A levator ani muscle repair system and method

Abstract

The present invention belongs to the field of medical device information management system, and specifically discloses a levator ani muscle repair system and method, which consists of six modules: ultrasonic positioning, absorbable sutures, minimally invasive suturing instruments, biofeedback training, drug sustained release and intelligent control. It innovatively realizes precise visual repair, reduces patient trauma with minimally invasive operation, promotes tissue repair by synergistically using absorbable sutures and drug sustained release, assists functional recovery through personalized biofeedback training, optimizes the surgical and treatment process with the help of intelligent control, and integrates multidisciplinary technologies to improve the repair effect, providing an efficient, safe and personalized new solution for the treatment of levator ani muscle injuries, which is expected to significantly improve the pelvic floor dysfunction of patients and improve their quality of life.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a system and method for repairing levator ani muscles. Background Art

[0002] The levator ani muscles are a key part of the pelvic floor muscles and are crucial to maintaining the normal position and function of the pelvic organs. Under the influence of factors such as childbirth, long-term increased abdominal pressure, and aging, the levator ani muscles are prone to damage, which in turn causes pelvic floor dysfunction, such as pelvic organ prolapse, urinary incontinence, and sexual dysfunction, which seriously reduce the patient's quality of life. Existing methods of repairing the levator ani muscles include large surgical repair trauma, slow recovery, and many complications. Conservative treatment is not effective for moderate to severe injuries. Therefore, a more efficient, safe, and convenient levator ani muscle repair solution is urgently needed. Summary of the invention

[0003] The present invention provides a levator ani muscle repair system, comprising:

[0004] Ultrasonic positioning module, used to obtain the anatomical structure and injury condition of the levator ani muscle in real time. The module includes a high-resolution ultrasonic probe with a frequency of 5-10 MHz and image processing software. The image processing software enhances and filters the ultrasonic image to improve image clarity and diagnostic accuracy;

[0005] The absorbable suture module is composed of a polylactic acid-glycolic acid copolymer (PLGA) absorbable suture with a tensile strength of 50-100 MPa and a degradation time of 3-6 months. The absorbable suture is added with drug-sustaining microspheres with a particle size of 10-50 μm. The drug-sustaining microspheres contain drugs that promote tissue repair and growth, wherein the growth factor is released within 1 week after surgery at a concentration of 30%-40% of the total content, and the antibiotic reaches an effective antibacterial concentration within 3 days after surgery;

[0006] The minimally invasive suturing instrument module has a slender operating rod with a length of 20-30 cm and a diameter of 5-8 mm, which can reach the injured part of the levator ani muscle through the natural cavity of the vagina or rectum. The head of the instrument is provided with a fine suturing needle and a suture guide device. The operating rod is also provided with an angle adjustment device with an angle adjustment range of 0-180 degrees.

[0007] The biofeedback training module is used to monitor the contraction of the patient's pelvic floor muscles in real time and convert it into intuitive visual signals to feed back to the patient. It has built-in multiple personalized training programs. The sensor of the biofeedback training module adopts an electromyographic sensor, which can accurately collect the electrophysiological signals of the pelvic floor muscles and present the feedback signals to the patient through the display screen;

[0008] The drug sustained-release module is realized through drug sustained-release microspheres in the absorbable sutures, which continuously release drugs during the degradation and absorption process of the sutures, providing a favorable microenvironment for the healing of the levator ani muscles;

[0009] The intelligent control module is connected to the above modules, receives the image information of the ultrasound positioning module and the muscle contraction signal of the biofeedback training module, intelligently optimizes and adjusts the operating parameters of the minimally invasive suturing instrument module based on this information, and records the patient's treatment process and rehabilitation data. The intelligent control module adopts a control system based on machine learning, which can automatically adjust the suturing speed, needle distance, suturing angle and other parameters of the minimally invasive suturing instrument according to the levator ani muscle injury characteristics in the ultrasound image and the muscle contraction force data of the biofeedback, with an error range of within ±5%.

[0010] On the other hand, the present invention also provides a method for using the levator ani muscle repair system, comprising the following steps:

[0011] Preoperative preparation steps: Perform a comprehensive pelvic floor examination on the patient, including ultrasound examination and pelvic floor muscle strength assessment using the ultrasound positioning module to determine the damage to the anal levator muscles and develop a personalized surgical plan. At the same time, the patient's intestines and perineum are cleaned and prepared;

[0012] Ultrasound positioning steps: At the beginning of the operation, the probe of the ultrasound positioning module is placed in the pelvic floor area through the vagina or rectum, the ultrasound equipment is started, a clear image of the levator ani muscles is obtained, and the injured part is analyzed and marked;

[0013] Minimally invasive suturing steps: Under the real-time guidance of ultrasound, the minimally invasive suturing instrument module is inserted into the pelvic floor through the natural cavity to the injured part, and the suture needle and suture guide device are used to pass the suture of the absorbable suture module through the damaged anal levator muscle tissue, and suture is performed according to the predetermined suturing method. During the process, the suturing parameters are adjusted with the assistance of the intelligent control module according to the ultrasound image and the operating feel. The suture needle distance is 5-8mm, and the suture speed is 2-3 stitches / minute;

[0014] Drug sustained release and repair steps: After suturing is completed, the drug sustained release microspheres of the drug sustained release module release drugs to promote the healing of the levator ani muscles. At the same time, the absorbable sutures are gradually degraded and absorbed in the body to maintain the suture fixation of the levator ani muscles until the tissue heals; Postoperative biofeedback training steps: During the patient's postoperative recovery period, the biofeedback training module is used to exercise the pelvic floor muscles. The sensor is attached to the perineal skin. According to the visual signals fed back by the module, the pelvic floor muscle contraction and relaxation training is carried out according to the personalized training plan. Each training time is 20-30 minutes, and training is carried out 3-5 times a day;

[0015] Follow-up and evaluation steps: Patients will be followed up regularly after surgery. Ultrasound examination, pelvic floor muscle strength test and other evaluation methods will be used at 1 month, 3 months and 6 months after surgery. The data recorded by the intelligent control module will be used to understand the repair of the anal levator muscles and the degree of recovery of pelvic floor function, and the rehabilitation training plan will be adjusted accordingly.

[0016] Beneficial effects:

[0017] 1. Accurate visual repair: Through high-resolution ultrasound probes and image processing software, the entire process of levator ani muscle repair can be visualized. Under the guidance of clear ultrasound images, doctors can accurately locate and repair the damaged area, greatly reducing unnecessary damage to surrounding tissues and improving surgical accuracy and success rate.

