An intelligent simulation method and system for a facial microplasty operation

Abstract

The application discloses a kind of intelligent simulation simulation method and system of facial microplasty operation, it is related to image processing technical field, the intelligent simulation simulation method is by obtaining high-precision facial data, and accurately calibrates facial defect site, and after facial three-dimensional image data is handled by normalization, key facial features are extracted by deep learning algorithm, provide basis for microplasty scheme.Different types of data are integrated by intelligent fusion technology, form comprehensive facial analysis atlas, support virtual simulation and surgical effect evaluation.Then automatically generate personalized surgical plan, predict postoperative effect, provide accurate operation strategy, such as material selection, injection depth and complication risk, significantly reduce surgical risk.System combines patient feedback, real-time adjustment scheme, and postoperative effect evaluation is carried out, ensure that effect meets expectation.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image processing, in particular to an intelligent simulation method and system for facial microplasty operation. BACKGROUND

[0002] In recent years, with the development of intelligent technology and computer simulation technology, more and more medical fields begin to use virtual simulation technology for preoperative simulation and planning. In particular, in the field of facial microplasty, intelligent simulation based on three-dimensional facial data of patients has gradually attracted attention.

[0003] However, in the existing simulation method, due to the great difference in facial muscles, fat, skin and other tissues of different individuals, the simulation effect of facial microplasty is limited in precision, which makes it difficult to avoid the damage risk of injection operation to the nerve and to accurately grasp the content of the filling or dissolving material, affecting the acceptance of the microplasty simulation result by the patient.

[0004] In summary, how to integrate more detailed facial anatomical information into the intelligent simulation process to accurately locate the facial defect site and reduce the risk of facial nerve damage and material injection is an urgent problem to be solved and optimized in the intelligent simulation system. SUMMARY

[0005] The present application provides an intelligent simulation method and system for facial microplasty operation, which solves the technical problem of how to integrate more detailed facial anatomical information into the intelligent simulation process to accurately locate the facial defect site and reduce the risk of facial nerve damage and material injection.

[0006] To solve the above technical problems, the present application provides an intelligent simulation method and system for facial microplasty operation, and the specific technical solutions are as follows:

[0007] In a first aspect, an intelligent simulation method for facial microplasty operation is provided, comprising the following steps:

[0008] Obtaining patient facial data, a plurality of facial defect feature data and a plurality of defect structure anatomical information data; and normalizing, extracting features and encoding processing each data;

[0009] Fusing and virtually simulating the processed each data to obtain a plurality of microplasty scheme information data; constructing the facial data, the plurality of facial defect feature data, the plurality of defect structure anatomical information data and the plurality of microplasty scheme information data into a facial microplasty prediction model;

[0010] The facial micro-reshaping prediction model can output a prediction result of micro-reshaping scheme information data corresponding to the defect structure dissection information data of the facial defect feature data;

[0011] Based on the prediction result of the facial micro-reshaping prediction model, an individualized facial micro-reshaping prediction scheme is obtained, and a surgical precise operation strategy is obtained based on the facial micro-reshaping prediction scheme, so as to provide a doctor-patient interactive feedback and evaluate the postoperative effect of micro-reshaping.

[0012] As a further optimization scheme of the present application, patient facial data is acquired, and a three-dimensional facial model of the patient is constructed; the three-dimensional facial model is analyzed to obtain a plurality of facial defect feature data, which is combined into a facial defect feature data set;

[0013] The plurality of facial defect feature data is positioned and marked to obtain a defect marking data set; and each facial defect feature data item in the defect marking data set is subjected to structure dissection to obtain a defect structure dissection information data set.

[0014] As a further optimization scheme of the present application, the three-dimensional facial model is analyzed to obtain a plurality of facial defect feature data combined into a facial defect feature data set, which comprises:

[0015] Based on the patient facial data, three-dimensional facial information data of the patient is obtained; the three-dimensional facial information data is preprocessed to obtain preprocessed three-dimensional facial information;

[0016] The preprocessed three-dimensional facial information is subjected to point cloud or grid processing to construct a three-dimensional facial model; facial feature data is obtained by extracting facial features from the three-dimensional facial model;

[0017] Facial defect feature data is obtained by detecting facial defects from the facial feature data; and different types of facial defect feature data are summarized to obtain a facial defect feature data set.

[0018] As a further optimization scheme of the present application, each facial defect feature data item in the defect marking data set is subjected to structure dissection to obtain a defect structure dissection information data set, which comprises:

[0019] The defect structure dissection information data set comprises spatial position and structure information data of facial defect skin layer, subcutaneous tissue layer, muscle layer, nerve direction and blood vessel distribution; the spatial position and structure information data contains the adhesion relationship between the spatial positioning and structure information of each layer and the layer thickness and width;

[0020] According to the obtained spatial position and structure information data, simulation is performed in combination with skin laxity, fat distribution and fat content of the patient, so that the facial simulation three-dimensional image is matched with the facial anatomical structure information data to obtain a matching result.

[0021] Based on the matching result, defect structure anatomical image data is obtained; the defect region anatomical structure of each defect structure anatomical image data is divided, and the divided defect region is partitioned and marked to accurately locate the position of each defect region anatomical data item.

[0022] As a further optimization scheme of the present application, the defect region anatomical structure of each defect structure anatomical image data is divided, and the divided defect region is partitioned and marked to accurately locate the position of each defect region anatomical data item, comprising:

[0023] For each defect region in the defect structure anatomical image data, the adjacent pixel points are connected together to form different defect partitions by C i ={p|I(p)=1+C(p,C j )}.

[0024] Wherein, C i represents the i-th connected region, p represents a pixel point in the image, I(p) represents the pixel vector of the pixel, C(p,C j ) represents the connected vector of pixel p and region C j .

[0025] The spatial position and structure information data of the facial defect skin layer, subcutaneous tissue layer, muscle layer, nerve direction and blood vessel distribution are topologically analyzed to divide the defect region into different structure layers and remove noise and connected broken defect regions.

[0026] The different structure layers are marked to accurately obtain the intersection points of the muscle layer, nerve direction and blood vessel distribution in the same defect region.

[0027] As a further optimization scheme of the present application, the shape of the obtained facial defect is detected to obtain two defect characteristic shapes of concave and convex, and the facial defect spatial volume is obtained by and respectively; in the formula, V1 represents the concave characteristic spatial volume, V2 represents the convex characteristic spatial volume, h1 represents the depth of the concave, h2 represents the height of the convex defect characteristic, r1 represents the inner diameter of the concave, r2 represents the inner diameter of the bottom of the convex, and L represents the top width of the convex.

[0028] According to the facial defect spatial volume, in combination with the skin laxity, fat distribution and fat content of the patient, G=(V×ρ 材料) x (1+k) to obtain the injection micro-integrated material content required for facial defects; in the formula, G represents the required injection micro-integrated material content value, V represents the recessed feature space volume V1 or the convex feature space volume V2, p 材料 represents the injection material density, and k represents the facial absorption rate correction coefficient.

