Simulation training method and system for minimally invasive surgery in obstetrics and gynecology department

Abstract

The invention discloses a simulation training method and system for a minimally invasive surgery in the obstetrics and gynecology department, and relates to the technical field of virtual reality, and the method comprises the following steps: obtaining related medical data on a patient in the obstetrics and gynecology department, and carrying out the preprocessing of a medical image; the processed two-dimensional image is converted into a three-dimensional model, an operation scene is constructed, and the anatomical model of the patient in the obstetrics and gynecology department and the scene are fused; generating a plurality of operation planning schemes, calculating an operation difficulty coefficient Nd of each operation scheme, and determining an optimal operation scheme according to the size of the operation difficulty coefficient Nd; establishing an interactive interface between the doctor and the virtual operation scene, and recording various indexes of the doctor in the simulated operation process; after the simulated operation is finished, the operation is analyzed, an operation analysis report is generated, and the simulated operation is evaluated and optimized; through virtual reality minimally invasive surgery simulation, the misoperation risk in a real surgery can be reduced, so that the operation error rate in the surgery is reduced.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and in particular to a gynecological and obstetric minimally invasive surgery simulation training method and system. Background Art

[0002] With the continuous advancement of medical technology, minimally invasive surgery in obstetrics and gynecology has become an important treatment method in modern medical practice. For example, in the treatment of fallopian tube obstruction, ovarian cysts, endometriosis, etc., laparoscopic instruments are inserted through small holes in the abdominal wall to observe the lesions in the abdominal cavity and perform surgical operations. This surgical method brings significant clinical benefits to patients by reducing trauma, accelerating patient recovery and reducing surgical risks. However, due to the complexity and sophistication of its operation, it places high demands on the doctor's surgical skills and experience. Therefore, it has become an important topic in obstetrics and gynecology medical education to conduct systematic minimally invasive surgery simulation training for doctors to improve the accuracy and proficiency of surgical operations.

[0003] In the Chinese invention application with application publication number CN113197665A, a method and system for simulating minimally invasive surgery based on virtual reality is disclosed. The system includes: data preprocessing module, data import module, central control module, three-dimensional image reconstruction module, three-dimensional stereo image generation module, stereo image processing module, surgery simulation module, warning reminder module, effect evaluation module, data storage module, and update display module. The present invention uses the virtual environment provided by VR equipment to allow doctors to observe the three-dimensional model of the surgical site in all directions in the virtual space, so that doctors can have a full and sufficient understanding of the patient's condition; the simulated surgery operation platform performed by VR equipment in the virtual space is convenient for doctors to simulate before surgery to achieve more specific preoperative planning.

[0004] In the above invention application, virtual reality technology is used to simulate and evaluate the operation so as to realize the preoperative planning of the operation. However, in actual operation, since the difficulty of the operation is unclear, it may take multiple simulations to get the best operation plan. The present invention evaluates the difficulty of the operation of obstetrics and gynecology patients before the simulated operation, outputs the best operation plan, and then uses virtual reality technology to simulate the operation. Doctors can understand the challenges and possible risks of the operation more objectively and make corresponding preparations. Through the operation plan, the medical team can more reasonably plan the simulated operation time and required resources, and then verify the operation plan through virtual reality technology, eliminate possible problems during the operation, improve the operation efficiency, and reduce the operation risk. Summary of the invention

[0005] 1. Technical issues to be solved

[0006] In view of the deficiencies in the prior art, the present invention provides a gynecological and obstetric minimally invasive surgery simulation training method and system.

[0007] (II) Technical solution

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0009] A gynecological minimally invasive surgery simulation training method includes the following steps: obtaining relevant medical data from gynecological patients, storing the data in a digital format, building a gynecological patient medical database, and preprocessing medical images stored in the gynecological patient medical database;

[0010] The processed two-dimensional image is converted into a three-dimensional model through three-dimensional reconstruction to generate an initial anatomical structure model of obstetrics and gynecology patients, and the initial anatomical structure model of obstetrics and gynecology patients is optimized and detailed to obtain an accurate anatomical structure model of obstetrics and gynecology patients. The surgical scene is constructed using virtual reality technology, and the accurate anatomical model of obstetrics and gynecology patients is integrated with the scene.

