Method and system for evaluating suture effect of anorectal operation based on image recognition

Abstract

The invention relates to the technical field of anorectal operation suturing, in particular to an anorectal operation suturing effect evaluation method and system based on image recognition, which can improve the objectivity and accuracy of evaluation and realize real-time feedback and immediate adjustment. The method comprises the following steps: acquiring treatment scheme data of an anorectal operation, and extracting a suture feature influence parameter set from the treatment scheme data; the suturing feature influence parameter set comprises a suturing tissue structure, a suturing wound shape, a suturing wound width and a suturing wound length; inputting the stitching feature influence parameter set into a pre-trained standard stitching feature contrast model to generate a standard stitching feature set; the standard suture feature set comprises a standard suture needle density, a standard suture edge distance and a standard suture needle distance; acquiring a surgical suturing image in real time, and segmenting and extracting suturing part sub-images from the surgical suturing image; and inputting the suturing part sub-image into a pre-constructed suturing feature image recognition model.

Description

Technical Field

[0001] The present invention relates to the technical field of anorectal surgery suturing, and in particular to an anorectal surgery suturing effect evaluation method and system based on image recognition. Background Art

[0002] Anorectal surgery is a common type of surgical procedure, in which suturing technology is crucial to the success of the operation. Accurate and precise suturing can not only promote wound healing, but also reduce the incidence of complications, directly affecting the patient's healing effect and postoperative recovery.

[0003] In anorectal surgery, the evaluation of the suture effect of the wound mainly relies on the doctor's intuitive observation and experience judgment, which is easily affected by the doctor's subjective factors, resulting in inaccurate and inconsistent evaluation results. At the same time, existing evaluation methods are usually performed after the operation is completed and cannot provide immediate feedback during the operation, making it difficult for doctors to adjust the suturing strategy in time to optimize the surgical effect. Summary of the invention

[0004] In order to solve the above technical problems, the present invention provides an anorectal surgery suturing effect evaluation method and system based on image recognition, which can improve the objectivity and accuracy of the evaluation and realize real-time feedback and immediate adjustment.

[0005] In a first aspect, the present invention provides an anorectal surgery suture effect evaluation method based on image recognition, the method comprising: Acquire treatment plan data for anorectal surgery, and extract a set of suture feature influencing parameters from the treatment plan data; the set of suture feature influencing parameters includes suture tissue structure, suture wound shape, suture wound width, and suture wound length; Inputting the suture feature influencing parameter set into a pre-trained standard suture feature control model to generate a standard suture feature set; the standard suture feature set includes a standard suture needle density, a standard suture margin and a standard suture needle distance; Acquire surgical suture images in real time, and segment and extract suture site sub-images from the surgical suture images; Inputting the suture site sub-image into a pre-built suture feature image recognition model to obtain a real-time suture feature set; the real-time suture feature set includes a real-time suture needle density, a real-time suture margin, and a real-time suture needle distance; Deviation analysis is performed on the real-time stitching feature set and the standard stitching feature set to obtain the real-time stitching effect evaluation grade.

[0006] Furthermore, a method for performing deviation analysis on the real-time stitching feature set and the standard stitching feature set to obtain the real-time stitching effect evaluation grade includes: Performing difference calculations on the real-time stitching feature set and the corresponding stitching features in the standard stitching feature set respectively to obtain a real-time stitching feature deviation set; the real-time stitching feature deviation set includes deviation values ​​of each stitching feature; Inputting the stitching feature influencing parameter set into a pre-built stitching effect influencing weight database to obtain a stitching effect influencing weight set; the stitching effect influencing weight set includes weight coefficients corresponding to the deviation values ​​of each stitching feature; According to the obtained stitching effect influence weight set, the real-time stitching feature deviation set is comprehensively calculated to obtain the real-time stitching effect score; The real-time suturing effect score is mapped within a pre-divided suturing effect evaluation grade range to obtain a real-time suturing effect evaluation grade.

[0007] Further, in response to the real-time suturing effect evaluation level being lower than a preset evaluation level threshold: Inputting the real-time suturing feature deviation set into a pre-built suturing feature compensation model to obtain a compensation suturing feature set for subsequent suturing operations; the compensation suturing feature set includes a compensation suturing needle density, a compensation suturing margin, and a compensation suturing needle distance; The compensating suturing feature set is fed back to the surgical suturing surgeon, and the surgeon is reminded to perform subsequent surgical suturing operations according to the compensating suturing feature set.

[0008] Furthermore, the formula for calculating the real-time suturing effect evaluation grade is: ; in, S Indicates the real-time suture effect evaluation level, Δ i represents the deviation value of the i-th stitching feature, wi represents the influence weight of the i-th stitching feature, n Represents the number of stitching features. The sum in the numerator of the formula calculates the deviation Δ of each stitching feature. i Multiply by its corresponding weight wi The denominator is the sum of all stitching feature weights.