[0029] According to the interlaced point of the muscle layer, the nerve direction and the blood vessel distribution in the same defect area, the micro-integrated material is accurately injected into the facial defect area of the patient, the simulation animation is displayed, the patient intuitively receives the operation process and interacts with the doctor to avoid the operation risk.

[0030] As a further optimization scheme of the present application, the facial micro-integrated prediction model comprises:

[0031] The obtained various facial defect feature data, various defect structure dissection information data and micro-integrated scheme information data sets are generated into structure data, and the structure data is encoded into sequence data to train the facial micro-integrated prediction model;

[0032] The sequence data is input into the facial micro-integrated prediction model; the facial micro-integrated prediction model comprises an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer, the intermediate representation data of the multiple hidden layers are transmitted to the output layer, and the output layer outputs the micro-integrated scheme information data recognition result corresponding to the defect structure dissection information data of the facial defect feature data set;

[0033] The newly obtained at least one facial defect feature data is input into the facial micro-integrated prediction model to output the micro-integrated scheme information data prediction result corresponding to the defect structure dissection information data of the facial defect feature data.

[0034] As a further optimization scheme of the present application, according to the prediction result of the facial micro-integrated prediction model, the corresponding micro-integrated scheme information data is obtained, and the corresponding micro-integrated scheme information data is compared with the historical similar facial defect feature micro-integrated scheme information data to obtain a comparison result;

[0035] Based on the comparison result, fine difference data is obtained, the fine difference data is subjected to correlation analysis to obtain a fine difference influence factor, and the facial micro-integrated prediction model parameters are further iteratively updated according to the fine difference influence factor to accurately obtain the micro-integrated personalized operation scheme prediction result;

[0036] The fine difference influence factor includes patient face shape features, facial features, age, gender and personalized needs, the output micro-integrated scheme information data prediction result is adjusted in real time to obtain a preliminary operation scheme;

[0037] According to the micro-integration scheme information data prediction result, a feedback information of a surgical effect diagram and a facial change curve is generated to iteratively optimize the preliminary surgical scheme and obtain a final micro-integration surgical scheme.

[0038] As a further optimization scheme of the application, the surgical precision operation strategy comprises:

[0039] According to the differences in the interweaving points of the muscle layer, nerve direction and blood vessel distribution of the facial defect anatomy structure in the same defect area, and the direction of the three major facial nerves, a micro-integration surgical path is customized to avoid the dense nerve interweaving area.

[0040] In a second aspect, the system provides an electronic device including a memory, a processor, and a facial micro-integration surgical operation intelligent simulation method program stored in the memory and executable on the processor. When the facial micro-integration surgical operation intelligent simulation method program is executed by the processor, the steps of the facial micro-integration surgical operation intelligent simulation method are implemented. The system includes:

[0041] The data acquisition module is used to acquire patient facial data, various facial defect feature data, and various defect structure anatomy information data;

[0042] The preprocessing module is used to normalize, extract features, and encode each data;

[0043] The simulation and simulation module is used to fuse and virtually simulate the processed data to obtain various micro-integration surgical scheme information data;

[0044] The model construction module is used to construct the facial data, various facial defect feature data, various defect structure anatomy information data, and various micro-integration surgical scheme information data into a facial micro-integration prediction model;

[0045] The scheme prediction module is used to output the prediction result of the micro-integration scheme information data corresponding to the defect structure anatomy information data of the facial defect feature data from the facial micro-integration prediction model;

[0046] The feedback evaluation module is used to obtain an individualized facial micro-integration prediction scheme based on the prediction result of the facial micro-integration prediction model, and obtain a surgical precision operation strategy based on the facial micro-integration prediction scheme for doctor-patient interaction feedback and evaluation of the micro-integration postoperative effect.

[0047] The present application has at least the following beneficial effects: the present application obtains high-precision data of the patient's face through various advanced image acquisition technologies (such as 3D face scanning, CT or MRI imaging, etc.), including facial anatomical structure, fat layer, muscle layer, nerve distribution, skin laxity and other characteristic information; facial defect information (such as wrinkles, facial depression, laxity, etc.) and the specific location, depth, etc. of the defect are accurately marked and matched with the patient's anatomical feature data, ensuring that the personalized defect site of each patient can be clearly defined.

[0048] By normalizing different sources and formats of facial data, the data has a unified standard, thereby avoiding the deviation caused by inconsistent data sources. This process can effectively improve the accuracy of data processing and the reliability of subsequent modeling; through deep learning algorithm or machine learning model, the facial data is feature extracted, and the key features of the face (such as fat layer thickness, skin laxity, muscle position, etc.) are extracted. These features can provide important basis for the generation of subsequent micro-surgery plan.

[0049] Different types of data (such as facial anatomical structure data, defect feature data, anatomical information data, etc.) are integrated through intelligent data fusion technology (such as multi-modal learning), thereby forming a comprehensive facial analysis atlas. This process can ensure that the relationship between data is fully explored and provide accurate basis for generating surgical plans; after processing the data, the effect of facial micro-surgery can be simulated, and the effect of different operation modes and surgical plans in the virtual environment can be evaluated. This process can realize the comparison and optimization of multiple micro-surgery plans, helping doctors choose the best plan; according to the facial features and defect data of the patient, the system can automatically generate multiple micro-surgery plans, and provide personalized treatment recommendations according to the expected effect and risk of each plan. This can greatly reduce the error of preoperative judgment and reduce unnecessary surgical risks.

[0050] Based on big data and deep learning model, all processed data (facial anatomical data, defect features, anatomical information, surgical plans, etc.) are fused and constructed into a facial micro-integration prediction model. The model can predict the micro-surgery plan of the facial defect site according to the specific situation of the patient and output its corresponding surgical effect; through the prediction results of the model, doctors can obtain detailed personalized surgical plans, including the amount of material used, injection depth, accurate injection point position, possible complications, etc. This prediction process can effectively avoid the uncertainty in traditional surgical plans, greatly reducing the risk of surgery.

[0051] Based on the output results of the facial micro-reshaping prediction model, personalized micro-reshaping operation plans can be generated. Each plan is tailored to the patient's facial features, defect locations, and muscle and fat distribution, etc. to ensure maximum compliance with the patient's needs; according to the personalized micro-reshaping plan, precise operation strategies are generated, which include specific steps, material selection, injection position, injection depth and pressure, etc. This operation strategy can provide doctors with an accurate execution framework and reduce the randomness and risk during the operation.

[0052] Through the interaction between the system and the patient, the patient can provide real-time feedback on their needs and expectations, and the doctor can adjust the operation plan according to the feedback information. In addition, real-time evaluation of the postoperative effect, combined with virtual simulation technology, can help doctors compare and adjust the postoperative effect to ensure that the postoperative effect meets the expectations. BRIEF DESCRIPTION OF DRAWINGS

[0053] Figure 1 is an intelligent simulation method flow diagram of facial micro-reshaping operation provided by an embodiment of the present application;

[0054] Figure 2 is an intelligent simulation system diagram of facial micro-reshaping operation provided by an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following detailed description of the application will be further described with reference to the accompanying drawings, it is necessary to point out here that the following detailed description is only used to further illustrate the application, and cannot be understood as limiting the scope of protection of the application, and those skilled in the art can make some non-essential improvements and adjustments to the application according to the above application content.

