adjustment. Specifically:

[0151] During the operation, the system collects real-time feedback data through sensors integrated on the surgical instruments and the patient's skin surface. The data includes changes in tissue tension, slight movements of suture positions, wound healing, etc. All of the information is input into the system through a high-frequency data stream R(t), which includes: Tension sensor data T i (t) represents the change in tension of the suture or surgical site during surgery. The system can detect the tightness of the skin or tissue during suturing.i (t) represents the reaction information when the surgical instrument contacts the patient's tissue. The changes in the hardness or softness of the monitored tissue will affect the system's adjustment of the suturing path. Position and movement data M i (t) Used to record the real-time position information of surgical instruments and target suturing sites to ensure that the suturing path is consistent with the actual operating environment.

[0152] Furthermore, the system analyzes the input real-time data, mainly by comparing the current suture path P(t) with the real-time data R(t) to determine whether path adjustment is needed. If the system detects that the current suture path deviates from the optimal state, the tension is too large or the tissue response is abnormal, the system will make the following adjustments: Path correction: The system calculates the path adjustment parameter δP(t) based on the data input by the sensor and adds it to the current path to generate a new path P new (t). The adjusted path takes into account the physical feedback detected in real time, ensuring that the path is more consistent with the actual situation at the surgical site, P new (t) = P(t) + δP(t). Based on the path correction, the system will further evaluate the performance of the adjusted path in terms of medical standards and surgical results. If real-time data indicates that the position or tension of the surgical instrument needs to be further optimized, the system will dynamically adjust the smoothness and stability of the path to ensure the accuracy and safety of the surgical operation.

[0153] Furthermore, after adjusting the path, the system uses a smoothing algorithm and re-optimization technology to ensure that the new path is operable during the operation. In order to prevent discontinuity or drastic changes in the adjusted path, the system uses an optimization function O(P new (t)) to smooth the path while maintaining an efficient surgical rhythm and operational safety. The system reduces sharp turns on the path by calculating the second-order derivative of the path, making the suturing process smoother. This can be expressed as:

[0154]

[0155] Furthermore, based on the smooth path, the system will further optimize the path according to the new feedback data to ensure the smoothness and stability of the path during surgery. The system will compare the difference between the adjusted path and the standard path and dynamically correct it to achieve the best surgical effect.

[0156] S400, using a high-precision mechanical device to perform a suturing operation, combined with real-time feedback information, to ensure the accurate implementation of the suturing route. Step S400 at least includes steps S410-S430:

[0157] S410, using a high-precision mechanical device to perform the planned suturing operation to ensure the accuracy of the suturing action. Specifically:

[0158] After the system completes the planning of the suturing path, all key suturing parameters (such as the location of the suturing point, the curvature of the path, the tension distribution, etc.) are transmitted to the high-precision mechanical device. The mechanical device is initially calibrated using the parameters to ensure that the suturing instrument is perfectly docked with the surgical environment. Before the operation begins, the system will calibrate the position of the mechanical device based on the three-dimensional coordinate data obtained from the image preprocessing module and the path planning module. This process includes the spatial positioning and angle adjustment of the robotic arm or automatic suturing device to ensure that the instrument can accurately reach each planned suturing point. Mechanical parameter setting: According to the input tissue tension and patient individual difference data T i and D i The system will adjust the mechanical parameters of the mechanical device, such as the force applied to each needle, the tension of the suture thread, etc., to ensure the accuracy and consistency of the operation.

[0159] Furthermore, during the operation, the mechanical device continuously adjusts its execution actions through real-time communication with the system to cope with minor changes in the surgical site. This real-time adjustment not only ensures the accuracy of the operation, but also greatly reduces human error. The system monitors the path execution during the operation through high-precision sensors to ensure that the mechanical device strictly follows the planned path P i If the sensor detects any deviation, the system will immediately adjust the motion trajectory of the robot arm to ensure the precise execution of each suture point. Combined with the real-time feedback data R(t), the system will continuously optimize the operation of the mechanical device during the execution process. As mentioned above, if the system detects a change in tissue tension, the mechanical device will automatically adjust the suturing force and speed to avoid excessive pulling or pressure on the tissue.