[0009] Furthermore, the method for segmenting and extracting the suture site sub-image from the surgical suture image comprises: Capture real-time images during surgery and transmit the acquired real-time images; Preprocess the acquired real-time images, including image enhancement and noise removal; Detect the edges of the suture area and extract the complete suture area through edge connection and morphological operations; Post-processing operations are performed on the extracted suture area, including removing small noise areas, filling holes and smoothing edges; According to the suture site area of ​​the post-processing operation, a sub-image containing the suture site is cropped from the original surgical image.

[0010] Furthermore, the method for performing deviation analysis between the real-time stitching feature set and the standard stitching feature set includes: Confirm that the real-time stitching feature set is consistent with the standard stitching feature set in terms of data type, unit, and precision; For each feature in the real-time stitching feature set, the deviation value between it and the corresponding feature in the standard stitching feature set is calculated respectively; All calculated deviation values ​​are sorted into a set, namely, a real-time stitching feature deviation set.

[0011] Furthermore, the formula for calculating the real-time suture needle distance by the suture feature image recognition model is: ; G Indicates the stitch length of the suture. gi Indicates i Suture needle to i +1 stitch distance, n Indicates the total number of suture needles in the suture area.

[0012] Furthermore, factors affecting the setting of the preset evaluation level threshold include surgery type, individual differences among patients, suturing technical specifications, historical data analysis, and safety risk control.

[0013] On the other hand, the present application also provides an anorectal surgery suture effect evaluation system based on image recognition, the system comprising: A data extraction module, which obtains treatment plan data of anorectal surgery and extracts a set of suture feature influencing parameters from the treatment plan data; the set of suture feature influencing parameters includes suture tissue structure, suture wound shape, suture wound width and suture wound length; A standard suture feature generation module, inputting the suture feature influencing parameter set into a pre-trained standard suture feature control model to generate a standard suture feature set; the standard suture feature set includes a standard suture needle density, a standard suture margin and a standard suture needle distance; A real-time image acquisition and segmentation module acquires surgical suture images in real time and extracts suture site sub-images from the surgical suture images; A suturing feature image recognition module, which inputs the suturing part sub-image into a pre-built suturing feature image recognition model to obtain a real-time suturing feature set; the real-time suturing feature set includes a real-time suturing needle density, a real-time suturing margin and a real-time suturing needle distance; The real-time suturing effect evaluation module performs deviation analysis on the real-time suturing feature set and the standard suturing feature set to obtain the real-time suturing effect evaluation grade.

[0014] Furthermore, the surgical suturing compensation module is used to input the real-time suturing feature deviation set into a pre-stored suturing feature compensation model to obtain a compensated suturing feature set for subsequent suturing operations when the real-time suturing effect evaluation level is lower than a preset evaluation level threshold; the compensated suturing feature set includes a compensated suturing needle density, a compensated suturing margin and a compensated suturing needle distance; the compensated suturing feature set is fed back to the surgical suturing surgeon, and the surgeon is reminded to perform subsequent surgical suturing operations according to the compensated suturing feature set.

[0015] Compared with the prior art, the present invention has the following beneficial effects: through the automated image recognition technology, the method can objectively and accurately extract and analyze suture features, reducing the influence of the doctor's subjective judgment on the evaluation results; it helps to reduce the inaccuracy and inconsistency of the evaluation results and improve the reliability of the evaluation; This method can acquire surgical suturing images and evaluate them in real time, providing doctors with immediate feedback on suturing effects; enabling doctors to promptly detect and correct suturing problems during surgery, thereby optimizing surgical outcomes and reducing the occurrence of complications; By generating a real-time suture effect evaluation grade, it provides important decision support for doctors. Doctors can adjust suture strategies based on the evaluation results to ensure the accuracy and precision of suture, thereby promoting wound healing and postoperative recovery of patients. Automated evaluation reduces the time and energy required for doctors to conduct subjective evaluations during surgery, allowing doctors to focus more on the surgical operation itself; it helps improve the overall efficiency of surgery, shortens surgery time, and reduces patient pain; This method provides a unified standard for evaluating suturing effects through a pre-trained standard suturing feature control model; this helps promote the standardization and regularization of anorectal surgical suturing techniques and improve medical quality and safety; In summary, the image recognition-based anorectal surgery suture effect evaluation method can significantly improve the objectivity and accuracy of the evaluation, achieve real-time feedback and immediate adjustment, and finely evaluate the suture quality. It also has standardization and repeatability, providing important support for the safety and effectiveness of anorectal surgery. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a flow chart of the present invention; Figure 2 is a flow chart for extracting sub-images of suture sites; Figure 3 is a flow chart for obtaining a real-time suturing effect evaluation grade; Figure 4 This is a structural diagram of an anorectal surgery suture effect evaluation system based on image recognition. DETAILED DESCRIPTION

[0017] In the description of this application, those skilled in the art should know that this application can be implemented as a method, an apparatus, an electronic device, and a computer-readable storage medium. Therefore, this application can be specifically implemented in the following forms: complete hardware, complete software (including firmware, resident software, microcode, etc.), a combination of hardware and software. In addition, in some embodiments, this application can also be implemented in the form of a computer program product in one or more computer-readable storage media, and the computer-readable storage medium contains computer program code.