[0056] The intelligent simulation method and system of facial micro-reshaping operation provided by the embodiment are as follows:

[0057] As shown in Figure 1 , an intelligent simulation method of facial micro-reshaping operation includes the following steps:

[0058] Step 11, obtaining patient facial data, multiple facial defect feature data and multiple defect structure dissection information data;

[0059] Step 12, normalizing, feature extracting and encoding processing each data;

[0060] Step 13, fusing and virtually simulating the processed each data to obtain multiple micro-reshaping operation plan information data;

[0061] Step 14, facial data, multiple facial defect feature data, multiple defect structure anatomical information data and multiple micro-integrated surgery scheme information data are constructed into a facial micro-integrated prediction model;

[0062] Step 15, the facial micro-integrated prediction model can output the prediction result of the micro-integrated scheme information data corresponding to the defect structure anatomical information data of the facial defect feature data;

[0063] Step 16, based on the prediction result of the facial micro-integrated prediction model, an individualized facial micro-integrated prediction scheme is obtained; based on the facial micro-integrated prediction scheme, an operation precise operation strategy is obtained for doctor-patient interaction feedback and evaluation of micro-integrated postoperative effect.

[0064] In the implementation of the present application, step 11 obtains the facial data of the patient through facial scanning equipment, digital facial photography, 3D modeling or other medical imaging technology. These data can include the patient's facial contour, skin condition, facial proportion; based on the facial scanning data, the features of facial defects such as wrinkles, scars, uneven skin color, facial symmetry are extracted; detailed anatomical data of facial structure is obtained through medical imaging or professional equipment, including but not limited to skeletal structure, muscle distribution, skin level information data; the accurate data of the patient's face provides a real basis for subsequent micro-integrated surgery scheme, ensuring the individualization of diagnosis and treatment; by comprehensively collecting different levels of facial data, the patient's facial problems can be accurately analyzed to avoid missed diagnosis; detailed facial anatomical structure data is provided for doctors to help better understand the root cause of facial defects.

[0065] Step 12 normalizes different types of data (facial images, defect features, anatomical information) to be within a unified scale range, usually adjusting the data to be between 0 and 1, reducing the influence of different data scales on model training; through image processing, machine learning or deep learning algorithm, key facial features and defect information such as facial expression features, skin condition, specific type and location of defects are extracted; the extracted features are converted into machine-readable numerical format (such as numerical encoding, one-hot encoding, etc.), which can help subsequent algorithms to process data; normalization helps to unify the scale between different data types, making the machine learning model more efficient and stable during training; feature extraction can filter out the most recognizable data points to improve the prediction accuracy of the model; after encoding, the data can be effectively read by the machine learning model to ensure that the subsequent algorithm can work smoothly.

[0066] Step 13: Fuse various data (facial data, defect features, anatomical information) to generate a comprehensive data set; these data can be combined through weighted average, principal component analysis (PCA), and multi-modal learning methods to produce a more comprehensive patient facial information; use computer graphics and virtual reality technology to simulate surgery based on the fused data, demonstrate the possible impact of different micro-integration surgery plans on the patient's face, and generate multiple surgery plan information; data fusion can integrate multi-dimensional information to provide more accurate facial features and defect profiles for doctors; virtual simulation allows patients to see the impact of different plans on facial appearance in advance, helping doctors provide personalized micro-integration recommendations; virtual simulation can predict the effectiveness of surgery, helping patients and doctors make more appropriate choices.

[0067] Step 14: Input the various data (facial data, defect features, anatomical information) obtained in steps 11 and 12, together with the surgery plan information generated by virtual simulation, into a machine learning model. Through training these data, a facial micro-integration prediction model is established. This model will be able to predict suitable micro-integration surgery plans based on the input patient facial information; through model training and learning, it can quickly and accurately analyze patient facial information and provide personalized surgery recommendations; reduce the subjective errors of doctors in data processing and plan selection, and improve the accuracy of medical decision-making.

[0068] Step 15: The model predicts based on the patient's facial defect features and anatomical data, and outputs micro-integration surgery plans that match the patient's facial problems. These plans will include specific surgery types, treatment methods, and surgery steps; through model output, doctors can customize the best treatment plan for each patient, avoiding one-size-fits-all treatment methods; precise prediction can help select the most suitable micro-integration plan for the patient, improving surgical effectiveness and patient satisfaction.

[0069] Step 16: Based on the prediction results of the facial micro-integration prediction model, a complete micro-integration surgery plan is generated, and operation strategies are provided for doctors; detailed operation guidelines are provided for doctors regarding surgery steps, methods, and precautions. Patients can also participate in feedback and discussion through the doctor-patient interaction platform to help adjust the plan; based on post-surgery feedback information and evaluation results, future micro-integration plans are further optimized; through personalized micro-integration prediction plans, the best treatment effect can be ensured for each patient; through postoperative evaluation and feedback, doctors can adjust the plan in real time to continuously improve the success rate of surgery; through doctor-patient interaction, patients can better understand the treatment process and effect, thereby enhancing trust and satisfaction.

[0070] In a preferred embodiment of the present application, step 11 further includes:

[0071] Step 111, obtaining patient facial data, constructing a three-dimensional facial model of the patient; analyzing the three-dimensional facial model to obtain a variety of facial defect feature data into a facial defect feature data set;

[0072] Step 112, positioning and marking the plurality of facial defect feature data to obtain a defect marking data set; structurally dissecting each facial defect feature data item in the defect marking data set to obtain a defect structural dissection information data set.

[0073] In the implementation of the present application, step 111 obtains detailed data of the patient's face through various sensors (such as 3D scanners, stereo cameras, depth sensors, etc.). These data can include facial contour, muscle structure, skin texture, etc. information; using the obtained data, through computer vision and three-dimensional modeling technology (such as point cloud reconstruction, surface fitting, etc.), two-dimensional image data is converted into a three-dimensional facial model. This three-dimensional model not only reflects the appearance of the face, but also presents the depth information of the face, which is convenient for further analysis; the structure and features of the three-dimensional model are analyzed by algorithm (such as image processing, machine learning, computer vision). Mainly from the facial morphology to extract feature points (such as the contours of eyes, nose, mouth, the height of zygomatic bone, etc.), identify the subtle defects of the face, and construct a multi-dimensional defect feature data set; the three-dimensional facial model can help doctors or technicians more accurately identify the subtle defects of the face, avoiding the distortion that may occur in traditional two-dimensional images; the facial features of each person are quite different, and three-dimensional modeling can provide detailed analysis for individuals, thereby providing data support for subsequent treatment, plastic surgery, and customized medical treatment; the facial defect feature data set obtained by analysis can automatically detect and mark defects, providing effective basis for subsequent repair or treatment.