[0011] Obtain the anatomical structure model of obstetrics and gynecology patients, use machine learning algorithms to generate multiple surgical planning plans, and calculate the surgical difficulty coefficient Nd of each surgical plan. Determine the optimal surgical plan based on the size of the surgical difficulty coefficient Nd, and output the optimal surgical plan in detail;

[0012] Establish an interactive interface between doctors and virtual surgical scenes, and use physical engine algorithms to simulate the interaction and collision effects of surgical instruments on tissues, and record various indicators of doctors during simulated surgery;

[0013] After the simulated surgery is completed, the surgery is analyzed through computing or image processing technology to generate a surgical analysis report. Based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery.

[0014] Furthermore, relevant medical data of obstetrics and gynecology patients are obtained, including: CT scans, MRI images and X-rays. These data are collected by corresponding medical equipment and stored in a digital format to build a medical database of obstetrics and gynecology patients. The medical images are preprocessed, and the preprocessing process includes denoising, image enhancement and image registration.

[0015] Furthermore, computer vision and image processing techniques are used to segment different tissue structures or organs in the preprocessed image, and extract the binary image or grayscale image of the area of ​​interest. Common segmentation methods include threshold segmentation, edge detection, and region growing. The segmented two-dimensional image is further converted into a three-dimensional model through three-dimensional reconstruction to generate an initial anatomical structure model of obstetrics and gynecology patients. Common three-dimensional reconstruction methods include voxelization, triangulated meshing, and surface reconstruction.

[0016] Furthermore, the defects and flaws of the initial anatomical model of obstetrics and gynecology patients are repaired by geometric repair and data smoothing technology, and the initial anatomical structure model of obstetrics and gynecology patients is optimized and detailed to obtain an accurate anatomical structure model of obstetrics and gynecology patients. Detail addition refers to adding more physiological details to the model, such as blood vessels, nerves and tissue structures, to make the model more realistic and practical.

[0017] The surgical scene is constructed using virtual reality technology and an accurate anatomical model of an obstetrician and gynecologist patient is integrated with the scene, including an operating table and surgical tools.

[0018] Furthermore, a large number of surgical case data are collected, and the collected data are preprocessed and feature extracted. The machine learning algorithm is trained according to the features and labels. The trained machine learning algorithm is used to input the anatomical structure model of obstetrics and gynecology patients to generate multiple surgical planning plans, and the number of surgical steps Bs, the complexity of the surgical steps Fz, and the operation time Sj required for minimally invasive surgery are calculated.

[0019] Furthermore, the number of surgical steps Bs, the complexity of surgical steps Fz and the surgical time Sj are obtained, and after dimensionless processing, they are associated to form the surgical difficulty coefficient Nd, wherein the surgical difficulty coefficient Nd is obtained as follows:

[0020]

[0021] The meanings of the parameters are: 0.12≤α≤0.64, 0.35≤β≤1.08, and 0.5≤α+β≤1.2, α and β are weights, and their specific values ​​are adjusted and set by the user.

[0022] Furthermore, the surgical difficulty coefficients Nd of different surgical plans are compared, and the optimal surgical plan is determined based on the size of the surgical difficulty coefficient Nd. The optimal surgical plan is output in detail. The optimal surgical plan includes surgical steps, instrument selection and surgical path diagram for doctors' reference and execution.

[0023] Furthermore, an interactive interface between the doctor and the virtual surgical scene is established through a tactile feedback head-mounted display (VR helmet), a handle controller and a tactile feedback device, and the physical engine algorithm is used to simulate the interaction and collision effects of surgical instruments on tissues. The head-mounted display provides an immersive three-dimensional visual effect, the handle controller is used to simulate the operation of surgical instruments, and the tactile feedback device enables the doctor to feel the force and touch during the virtual surgery.

[0024] Furthermore, various indicators of the doctor during the simulated operation are recorded, such as operation time and accuracy. When tissue damage and bleeding are caused by improper operation, it is detected whether the doctor makes corresponding emergency treatment in time. If the emergency treatment is not made in time or the emergency treatment is improper, the operation is directly judged as a failure and the operation is ended.

[0025] Furthermore, based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery. If the operation fails, every step and link of the operation, including anesthesia operation, surgical operation, instrument use and wound treatment, is reviewed to analyze the cause of the failure of the operation, and the correct techniques and steps are demonstrated. If the operation is successful, surgical optimization suggestions are output to the doctor.