[0018] The above-mentioned computer-readable storage medium may adopt any combination of one or more computer-readable storage media. Computer-readable storage media include: electrical, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media include: portable computer disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, flash memories, optical fibers, optical disc read-only memories, optical storage devices, magnetic storage devices, or any combination of the above. In the present application, computer-readable storage media can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or device.

[0019] The acquisition, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws.

[0020] The present application describes the provided methods, devices, and electronic devices through flowcharts and / or block diagrams.

[0021] It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions. These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer or other programmable data processing device to produce a machine, and these computer-readable program instructions are executed by a computer or other programmable data processing device to produce a device that implements the functions / operations specified by the boxes in the flowchart and / or block diagram.

[0022] These computer-readable program instructions may also be stored in a computer-readable storage medium that enables a computer or other programmable data processing device to work in a specific manner. In this way, the instructions stored in the computer-readable storage medium produce an instruction device product including functions / operations specified in the blocks in the flowchart and / or block diagram.

[0023] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable data processing apparatus to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.

[0024] The present application is described below in conjunction with the drawings in the present application.

[0025] Embodiment 1: Figure 1 to Figure 2 As shown, the anorectal surgery suture effect evaluation method based on image recognition of the present invention specifically includes the following steps: S1. Acquire treatment plan data for anorectal surgery, and extract a set of suture feature influencing parameters from the treatment plan data; the set of suture feature influencing parameters includes suture tissue structure, suture wound shape, suture wound width, and suture wound length; The treatment plan data for anorectal surgery is obtained through the surgical plan prepared by the doctor before the operation. The surgical plan includes the patient's medical history, preoperative examination results, surgical indication analysis and surgical risk assessment; Using natural language processing and image recognition technology, the suture feature influencing parameter set is automatically extracted from the surgical plan. The suture feature influencing parameter set includes: Suture tissue structure: refers to the type of anorectal tissue that needs to be sutured. Different tissue types have different suturing requirements; Suture wound shape: refers to the geometric shape of the wound. Different shapes will affect the difficulty and effect of suturing; Suture wound width: refers to the distance between the two edges of the wound. The width will affect the suture tension distribution and healing speed. Suture wound length: refers to the longitudinal length of the wound. The length will also affect the complexity of suture and the healing effect. After completing the extraction of the set of parameters affecting stitching features, the set is stored in the system for use in subsequent steps; at the same time, encryption and access control measures should be taken to ensure the security and privacy of the data.

[0026] In this step, by directly extracting the suture feature influencing parameters from the detailed surgical plan made by the doctor before the operation, it can be ensured that the data based on the evaluation is the latest and most accurate; this avoids the deviation of the evaluation results caused by errors in the information transmission or recording process, thereby improving the accuracy and reliability of the evaluation; this step reduces the interference of human factors by automatically extracting the suture feature influencing parameters, making the evaluation results more objective and consistent; using natural language processing and image recognition technology, it is possible to extract the suture feature influencing parameters before or during the operation, which makes it possible to evaluate the surgical suture effect immediately; it helps doctors to make timely adjustments during the operation. The invention can adjust the suturing strategy and optimize the surgical effect; automatically extract the set of parameters affecting suturing features, reduce the workload of doctors in manually inputting data, and improve the efficiency of surgical preparation and evaluation; enable doctors to focus more on the surgery itself without spending too much time on data sorting and analysis; after completing the extraction of the set of parameters affecting suturing features, the security and privacy of the data can be ensured by taking encryption and access control measures; this step S1 automatically extracts the set of parameters affecting suturing features, and provides accurate, objective and timely data support for the evaluation of the suturing effect of anorectal surgery, which helps to improve the surgical effect, reduce the incidence of complications, and protect the data security and privacy of patients.