[0074] Step 112 is based on the multi-dimensional defect data set obtained in step 111. The system automatically marks the facial defect area, such as wrinkles, spots, moles, facial asymmetry, etc. through algorithm. These defect features are located in specific facial areas (such as forehead, eye corner, lip, etc.), generating a defect marking data set; further structural analysis of these defects is performed. For example, analyze the depth of wrinkles, the size of moles, the degree of skin relaxation, etc., or obtain more detailed dissection data through CT scanning, MRI, etc. medical imaging technology. These data are converted into "anatomical information data set", which is detailed structural analysis data of facial defects; positioning and marking can help doctors or technicians quickly and accurately identify and distinguish the specific location and type of facial defects, thereby helping to develop treatment plans; through anatomical analysis of facial defects, more dimensional data can be obtained to better understand the causes and nature of the defects; through detailed defect marking and anatomical information, personalized treatment or repair plans can be developed for patients to ensure more accurate and efficient results.

[0075] In a preferred embodiment of the present application, the three-dimensional face model in step 111 is analyzed to obtain a plurality of face defect feature data to form a face defect feature data set, including:

[0076] Step 1111, based on the patient face data to obtain three-dimensional face information data; the three-dimensional face information data is preprocessed to obtain preprocessed three-dimensional face information;

[0077] Step 1112, the preprocessed three-dimensional face information is processed by point cloud or grid to construct a three-dimensional face model; the face feature data is extracted from the three-dimensional face model to obtain face feature data;

[0078] Step 1113, the face defect feature data is detected to obtain face defect feature data; different types of face defect feature data are summarized to obtain face defect feature data set.

[0079] In the embodiment of the present application, step 1111 obtains a high-precision three-dimensional face model;

[0080] 3D scanning, using a three-dimensional scanner to scan the face to obtain point cloud data;

[0081] Stereovision, using two or more cameras to shoot face images from different angles, and using stereoscopic matching algorithm to reconstruct three-dimensional model;

[0082] Depth sensor, such as Kinect, LiDAR and other sensors, can also obtain three-dimensional information of face directly through depth map; the generated three-dimensional face information is usually in the form of point cloud or grid.

[0083] Processing the original three-dimensional data, including:

[0084] Noise removal, noise or irregular points may occur in the process of three-dimensional model scanning, which need to be removed by Gaussian filter; point cloud registration, when multiple view point cloud data is obtained, they are aligned and combined based on iterative closest point (ICP) algorithm; grid reconstruction, point cloud is converted into triangular grid model by Poisson reconstruction or Delaunay triangulation method;

[0085] Based on the preprocessed face data in step 1111, the geometric features of the face are crucial for identifying face defects; through ASM algorithm or AAM algorithm, the face feature points (such as eye, nose, mouth and other positions) are calibrated on the three-dimensional face model; for two-dimensional image, through E=∑ i ||I(x i )-T(x i || 2; find the key points by minimizing the objective function; where I(x i ) represents the pixel value of the input image, T(x i ) represents the texture of the target model at the x i position, E represents the key points of the facial features, and i represents the i-th facial feature point;

[0086] By calculating the geometric features of the face mesh, such as curvature, normal vector, face symmetry, etc., deeper information can be obtained, the curve shape of the face is described by the Gaussian curvature and average curvature of the geometric feature vertices of each face network, and the surface direction of each vertex is described by the normal vector of the vertex;

[0087] Based on step 1112, through step 1113, by analyzing the left and right symmetry of the face, deformities caused by diseases, trauma or congenital defects can be detected; symmetry detection can be evaluated by calculating the Euclidean distance between the left and right symmetric points; facial defects may include but are not limited to spots, scars, acne, depressions, deformities, etc. Detection of facial defects;

[0088] The gradient of the image is calculated using the Sobel operator or the Laplacian operator to detect edges or discontinuous regions, and the local features of the depth map, texture image or mesh model are used to detect the defects of the face, for example, morphological operations (dilation, erosion, etc.) are used to enhance the defect area, and then the area of the defect is detected by thresholding;

[0089] The above extracted facial geometric features, symmetry detection, defect area and other information are collected into a multi-dimensional feature data set. Each record of the data set can include:

[0090] The spatial coordinates (x, y, z) of the key points; the facial geometric features (such as curvature, normal vector); the facial symmetry information; the defect label (such as the label of whether there is a scar or acne); the size, shape and location details of the defect; these feature data sets can be used for machine learning model training to help the system automatically identify and classify different types of facial defects.

[0091] In a preferred embodiment of the present application, the defect feature data items in the defect label data set in step 112 are subjected to structural dissection to obtain a defect structural dissection information data set, which includes:

[0092] Step 1121, the defect structural dissection information data set includes the spatial position and structural information data of the skin layer, subcutaneous tissue layer, muscle layer, nerve direction and blood vessel distribution of the facial defect; the spatial position and structural information data contains the adhesion relationship between the spatial positioning and structural information of each layer and the layer thickness;

[0093] Step 1122, according to the acquired spatial position and structure information data, combined with the skin laxity, fat distribution and fat content of the patient, simulation is carried out; so that the facial simulation three-dimensional image is matched with the facial anatomical structure information data, to obtain a matching result;

[0094] Step 1123, based on the matching result, to obtain the defect structure anatomical image data; the defect area anatomical structure of each defect structure anatomical image data is divided, and the divided defect area is partitioned and marked, so as to accurately determine the position of each defect area anatomical data item.

[0095] In the implementation of the present application, step 1121 first, the different levels of information of the face are collected and organized into a data set, including:

[0096] Skin layer, the condition of the facial surface skin, such as thickness, tightness;

[0097] Subcutaneous tissue layer, fat layer under the skin, affecting the contour and volume of the face;

[0098] Muscle layer, distribution, thickness and functional changes of facial muscle tissue;

[0099] Nerve layer, related to the distribution and function of facial nerves, which may affect facial expression and movement;

[0100] Vascular layer, vascular distribution, especially the microvascular condition of the face.

[0101] The spatial position and structure information of each layer are extracted and recorded, and the mutual adhesion relationship between each layer (for example, the adhesion of the skin layer and the subcutaneous tissue layer, etc.) and the layer thickness, width and other data are also recorded in detail; through the accurate modeling of different levels of the face, the function of each layer and its influence on defects can be more comprehensively understood; this can help doctors or professionals understand how skin, muscle, nerve, blood vessel and other levels affect each other, help diagnose the root cause of defects; analysis of these data can better predict facial changes, especially skin laxity, fat distribution changes and other problems during the aging process.