[0160] Furthermore, during operation, the mechanical device strictly follows the preset accuracy standards to ensure high consistency of the suturing action. This not only reduces intraoperative errors, but also ensures the stability of the postoperative effect. The system uses a closed-loop control algorithm to adjust the action of the mechanical device in real time to ensure that the mechanical parameters of each suture (such as the insertion depth, angle, and speed of the needle) remain consistent, thereby achieving a highly consistent suturing effect throughout the entire operation. The system corrects possible minor operational errors through continuous error detection and real-time compensation mechanisms. As described above, if the suture position is offset due to tissue movement or patient micro-movement, the system will immediately adjust the position and angle of the mechanical device to ensure the accuracy of the suture operation.

[0161] Furthermore, after the suturing operation is completed, the system evaluates the suturing results through sensors and image processing modules to ensure that all suturing points meet the expected medical standards and aesthetic requirements. The system will conduct a detailed inspection of each stitch through high-definition camera equipment and image analysis modules to ensure that the tightness and position of the suture line meet the expected standards. Based on the real-time feedback data after the operation, the system will generate a postoperative evaluation report and provide further adjustment suggestions when necessary to ensure the patient's postoperative recovery effect is optimal.

[0162] S420: During a complex or long suturing process, the system can automatically take over part of the suturing operation to reduce the doctor's fatigue and operating pressure.

[0163] Before the operation begins, the system automatically determines the degree of intervention of the mechanical assistance system by analyzing the complexity and expected duration of the operation. Based on the input patient data and surgical planning results, the system assigns specific suturing tasks to mechanical devices. According to the complexity of the operation and the doctor's operating habits, the system will decide whether to perform fully automated suturing or partially assisted suturing. For suturing sections that require long time and high precision, the system will give priority to automatic suturing devices. After the task is assigned, the system will assign the suturing path data P to the input suturing path data P. i , tissue tension T i and the individual difference parameter D of the patients i Initialize the working parameters of the automatic suturing device, such as needle length, suture thread tension, speed, etc.

[0164] Furthermore, when the suturing operation begins, the mechanical assistance system will automatically perform the suturing task according to the preset path and parameters. The system monitors the suturing process in real time through sensors to ensure that each step is consistent with the plan. During the execution process, the robotic arm or automatic suturing device will strictly follow the planned suturing path P i If any deviation is found in real-time monitoring, such as position changes caused by micro-movement of the patient, the system will immediately adjust the suturing path to ensure the accuracy of the operation. The system continuously monitors changes in tissue tension or other abnormal conditions (such as sudden changes in suture tension) during the suturing process through a feedback mechanism, and immediately adjusts the operating parameters of the robotic arm to ensure the quality and consistency of the suturing.

[0165] Furthermore, in the partially automated suturing mode, the system allows doctors to intervene in key operations or perform manual intervention when fine-tuning is required. The system dynamically adjusts the parameters of the automated suturing device based on the doctor's input data. The doctor can adjust the working state of the automated suturing device through a manual control interface or voice commands, such as adjusting the needle length or switching the suturing mode (such as switching from continuous suturing to intermittent suturing). The system will provide real-time feedback to the doctor on the current suturing progress and quality through visual or auditory signals, helping the doctor to make fine adjustments when necessary to ensure that every step of the operation meets the expected medical and aesthetic standards.

[0166] Furthermore, after the automated suturing is completed, the system evaluates the overall effect of the suturing through sensors and image analysis modules. The system generates a detailed surgical report and provides recommendations for follow-up care or adjustments if necessary. The system uses high-definition image data and sensor feedback to perform a detailed analysis of the tightness, uniformity, and position of each suture point to ensure that the suture quality meets the expected standards. Based on the automated evaluation results, the system can provide recommendations for postoperative care, such as whether the tightness of the suture needs to be adjusted, or whether additional suturing or loosening is required in certain areas.