[0027] S2, inputting the suture feature influencing parameter set into a pre-trained standard suture feature control model to generate a standard suture feature set; Input the set of stitching feature influencing parameters into the trained standard stitching feature comparison model; the model will calculate the corresponding standard stitching feature set based on these parameters and the knowledge learned internally; The result of model inference is a set of standard suture needle density, standard suture margin, and standard suture needle distance. These standard features will serve as the benchmark for subsequent real-time suture effect evaluation to measure whether the actual effect of surgical suture meets the standard. In practical applications, the standard suture feature control model needs to be regularly verified and optimized to ensure that the output standard features always meet the latest clinical requirements and best practices; The standard stitching feature set includes: The standard suture needle density refers to the number of suture needles per unit length, which depends on the wound width and tissue type; the mathematical expression of the standard suture needle density is: Dstd = f 1( P 1, P 2, P 3, P 4); The standard suture margin refers to the distance between the suture line and the wound edge, which is used to maintain the integrity of the wound edge; the mathematical expression of the standard suture margin is: Mstd = f 2( P 1, P 2, P 3, P 4); The standard suture stitch length refers to the distance between two adjacent stitches, which helps to maintain uniform closure of the wound; the mathematical expression of the standard suture stitch length is: Sstd = f 3( P 1, P 2, P 3, P 4); In this step, by inputting the suture feature influencing parameter set into the pre-trained standard suture feature control model, a set of standardized and scientific suture feature sets can be generated; it provides a clear benchmark for the subsequent real-time suture effect evaluation, helps to unify the evaluation standards, and reduces the influence of subjective factors; the evaluation method based on the standard suture feature set can accurately reflect the actual effect of surgical suture; by comparing the real-time suture features with the standard features, it can timely discover the deviation in the suture process, so as to evaluate whether the suture effect meets the standard, which helps to improve the accuracy and reliability of the evaluation; the standard suture feature control model needs to be verified and optimized regularly to ensure that the standard features it outputs are always It complies with the latest clinical requirements and best practices; it enables the evaluation method to adapt to changes in different patients and different surgical conditions, and maintain its effectiveness and adaptability; by introducing a standardized suture effect evaluation method, it can promote the standardization and refinement of surgical operations, reduce the occurrence of complications, and improve patients' healing effects and postoperative recovery speed; at the same time, this evaluation method also helps to improve the overall quality of medical services and enhance patients' trust and satisfaction with the medical process; this step has important application value in the evaluation of anorectal surgery suture effects, and by providing a standardized evaluation benchmark and an instant feedback mechanism, it helps to improve surgical quality, reduce risks, and ultimately improve patients' prognosis and quality of life.

[0028] S3, acquiring the surgical suture image in real time, and segmenting and extracting the suture site sub-image from the surgical suture image; The method for segmenting and extracting a suture site sub-image from a surgical suture image comprises: Capturing images during the operation through an image acquisition device, connecting the image acquisition device to an image processing system, so that the images during the operation can be transmitted to the processing system in real time and without delay; Before image segmentation, the acquired real-time image is preprocessed, including image enhancement and noise removal, to improve image quality and reduce the impact of interference factors on subsequent processing; In the evaluation of anorectal surgery suture effect, the purpose of image segmentation is to accurately separate the suture site from the entire surgical image; the edge of the suture site is detected using an edge detection operator, and then the complete suture site area is extracted through edge connection or morphological operations; After the segmentation is completed, post-processing operations are performed, including removing small noise areas, filling holes and smoothing edges to further improve the accuracy and completeness of the segmentation results; Based on the segmentation results, sub-images containing the suture sites are cropped from the original surgical images; these sub-images will serve as inputs for the subsequent suture feature image recognition model; The extracted suture site sub-image is saved to a specified storage location.

[0029] In this step, through the real-time connection between the image acquisition device and the image processing system, the images during the operation can be transmitted to the processing system immediately and without delay; this ensures that the evaluation of the suturing effect can keep up with the progress of the operation, providing doctors with immediate feedback, which helps to adjust the suturing strategy in time and optimize the operation effect; the real-time image is preprocessed before image segmentation, which reduces the influence of interference factors on subsequent image segmentation and feature recognition, making the segmentation result more accurate and the feature recognition more reliable; the edge detection operator is used to accurately segment the suture site, which can accurately separate the suture site from the complex surgical image; this lays a solid foundation for subsequent feature extraction and effect evaluation, and improves the accuracy and reliability of the entire evaluation system. The post-processing operation after the segmentation is completed further improves the accuracy and completeness of the segmentation results; reduces the impact of image noise, holes and other problems on subsequent processing, so that the final suture site sub-image is more in line with the evaluation requirements; the sub-image containing the suture site cut out according to the segmentation result is used as the input of the subsequent suture feature image recognition model, which simplifies the processing flow and improves the processing efficiency; through the real-time image segmentation and extraction of S3 step, the doctor can get instant feedback on the suture effect during the operation; it helps the doctor to adjust the suture strategy in time, reduce the occurrence of complications, and improve the success rate of the operation and the patient's satisfaction; at the same time, it also provides more accurate and detailed image data for postoperative evaluation and medical records.

[0030] S4, inputting the suture part sub-image into a pre-constructed suture feature image recognition model to obtain a real-time suture feature set; the real-time suture feature set includes a real-time suture needle density, a real-time suture margin and a real-time suture needle distance; The suture feature image recognition model is a model based on deep learning and traditional image processing technology. After being trained with a large amount of labeled suture image data, it can automatically identify and extract the key feature parameters of the suture site. The suture site sub-image is input into a pre-built suture feature image recognition model, and the model identifies the number of suture needles per unit area, evaluates the suture needle density, measures the distance between the suture line and the wound edge, obtains the real-time suture margin, calculates the average distance between adjacent suture needles, and obtains the suture needle distance; After completing feature recognition, the model outputs a real-time stitched feature set; The formula for calculating the real-time suture needle density by the suture feature image recognition model is: ; in, D represents the density of suture needles, N Indicates the total number of suture needles in the suture area, A Indicates the area of ​​the suture region; The formula for calculating the real-time stitching margin by the stitching feature image recognition model is: ; M represents the average stitching margin, mi Indicates i The margin distance of the measuring points, n Indicates the number of measurement points; The formula for calculating the real-time suture needle distance by the suture feature image recognition model is: ; G Indicates the stitch length of the suture. gi Indicates i Suture needle to i +1 stitch distance, n Indicates the total number of suture needles in the suture area.