[0018] 2. Minimally invasive surgery has significant advantages: Specially designed minimally invasive suturing instruments enter the pelvic floor through the natural cavity of the human body, avoiding the large incision of traditional surgery, reducing patient trauma and pain, and ensuring rapid postoperative recovery and shortened hospital stay, thus reducing medical costs and physical burden. It fully reflects the minimally invasive concept and helps improve the quality of life of patients.

[0019] 3. Synergistic effect of sutures and drugs: absorbable sutures have both good mechanical properties and drug sustained-release function. While reliably suturing the levator ani muscles, drug sustained-release microspheres continuously release drugs to promote tissue repair and prevent infection, creating better conditions for the healing of the levator ani muscles, shortening the healing time, and enhancing the stability and reliability of the repair effect.

[0020] 4. Personalized rehabilitation training: The biofeedback training module customizes the training plan according to the individual differences of patients, and guides patients to perform targeted pelvic floor muscle exercises through real-time feedback signals, fully mobilizes the subjective initiative of patients, improves training compliance and effect, effectively promotes the recovery of levator ani muscle function after repair, and reduces the risk of recurrence of pelvic floor dysfunction.

[0021] 5. Intelligent integrated management: The intelligent control module realizes intelligent coordination and management of the entire repair system. It automatically optimizes the operating parameters of the suture instrument according to the ultrasound image and muscle contraction signal to ensure the accuracy of the operation; at the same time, it comprehensively records the patient's treatment data, provides scientific decision-making support for doctors, and improves the overall quality and efficiency of repair treatment.

[0022] 6. Model of multidisciplinary integration and innovation: This invention integrates the cutting-edge achievements of multiple disciplines such as ultrasound diagnosis, material science, minimally invasive device design, biofeedback technology, drug sustained-release technology, and intelligent control technology, and innovatively constructs a new and comprehensive anal levator muscle repair solution, which expands the treatment methods for pelvic floor dysfunction and has broad clinical application prospects and important promotion value. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 Working Principle Diagram DETAILED DESCRIPTION

[0024] Example 1

[0025] A high-resolution ultrasound probe with a frequency of 5-10MHz is used, along with specialized image processing software. The software can enhance and filter ultrasound images, clearly and accurately present the anatomical structure and injury status of the levator ani muscle, including information such as the location, degree, and range of the injury, providing precise guidance for subsequent repair operations.

[0026] It is composed of absorbable sutures made of polylactic acid-glycolic acid copolymer (PLGA), with a tensile strength of 50-100MPa and a degradation time of 3-6 months, which can meet the mechanical requirements of the levator ani muscle repair process. The sutures are evenly distributed with drug-sustaining microspheres with a particle size of 10-50μm, which contain growth factors that promote tissue repair and antibiotics that prevent infection. The growth factor release amount reaches 30%-40% of the total content within 1 week after surgery, and the antibiotic reaches an effective antibacterial concentration within 3 days after surgery, which continuously creates a favorable microenvironment for the healing of the levator ani muscle during the degradation of the sutures.

[0027] The slender operating rod with a length of 20-30cm and a diameter of 5-8mm can reach the injured part of the levator ani muscle through the natural cavity of the vagina or rectum. The instrument head is equipped with a fine suture needle and a suture guide device. The angle adjustment device on the operating rod can be flexibly adjusted within the range of 0-180 degrees, which is convenient for doctors to operate accurately according to the surgical site and operation requirements, ensuring the accuracy and stability of suture.

[0028] The electromyographic sensor is used to monitor the contraction of the patient's pelvic floor muscles in real time, and it is converted into an intuitive visual signal and displayed on the display screen. The module has built-in multiple personalized training programs. The patient performs pelvic floor muscle contraction and relaxation training according to the feedback signal. Each training lasts 20-30 minutes, 3-5 times a day, so as to enhance the strength and coordination of the levator ani muscles and promote their functional recovery.

[0029] It is mainly achieved by drug-sustaining microspheres in absorbable sutures. When the sutures degrade, the microspheres continuously release drugs according to a predetermined release curve, providing stable drug support for the healing of the levator ani muscles, inhibiting inflammatory reactions, accelerating the tissue repair process, and improving the success rate and stability of repair.

[0030] It is connected to other modules to receive image data from the ultrasound positioning module and muscle contraction signals from the biofeedback training module. The machine learning-based algorithm can automatically optimize the operating parameters of the minimally invasive suturing instrument module based on this information, such as controlling the suturing needle distance to 5-8mm and adjusting the suturing speed to 2-3 needles / minute, with an error range of ±5%. At the same time, it records the patient's entire treatment process and rehabilitation data, providing a key reference for doctors' subsequent diagnosis and adjustment of treatment plans.

[0031] Patients undergo a comprehensive pelvic floor examination before surgery, and use the ultrasound positioning module for ultrasound scanning and pelvic floor muscle strength assessment. The doctor determines the details of the levator anus muscle injury and develops a personalized surgical plan. At the same time, patients need to clean their intestines and perineum to reduce the risk of surgical infection. At the beginning of the operation, the doctor gently places the probe of the ultrasound positioning module in the pelvic floor area through the vagina or rectum, starts the ultrasound device to obtain a clear image of the levator anus muscle, accurately determines the location, degree and range of the injury by analyzing the image, and clearly marks it on the image to navigate the subsequent minimally invasive suturing operation. Under real-time ultrasound monitoring, the doctor controls the minimally invasive suturing instrument module to insert it into the pelvic floor through the natural cavity and reach the marked levator anus muscle injury site. With the help of the suture needle and suture guide device on the head of the instrument, the suture of the absorbable suture module is accurately passed through the damaged tissue, and the operation is performed according to the predetermined suturing method. During the process, according to the ultrasound image feedback and operation feel, combined with the parameter suggestions of the intelligent control module, the suture depth, angle, needle distance and other parameters are flexibly adjusted to ensure accurate anatomical reduction of the levator anus muscle and firm suture. After the suture is completed, the drug-release microspheres in the absorbable suture immediately start the drug release program, growth factors promote the proliferation and differentiation of levator ani muscle cells, and antibiotics prevent infection, creating favorable conditions for healing. Over time, the absorbable sutures gradually degrade and absorb, and their mechanical properties maintain the suture state of the levator ani muscle for a period of time until the new tissue replaces the sutures and the levator ani muscle heals naturally. During the patient's postoperative recovery, the biofeedback training module is enabled for pelvic floor muscle training. The sensor is properly attached to the perineal skin. After starting the device, follow the personalized training plan to perform regular pelvic floor muscle contraction and relaxation training according to the visual feedback signal on the display. The duration of each training session is strictly controlled to 20-30 minutes, and training is insisted on 3-5 times a day. Through continuous training, the strength and coordination of the levator ani muscles are strengthened, the function of the repaired levator ani muscles is restored to an ideal state, the overall functional level of the pelvic floor muscles is improved, and the recurrence of pelvic floor dysfunction is prevented. Patients need to return to the hospital for follow-up regularly after surgery. Doctors use ultrasound examinations, pelvic floor muscle strength tests and other means to evaluate the repair of the levator ani muscles and the degree of recovery of pelvic floor function at 1 month, 3 months and 6 months after surgery. With the help of detailed treatment and rehabilitation data recorded by the intelligent control module, doctors can deeply analyze the patient's rehabilitation progress and accurately adjust and optimize the rehabilitation training plan accordingly to ensure that patients receive the best treatment effect and rehabilitation experience.