[0102] Step 1122 uses three-dimensional simulation technology to simulate the face based on the spatial position and structure information data obtained in step 1121 and the specific facial features of the patient (such as skin laxity, fat distribution, fat content, etc.). During the simulation process, by comparing the patient's facial anatomical structure information with the three-dimensional image, the simulation parameters are adjusted to make the simulation results consistent with the actual facial structure. This process may use deep learning, machine learning, and other technologies to optimize the simulation effect and ensure the accuracy of the simulation results. By combining the specific data of the individual patient, the simulation can provide accurate facial dynamics and structural performance, making the simulation process more personalized and realistic. Doctors can see the changes in the face in advance through the simulation results, helping them make precise decisions in treatment or surgical plans and reducing risks. Through the automated matching process, human errors can be reduced to ensure that the simulation image is consistent with the actual facial anatomy as much as possible, improving the effectiveness of subsequent treatment.

[0103] Step 1123 forms detailed anatomical images of facial defects based on the matching results obtained in step 1122. These images not only include the anatomical information of each layer of the face, but also show the specific performance of defects (such as wrinkles, sagging, fat accumulation, muscle relaxation, etc.) in these layers. Through further analysis of the defect area, the defect area in the facial anatomical image is partitioned. For example, analyze whether the wrinkles in a certain part are related to skin laxity, fat distribution, or muscle relaxation. The anatomical structure of each region will be divided separately according to its characteristics. Label the partitioned defect area to ensure that each defect data item accurately corresponds to a specific facial anatomical site. This process is automatically implemented through algorithms to avoid errors in manual operations and accurately mark the specific site of the defect area. Through accurate anatomical images and labeling, doctors can clearly understand the specific location and impact range of each defect, providing more scientific data support for subsequent treatment. By partitioning and labeling the defect area, detailed anatomical analysis can be provided for each defect area to help doctors identify the underlying causes. Based on the precise positioning of the defect and anatomical data, doctors can develop more personalized treatment or surgical plans to improve the success rate and effectiveness of treatment.

[0104] In a preferred embodiment of the present application, the defect area anatomical structure of each defect structure anatomical image data is divided in step 1123, and the divided defect area is partitioned and labeled to accurately locate the defect area anatomical data item, including:

[0105] Step 11231, for each defect area in the defect structure anatomical image data, through C i = {p | I (p) = 1 + C (p, C j )}, connect adjacent pixel points together to form different defect partitions;

[0106] wherein C i represents the i-th connected region, p represents a pixel point in the image, I(p) represents the pixel vector of the pixel, C(p,C j ) represents the connected vector of pixel p and region C j .

[0107] Step 11232, topological analysis is performed on different defect partitions according to the spatial position and structural information data of the facial defect skin layer, subcutaneous tissue layer, muscle layer, nerve direction and blood vessel distribution, so that the defect region is divided into different structural layers, and noise and disconnected defect regions are removed;

[0108] Step 11233, different structural layers are marked to accurately obtain the interlaced point of the muscle layer, nerve direction and blood vessel distribution in the same defect region.

[0109] In the implementation of the present application, step 11231 connects adjacent pixel points in the defect region of each defect structure dissection image data using image processing technology. This process is achieved through a "connectedness analysis" method, which generally identifies continuous regions in the image through algorithms, and then determines which pixel points belong to the same defect region. According to the connection of adjacent pixel points, the facial defect region is automatically divided into different "partitions". These partitions represent different parts of the facial defect in the image, and are divided according to spatial position, shape, color and other characteristics. By automatically identifying and connecting adjacent pixel points, different defect regions can be quickly and accurately divided, reducing subjective bias and inconsistency of manual division. Automatic partitioning technology can greatly improve the analysis speed, especially when faced with complex facial images, it can quickly obtain clear defect regions, saving time for subsequent processing. Through connectedness analysis of adjacent pixel points, isolated noise points in the image can be effectively avoided, ensuring that the divided defect regions are more representative and accurate.

[0110] Step 11232 Topological analysis is a mathematical method used to analyze the structural relationships in an image, particularly when dealing with image segmentation, it helps to more accurately define the relative positions and connectivity between regions. In this step, the system uses spatial location and structural information data of facial defects (including skin layer, subcutaneous tissue layer, muscle layer, etc.) for topological analysis; In the facial dissection image, there may be some pseudo-defect regions or image noise, especially due to lighting changes or texture differences. Through topological analysis, the system can identify and remove these non-real noise regions. At the same time, for the defect regions with broken connections, topological analysis can reconnect the broken parts to ensure the integrity of each defect region; Through topological analysis, the defect regions can be accurately divided into different anatomical levels (such as skin layer, fat layer, muscle layer, nerve layer and blood vessel layer) according to the spatial positioning and structural information between different tissue layers, which helps to analyze the depth and level of facial defects in detail; Through topological analysis, irrelevant noise and pseudo-defects in the image can be effectively eliminated to ensure the purity and accuracy of the segmentation results; For defect regions with broken or irregular shapes, topological analysis can repair these missing areas, making the defect regions more coherent and consistent; By distinguishing different anatomical layers, the deep reasons for facial defects can be better understood, such as some defects may be caused by skin laxity, while others may involve fat distribution or muscle relaxation.

[0111] Step 11233 Based on the results of steps 11231 and 11232, the segmented facial defect regions are labeled by layer. The purpose of this step is to clearly mark the specific tissue layer (such as skin layer, muscle layer, nerve layer, blood vessel layer) to which each defect region belongs; Different tissue layers of the face are usually interwoven, especially between muscle, nerve and blood vessel layers. By analyzing facial dissection data and spatial location, these interwoven points can be accurately located, i.e. the intersection points of different levels within the same defect region are marked. Through this accurate labeling, it can be clearly known which areas involve multi-level structural interweaving; The hierarchical labeling of different structural layers can clearly show the hierarchical information of each defect region, so that subsequent treatment can more accurately target specific tissue layers for intervention; By accurately marking the interwoven points, doctors or professionals can understand the relationship between different levels of structure and their role in the defect region. For example, the intersection of nerve and blood vessel layers may involve facial sensation and motor function, so special attention is needed during treatment; Accurate positioning of the intersection point is crucial for developing personalized treatment plans, especially when performing facial plastic surgery, anti-aging treatment, etc. Accurate hierarchical analysis can help doctors better control the depth and range of treatment and avoid damaging important structures such as nerves and blood vessels.

[0112] In a preferred embodiment of the present application, step 11233 further comprises:

[0113] In step 112331, shape detection is performed on the acquired facial defects to obtain both concave and convex defect feature shapes, and the spatial volumes of the defects are obtained by and respectively; wherein V1 represents the spatial volume of the concave feature, V2 represents the spatial volume of the convex feature, h1 represents the depth of the concave feature, h2 represents the height of the convex defect feature, r1 represents the inner diameter of the concave feature, r2 represents the inner diameter of the bottom of the convex feature, and L represents the width of the top of the convex feature.

[0114] In step 112332, the spatial volume of the facial defect is combined with the skin laxity, fat distribution, and fat content of the patient to obtain the required injection micro-filler content of the facial defect by G=(V x p 材料 ) x (1+k); wherein G represents the required injection micro-filler content value, V represents the spatial volume V1 of the concave feature or the spatial volume V2 of the convex feature, p 材料 represents the density of the injection material, and k represents the absorption correction coefficient of the face.