[0031] In this step, the pre-built suture feature image recognition model can automatically and efficiently identify the key feature parameters in the surgical suture image, reducing the subjectivity and time cost of the doctor's evaluation of the suture effect and improving the efficiency and accuracy of the evaluation; the model based on deep learning and traditional image processing technology, after training with a large amount of labeled data, can accurately identify and extract the feature parameters of the suture site, reducing the errors caused by human factors, making the evaluation results more objective and reliable; during the operation, the suture feature set is obtained and analyzed in real time, which can provide the doctor with instant feedback on the suture effect; if the evaluation result shows that the suture effect does not meet the expected standard, the doctor can immediately Adjust the suturing strategy based on feedback, optimize the surgical effect, reduce the occurrence of complications, and improve the patient's healing effect and postoperative recovery; by performing deviation analysis on the real-time suturing feature set and the standard suturing feature set, and combining it with the predetermined suturing effect influence weight, the real-time suturing effect evaluation level can be obtained; it not only provides doctors with quantitative indicators of suturing quality, but also can serve as a basis for intelligent auxiliary decision-making, helping doctors to formulate more scientific and reasonable surgical plans; this step realizes accurate evaluation and instant feedback of the suturing effect of anorectal surgery by introducing the suturing feature image recognition model, which helps to improve the overall quality and safety of the operation and bring better treatment effects and rehabilitation experience to patients.

[0032] S5, performing deviation analysis on the real-time stitching feature set and the standard stitching feature set to obtain a real-time stitching feature deviation set; The method for performing deviation analysis between a real-time stitching feature set and a standard stitching feature set comprises: Verify that the live stitch feature set is consistent with the standard stitch feature set in data type, units, and precision to allow for accurate comparison For each feature in the real-time stitching feature set, the deviation value between it and the corresponding feature in the standard stitching feature set is calculated respectively; the deviation value is obtained by subtraction operation, that is, the real-time value minus the standard value; the deviation value indicates the deviation direction of the real-time value relative to the standard value, a positive deviation indicates that the real-time value is higher than the standard value, and a negative deviation indicates that the real-time value is lower than the standard value; All calculated deviation values ​​are sorted into a set, namely, a real-time stitching feature deviation set.

[0033] In this step, by ensuring the consistency of the real-time suturing feature set and the standard suturing feature set in data type, unit and precision, a solid foundation is laid for deviation analysis; errors that may be caused by differences in data formats are eliminated, thereby improving the accuracy of the evaluation; deviation analysis directly calculates the difference between the real-time value and the standard value, that is, the deviation value, through subtraction operations; this quantification method enables doctors to intuitively understand in which aspects of the suturing operation there are deviations and the degree of deviation; the deviation value not only indicates the degree of deviation, but also clarifies the direction of deviation; the results of the deviation analysis can be fed back to the surgical suturing doctor in real time; this immediacy enables doctors to quickly identify problems during the operation and take corresponding compensatory measures, thereby optimizing the suturing effect and reducing the occurrence of complications; through a standardized deviation analysis process, the suturing operations of different doctors or the same doctor at different time points can be objectively and consistently evaluated; it helps to improve the consistency and repeatability of surgical results and improve the overall medical quality.

[0034] S6. Based on a predetermined suturing effect influence weight, comprehensively calculate the real-time suturing feature deviation set to obtain the real-time suturing effect evaluation grade; wherein the suturing effect influence weight is determined according to the suturing feature influence parameter set; Inputting the stitching feature influencing parameter set into a pre-built stitching effect influencing weight database to obtain a stitching effect influencing weight set; the stitching effect influencing weight set includes weight coefficients corresponding to the deviation values ​​of each stitching feature; For each suture feature deviation, its contribution to the overall score is calculated according to its corresponding suture effect influence weight. The formula for calculating the real-time suture effect evaluation level is: ; in, S Indicates the real-time suture effect evaluation level, Δ i represents the deviation value of the i-th stitching feature, wi represents the influence weight of the i-th stitching feature, n Represents the number of stitching features. The sum in the numerator of the formula calculates the deviation Δ of each stitching feature. i Multiply by its corresponding weight wi The denominator is the sum of all stitching feature weights.

[0035] In this step, by introducing the suturing effect influence weight set, the evaluation process no longer relies solely on the doctor's intuitive judgment and experience, but is based on objective data and scientific weight distribution, thereby greatly improving the accuracy and reliability of the evaluation results; the evaluation method can be carried out in real time, and the doctor can immediately obtain feedback information on the suturing effect during the operation; it helps the doctor to adjust the suturing strategy in time, optimize the surgical effect, and reduce the occurrence of complications; the determination and application of the suturing effect influence weights help promote the standardization and normalization of anorectal surgical suturing operations; the doctor will pay more attention to the precise control of various suturing features during the operation to achieve the best suturing effect; by comprehensively calculating the real-time suturing feature deviation set, the real-time suturing effect evaluation level is obtained, which helps the doctor to make more wise decisions during the operation and further improve the quality of the operation; accurate and fine suturing can not only promote wound healing, but also reduce the incidence of complications, thereby improving the patient's healing effect and postoperative recovery; this step S6 realizes accurate evaluation and immediate feedback of the real-time suturing feature deviation set by introducing the suturing effect influence weight set, which can improve the anorectal surgical suturing effect, promote standardized operation, and improve surgical quality and patient satisfaction.