[0032] Example 2

[0033] A 35-year-old female patient developed pelvic organ prolapse and urinary incontinence after childbirth. After examination, she was diagnosed with moderate levator ani muscle injury. The levator ani muscle repair system of the present invention was used for treatment, and the steps are as follows:

[0034] Preoperative preparation: Complete intestinal and perineal cleaning preparation, receive a comprehensive pelvic floor examination, and ultrasound positioning shows partial tearing of the levator ani muscle, based on which the surgical plan is formulated. Ultrasound positioning: During the operation, the ultrasound probe is placed through the vagina to clearly show the injured part of the levator ani muscle and mark the area to be repaired. Minimally invasive suturing: Under ultrasound guidance, the minimally invasive suturing instrument is inserted into the pelvic floor through the vagina, and the absorbable suture is passed through the damaged tissue. A total of 8 stitches are sutured with a needle distance of 6mm. The intelligent control module assists in adjusting the suturing parameters to ensure good anatomical reduction. Drug sustained release and repair: After the operation, the drug sustained-release microspheres begin to release drugs, the patient has no obvious discomfort, and the wound heals well. Postoperative biofeedback training: Starting 2 weeks after the operation, training is carried out 4 times a day, 25 minutes each time, and targeted pelvic floor muscle exercises are performed based on biofeedback signals. Follow-up and evaluation: Ultrasound examination 1 month after the operation showed that the levator ani muscle had initially healed and the muscle strength was enhanced; at 3 months, the symptoms of pelvic organ prolapse and urinary incontinence were significantly improved; at the 6-month follow-up, the levator ani muscle recovered well and the pelvic floor function was basically normal.

[0035] Significantly improve the accuracy and success rate of repair: Ultrasonic positioning and intelligent control technology ensure accurate surgical operations, reduce surgical risks and the incidence of complications, lay a solid foundation for patient rehabilitation, improve the success rate of repair, and effectively solve the problem of pelvic floor dysfunction in patients. Greatly reduce patient trauma and pain: Minimally invasive technology reduces surgical trauma, reduces postoperative pain, accelerates the patient's postoperative recovery process, shortens hospital stay, reduces economic burden, improves patient comfort and satisfaction, and enables them to return to normal life and work faster. Effectively promote tissue repair and functional recovery: The synergistic effect of absorbable sutures and drug sustained release, combined with personalized biofeedback training, provides all-round support for the healing of the levator ani muscles, accelerates tissue repair, enhances muscle strength and coordination, reduces the risk of recurrence, comprehensively improves pelvic floor function, and improves the quality of life of patients. Realize intelligent and personalized treatment: The intelligent control module is combined with personalized training programs to accurately customize treatment plans and optimize surgical parameters according to individual differences and disease characteristics of patients, meet diversified treatment needs, improve treatment targeting and effectiveness, and promote the development of medical services in the direction of precision and personalization. Powerfully promote the advancement of pelvic floor repair technology: This invention integrates multidisciplinary advanced technologies and innovative design concepts, opens up new ways for the treatment of pelvic floor dysfunction, expands technical means and methods, has important clinical application value and broad market prospects, and is expected to lead technological innovation and development in the field of pelvic floor repair.

[0036] Example 3

[0037] The algorithm model used: "Pelvic Floor Muscle Dynamic Response Neural Network Algorithm (PFM-DRNN)"

[0038] Intelligent ultrasound image optimization based on PFM-DRNN: PFM-DRNN is used to perform real-time optimization of the images obtained by the ultrasound positioning module. It can automatically adjust the contrast and resolution of the image according to the dynamic characteristics of the levator ani muscle, more clearly display the subtle structure and damaged area of ​​the levator ani muscle, improve diagnostic accuracy, reduce the misdiagnosis rate caused by image blur, and provide a more reliable basis for subsequent repair.

[0039] PFM-DRNN-driven adaptive control of minimally invasive suturing instruments: PFM-DRNN analyzes the pelvic floor muscle contraction data collected by the biofeedback training module and the status of the levator ani muscles in ultrasound images, and adjusts the operating parameters of the minimally invasive suturing instruments in real time, such as the bending angle of the suture needle and the tension of the suture thread, so that the suturing process is more in line with the physiological characteristics of the levator ani muscles, reducing the difficulty of surgical operations and improving the accuracy and stability of suturing.

[0040] PFM-DRNN model for predicting personalized drug sustained-release curve: Based on the patient's individual physiological parameters (such as age, weight, body metabolic rate, etc.) and the degree of levator ani muscle injury, PFM-DRNN is used to construct a personalized drug sustained-release curve model to accurately control the release rate and dosage of drugs in the drug sustained-release module, ensuring that the drug continues to play an effective role during the critical period of levator ani muscle repair, improving tissue repair efficiency, and reducing drug waste and potential adverse reactions.

[0041] PFM-DRNN-assisted biofeedback training program optimization: With the help of PFM-DRNN, the patient's pelvic floor muscle training data is deeply analyzed, including muscle fatigue level, contraction strength growth trend, etc., to automatically generate highly personalized training programs for the biofeedback training module, dynamically adjust the training intensity and frequency, avoid overtraining or undertraining, accelerate the recovery of levator ani muscle function, and improve the durability of training effects.

[0042] Postoperative rehabilitation assessment and early warning system implemented by PFM-DRNN: PFM-DRNN is used to continuously monitor the recovery of the patient's pelvic floor muscles after surgery. By comparing a large amount of clinical data and the patient's individual rehabilitation data, possible complications or delayed rehabilitation risks can be predicted in advance, and early warnings can be issued to doctors in a timely manner. Doctors can take corresponding intervention measures based on the early warning information, such as adjusting the rehabilitation training plan, supplementing drug treatment, etc., to effectively ensure the patient's rehabilitation process and improve the success rate of surgery and patient satisfaction.