[0167] S430, the system monitors the suturing operation performed by the machine in real time through sensors and feedback mechanisms to ensure high consistency with the planned path. If deviations or abnormalities are found, the system can immediately adjust the parameters of the mechanical operation to ensure the quality of the operation. This function ensures the stability and consistency of suturing during the operation and minimizes postoperative complications and scar formation. Specifically:

[0168] First, the early warning and control execution module continuously receives real-time data obtained from sensors on the crane, including but not limited to core data indicators such as temperature t, humidity h, dust concentration d, vibration data v, and the speed and position of the crane.

[0169] Furthermore, after the suturing operation begins, the system's built-in sensors (including high-precision displacement sensors, pressure sensors, etc.) collect key data during the suturing process in real time. The data includes the position of the robotic arm, the tension of the suture thread, and the feedback response of the patient's tissue. The real-time data will be compared with the pre-planned suture path P i The displacement sensor monitors the position of the robot arm or suture machine in three-dimensional space in real time to ensure that each suture point P i If the sensor detects that the robot arm deviates from the path, it will issue a correction command to adjust the movement trajectory of the robot arm. The system monitors the tension P of the suture thread through a pressure sensor. i, ensuring that the tension is within the preset range. If abnormal tension fluctuations are detected (such as too high or too low tension), the system will immediately adjust the suturing speed or force to prevent damage to the tissue.

[0170] Furthermore, the system quickly processes the collected real-time data and plans the path P i The system compares the position of the suture with other preset parameters. If the system detects any deviation or abnormality (such as position offset, abnormal tension, abnormal tissue response, etc.), the automatic adjustment mechanism will be triggered immediately. When the system detects a position deviation, it will calculate the offset δP(t) and adjust the path of the robot or suturer to ensure that the subsequent suture operation returns to the correct track. The adjusted path P new (t) will be updated in real time to adapt to the current surgical environment. If the system detects abnormal tension or the tissue response is not as expected, it will make corrections by adjusting the suture force or the tension of the suture to avoid unnecessary tissue damage or uneven tension.

[0171] Furthermore, the system continuously monitors the changes of all parameters during the suturing process through a closed-loop control mechanism, and continuously optimizes the suturing operation based on the feedback data. The mechanism ensures that the system can maintain a high degree of accuracy in the suturing operation even when slight changes occur at the surgical site. Through real-time monitoring and feedback, the system can automatically correct any detected deviations to ensure the continuity and accuracy of the suturing operation. If the system detects continuous tension fluctuations, it will immediately adjust the tension and speed of the suturer through a closed-loop control system to ensure uniform tension of the suture. The system continuously analyzes real-time feedback data, automatically compensates for slight errors in the operation, and ensures that the final suturing effect is highly consistent with the planned path. The compensation process may involve fine-tuning the movement of the robotic arm, adjusting the tension or speed of the suture, etc. All of the adjustments are performed in real time to ensure the surgical effect.

[0172] Furthermore, after the operation is completed, the system will review and evaluate the entire suturing process, recording all real-time monitoring data and adjustments. The data will be used for postoperative evaluation and further system optimization. The system will record and analyze all data from real-time monitoring (such as position, tension, adjustment history) to provide a detailed basis for postoperative evaluation. Based on the real-time data and adjustment history during the operation, the system will generate a postoperative evaluation report and, if necessary, make recommendations for further adjustments or follow-up care to ensure the best postoperative results.

[0173] Figure 2 FIG. 2 shows a structural block diagram of an intelligent guidance system for facial beauty suture routes according to an embodiment of the present application. Figure 2 As shown, the system may include:

[0174] High-definition image acquisition module: used to obtain high-definition images of the patient's face, especially for detailed capture of the wound area. The module collects image data in real time through high-resolution camera equipment to ensure image clarity, detail retention and color accuracy, providing high-quality basic data for subsequent processing.