[0036] S7, in response to the real-time suturing effect evaluation level being lower than a preset evaluation level threshold, inputting the real-time suturing feature deviation set into a pre-constructed suturing feature compensation model to obtain a compensation suturing feature set for subsequent suturing operations; the compensation suturing feature set includes a compensation suturing needle density, a compensation suturing margin, and a compensation suturing needle distance; Inputting a real-time stitching feature deviation set into a stitching feature compensation model, the real-time stitching feature deviation set including a specific deviation value of each stitching feature; The suture feature compensation model outputs a set of compensation suture features, namely, a recommended compensation suture needle density, a compensation suture margin and a compensation suture needle distance; The factors affecting the setting of the preset evaluation level threshold include: Type of surgery: Different types of anorectal surgery have different requirements for suture quality; the complexity of the surgery will also affect the setting of the threshold; highly complex surgeries are often accompanied by higher risks and require higher suture results; Individual differences among patients: factors such as the patient’s age, health status, and tissue type may affect the evaluation of suture results; the patient’s special condition or medical history may also be a factor to be considered when setting the threshold; Suture technology specifications: The standards and specifications for suture technology in the medical community are constantly developing and improving; when setting the evaluation level threshold, it is necessary to refer to the latest suture technology standards and specifications to ensure the accuracy and reliability of the evaluation results; Historical data analysis: By analyzing the suture effect evaluation results and patient prognosis in historical surgical data, some rules and experiences can be summarized; these rules and experiences can be used as the basis for setting the evaluation level threshold; Safety risk control: When setting the evaluation level threshold, the safety and risk control during the operation should be considered; if the threshold is set too loosely, some potential suture quality problems will be ignored, increasing the surgical risk and the incidence of complications; if the threshold is set too strictly, it will lead to frequent compensatory operations, increasing the operation time and complexity.

[0037] In this step, by evaluating the suturing effect in real time and comparing it with the preset evaluation level threshold, potential problems of suturing quality can be discovered in real time during the operation; once it is found that the suturing effect is lower than expected, the compensation mechanism is immediately activated to provide doctors with immediate feedback and adjustment suggestions; it helps doctors to respond quickly during the operation and optimize the suturing strategy, thereby improving the quality of the operation and the prognosis of the patient; based on the real-time suturing feature deviation set, the suturing feature compensation model can output a targeted compensation suturing feature set, and the personalized compensation suggestions can fully consider factors such as the type of operation, individual differences of patients, and the standards and specifications of suturing technology, providing doctors with more accurate and effective guidance; by timely discovering and correcting suturing quality problems, this step helps to reduce the risks and incidence of complications during the operation; it avoids problems such as poor wound healing and infection caused by improper suturing, and improves the safety and reliability of the operation; through instant feedback and personalized compensation suggestions, doctors can perform suturing operations more efficiently during the operation; it reduces the extension of operation time and the increase of complexity caused by repeated inspections and adjustments, and improves the overall efficiency and effect of the operation; this step can not only improve the quality of the operation and the prognosis of the patient in the evaluation of the suturing effect of anorectal surgery, but also reduce the incidence of surgical risks and complications, and improve the efficiency and effect of the operation.

[0038] S8, feeding back the compensation suturing feature set to the surgeon, and reminding the surgeon to perform subsequent suturing operations according to the compensation suturing feature set; The compensation suturing feature set is first transmitted in real time in the operating room to the display device, including the operating room display screen and the doctor's personal device; the transmission is carried out through a secure network channel to ensure the confidentiality and integrity of the data; The set of compensatory suturing features should be presented to the doctor in an intuitive and easy-to-understand way so that the doctor can quickly understand the current suturing situation and the aspects that need to be adjusted; After the doctor accepts the compensatory suturing feature set and adjusts the suturing strategy, the surgical suturing images are continuously monitored and the new suturing effect is evaluated in real time. This process is repeated until the suturing effect evaluation level reaches or exceeds the preset threshold, ensuring that the suturing quality is continuously optimized and improved during the operation. After the stitching operation is completed, the entire evaluation process and compensation suggestions are recorded, including the real-time stitching feature set, the standard stitching feature set, the real-time stitching effect evaluation level, the compensation stitching feature set, and the final stitching effect.