[0043] Example 4

[0044] The algorithm model used is: "Multi-modal Pelvic Data Fusion Evolutionary Algorithm (MPDF-EA)" MPDF-EA optimized ultrasound and bioelectric signal fusion positioning: the image data of the ultrasound positioning module and the pelvic floor electromyography signal of the biofeedback training module are fused and analyzed through MPDF-EA to achieve three-dimensional precise positioning of the levator ani muscle injury. It can not only accurately determine the coordinates of the injury on the plane, but also determine its depth information, overcoming the limitations of single modality positioning, providing more accurate navigation for minimally invasive suturing instruments, reducing the blindness of surgical operations, and reducing the risk of damage to surrounding tissues. Intelligent selection of absorbable suture materials based on MPDF-EA: Based on multimodal data such as the patient's pelvic floor muscle mechanical properties, body metabolism, and levator ani muscle injury type, MPDF-EA is used to screen the most suitable suture material from a variety of absorbable suture material libraries and optimize its degradation time and mechanical performance parameters to ensure that the suture can provide sufficient support during the entire repair process and degrade on time, avoiding repair failure or complications caused by improper suture selection and improving the stability and reliability of the repair effect.

[0045] MPDF-EA-driven minimally invasive suture path planning: MPDF-EA is used to conduct a comprehensive analysis of the anatomical structure of the levator ani muscle, injury morphology, and kinematic model of surgical instruments, and to plan the optimal suturing path for minimally invasive suturing instruments, thereby avoiding collision between instruments and surrounding tissues and unnecessary tissue pulling during suturing, shortening operation time, reducing surgical trauma, improving surgical efficiency and quality, and reducing the difficulty and fatigue of doctors' operations.

[0046] MPDF-EA generation of personalized biofeedback training model: MPDF-EA analyzes the multimodal information of the patient's pelvic floor muscle physiological parameters, living habits, psychological state, etc., and generates a unique biofeedback training model, including personalized customization of training content, training time, feedback method, etc. For example, for office workers, a more flexible fragmented training program is designed; for patients with greater psychological pressure, a more interesting and relaxing feedback form is adopted to improve the patient's training compliance and enthusiasm, and promote the rapid recovery of the levator ani muscle function.

[0047] Postoperative remote rehabilitation monitoring and management supported by MPDF-EA: With the help of MPDF-EA, a postoperative remote rehabilitation monitoring platform for patients is established. The data collected by patients using the biofeedback training module at home is integrated and analyzed with the clinical data of the hospital. Doctors can remotely understand the patient's rehabilitation progress in real time and adjust rehabilitation suggestions and training plans in time according to the analysis results of MPDF-EA, so as to achieve full and accurate management of patients' postoperative rehabilitation, improve the utilization efficiency of medical resources, and facilitate patients' rehabilitation treatment.

[0048] Example 5

[0049] Algorithm model used: "Quantum Annealing-assisted Pelvic Repair Intelligent Algorithm (QA-PRIA)" QA-PRIA realizes quantum enhancement processing of ultrasound images: quantum annealing technology is used to process the image of the ultrasound positioning module, which can search for the optimal parameter combination of image enhancement in a very short time, significantly improve the signal-to-noise ratio and edge clarity of the image, make the injury details of the levator ani muscle clearer, provide doctors with more accurate diagnostic information, help to formulate more accurate surgical plans, and improve the success rate and safety of surgery. Precise regulation of drug release of absorbable sutures based on QA-PRIA: The global optimization capability of the quantum annealing algorithm is used to accurately control the drug release process in the drug sustained-release module. According to the different stages of levator ani repair and the individual response of the patient, QA-PRIA is used to adjust the degradation rate and drug release amount of the drug sustained-release microspheres in real time to ensure that the concentration of the drug in the local tissue is always in the optimal treatment range, maximize the role of the drug in promoting tissue repair and preventing infection, reduce drug side effects, and accelerate the healing process of the levator ani muscle.

[0050] QA-PRIA optimizes the energy efficiency management of minimally invasive suturing instruments: During the operation of minimally invasive suturing instruments, QA-PRIA intelligently manages the energy consumption of the instruments. Based on factors such as the hardness of the surgical site, the elasticity of the tissue, and the difficulty of suturing, the energy output of the instrument is dynamically adjusted, so that the instrument can complete the suturing task with the lowest energy consumption while ensuring the operating accuracy, reduce the wear and failure probability of surgical instruments, extend the service life of the instruments, and reduce the risk of thermal damage to the patient's body during surgery.

[0051] QA-PRIA customization of personalized biofeedback training plan: With the rapid search and optimization capabilities of the quantum annealing algorithm, combined with the patient's pelvic floor muscle function assessment data, lifestyle and rehabilitation goals, a personalized training plan is generated for the biofeedback training module. QA-PRIA can find the most suitable program for the patient from a large number of training program combinations, including progressive adjustment of training intensity, personalized design of training movements, and optimized configuration of feedback signals, so as to achieve the best training effect, improve the recovery speed and quality of the patient's pelvic floor muscles, and reduce the recurrence rate of pelvic floor dysfunction.

[0052] QA-PRIA-supported intelligent postoperative rehabilitation prediction and intervention decision-making: QA-PRIA is used to deeply analyze and predict the patient's postoperative rehabilitation data, and by establishing a complex pelvic floor function recovery model, the patient's possible rehabilitation problems and potential risks can be judged in advance. Doctors can formulate targeted intervention measures in advance based on the prediction results of QA-PRIA, such as adjusting the drug treatment plan, increasing the intensity of rehabilitation training, or changing the training method, etc., to achieve intelligent and precise intervention in the patient's postoperative rehabilitation process, improve the effect of rehabilitation treatment and the patient's quality of life.