[0115] In step 112333, the muscle layer, nerve path, and blood vessel distribution are used to determine the intersection points in the same defect area, and the micro-filler is precisely injected into the facial defect area of the patient. Through the simulation of the moving picture, the patient can intuitively receive the surgical process and interact with the doctor to avoid surgical risks.

[0116] In the implementation of the present application, step 112331 uses advanced image processing technology or 3D scanning technology to accurately measure the face. By detecting the concave and convex features of the facial defects, the system can quantitatively analyze the irregular areas of the face and further extract the spatial volumes of these defect areas. Specifically, the shapes and volumes of the concave and convex features can reflect the depth and severity of the patient's facial defects. Through high-precision measurement of the defect area, the doctor can accurately determine the specific location that needs to be repaired, avoiding errors. The facial defects can be quantified, avoiding relying solely on subjective observation and improving the accuracy of the operation. A customized treatment plan is developed for each patient, and appropriate micro-filler is selected based on the different defect volumes.

[0117] Step 112332 combines factors such as the spatial volume of facial defects, the skin laxity of the patient, the fat distribution, and the fat content to further calculate the specific content of the micro-filler material that needs to be injected. Skin laxity determines the filling needs of the material, while fat distribution and fat content affect the uniform distribution and effect of the injection amount; by considering the characteristics of the skin and fat layers, doctors can accurately determine the injection amount of micro-filler material according to individual differences to ensure a natural effect; excessive injection may cause unnatural appearance or complications, and accurate calculation of the injection amount can avoid these problems; appropriate injection amount can reduce postoperative discomfort and recovery time.

[0118] Step 112333 performs very precise injection operations according to the intersection points of the facial muscle layer, nerve layer, and blood vessel layer to avoid damaging important tissues. By using 3D animation or virtual reality technology, patients can visually see the operation process and interact with doctors to provide real-time feedback. This simulation animation can help patients better understand the operation process and risks, increase their trust in the operation; when injecting micro-filler material, important structures such as blood vessels and nerves can be avoided to reduce the risk of postoperative complications and improve surgical safety; through visual simulation animation, patients can not only clearly understand the operation process but also make adjustments according to the feedback provided by the animation; visualization makes patients feel more secure and reduces preoperative anxiety; the interaction between patients and doctors allows the treatment plan to be adjusted at any time to ensure the best results.

[0119] In a preferred embodiment of the present application, the facial micro-filler prediction model in step 14 includes:

[0120] Step 141 generates structure data from the acquired multiple facial defect feature data, multiple defect structure dissection information data, and micro-filler scheme information data sets, and encodes the structure data into sequence data to train the facial micro-filler prediction model;

[0121] Step 142 inputs the sequence data into the facial micro-filler prediction model; the facial micro-filler prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer, the intermediate representation data of multiple hidden layers are transmitted to the output layer, and the output layer outputs the micro-filler scheme information data recognition result corresponding to the defect structure dissection information data representing the facial defect feature data set;

[0122] Step 143 inputs the newly acquired at least one facial defect feature data into the facial micro-filler prediction model to output the micro-filler scheme information data prediction result corresponding to the defect structure dissection information data representing the facial defect feature data.

[0123] In the implementation of the present application, step 141 integrates facial defect feature data, defect structure dissection information data, and micro-sculpture scheme information data from multiple sources to form a data set containing multi-dimensional information (i.e., "structure data"). These data usually contain different defect features of the patient's face (such as concave, convex, skin laxity, etc.), as well as the corresponding anatomical structure and treatment scheme (such as injection amount, injection position, etc.). Then, these structure data are encoded into sequence data (for example, by numerical or vectorization processing), and used to train a deep learning model (such as a neural network). During the training process, the model will learn how to predict the corresponding micro-sculpture scheme (such as filler type, dose, injection position, etc.) according to the input data (facial defect features, dissection information, etc.); by integrating multiple data sources (defect features, dissection information, micro-sculpture scheme) into a structured data set, all relevant information can be fully utilized to improve the predictive ability of the model; through the trained neural network model, personalized micro-sculpture treatment schemes can be automatically generated according to the input facial defect feature data, reducing manual intervention; the training of the model can give more personalized and precise treatment schemes according to the facial features, dissection structure, etc. of different patients.

[0124] Step 142 applies the facial micro-sculpture prediction model trained in step 141 to actual prediction. New facial defect data (such as patient facial features, skin condition, etc.) is input into the model. The model includes multiple hidden layers, each layer extracting different levels of features from the input data, and finally producing micro-sculpture scheme prediction results in the output layer. Specifically, the input layer of the model receives defect data and passes it to multiple hidden layers for feature extraction and processing. Each layer performs a nonlinear transformation on the data to capture more complex features, and finally outputs the prediction results about the treatment scheme in the output layer, such as the type, dose, and injection position of the micro-sculpture material; the multi-layer neural network can extract complex features in the data layer by layer, thereby capturing the details of facial defects and making the prediction more accurate; the multiple hidden layers of the model help to handle complex nonlinear relationships, which can improve the understanding of the complexity of facial defects and the prediction accuracy; new facial defect data can be quickly predicted, thereby providing real-time personalized micro-sculpture scheme and improving the efficiency of diagnosis and treatment.

[0125] Step 143: The newly acquired facial defect feature data (such as new photos, scanning data or symptom changes of the patient during the visit) is input into the facial micro-orthopedic prediction model that has been trained, and the model will predict the corresponding micro-orthopedic scheme based on these new data. This means that even if it is a new patient or a new problem during the treatment process, the model can efficiently predict and generate appropriate treatment schemes based on the existing training results; even if the patient's facial features change or there are different defects, the model can quickly adapt to new inputs and output corresponding micro-orthopedic scheme predictions; by continuously inputting new data, the model can continuously optimize, adjust, and improve the adaptability and prediction accuracy of new facial defect data; as the patient's treatment process changes, the model can adjust the treatment scheme at any time according to the new defect feature data, ensuring that the treatment effect continuously reaches the best state.

[0126] In a preferred embodiment of the present application, step 14 further comprises:

[0127] Step 144: According to the prediction result of the facial micro-orthopedic prediction model, the corresponding micro-orthopedic scheme information data is obtained, and the corresponding micro-orthopedic scheme information data is compared with the historical similar facial defect feature micro-orthopedic scheme information data to obtain a comparison result.

[0128] Step 145: Based on the comparison result, fine difference data is obtained, and the fine difference data is subjected to correlation analysis to obtain a fine difference influence factor; and the facial micro-orthopedic prediction model parameters are further iteratively updated according to the fine difference influence factor, to accurately obtain a micro-orthopedic individualized surgery scheme prediction result.

[0129] Step 146: The fine difference influence factor includes patient face shape features, facial feature features, age, gender, and individualized needs, and the output micro-orthopedic scheme information data prediction result is adjusted in real time to obtain a preliminary surgery scheme.

[0130] Step 147: According to the micro-orthopedic scheme information data prediction result, feedback information of the surgery effect diagram and the facial change curve is generated to iteratively optimize the preliminary surgery scheme and obtain a micro-orthopedic surgery final scheme.