[0039] In this step, through the compensating suturing feature set transmitted in real time in the operating room, the doctor can instantly obtain accurate feedback on the suturing effect; it ensures that the doctor can quickly identify problems and adjust the suturing strategy during the operation, thereby effectively reducing suturing quality problems caused by subjective judgment or delayed feedback; the intuitive display and easy understanding of the compensating suturing feature set help doctors more accurately grasp the precision and standardization of suturing; it not only promotes wound healing, but also significantly reduces the incidence of complications, directly improves the overall quality of the operation and the patient's postoperative recovery effect; by continuously monitoring the surgical suturing images and evaluating the new suturing effect in real time, a closed-loop evaluation and adjustment mechanism is constructed; it ensures that every step of the operation is carried out under strict monitoring, greatly improving the controllability and safety of the operation; the detailed records after the suturing operation are completed provide valuable data support for the evaluation of the surgical effect and subsequent improvements; it can not only be used for personal review and summary of doctors, but also as a basis for hospitals or research institutions to improve surgical techniques and optimize evaluation models.

[0040] Embodiment 2: Figure 3 As shown, the anorectal surgery suturing effect evaluation system based on image recognition of the present invention specifically includes the following modules; A data extraction module, which obtains treatment plan data of anorectal surgery and extracts a set of suture feature influencing parameters from the treatment plan data; the set of suture feature influencing parameters includes suture tissue structure, suture wound shape, suture wound width and suture wound length; A standard suture feature generation module, inputting the suture feature influencing parameter set into a pre-trained standard suture feature control model to generate a standard suture feature set; the standard suture feature set includes a standard suture needle density, a standard suture margin and a standard suture needle distance; A real-time image acquisition and segmentation module acquires surgical suture images in real time and extracts suture site sub-images from the surgical suture images; A suturing feature image recognition module, which inputs the suturing part sub-image into a pre-built suturing feature image recognition model to obtain a real-time suturing feature set; the real-time suturing feature set includes a real-time suturing needle density, a real-time suturing margin and a real-time suturing needle distance; The real-time suturing effect evaluation module performs deviation analysis on the real-time suturing feature set and the standard suturing feature set to obtain the real-time suturing effect evaluation grade.

[0041] The system automatically extracts and analyzes suture features through image recognition technology, reducing the impact of doctors' subjective judgment on the evaluation results, improving the objectivity and accuracy of the evaluation; and helping to reduce the inconsistency of evaluation results caused by differences in doctors' experience; The system can acquire and evaluate surgical suturing images in real time, providing doctors with immediate feedback on suturing results. This enables doctors to adjust suturing strategies in a timely manner during surgery, optimize surgical results, reduce complications, and promote faster recovery for patients. The application of advanced image recognition technology in the evaluation of anorectal surgical suture results has realized intelligent decision-making assistance; it has not only improved the efficiency and accuracy of surgical evaluation, but also reduced the workload of doctors, allowing them to focus more on the surgical operation itself; The system can store and manage relevant data during the surgical suturing process, providing a rich data source for subsequent data analysis and research, and helping to further improve and optimize suturing techniques and evaluation methods; by improving the accuracy and timeliness of suturing effect evaluation, the system helps to improve the overall medical quality of anorectal surgery; accurate evaluation results help doctors develop more reasonable treatment plans and rehabilitation plans, thereby better meeting the needs of patients.

[0042] The various variations and specific embodiments of the anorectal surgery suturing effect evaluation method based on image recognition in the aforementioned embodiment 1 are also applicable to the anorectal surgery suturing effect evaluation system based on image recognition in this embodiment. Through the aforementioned detailed description of the anorectal surgery suturing effect evaluation method based on image recognition, those skilled in the art can clearly know the implementation method of the anorectal surgery suturing effect evaluation system based on image recognition in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here.

[0043] In addition, the present application also provides an electronic device, including a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor. The transceiver, the memory, and the processor are respectively connected via a bus. When the computer program is executed by the processor, each process of the above-mentioned method for controlling output data is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be described here.

[0044] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for evaluating the suture effect of anorectal surgery based on image recognition, characterized in that: The method comprises: Acquire treatment plan data for anorectal surgery, and extract a set of suture feature influencing parameters from the treatment plan data; the set of suture feature influencing parameters includes suture tissue structure, suture wound shape, suture wound width, and suture wound length; Inputting the suture feature influencing parameter set into a pre-trained standard suture feature control model to generate a standard suture feature set; the standard suture feature set includes a standard suture needle density, a standard suture margin and a standard suture needle distance; Acquire surgical suture images in real time, and segment and extract suture site sub-images from the surgical suture images; Inputting the suture site sub-image into a pre-built suture feature image recognition model to obtain a real-time suture feature set; the real-time suture feature set includes a real-time suture needle density, a real-time suture margin, and a real-time suture needle distance; Deviation analysis is performed on the real-time stitching feature set and the standard stitching feature set to obtain the real-time stitching effect evaluation grade.