[0053] Example 6

[0054] Algorithm model used: "Chaos Theory-based Adaptive Algorithm for Pelvic Repair (CTA-APR)" CTA-APR-driven ultrasound image chaos feature extraction and analysis: Using chaos theory to extract and analyze the features of the levator anus muscle images obtained by the ultrasound positioning module can capture the nonlinear and chaotic features hidden in the image, which are important for identifying minor injuries and lesions of the levator anus muscle. Through the CTA-APR algorithm, doctors can more keenly detect potential levator anus muscle problems, intervene and treat in advance, avoid worsening of the disease, and improve the early diagnosis rate and treatment effect of the disease. CTA-APR dynamic optimization of the mechanical properties of absorbable sutures: According to the mechanical changes of the levator anus muscle during the repair process, the CTA-APR algorithm is used to dynamically adjust the mechanical properties of the absorbable sutures. By real-time monitoring of the contraction force of the pelvic floor muscles, the tension of the tissues, and the degradation of the sutures, CTA-APR can automatically optimize the elastic modulus, tensile strength and other parameters of the sutures, so that they can provide just the right support for the levator ani muscles at different stages of repair, ensure the stability of the repair effect, and reduce the risk of repair failure caused by the mismatch of the mechanical properties of the sutures. Chaotic motion control of minimally invasive suturing instruments implemented by CTA-APR: In minimally invasive suturing operations, a chaotic motion control strategy is introduced, and the CTA-APR algorithm is used to generate the motion trajectory of suturing instruments with chaotic characteristics. This chaotic motion can make the suture needle more flexible and accurate when passing through the tissue to avoid important structures such as blood vessels and nerves, while increasing the uniformity of tissue puncture, reducing tissue damage and postoperative pain. Compared with traditional deterministic motion control, chaotic motion control can improve the safety and minimally invasiveness of surgery, creating more favorable conditions for patients' postoperative recovery. CTA-APR adaptive adjustment of personalized biofeedback training intensity: Based on the sensitivity and adaptability of chaos theory, the CTA-APR algorithm can adaptively adjust the intensity of biofeedback training according to the real-time training response and recovery of the patient's pelvic floor muscles. When the patient's pelvic floor muscle strength increases rapidly, the training intensity is appropriately increased; when fatigue or slow recovery occurs, the intensity is timely reduced to avoid muscle damage and decreased training enthusiasm caused by overtraining. Through this adaptive training intensity adjustment, the stability and durability of the training effect are improved, and the gradual recovery and improvement of the levator ani muscle function are promoted. Chaos monitoring and early warning of the postoperative rehabilitation process supported by CTA-APR: CTA-APR is used to monitor and analyze various data in the patient's postoperative rehabilitation process, and a chaos prediction model for the rehabilitation status is constructed. By monitoring the parameter changes of the model, abnormal conditions and potential risks in the rehabilitation process, such as delayed tissue healing and signs of infection, are discovered in advance, and early warning signals are issued in a timely manner.Doctors can take appropriate measures to intervene based on the early warning information to ensure the smooth progress of the patient's recovery and improve the quality and safety of postoperative rehabilitation.

[0055] Example 7

[0056] Algorithm model used: "Deep Learning and Genetic Algorithm Fusion for Pelvic Repair Optimization (DLGA-FPRO)" Intelligent diagnosis and repair planning of ultrasound images realized by DLGA-FPRO: A large number of ultrasound images of the levator ani muscles are learned and trained by the deep learning model, and the model parameters are optimized by combining the genetic algorithm to realize the automatic diagnosis of ultrasound images and intelligent planning of repair plans. DLGA-FPRO can quickly and accurately identify the type, degree and range of injury of the levator ani muscles, and generate the best surgical repair path and suturing strategy according to the individual situation of the patient, providing doctors with scientific and accurate surgical guidance, improving surgical efficiency and quality, and reducing surgical time and patient pain. Optimization design of absorbable suture materials and structures based on DLGA-FPRO: The DLGA-FPRO algorithm is used to optimize the material composition and structure of absorbable sutures. By performing deep learning and genetic algorithm optimization on multi-dimensional data such as biocompatibility, mechanical properties and drug sustained release characteristics of different materials, absorbable suture materials and structures with better performance are developed. For example, a suture with gradient degradation characteristics is designed to provide strong support in the early stage of repair, and gradually degrade and release drugs in the later stage, so as to meet the different needs in the repair process of the levator ani muscle and improve the repair effect and tissue healing quality. DLGA-FPRO-driven intelligent operation assistance for minimally invasive suturing instruments: During the minimally invasive suturing process, the DLGA-FPRO algorithm provides doctors with intelligent operation assistance through real-time analysis of the operation data and ultrasound images of surgical instruments. It can predict the next best operation action of the surgical instrument and intuitively present the operation prompts to the doctor through virtual reality (VR) or augmented reality (AR) technology, helping the doctor to control the suturing instrument more accurately, reduce the errors and risks of surgical operation, and improve the success rate and safety of the operation, which is especially important for complex levator ani muscle injury repair surgery. DLGA-FPRO generation of personalized biofeedback training program: With the help of deep learning models, the patient's pelvic floor muscle physiological data, exercise habits, rehabilitation history and other information are deeply analyzed, and combined with the optimization capabilities of genetic algorithms, a highly personalized training program is generated for the biofeedback training module. DLGA-FPRO can accurately customize the training content, intensity, frequency and feedback method according to the characteristics and needs of each patient, so that the training program is more in line with the patient's actual situation, improve the patient's training compliance and enthusiasm, accelerate the recovery of the levator ani muscle function, and reduce the recurrence rate of pelvic floor dysfunction. DLGA-FPRO supports postoperative rehabilitation effect prediction and intelligent intervention: DLGA-FPRO algorithm is used to continuously monitor and analyze the patient's postoperative rehabilitation data and establish a prediction model for postoperative rehabilitation effect.Through this model, doctors can predict the patient's rehabilitation process and final rehabilitation effect in advance, and conduct intelligent intervention based on the predicted results. For example, when it is predicted that the patient may have delayed rehabilitation, timely adjust the rehabilitation training plan, increase physical therapy methods or optimize the drug treatment plan, etc., to achieve full and accurate management of the patient's postoperative rehabilitation, improve the success rate of rehabilitation treatment and the patient's quality of life.