[0131] In the implementation of the present application, step 144 predicts the facial features of the patient according to a pre-trained facial micro-sculpture prediction model. The model generates a preliminary micro-sculpture plan based on the patient's facial features such as facial contour, facial feature proportion, skin quality, etc.; then, the preliminary micro-sculpture plan is compared with the micro-sculpture plans of similar facial defect features in history. The historical data usually come from past patient cases, which can provide a reference for the current individual; the comparison process helps to ensure the rationality of the prediction plan, and with the experience of historical data, some potential micro-sculpture plans can be found, thereby increasing the success rate of the plan; through comparison with historical data, the current patient's plan can also be optimized, reducing errors and unsuitable treatment plans.

[0132] Step 145 extracts some "fine difference" data based on the comparison results after comparison. These data usually include some more detailed differences, such as minor changes in facial morphology, muscle tightness, etc., which may affect the final surgical effect; then, correlation analysis is performed on these difference data to identify "fine difference influencing factors" that have a significant impact on the surgical effect. These factors can be minor differences in facial structure, age, gender factors, based on these influencing factors, the parameters of the facial micro-sculpture model are further updated and iterated to make the prediction results more accurate and personalized.

[0133] This step can ensure that the personalized surgical plan is more accurately adapted to the unique facial features of the patient, thereby avoiding the blind application of historical data; by analyzing the fine differences, some factors that may affect the effect can be identified, further improving the success rate of the surgery and reducing possible side effects or unsatisfactory results.

[0134] Step 146 further integrates the patient's individual needs based on step 145, including facial contour, facial feature proportion, age, gender, etc., combined with the fine difference influencing factors extracted before, to adjust the prediction results of the micro-sculpture plan. These adjustments are not limited to facial feature adjustments, but also include the patient's individual aesthetic needs, such as whether to need a more youthful, more natural or more three-dimensional effect; through real-time adjustment and optimization, the individual needs of the patient can be better met, enhancing the personalization and customizability of the plan, and improving patient satisfaction; carefully considering age, gender, etc. factors, the surgical plan is more in line with the physiological characteristics, avoiding too extreme or not in line with the natural facial aesthetics of the treatment.

[0135] Step 147, according to the prediction results of the micro-integration scheme, the system will generate surgical effect map and facial change curve, these images and curves show the facial change effect before and after surgery; through the effect map and the change curve, the patient and the doctor can intuitively see the expected result of the surgical effect, which helps both parties to confirm whether the surgical plan is appropriate; this process also provides a feedback mechanism to help the iteration optimization of the plan, to ensure that the final plan is the most appropriate, meets the needs of the patient and is effective; the generation of effect map and facial change curve enables the patient to intuitively feel the possible changes before the actual surgery, helping doctors and patients to better communicate and adjust the plan; this feedback mechanism can continuously optimize the surgical plan, increase the success rate of surgery and the satisfaction of patients.

[0136] In a preferred embodiment of the present application, the surgical precision operation strategy in step 16 includes:

[0137] Step 161, according to the differences in the interlaced points of the muscle layer, nerve direction and blood vessel distribution of the facial defect anatomy in the same defect area, and the direction of the three major nerves of the face, a micro-integrated surgical path is customized to avoid the dense interlaced area of nerves.

[0138] In the implementation of the present application, in step 161, before surgery, the doctor will conduct a detailed analysis of the patient's facial defect area based on the anatomical structure. Specifically, the interlaced points of the muscle layer, nerve layer and blood vessel layer in the analysis area, and the direction of the three major nerves of the face (such as the trigeminal nerve, facial nerve, etc.); the dense distribution of facial muscles, nerves and blood vessels needs to be very careful to avoid damaging these key structures during microplasty. Through 3D modeling or anatomical images, the doctor can accurately understand the anatomical structure of different levels to identify the area of nerve interlacing; based on these anatomical analyses, the doctor will customize a micro-integrated surgical path to ensure that the dense interlaced area of nerves is avoided, thereby minimizing the risk of nerve damage during surgery; by accurately analyzing and customizing the surgical path, the risk of damage to nerves, blood vessels and muscles can be significantly reduced, avoiding postoperative complications and sequelae such as nerve palsy or muscle function impairment; improve the safety of surgery, especially in sensitive areas such as the face, to ensure that micro-integrated surgery is more precise and effective, reducing the possibility of postoperative discomfort or failure.

[0139] As shown in Figure 2 , an intelligent simulation system for facial microplasty operation includes:

[0140] Data acquisition module: used for acquiring patient facial data, various facial defect feature data and various defect structure anatomical information data;

[0141] Preprocessing module: used for normalizing, feature extracting and encoding processing of each data;

[0142] The simulation module is used for fusing and virtually simulating the processed data to obtain micro-surgery scheme information data;

[0143] The model construction module is used for constructing the facial data, the facial defect feature data, the defect structure anatomical information data and the micro-surgery scheme information data into a facial micro-surgery prediction model;

[0144] The scheme prediction module is used for the facial micro-surgery prediction model to output the prediction result of the micro-surgery scheme information data corresponding to the defect structure anatomical information data of the facial defect feature data;

[0145] The feedback evaluation module is used for obtaining an individualized facial micro-surgery prediction scheme based on the prediction result of the facial micro-surgery prediction model, obtaining a surgery accurate operation strategy based on the facial micro-surgery prediction scheme, and feeding back and evaluating the micro-surgery postoperative effect in the doctor-patient interaction.

[0146] When the above-mentioned module functions are realized in the form of software function units and used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts of the prior art that make essential contributions can be embodied in the form of a software product stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, and various program code storage media.

[0147] Therefore, the purpose of the present application can also be achieved by running a program or a set of programs on any computing device. The computing device can be a commonly known general-purpose intelligent device. Therefore, the purpose of the present application can also be achieved by only providing a program product containing program code for implementing the method or system. That is, such a program product also constitutes the present application, and the storage medium storing such a program product also constitutes the present application. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should be pointed out that in the device and method of the present application, the steps can be obviously decomposed and / or recombined. These decompositions and / or recombination should be regarded as equivalent solutions of the present application. Moreover, the steps of performing the above series of processes can naturally be executed in time sequence according to the order of description, but do not necessarily have to be executed in time sequence. Some steps can be executed in parallel or independently of each other.