[0026] A gynecological and obstetric minimally invasive surgery simulation training system, comprising:

[0027] A data processing module, which obtains relevant medical data of obstetrics and gynecology patients, stores the data in a digital format, builds a medical database of obstetrics and gynecology patients, and pre-processes the medical images stored in the medical database of obstetrics and gynecology patients;

[0028] The model building module converts the processed two-dimensional image into a three-dimensional model through three-dimensional reconstruction, generates an initial anatomical structure model of obstetrics and gynecology patients, optimizes the initial anatomical structure model of obstetrics and gynecology patients and adds details to obtain an accurate anatomical structure model of obstetrics and gynecology patients, builds a surgical scene using virtual reality technology, and integrates the accurate anatomical model of obstetrics and gynecology patients with the scene;

[0029] The surgical planning module obtains the anatomical structure model of obstetrics and gynecology patients, uses machine learning algorithms to generate multiple surgical planning plans, and calculates the surgical difficulty coefficient Nd of each surgical plan. The optimal surgical plan is determined based on the size of the surgical difficulty coefficient Nd, and the optimal surgical plan is output in detail;

[0030] The simulation module establishes an interactive interface between the doctor and the virtual surgical scene, and uses the physical engine algorithm to simulate the interaction and collision effects of surgical instruments on tissues, and records the doctor's various indicators during the simulated surgery;

[0031] Evaluation teaching module: After the simulated surgery is completed, the surgery is analyzed through computing or image processing technology to generate a surgery analysis report. Based on the surgery analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery.

[0032] (III) Beneficial effects

[0033] The present invention provides a gynecological and obstetric minimally invasive surgery simulation training method and system, which has the following beneficial effects:

[0034] 1. By integrating the anatomical model of gynecological and obstetric patients with the surgical scene, doctors can observe the anatomical structure of gynecological and obstetric patients in real time, including the location and distribution of important structures such as blood vessels and nerves. This helps doctors perform surgical operations more accurately and avoid accidental injury to important structures.

[0035] 2. By using machine learning algorithms to calculate and analyze the surgical difficulty coefficient Nd, and based on the size of the surgical difficulty coefficient Nd, the operational difficulty of the surgical plan is evaluated and the optimal surgical plan is determined. The surgical path and operation process can be determined in advance, possible risk points can be found, and corresponding surgical plans can be formulated, which can reduce surgical risks and improve surgical safety.

[0036] 3. After the simulated surgery, the surgery is analyzed through computing or image processing technology to generate a surgical analysis report. Based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery. This can identify and improve possible problems during the operation, help doctors learn surgical skills and operating procedures, improve their skill level, and thus improve surgical efficiency and obstetrics and gynecology patient satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a flow chart of a gynecological and obstetric minimally invasive surgery simulation training method of the present invention;

[0038] Figure 2 This is a structural schematic diagram of a gynecological and obstetric minimally invasive surgery simulation training system of the present invention;

[0039] In the figure: 10, data processing module; 20, model building module; 30, surgery planning module; 40, simulation module; 50, evaluation and teaching module. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] See also Figure 1 The present invention provides a gynecological and obstetric minimally invasive surgery simulation training method, comprising the following steps:

[0042] Step 1: Obtain relevant medical data of obstetrics and gynecology patients, store the data in a digital format, build a medical database of obstetrics and gynecology patients, and pre-process the medical images stored in the medical database of obstetrics and gynecology patients;

[0043] Step 101: Obtain relevant medical data of obstetrics and gynecology patients, including CT scans, MRI images and X-rays. These data are collected by corresponding medical equipment and stored in a digital format to build a medical database of obstetrics and gynecology patients.

[0044] Step 102: Obtain a medical database of obstetrics and gynecology patients and preprocess the medical images. The preprocessing process includes denoising, image enhancement and image registration. Among them, denoising is mainly to remove noise interference in the image to reduce the error of subsequent processing; image enhancement can improve the contrast and details of the image to make the model more accurate; image registration is used to align images under different scans or viewing angles to obtain more comprehensive information;

[0045] Step 103: Use computer vision and image processing technology to segment different tissue structures or organs in the preprocessed image, and extract a binary image or grayscale image of the area requiring surgery. Common segmentation methods include threshold segmentation, edge detection, and region growing.

[0046] When using, combine the contents in step 101 to step 103:

[0047] By acquiring relevant medical data from obstetrics and gynecology patients, storing the data in a digital format, building a medical database for obstetrics and gynecology patients, and preprocessing the medical images stored in the medical database for obstetrics and gynecology patients, the image quality, accuracy, and interpretability can be improved, providing more information and support for doctors' diagnosis and treatment.