[0057] Example 8

[0058] Algorithm model used: "Bee Colony Optimization-based Intelligent Decision-making Algorithm for Pelvic Repair (BCO-IDAPR)" BCO-IDAPR optimized ultrasound image feature selection and diagnostic decision: The bee colony optimization algorithm is used to select and optimize the features in the ultrasound positioning module image, screen out the feature subset most relevant to the diagnosis of levator ani muscle injury, and improve the accuracy and efficiency of diagnosis. BCO-IDAPR simulates the foraging behavior of the bee colony and quickly finds the optimal feature combination in the huge image feature space, providing doctors with more concise and accurate diagnostic information, which helps to quickly formulate a reasonable treatment plan and reduce patients' waiting time and anxiety. BCO-IDAPR intelligent regulation of the degradation time of absorbable sutures: According to the individual differences of patients and the progress of levator ani muscle repair, the degradation time of absorbable sutures is intelligently regulated using the BCO-IDAPR algorithm. By simulating the division of labor and cooperation mechanism of bee colonies, the algorithm can find the most suitable solution for patients among many combinations of degradation time parameters, ensure that the suture degrades within the appropriate time, provide sufficient support for the levator ani muscles, avoid tissue inflammation caused by suture residue, promote normal tissue healing, and improve the stability and safety of the repair effect. BCO-IDAPR-guided minimally invasive suture instrument path optimization and obstacle avoidance: In minimally invasive suture operations, the BCO-IDAPR algorithm simulates the behavior of bees to find the optimal path, plans the best suture path for suture instruments, and realizes intelligent obstacle avoidance. It can quickly calculate the safe path to avoid important tissues such as blood vessels and nerves based on the anatomical structure of the pelvic floor tissue and the real-time position information of the surgical instrument, while optimizing the length and angle of the suture path, reducing surgical trauma and operation time, improving the accuracy and safety of the operation, and reducing the risk and incidence of surgical complications. BCO-IDAPR dynamic generation of personalized biofeedback training plans: Based on the adaptability and dynamics of the bee colony optimization algorithm, BCO-IDAPR dynamically generates personalized biofeedback training plans based on the real-time training data and rehabilitation status of the patient's pelvic floor muscles. The algorithm can continuously adjust the parameters in the training program, such as training intensity, frequency, movement patterns, etc., to adapt to the patient's physical changes and recovery process, improve the sustainability and adaptability of the training effect, help patients recover the function of the levator ani muscles faster, and improve the quality of life. Postoperative rehabilitation risk assessment and intelligent early warning supported by BCO-IDAPR: Use BCO-IDAPR to conduct comprehensive analysis and risk assessment of the patient's postoperative rehabilitation data, and build a postoperative rehabilitation risk prediction model. By simulating the information transmission and collaboration mechanism of the bee colony, the algorithm can promptly detect potential risk factors in the rehabilitation process, such as signs of infection, poor tissue healing, etc., and issue intelligent early warnings in advance.Doctors can take corresponding preventive and treatment measures based on the early warning information, effectively reduce the risk of postoperative recovery, ensure the smooth recovery of patients, and improve the quality and efficiency of medical services.

[0059] Example 9

[0060] Algorithm model used: "Hybrid Augmented Intelligent Pelvic Repair Algorithm (HAIPRA)"

[0061] Modeling and solving process: Ultrasonic image data of the levator ani muscle are collected from the ultrasound positioning module, including image samples of different angles, different degrees of injury and different individuals. These images are preprocessed by denoising, grayscale normalization and other operations to improve image quality and data consistency. At the same time, the electrophysiological signal data of the patient's pelvic floor muscle is obtained from the biofeedback training module, filtered, amplified and feature extracted, and characteristic parameters related to muscle contraction force, fatigue degree, etc. are extracted. In addition, the individual physiological parameters of the patient, such as age, weight, height, body metabolic rate, etc., and detailed clinical diagnostic information of levator ani muscle injury, including injury type, location, range, etc., are collected to construct a multimodal data set.

[0062] Model construction phase: Image feature extraction model based on deep learning: A convolutional neural network (CNN) is constructed to automatically learn the features of the levator ani muscle in ultrasound images. The architecture of CNN includes multiple convolutional layers, pooling layers, and fully connected layers. By training on a large number of ultrasound images, CNN can automatically extract feature maps related to the structure and injury of the levator ani muscle, which will be used as one of the inputs of the subsequent model. Injury classification model based on support vector machine: The features extracted by CNN are classified using support vector machine (SVM) to determine the type and degree of injury of the levator ani muscle. SVM separates feature data of different categories by finding an optimal hyperplane, thereby achieving accurate classification of levator ani muscle injury. When training SVM, the cross-validation method is used to select the optimal model parameters, such as kernel function type, penalty parameter, etc., to improve the generalization ability of the model. Parameter optimization model based on particle swarm optimization: A parameter optimization model based on particle swarm optimization (PSO) is constructed for the degradation time of absorbable sutures, drug release parameters of drug sustained-release microspheres, operating parameters of minimally invasive suture instruments, and parameters of biofeedback training programs. These parameters are encoded as the position vector of the particle, and each particle represents a set of parameter combinations. According to the pre-defined fitness function, the advantages and disadvantages of the parameter combination represented by each particle are evaluated. The fitness function comprehensively considers multiple factors such as repair effect, surgical safety, and patient comfort. For example, for the degradation time of absorbable sutures, the fitness function will consider whether the sutures provide sufficient support while avoiding inflammatory reactions caused by long-term residues; for drug release parameters, the effective concentration and duration of the drug in the critical period of levator ani repair will be considered. Through information exchange and position update between particles, the PSO algorithm continuously searches for the optimal parameter combination until the preset convergence conditions are met. Rehabilitation prediction model based on time series analysis: For the postoperative rehabilitation process of patients, time series analysis methods such as autoregressive moving average model (ARIMA) or long short-term memory network (LSTM) are used to establish a prediction model for rehabilitation effect. The pelvic floor muscle function assessment data collected regularly after surgery are input into the model as time series data. The model learns the time variation law of rehabilitation data and predicts the recovery trend of the patient's pelvic floor muscle function in the future, including the growth of muscle strength and the improvement of dysfunction symptoms. By analyzing the predicted results, possible recovery delays or complication risks can be discovered in advance, providing doctors with timely intervention recommendations.

[0063] Model fusion and collaboration stage: The image features extracted by CNN, the injury classification results of SVM and other relevant clinical data are fused by weighted fusion to obtain a comprehensive levator ani injury assessment index. This index not only takes into account the anatomical structure information on the image, but also combines clinical diagnosis and physiological parameters and other information to provide a more comprehensive and accurate basis for subsequent treatment decisions. During the treatment process, the parameters optimized by PSO are transmitted to the corresponding modules in real time. For example, the production process of absorbable sutures is customized according to the optimized degradation time and drug release parameters; the control system of minimally invasive suturing instruments is adjusted according to the optimized operating parameters to achieve intelligent operation assistance; the biofeedback training module provides patients with personalized training programs according to the optimized training plan parameters. At the same time, the rehabilitation prediction model continuously updates the prediction results, adjusts the model parameters in time according to the deviation between the actual rehabilitation data and the predicted data, improves the accuracy of the prediction, and feeds back the prediction results to the doctor so that the doctor can dynamically adjust the treatment plan.

[0064] Model verification and optimization phase: Use an independent test data set to verify the entire HAIPRA model and evaluate the model's performance indicators in terms of diagnostic accuracy, treatment effect prediction, parameter optimization, etc. For example, calculate the accuracy, recall rate, and F1 value of ultrasound image diagnosis, evaluate the consistency between the actual recovery of patients after surgical repair and the model prediction results, and analyze the degree to which the optimized parameters improve the treatment effect. Based on the verification results, further optimize and improve the model. If it is found that the performance of a certain module is not ideal, such as CNN's insufficient feature extraction of certain types of levator ani muscle injuries, it can be improved by increasing training data, adjusting the network structure, or optimizing the training algorithm. At the same time, continuously collect new clinical data, update and optimize the model online to meet the needs of different patient groups and complex conditions, and improve the clinical practicality and reliability of the model.