2. The anorectal surgery suture effect evaluation method based on image recognition according to claim 1, characterized in that: The method of performing deviation analysis on the real-time stitching feature set and the standard stitching feature set to obtain the real-time stitching effect evaluation grade includes: Performing difference calculations on the real-time stitching feature set and the corresponding stitching features in the standard stitching feature set respectively to obtain a real-time stitching feature deviation set; the real-time stitching feature deviation set includes deviation values ​​of each stitching feature; Inputting the stitching feature influencing parameter set into a pre-built stitching effect influencing weight database to obtain a stitching effect influencing weight set; the stitching effect influencing weight set includes weight coefficients corresponding to the deviation values ​​of each stitching feature; According to the obtained stitching effect influence weight set, the real-time stitching feature deviation set is comprehensively calculated to obtain the real-time stitching effect score; The real-time suturing effect score is mapped within a pre-divided suturing effect evaluation grade range to obtain a real-time suturing effect evaluation grade.

3. The method for evaluating the effect of anorectal surgery suturing based on image recognition according to claim 2, characterized in that: In response to the real-time stitching effect evaluation level being lower than a preset evaluation level threshold: Inputting the real-time suturing feature deviation set into a pre-built suturing feature compensation model to obtain a compensation suturing feature set for subsequent suturing operations; the compensation suturing feature set includes a compensation suturing needle density, a compensation suturing margin, and a compensation suturing needle distance; The compensating suturing feature set is fed back to the surgical suturing surgeon, and the surgeon is reminded to perform subsequent surgical suturing operations according to the compensating suturing feature set.

4. The anorectal surgery suture effect evaluation method based on image recognition according to claim 1, characterized in that: The formula for calculating the real-time suturing effect evaluation level is: ； in, S Indicates the real-time suture effect evaluation level, Δ i represents the deviation value of the i-th stitching feature, wi represents the influence weight of the i-th stitching feature, n Represents the number of stitching features. The sum in the numerator of the formula calculates the deviation Δ of each stitching feature. i Multiply by its corresponding weight wi The denominator is the sum of all stitching feature weights.

5. The method for evaluating the effect of anorectal surgery suturing based on image recognition according to claim 1, characterized in that: The method for segmenting and extracting a suture site sub-image from a surgical suture image comprises: Capture real-time images during surgery and transmit the acquired real-time images; Preprocess the acquired real-time images, including image enhancement and noise removal; Detect the edges of the suture area and extract the complete suture area through edge connection and morphological operations; Post-processing operations are performed on the extracted suture area, including removing small noise areas, filling holes and smoothing edges; According to the suture site area of ​​the post-processing operation, a sub-image containing the suture site is cropped from the original surgical image.

6. The method for evaluating the effect of anorectal surgery suturing based on image recognition according to claim 1, characterized in that: The method for performing deviation analysis between a real-time stitching feature set and a standard stitching feature set comprises: Confirm that the real-time stitching feature set is consistent with the standard stitching feature set in terms of data type, unit, and precision; For each feature in the real-time stitching feature set, the deviation value between it and the corresponding feature in the standard stitching feature set is calculated respectively; All calculated deviation values ​​are sorted into a set, namely, a real-time stitching feature deviation set.

7. The method for evaluating the effect of anorectal surgery suturing based on image recognition according to claim 1, characterized in that: The formula for calculating the real-time suture needle distance by the suture feature image recognition model is: ； G Indicates the stitch length of the suture. gi Indicates i Suture needle to i +1 stitch distance, n Indicates the total number of suture needles in the suture area.

8. The method for evaluating the effect of anorectal surgery suturing based on image recognition according to claim 3, characterized in that: The factors affecting the setting of the preset evaluation level threshold include the type of surgery, individual differences among patients, suturing technical specifications, historical data analysis, and safety risk control.

9. An anorectal surgery suture effect evaluation system based on image recognition, characterized in that: The system comprises: A data extraction module, which obtains treatment plan data of anorectal surgery and extracts a set of suture feature influencing parameters from the treatment plan data; the set of suture feature influencing parameters includes suture tissue structure, suture wound shape, suture wound width and suture wound length; A standard suture feature generation module, inputting the suture feature influencing parameter set into a pre-trained standard suture feature control model to generate a standard suture feature set; the standard suture feature set includes a standard suture needle density, a standard suture margin and a standard suture needle distance; A real-time image acquisition and segmentation module acquires surgical suture images in real time and extracts suture site sub-images from the surgical suture images; A suturing feature image recognition module, which inputs the suturing part sub-image into a pre-built suturing feature image recognition model to obtain a real-time suturing feature set; the real-time suturing feature set includes a real-time suturing needle density, a real-time suturing margin and a real-time suturing needle distance; The real-time suturing effect evaluation module performs deviation analysis on the real-time suturing feature set and the standard suturing feature set to obtain the real-time suturing effect evaluation grade.

10. The anorectal surgery suturing effect evaluation system based on image recognition according to claim 9, characterized in that: Also includes: The surgical suturing compensation module is used to input the real-time suturing feature deviation set into a pre-stored suturing feature compensation model to obtain a compensating suturing feature set for subsequent suturing operations when the real-time suturing effect evaluation level is lower than a preset evaluation level threshold; the compensating suturing feature set includes compensating suturing needle density, compensating suturing margin and compensating suturing needle distance; the compensating suturing feature set is fed back to the surgical suturing surgeon, and the surgeon is reminded to perform subsequent surgical suturing operations according to the compensating suturing feature set.

Images