[0175] Image preprocessing module: performs a series of optimization operations on the collected images, including denoising, contrast enhancement and brightness adjustment, to improve the usability and stability of the images. The preprocessed images have higher contrast and detail clarity, providing high-quality input data for feature extraction.

[0176] Feature extraction and data enhancement module: Use deep learning algorithms to analyze preprocessed images and automatically extract key features related to surgery, such as wound edge contours, depth information, skin texture, etc. At the same time, data enhancement technology is used to generate diverse image samples to improve the robustness of the system in different surgical scenarios.

[0177] Automatic suturing route planning module: Based on the extracted key features, combined with facial anatomy and aesthetic principles, the module automatically plans the optimal suturing route. This module uses a multi-objective optimization algorithm to ensure that the suturing route meets both medical standards and aesthetic requirements, and ultimately generates the optimal suturing solution.

[0178] Dynamic path optimization module: During the operation, real-time monitoring is performed and the suturing route is dynamically optimized based on the feedback data. The module collects real-time data of the operation through sensors, compares the current path with the expected path, and adjusts the path parameters in time to ensure the accuracy and stability of the suturing operation.

[0179] Guidance display module: displays the planned suturing route in three-dimensional or highlighted form in the surgical field, providing intuitive visual guidance to help doctors perform surgical operations accurately.

[0180] High-precision mechanical execution module: Use the mechanical arm or automatic suturing device to strictly follow the suturing route planned by the system. The module ensures the consistency and stability of the suturing action through the control of high-precision mechanical devices, reducing human errors in surgery.

[0181] Automated suturing support module: In long or complex surgeries, the system can take over part or all of the suturing operations, reducing the doctor's operating burden and improving surgical efficiency and stability. The module ensures the accuracy and consistency of suturing operations through real-time monitoring and adjustment.

[0182] Real-time feedback and path adjustment module: The sensor is used to monitor the execution status of the suturing process in real time. If an execution deviation or abnormality is detected, the system immediately adjusts the path or operating parameters to ensure the stability of the surgical effect and reduce the occurrence of postoperative complications.

[0183] Postoperative evaluation and feedback module: After the operation is completed, the system evaluates the suturing effect through sensors and image analysis modules, generates a postoperative report, and provides further adjustment suggestions when necessary to ensure the patient's postoperative recovery effect is optimal.

[0184] The key innovative features of the present invention include:

[0185] (1) Integrate high-definition image acquisition and intelligent image preprocessing to achieve accurate extraction of wound features.

[0186] (2) Automatic suturing path planning based on facial anatomy and aesthetic models provides personalized optimal suturing solutions.

[0187] (3) Dynamic path optimization and real-time feedback mechanism to ensure precise adjustment and execution of the suturing path during surgery.

[0188] (4) High-precision mechanical assistance system that automatically performs or assists in suturing operations, reducing the surgeon’s surgical burden and improving surgical accuracy.

[0189] The following are its main beneficial effects:

[0190] The present invention automatically plans and accurately guides the suture path in facial cosmetic surgery by combining facial wound images, anatomical structure data and aesthetic principles, significantly improving the accuracy and aesthetics of sutures. Advanced image processing algorithms and deep learning models are used to analyze facial structures in real time, and multi-objective optimization algorithms and dynamic path adjustment formulas are used to ensure that the suture path meets individualized anatomical structures and aesthetic standards. Compared with traditional suturing methods that rely on the doctor's experience, the present invention can effectively reduce human operation errors, reduce the risk of postoperative scar formation, and improve the overall effect of the surgery and patient satisfaction. At the same time, through real-time monitoring and dynamic adjustment mechanisms, the system can adapt to changes during the operation, ensure the accuracy and consistency of each suture, and further improve the safety and stability of the operation.