[0065] Through the above modeling and solving process, the HAIPRA algorithm can comprehensively utilize a variety of technical means to achieve all-round optimization and precise control of the levator ani muscle repair process, provide patients with more efficient, safe and personalized treatment plans, and improve the treatment effect of pelvic floor dysfunction and the quality of life of patients.

[0066] Example 10

[0067] The algorithm model used: "Adaptive Evolutionary Neural Network Algorithm for Pelvic Repair (AENNA-PR)"

[0068] AENNA-PR is used to reconstruct the low-resolution levator ani muscle images obtained by the ultrasound positioning module with super-resolution. Through the learning ability of the neural network, the image features and mapping relationships are automatically learned from a large number of high- and low-resolution image pairs, and the low-resolution images are upgraded to high-resolution images, clearly showing the subtle structure and injury details of the levator ani muscle, significantly improving the accuracy of injury identification, reducing misdiagnosis and missed diagnosis caused by insufficient image resolution, and providing a reliable foundation for subsequent precise repair. At the same time, AENNA-PR can adaptively adjust the model parameters of image reconstruction and injury identification, optimize the weights and thresholds of the neural network according to the image characteristics and injury types of different patients, and further enhance the recognition ability of complex injury conditions. Even tiny tears or lesions can be accurately detected, effectively improving the sensitivity and specificity of diagnosis.

[0069] Develop an absorbable suture material with self-repair function, and use AENNA-PR for intelligent regulation. When the suture is stretched or damaged by external force, the smart material inside it can sense the stress change and self-repair through the micro-nano structure controlled by the AENNA-PR algorithm, maintaining the mechanical integrity of the suture and ensuring that stable support is continuously provided during the repair of the levator ani muscle. According to the healing process of the levator ani muscle and the individual physiological state of the patient, AENNA-PR adjusts the degradation rate of the suture and the drug release pattern in real time. Through the comprehensive analysis of pelvic floor electromyography signals, ultrasound image features and patient body metabolic data, the drug release amount and time of drug sustained-release microspheres are precisely controlled, so that the drug can act accurately on the repair site and promote tissue regeneration, while avoiding excessive or insufficient use of drugs, improving the treatment effect and reducing the potential risk of adverse reactions.

[0070] AENNA-PR optimized intelligent navigation and tactile feedback enhancement for minimally invasive suturing instruments: The AENNA-PR-based intelligent navigation system is integrated into the minimally invasive suturing instrument, combined with ultrasound images and pre-built pelvic floor anatomical models to provide the instrument with real-time and accurate navigation information, guiding the suture needle to accurately reach the site of injury, avoiding important blood vessels and nerve structures, and significantly improving the safety and accuracy of the operation. At the same time, the tactile feedback function of the instrument is enhanced through the AENNA-PR algorithm, so that doctors can more clearly feel the texture, hardness and suture strength of the tissue during the operation, as if they were directly in contact with the tissue, so as to better control the suturing operation, reduce tissue damage and suturing errors caused by insensitive tactile sensation, and further improve the quality of surgery and the patient's postoperative recovery effect.

[0071] AENNA-PR supports personalized biofeedback training gamification interaction and incentive mechanism: A gamification interaction interface based on AENNA-PR is designed for the biofeedback training module, which transforms pelvic floor muscle training into interesting game tasks, such as simulated sports challenges, situational interactive games, etc., to improve patients' training enthusiasm and participation. AENNA-PR dynamically adjusts the game difficulty and reward mechanism according to the patient's training performance and psychological state to motivate patients to continue training. At the same time, through real-time analysis of the patient's physiological data and behavioral data during the game, AENNA-PR continuously optimizes the training plan, personalizes the increase or decrease of training intensity and frequency, ensures the maximization of training effects, accelerates the recovery of levator ani muscle function, and improves the patient's psychological state and quality of life.

[0072] AENNA-PR realizes remote intelligent monitoring and holographic diagnosis of postoperative rehabilitation: AENNA-PR is used to establish a remote intelligent monitoring platform for postoperative rehabilitation. Patients use rehabilitation equipment equipped with sensors at home to collect real-time data on pelvic floor muscle activity, body posture, and living habits, and upload them to the cloud via wireless transmission. AENNA-PR conducts a comprehensive analysis of these multi-source data, and combines the hospital's clinical diagnosis data to build a holographic rehabilitation model for patients, achieving a comprehensive and visual diagnosis of the patient's rehabilitation status. Doctors can access the holographic model at any time through a remote terminal, intuitively understand the patient's rehabilitation progress, and promptly identify potential problems. Through the intelligent suggestions generated by AENNA-PR, they can provide patients with accurate rehabilitation guidance and intervention measures, realize the full intelligent management of postoperative rehabilitation, and improve the utilization efficiency of medical resources and the patient's rehabilitation satisfaction.

[0073] Modeling and solving process: Collect a large amount of ultrasound image data of the levator ani muscles of different individuals and different degrees of injury, including normal and pathological image samples, and annotate and classify them. At the same time, collect the patient's pelvic floor muscle electrophysiological signal data, clinical diagnosis information, physiological parameter data, and various monitoring data during postoperative rehabilitation to establish a comprehensive database covering multimodal information. Preprocess the image data, including image enhancement, denoising, normalization and other operations to improve image quality and data consistency; perform feature extraction and quantification on other data and convert them into a format suitable for model input.

[0074] Neural network model construction: An adaptive evolutionary neural network model with multiple hidden layers is constructed. The input layer receives multimodal information such as preprocessed ultrasound image data, pelvic floor muscle electrophysiological signal data, and physiological parameter data. The output layer outputs decision information related to levator ani repair, such as image reconstruction results, injury identification categories, suture control parameters, surgical instrument operation instructions, biofeedback training programs, and rehabilitation prediction results. In the hidden layer of the neural network, an adaptive evolutionary algorithm is used to optimize the connection weights and thresholds of neurons. The algorithm simulates the natural selection and genetic variation mechanism in the biological evolution process, evaluates the pros and cons of each individual (i.e., a set of parameter configurations of the neural network) according to the fitness function, selects excellent individuals for genetic operations, such as crossover and mutation, and gradually evolves the optimal neural network parameters so that it can better adapt to the complex and changeable levator ani repair task requirements.