[0048] Step 2: convert the processed two-dimensional image into a three-dimensional model through three-dimensional reconstruction to generate an initial anatomical structure model of the obstetrics and gynecology patient, optimize the model and add details to the initial anatomical structure model of the obstetrics and gynecology patient to obtain an accurate anatomical structure model of the obstetrics and gynecology patient, use virtual reality technology to build a surgical scene, and integrate the accurate anatomical model of the obstetrics and gynecology patient with the scene;

[0049] Step 201: The segmented two-dimensional image is further converted into a three-dimensional model through three-dimensional reconstruction to generate an initial anatomical structure model of a gynecological patient. Common three-dimensional reconstruction methods include voxelization, triangular meshing, and surface reconstruction.

[0050] Step 202: repair the defects and flaws of the initial anatomical model of the obstetrics and gynecology patient by using geometric repair and data smoothing technology, optimize the initial anatomical structure model of the obstetrics and gynecology patient and add details to obtain an accurate anatomical structure model of the obstetrics and gynecology patient. Adding details means adding more physiological details to the model, such as blood vessels, nerves and tissue structures, to make the model more realistic and practical.

[0051] Step 203: after obtaining the accurate anatomical structure model of the obstetrics and gynecology patient, construct a surgical scene using virtual reality technology, and integrate the accurate anatomical model of the obstetrics and gynecology patient with the scene, wherein the surgical scene includes an operating table and surgical tools;

[0052] When used, combine the contents in step 201 to step 203:

[0053] By integrating the anatomical model of gynecological and obstetric patients with the surgical scene, doctors can observe the anatomical structure of gynecological and obstetric patients in real time, including the location and distribution of important structures such as blood vessels and nerves. This helps doctors perform surgical operations more accurately and avoid accidental injury to important structures.

[0054] Step 3: Obtain the anatomical structure model of obstetrics and gynecology patients, use machine learning algorithms to generate multiple surgical planning plans, and calculate the surgical difficulty coefficient Nd of each surgical plan. Determine the optimal surgical plan based on the size of the surgical difficulty coefficient Nd, and output the optimal surgical plan in detail;

[0055] Step 301: collect a large amount of surgical case data, pre-process and extract features from the collected data, train a machine learning algorithm based on the features and labels, use the trained machine learning algorithm, input the anatomical structure model of obstetrics and gynecology patients, generate multiple surgical planning plans, and calculate the number of surgical steps Bs, the complexity of the surgical steps Fz, and the surgical time Sj required for minimally invasive surgery;

[0056] Step 302: Obtain the number of surgical steps Bs, the complexity of surgical steps Fz and the surgical time Sj, and after dimensionless processing, associate them to form a surgical difficulty coefficient Nd, wherein the surgical difficulty coefficient Nd is obtained as follows:

[0057]

[0058] The meaning of the parameters is 0.12≤α≤0.64, 0.35≤β≤1.08, and 0.5≤α+β≤1.2, α and β are weights, and their specific values ​​are adjusted and set by the user;

[0059] Step 303: Compare the surgical difficulty coefficients Nd of different surgical plans, determine the optimal surgical plan based on the size of the surgical difficulty coefficient Nd, and output the optimal surgical plan in detail. The optimal surgical plan includes surgical steps, instrument selection and surgical path diagram for doctors to refer to and execute.

[0060] When used, combine the contents in step 301 to step 303:

[0061] By using machine learning algorithms to calculate and analyze the surgical difficulty coefficient Nd, and evaluating the operational difficulty of the surgical plan based on the size of the surgical difficulty coefficient Nd, the optimal surgical plan can be determined. The surgical path and operation process can be determined in advance, possible risk points can be found, and corresponding surgical plans can be formulated, which can reduce surgical risks and improve surgical safety.

[0062] Step 4: Establish an interactive interface between the doctor and the virtual surgical scene, and use the physical engine algorithm to simulate the interaction and collision effects of surgical instruments on tissues, and record various indicators of the doctor during the simulated surgery;

[0063] Step 401: Establish an interactive interface between the doctor and the virtual surgical scene through a tactile feedback head-mounted display (such as a VR helmet), a handle controller, and a tactile feedback device, and use a physical engine algorithm to simulate the interaction and collision effects of surgical instruments on tissues. It should be noted that the head-mounted display provides an immersive three-dimensional visual effect, the handle controller is used to simulate the operation of surgical instruments, and the tactile feedback device enables the doctor to feel the force and touch during the virtual surgery.

[0064] Step 402, record various indicators of the doctor during the simulated operation, such as operation time and accuracy. When tissue damage and bleeding are caused by improper operation, check whether the doctor makes corresponding emergency treatment in time. If the emergency treatment is not made in time or the emergency treatment is improper, it is directly judged as a failure and the operation is ended.