Claims

1. An intelligent simulation method for facial microplastic surgery operation, characterized in that, The method comprises the following steps: acquiring patient facial data, various facial defect feature data, and various defect structure anatomical information data; normalizing, feature extracting, and encoding each data; fusing and virtually simulating the processed data to obtain various micro-integration surgery scheme information data; constructing facial micro-integration prediction model from facial data, various facial defect feature data, various defect structure anatomical information data, and various micro-integration surgery scheme information data; the facial micro-integration prediction model can output the prediction result of the micro-integration scheme information data corresponding to the defect structure anatomical information data of the facial defect feature data; based on the prediction result of the facial micro-integration prediction model, obtaining an individualized facial micro-integration prediction scheme; based on the facial micro-integration prediction scheme, obtaining a precise operation strategy for surgery, which is used for doctor-patient interaction feedback and evaluation of micro-integration postoperative effect; acquiring patient facial data, constructing a three-dimensional facial model of the patient, analyzing the three-dimensional facial model to obtain various facial defect feature data, and integrating the facial defect feature data into a facial defect feature data set; positioning and marking the various facial defect feature data to obtain a defect marking data set; and performing structure dissection on each facial defect feature data item in the defect marking data set to obtain a defect structure anatomical information data set; the defect structure anatomical information data set comprises spatial position and structure information data of facial defect skin layer, subcutaneous tissue layer, muscle layer, nerve direction, and blood vessel distribution; the spatial position and structure information data contains the adhesion relationship between the spatial positioning and structure information of each layer and the layer thickness and width; based on the obtained spatial position and structure information data, combining the skin laxity, fat distribution, and fat content of the patient to perform simulation; matching the facial simulation three-dimensional image with the facial anatomical structure information data to obtain a matching result; based on the matching result, obtaining defect structure dissection image data; For each defect structure, the defect area in the dissected image data is connected by adjacent pixels together to form different defect partitions; where C i represents the i-th connected region, p represents a pixel in the image, I(p) represents the pixel vector of the pixel, C(p, C j ) represents the connected vector of pixel p and region C j ; dividing the defect area dissection structure of each defect structure dissection image data, partitioning and marking the divided defect area, and accurately determining the position of each defect area dissection data item; performing topological analysis on different defect partitions according to the spatial position and structure information data of the facial defect skin layer, subcutaneous tissue layer, muscle layer, nerve direction, and blood vessel distribution, so as to divide the defect area into different structure layers and remove noise and disconnected defect areas; The acquired facial defects are subjected to shape detection to acquire both concave and convex defect feature shapes, and are respectively subjected to and to acquire facial defect space volumes; wherein, V1 represents a concave feature space volume, V2 represents a convex feature space volume, h1 represents a depth of the concave, h2 represents a height of the convex defect feature, r1 represents an inner diameter of the concave; r2 represents an inner diameter of the bottom of the convex; and L represents a top width of the convex. According to the facial defect space volume, combined with the skin laxity, fat distribution and fat content of the patient, through to obtain the required injection micro-fine material content of the facial defect; in the formula, G represents the required injection micro-fine material content value, V represents the recess feature space volume V1 or the convex feature space volume V2, , wherein ρ represents the injection material density, and k represents the facial absorption rate correction coefficient. layer-by-layer marking different structure layers to accurately obtain the interweaving points of the muscle layer, nerve direction, and blood vessel distribution in the same defect area; based on the interweaving points of the muscle layer, nerve direction, and blood vessel distribution in the same defect area, accurately injecting micro-integration material into the defect area of the patient's face, displaying the simulation animation, so that the patient can intuitively receive the surgical process and interact with the doctor to avoid surgical risks; based on the prediction result of the facial micro-integration prediction model, obtaining corresponding micro-integration scheme information data, comparing the corresponding micro-integration scheme information data with historical similar facial defect feature micro-integration scheme information data, and obtaining a comparison result; Based on the comparison result, fine difference data is obtained to perform correlation analysis on the fine difference data to obtain a fine difference influence factor; and the face micro-reshaping prediction model parameters are further iteratively updated according to the fine difference influence factor to accurately obtain a micro-reshaping personalized surgery scheme prediction result; The fine difference influence factor includes patient face shape features, facial feature features, age, gender, and personalized needs, and the micro-reshaping scheme information data prediction result output is adjusted in real time to obtain a preliminary surgery scheme; According to the micro-reshaping scheme information data prediction result, feedback information of a surgery effect diagram and a face change curve is generated to iteratively optimize the preliminary surgery scheme and obtain a micro-reshaping surgery final scheme.

2. The intelligent simulation method for facial microplastic surgery operation according to claim 1, characterized in that, The three-dimensional face model is analyzed to obtain a plurality of face defect feature data to form a face defect feature data set, including: Based on the patient face data, three-dimensional face information data of the patient is obtained; and the three-dimensional face information data is preprocessed to obtain preprocessed three-dimensional face information; The preprocessed three-dimensional face information is processed by point cloud or grid to construct a three-dimensional face model; and face feature data is obtained by extracting face features from the three-dimensional face model; Face defect feature data is obtained by detecting face defects from the face feature data; and different types of face defect feature data are summarized to obtain a face defect feature data set. 3.The intelligent simulation method of a facial microplasty operation according to claim 1, wherein, The face micro-reshaping prediction model includes: The obtained plurality of face defect feature data, plurality of defect structure dissection information data, and micro-reshaping scheme information data set are generated into structure data, and the structure data is encoded into sequence data to train the face micro-reshaping prediction model; The sequence data is input into the face micro-reshaping prediction model; the face micro-reshaping prediction model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer, and an output layer, intermediate representation data of a plurality of hidden layers are transmitted to the output layer, and the output layer outputs micro-reshaping scheme information data recognition results corresponding to the defect structure dissection information data representing the face defect feature data set; The newly obtained at least one face defect feature data is input into the face micro-reshaping prediction model to output micro-reshaping scheme information data prediction results corresponding to the defect structure dissection information data representing the face defect feature data.

4. The intelligent simulation method for facial microplastic surgery operation according to claim 1, characterized in that, The surgery precision operation strategy includes: According to the differences in the interweaving point positions of the muscle layer, nerve direction, and blood vessel distribution of the face defect dissection structure in the same defect area, and the direction of the three major nerves of the face, a micro-reshaping surgery path is customized to avoid the dense area of nerve interweaving.

5. An intelligent simulation system for facial plastic surgery operation, characterized in that, The system sets an electronic device including a memory, a processor, and a face micro-reshaping surgery operation intelligent simulation method program stored on the memory and executable on the processor, and the face micro-reshaping surgery operation intelligent simulation method program is executed by the processor to implement the steps of the face micro-reshaping surgery operation intelligent simulation method according to any one of claims 1-4, and the system includes: The data acquisition module is configured to acquire patient facial data, various facial defect feature data, and various defect structure anatomical information data; The preprocessing module is configured to normalize, extract features, and encode each data; The simulation module is configured to fuse and virtually simulate the processed data to obtain various micro-integration surgery scheme information data; The model construction module is configured to construct a facial micro-integration prediction model from the facial data, various facial defect feature data, various defect structure anatomical information data, and various micro-integration surgery scheme information data; The scheme prediction module is configured to enable the facial micro-integration prediction model to output a prediction result of the micro-integration scheme information data corresponding to the defect structure anatomical information data of the facial defect feature data; The feedback evaluation module is configured to obtain an individualized facial micro-integration prediction scheme based on the prediction result of the facial micro-integration prediction model, obtain a precise operation strategy based on the facial micro-integration prediction scheme, and provide a doctor-patient interactive feedback and evaluate the postoperative effect of micro-integration.

Images