[0075] Model training and optimization: The organized data set is divided into training set, validation set and test set, and distributed according to a certain ratio. The training set is used to train the AENNA-PR model, and the parameters of the neural network are continuously adjusted through the back propagation algorithm to minimize the error function between the predicted results and the actual labels. During the training process, the validation set is used regularly to evaluate the performance of the model, and the training parameters such as learning rate and number of iterations are adjusted according to the evaluation results to prevent overfitting and ensure that the model has good generalization ability. For different task modules, such as ultrasound image super-resolution reconstruction, injury identification, and absorbable suture regulation, corresponding loss functions and optimization targets are designed respectively. For example, in the image super-resolution reconstruction task, the mean square error loss function based on pixel difference is used, and combined with indicators such as structural similarity index (SSIM) for comprehensive evaluation; in the injury identification task, the cross entropy loss function is used in combination with indicators such as accuracy and recall rate for optimization; for tasks such as absorbable suture regulation and biofeedback training program generation, special loss functions are designed according to clinical treatment effects and patient rehabilitation indicators to achieve accurate optimization and improvement of model performance.

[0076] Model fusion and collaborative work: In the AENNA-PR model, information sharing and collaborative work are achieved between various task modules. For example, the output of the ultrasound image super-resolution reconstruction module is used as the input of the injury recognition module, and the injury recognition results provide decision-making basis for the absorbable suture regulation and surgical instrument navigation modules; the pelvic floor muscle electrophysiological signals and rehabilitation monitoring data are used to optimize the biofeedback training program and update the postoperative rehabilitation prediction module. Through this close module collaboration, the entire system can be adaptively adjusted and optimized according to the patient's real-time situation, providing a comprehensive, integrated intelligent solution for levator ani repair.

[0077] Model verification and evaluation: The trained AENNA-PR model is fully verified and evaluated using the test set, and the performance indicators of each task module are calculated, such as the peak signal-to-noise ratio (PSNR) of ultrasound image super-resolution reconstruction, the accuracy and F1 value of injury identification, the error rate of absorbable suture regulation, the accuracy of surgical instrument navigation, the effectiveness indicators of the biofeedback training program, and the accuracy of postoperative rehabilitation prediction. The evaluation results are compared and analyzed with other existing methods and technologies to demonstrate the advantages and innovations of the AENNA-PR model in the field of levator ani repair. At the same time, feedback from clinicians and patients is collected to further optimize and improve the model to make it more in line with actual clinical needs and user experience requirements, continuously improve the reliability and practicality of the model, and bring better treatment effects and rehabilitation experience to patients with pelvic floor dysfunction.

[0078] The levator ani muscle repair system and method of the present invention provide efficient, safe and personalized solutions for the treatment of levator ani muscle injuries by virtue of innovative design and technology integration, and have shown good application effects and broad development prospects in clinical practice. With the continuous advancement and improvement of technology, it is expected to bring benefits to more patients with pelvic floor dysfunction, promote pelvic floor repair technology to a new height, and contribute to the development of medical and health care.

Claims

1. A levator ani muscle repair system, characterized in that: include: Ultrasound positioning module, used to obtain the anatomical structure and injury condition of the levator ani muscle in real time, the module includes a high-resolution ultrasound probe and image processing software; An absorbable suture module, composed of polylactic-co-glycolic acid absorbable suture; A minimally invasive suturing instrument module having an elongated operating rod with a length of 20-30 cm and a diameter of 5-8 mm; The biofeedback training module is used to monitor the contraction of the patient's pelvic floor muscles in real time and convert it into intuitive visual signals to feed back to the patient. It also has a built-in personalized training program. The sensor of the biofeedback training module uses an electromyographic sensor, which can accurately collect the electrophysiological signals of the pelvic floor muscles and present the feedback signals to the patient through a display screen. The drug sustained-release module is realized through drug sustained-release microspheres in the absorbable sutures, which continuously release drugs during the degradation and absorption process of the sutures, providing a favorable microenvironment for the healing of the levator ani muscles; The intelligent control module is connected to the above modules, receives the image information of the ultrasound positioning module and the muscle contraction signal of the biofeedback training module, intelligently optimizes and adjusts the operating parameters of the minimally invasive suturing instrument module based on this information, and records the patient's treatment process and rehabilitation data.

2. The levator ani muscle repair system according to claim 1, characterized in that: The absorbable suture is added with drug-sustaining microspheres with a particle size of 10-50 μm, which contain drugs that promote tissue repair and growth, wherein the growth factor release amount reaches 30%-40% of the total content within 1 week after surgery, and the antibiotic reaches an effective antibacterial concentration within 3 days after surgery.

3. The levator ani muscle repair system according to claim 1, characterized in that: It also includes a fine suture needle and a suture guide device, and the operating rod is also provided with an angle adjustment device, and the angle adjustment range is 0-180 degrees.

4. The levator ani muscle repair system according to claim 1, characterized in that: The intelligent control module adopts a control system based on machine learning, which can automatically adjust the suturing speed, needle distance and suturing angle parameters of the minimally invasive suturing instrument according to the levator ani muscle injury characteristics in the ultrasound image and the muscle contraction force data of the biofeedback, with an error range of less than ±5%.

5. A method for using the levator ani muscle repair system according to claim 1, characterized in that: The following steps are involved: Preoperative preparation steps: Perform a comprehensive pelvic floor examination on the patient, including ultrasound examination and pelvic floor muscle strength assessment using the ultrasound positioning module to determine the damage to the anal levator muscles and develop a personalized surgical plan. At the same time, the patient's intestines and perineum are cleaned and prepared; Ultrasound positioning step: At the beginning of the operation, the probe of the ultrasound positioning module is placed in the pelvic floor area through the vagina or rectum. Start the ultrasound device to obtain a clear image of the levator ani muscles, analyze and mark the injured area; Minimally invasive suturing steps: Use the suture needle and suture guide device to pass the suture of the absorbable suture module through the damaged levator ani muscle tissue, and suture according to the predetermined suturing method. During this period, the intelligent control module assists in adjusting the suturing parameters according to the ultrasound image and the operating feel; Drug sustained release and repair steps: After suturing is completed, the drug sustained release microspheres in the drug sustained release module release drugs to promote the healing of the levator ani muscles. At the same time, the absorbable sutures are gradually degraded and absorbed in the body to maintain the sutured and fixed state of the levator ani muscles until the tissue heals; Postoperative biofeedback training steps: During the patient's postoperative recovery period, the biofeedback training module is used to exercise the pelvic floor muscles. The sensor is attached to the perineal skin, and the pelvic floor muscle contraction and relaxation training is performed according to the personalized training plan based on the visual signals fed back by the module; Follow-up and evaluation steps: Patients are followed up regularly after surgery. Through evaluation methods such as ultrasound examination and pelvic floor muscle strength test, and using data recorded by the intelligent control module, the repair of the anal levator muscles and the degree of recovery of pelvic floor function are understood, and the rehabilitation training plan is adjusted accordingly.

Images