[0065] When used, combine the contents in step 401 and step 402:

[0066] By establishing an interactive interface between doctors and virtual surgical scenes and recording various indicators of doctors during simulated operations, doctors can gain a more realistic surgical experience, learn surgical techniques and operating procedures, improve their skill level, and reduce the risk of misoperation in real operations. Doctors and surgical team members can practice repeatedly in a simulated environment, become familiar with surgical steps and instrument use, and thus reduce the error rate during surgery.

[0067] Step 5: After the simulated surgery is completed, the surgery is analyzed through computing or image processing technology to generate a surgery analysis report. Based on the surgery analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery.

[0068] Step 501: After the simulated surgery is completed, key information about the surgical process is extracted, such as the frequency of use of surgical instruments, the time interval during the surgery, and the number of operations by doctors and nurses, and the surgery is analyzed through computing or image processing technology to generate a surgical analysis report;

[0069] Step 502: Based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery. If the surgery fails, each step and link of the surgery is reviewed, including anesthesia operation, surgical operation, instrument use and wound treatment, the cause of the failure of the surgery is analyzed, and the correct techniques and steps are demonstrated. If the surgery is successful, the surgery optimization suggestions are output to the doctor.

[0070] When using, combine the contents in step 501 and step 502:

[0071] After the simulated surgery is completed, the surgery is analyzed through computing or image processing technology to generate a surgical analysis report. Based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery. This can identify and improve possible problems during the operation, help doctors learn surgical techniques and operating procedures, improve their skill levels, and thus improve surgical efficiency and obstetrics and gynecology patient satisfaction.

[0072] See also Figure 2 The present invention provides a gynecological and obstetric minimally invasive surgery simulation training system, comprising:

[0073] The data processing module 10 acquires the medical data related to the obstetrics and gynecology patients, stores the data in a digital format, builds a medical database for obstetrics and gynecology patients, and pre-processes the medical images stored in the medical database for obstetrics and gynecology patients;

[0074] The model building module 20 converts the processed two-dimensional image into a three-dimensional model through three-dimensional reconstruction, generates an initial anatomical structure model of the obstetrics and gynecology patient, optimizes the initial anatomical structure model of the obstetrics and gynecology patient and adds details to obtain an accurate anatomical structure model of the obstetrics and gynecology patient, builds a surgical scene using virtual reality technology, and integrates the accurate anatomical model of the obstetrics and gynecology patient with the scene;

[0075] The surgical planning module 30 obtains the anatomical structure model of the obstetrics and gynecology patient, generates multiple surgical planning schemes using a machine learning algorithm, calculates the surgical difficulty coefficient Nd of each surgical scheme, determines the optimal surgical scheme according to the magnitude of the surgical difficulty coefficient Nd, and outputs the optimal surgical scheme in detail;

[0076] The simulation module 40 establishes an interactive interface between the doctor and the virtual surgical scene, and uses a physical engine algorithm to simulate the interaction and collision effects of surgical instruments on tissues, and records various indicators of the doctor during the simulated surgery;

[0077] Evaluation teaching module 50, after the simulated surgery is completed, the surgery is analyzed through computing or image processing technology, a surgery analysis report is generated, and based on the surgery analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery.

[0078] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution.

[0079] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0080] The above description is only a specific implementation manner 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 changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A gynecological and obstetric minimally invasive surgery simulation training method, characterized by: The steps include: Obtain relevant medical data from obstetrics and gynecology patients, store the data in a digital format, build a medical database for obstetrics and gynecology patients, and pre-process the medical images stored in the medical database for obstetrics and gynecology patients; The processed two-dimensional image is converted into a three-dimensional model through three-dimensional reconstruction to generate an initial anatomical structure model of obstetrics and gynecology patients, and the initial anatomical structure model of obstetrics and gynecology patients is optimized and detailed to obtain an accurate anatomical structure model of obstetrics and gynecology patients. The surgical scene is constructed using virtual reality technology, and the accurate anatomical model of obstetrics and gynecology patients is integrated with the scene. Obtain the anatomical structure model of obstetrics and gynecology patients, use machine learning algorithms to generate multiple surgical planning plans, and calculate the surgical difficulty coefficient Nd of each surgical plan. Determine the optimal surgical plan based on the size of the surgical difficulty coefficient Nd, and output the optimal surgical plan in detail; Establish an interactive interface between doctors and virtual surgical scenes, and use physical engine algorithms to simulate the interaction and collision effects of surgical instruments on tissues, and record various indicators of doctors during simulated surgery; After the simulated surgery is completed, the surgery is analyzed through computing or image processing technology to generate a surgical analysis report. Based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery.

2. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 1, characterized in that: Obtain relevant medical data from obstetrics and gynecology patients, including CT scans, MRI images and X-rays, collect them through corresponding medical equipment, and store them in digital format to build a medical database for obstetrics and gynecology patients. Preprocess the medical images, including denoising, image enhancement and image registration.

3. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 2, characterized in that: Computer vision and image processing techniques are used to segment different tissue structures or organs in the preprocessed image, extract the binary image or grayscale image of the area of ​​interest, and convert the segmented two-dimensional image into a three-dimensional model through three-dimensional reconstruction to generate the initial anatomical structure model of the obstetrics and gynecology patient.

4. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 3, characterized in that: The defects and flaws of the initial anatomical model of obstetrics and gynecology patients are repaired by geometric repair and data smoothing technology, and the initial anatomical structure model of obstetrics and gynecology patients is optimized and details are added to obtain an accurate anatomical structure model of obstetrics and gynecology patients.

5. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 4, characterized in that: Collect data from a large number of surgical cases, preprocess and extract features from the collected data, train the machine learning algorithm based on the features and labels, use the trained machine learning algorithm, input the anatomical structure model of gynecological and obstetric patients to generate multiple surgical planning plans, and calculate the number of surgical steps Bs, the complexity of the surgical steps Fz, and the operation time Sj required for minimally invasive surgery.

6. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 5, characterized in that: The number of surgical steps Bs, the complexity of surgical steps Fz and the surgical time Sj are obtained, and after dimensionless processing, they are associated to form the surgical difficulty coefficient Nd. The surgical difficulty coefficient Nd is obtained as follows: The meanings of the parameters are: 0.12≤α≤0.64, 0.35≤β≤1.08, and 0.5≤α+β≤1.2, α and β are weights, and their specific values ​​are adjusted and set by the user.

7. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 6, characterized in that: Through the tactile feedback head-mounted display, handle controller and tactile feedback device, an interactive interface between the doctor and the virtual surgical scene is established, and the physical engine algorithm is used to simulate the interaction and collision effects of surgical instruments on tissues.

8. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 7, characterized in that: Record various indicators during the simulated surgery, including: operation time, accuracy and whether emergency treatment was taken.

9. A gynecological and obstetric minimally invasive surgery simulation training method according to claim 8, characterized in that: Based on the surgical analysis report, the trained machine learning model is used to evaluate and optimize the simulated surgery. If the operation fails, every step and link of the operation, including anesthesia operation, surgical operation, instrument use and wound treatment, is reviewed to analyze the cause of the failure and demonstrate the correct techniques and steps. If the operation is successful, surgical optimization suggestions are provided to the doctor.

10. A gynecological and obstetric minimally invasive surgery simulation training system, characterized by: include: A data processing module (10) is used to obtain relevant medical data of obstetrics and gynecology patients, store the data in a digital format, construct a medical database of obstetrics and gynecology patients, and pre-process the medical images stored in the medical database of obstetrics and gynecology patients; A model building module (20) converts the processed two-dimensional image into a three-dimensional model through three-dimensional reconstruction, generates an initial anatomical structure model of the obstetrics and gynecology patient, optimizes the initial anatomical structure model of the obstetrics and gynecology patient and adds details to obtain an accurate anatomical structure model of the obstetrics and gynecology patient, constructs a surgical scene using virtual reality technology, and integrates the accurate anatomical model of the obstetrics and gynecology patient with the scene; A surgical planning module (30) acquires an anatomical structure model of a gynecological patient, generates multiple surgical planning schemes using a machine learning algorithm, calculates a surgical difficulty coefficient Nd of each surgical scheme, determines an optimal surgical scheme based on the magnitude of the surgical difficulty coefficient Nd, and outputs the optimal surgical scheme in detail; A simulation module (40) is used to establish an interactive interface between the doctor and the virtual surgical scene, and to use a physical engine algorithm to simulate the interaction and collision effects of surgical instruments on tissues, and to record various indicators of the doctor during the simulated surgery; The evaluation teaching module (50) analyzes the surgery after the simulated surgery by using computing or image processing technology to generate a surgery analysis report, and uses the trained machine learning model to evaluate and optimize the simulated surgery based on the surgery analysis report.

Images