[0191] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various changes or substitutions within the technical scope disclosed in the present application, and the above should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. An intelligent guidance method for facial beauty suture route, characterized in that: The following steps are involved: S100, collecting images of the patient's facial wounds through a high-definition camera device, and performing data enhancement and preprocessing on the collected images to obtain key features related to the surgery; S200, based on the feature data extracted in step S100, using a deep learning algorithm combined with facial anatomy and aesthetic models, automatically generating a preliminary suturing route, and dynamically adjusting the route according to real-time feedback; Based on the key feature data extracted in step S100, a preliminary suturing route is generated by combining a deep learning algorithm with a facial anatomy and aesthetic model; Based on real-time feedback during the operation, the initial suturing route is dynamically adjusted to adapt to changes in the surgical environment; sensors are used to collect real-time data and the data is fed back to the path planning module for real-time adjustment of the initial suturing route; The adjusted suture path is optimized using a multi-objective optimization algorithm to generate a final suture plan that meets medical and aesthetic standards; the optimization process combines patient individual difference data and postoperative recovery prediction models to ensure the personalization and accuracy of the final suture path; S300, during the operation, displaying the suturing route generated in step S200 in the operation field in a three-dimensional highlighted manner, monitoring the operation progress in real time, and collecting and processing feedback data; S400. Based on the feedback data collected in step S300, a suturing operation is performed by a high-precision mechanical device, and operating parameters of the mechanical device are adjusted according to the feedback information to achieve precise suturing.

2. The method according to claim 1, characterized in that Step S100 includes: S110, using a high-resolution camera to collect images of the patient's facial wound in real time, and obtain fine structures of the wound and texture features of the surrounding skin; S120, performing denoising, contrast enhancement, and brightness adjustment on the collected image to ensure image clarity and stability, and provide high-quality images for subsequent feature extraction; S130. Based on the image processed in step S120, use a deep learning model to analyze and extract key feature data related to the surgery.

3. The method according to claim 1, characterized in that Step S200 includes: S210, based on the key feature data extracted in step S130, using a deep learning algorithm combined with facial anatomy and aesthetic models to automatically generate a preliminary suturing route; S220, dynamically adjusting the suturing path in combination with real-time feedback during the operation; S230, optimizing the adjusted suture path by using a multi-objective optimization algorithm.

4. The method according to claim 3, characterized in that The stitching path generation in step S210 includes: Based on the key feature vector extracted in step S130, preliminary path planning is performed in combination with the facial anatomical matrix; The preliminary path is combined with the aesthetic criterion vector to optimize the path.

5. The method according to claim 1, characterized in that Step S300 includes: S310, during the operation, the suturing route is superimposed and displayed in the doctor's surgical field of view in a three-dimensional manner, and is adjusted according to real-time feedback; S320, highlights key suture points and routes in the surgical field of view through highlight marking technology, and updates the display content in real time; S330, continuously collect data from the surgical site and feed it back to the path planning module.

6. The method according to claim 5, characterized in that The generation of the highlight mark in step S320 relies on real-time data input of the surgical environment, including the position of surgical instruments, the progress of the surgery, and slight changes in the patient's face.

7. The method according to claim 1, characterized in that Step S400 includes: S410, using a high-precision mechanical device to perform the planned suturing operation; S420, during a complex or long suturing process, the system can automatically take over part of the suturing operation; S430, monitoring the suturing operation performed by the machine in real time through sensors and feedback mechanisms.

8. The method according to claim 7, characterized in that The automatic suturing support system in step S420 includes an automatic suturing device and a robotic arm, which can automatically adjust the suturing mode according to the complexity of the operation and the doctor's operating habits.

9. The method according to claim 8, characterized in that The real-time monitoring in step S430 includes a displacement sensor and a pressure sensor, which monitors the position of the robot arm and the tension of the suture thread during the suturing process in real time, and immediately adjusts the suturing operation parameters when deviations or abnormalities are detected.

10. The method according to claim 7, characterized in that After the surgery is completed, the system will generate a detailed surgical report and provide postoperative care and adjustment recommendations when necessary to ensure the patient's postoperative recovery is optimal.

Images