Endoscope-based Anal Fistula Model Construction Method, System and Application

Abstract

The present application proposes a method, system and application for constructing an anal fistula model based on an endoscope. The method includes: obtaining data and adjusting it to obtain an operation guide for an electronic colonoscope; performing an examination according to the operation guide; judging whether the patient has an anal fistula through an analysis model; if there is an anal fistula, parsing out the first anal fistula data and searching for relevant anal fistula cases, and then predicting the second anal fistula data; constructing a plurality of complete three-dimensional anal fistula models around the first anal fistula data and the second anal fistula data. The present application provides comprehensive and multi-dimensional data support for model construction by integrating various data types, intelligently analyzes anal fistula-related data with the aid of an analysis model, simplifies the modeling process, improves the diagnosis efficiency, and is of great significance to the accuracy and rapidity of clinical diagnosis.

Description

Technical Field

[0001] This application relates to the field of role simulation. Specifically, it relates to a method, system, and application for constructing an anal fistula model based on an endoscope. Background Art

[0002] As a common disease in the anorectal department, the pathogenesis of anal fistula is complex, and the prevalence rate is on the rise, seriously affecting the health and quality of life of patients. For accurate diagnosis and effective treatment of anal fistula, the construction of an anal fistula model plays a crucial role. Early diagnosis of anal fistula relies on digital rectal examination and probe examination. These methods have extremely high requirements for doctors' experience and are seriously affected by subjective factors. In the face of complex anal fistulas with multiple fistula branches and deep positions, it is difficult to guarantee the diagnostic accuracy. With the development of medical imaging technology, detection methods such as CT, MRI, and endoscopes have gradually been applied to the diagnosis of anal fistula, providing more data support for the construction of anal fistula models.

[0003] However, the existing construction of anal fistula models overly relies on detection data. Taking CT and MRI as examples, although they can provide detailed anatomical structure information of anal fistulas, the detection process is cumbersome, time-consuming, and the examination cost is relatively high, bringing a greater burden to patients. Moreover, the construction of the model often requires a large amount of manpower to process and analyze these detection data, resulting in low efficiency of model construction. Even with the introduction of computer-aided technology, due to the lack of integration of comprehensive information such as patients' symptoms and medical histories, it is still impossible to efficiently construct an accurate anal fistula model. In actual clinical applications, the low diagnostic efficiency not only delays the treatment of patients but also causes a certain degree of waste of medical resources. Summary of the Invention

[0004] Based on the problems existing in the prior art, this application provides a method, system, and application for constructing an anal fistula model based on an endoscope. The specific solutions are as follows:

[0005] In the first part, this application proposes a method for constructing an anal fistula model based on an endoscope, including the following:

[0006] Obtain the patient's body data and symptom manifestation data related to anal fistula, select a corresponding operation template according to the body data, and adjust the operation template according to the symptom manifestation data to obtain an operation guide for the electronic colonoscope for this patient;

[0007] Control the electronic colonoscope to examine the patient according to the operation guide to obtain detection image data; judge whether the patient has an anal fistula according to the detection image data and the symptom manifestation data through a preset analysis model;

[0008] If there is an anal fistula, the first anal fistula data involving the internal orifice and fistula tract of the anal fistula is parsed from the detected image data in combination with the preset non-anal fistula pathological data, and relevant anal fistula cases are searched in the anal fistula medical record database based on the first anal fistula data and the symptom manifestation data;

[0009] One or more sets of second anal fistula data are predicted by the parsing model according to the preset medical detection data, symptom manifestation data, anal fistula cases and the first anal fistula data;

[0010] A primary three-dimensional model of the anal fistula is constructed around the first anal fistula data, and a plurality of complete three-dimensional models of the anal fistula are constructed on the basis of the primary three-dimensional model in combination with the second anal fistula data.

[0011] In some specific embodiments, each operation template corresponds to non-anal fistula pathological data obtained by performing an electronic colonoscopy operation according to the operation template, and the pathological features and pathological regions are pre-annotated in the anal fistula case data;

[0012] The non-anal fistula pathological data corresponding to the operation template is adjusted according to the difference between the operation template and the operation guide to obtain reference image data;

[0013] The local features of the corresponding pathological regions in the detected image data are extracted by the parsing model and compared with the corresponding pathological features to quickly analyze the difference between the detected image data and the reference image data;

[0014] Based on the comprehensive difference analysis results and the symptom manifestation data, it is judged whether the patient has an anal fistula.

[0015] In some specific embodiments, the non-anal fistula pathological data is divided into healthy data and non-anal fistula disease data;

[0016] The healthy data includes the morphological data of healthy intestinal mucosa and histological pathological data detected sequentially according to the operation template, and the non-anal fistula disease data includes the image data of inflammatory bowel disease, intestinal polyp image data and intestinal tumor image data detected sequentially according to the operation template.

[0017] In some specific embodiments, the parsing model is used to analyze the difference between the detected image data and the healthy data to obtain a first difference region;

[0018] Analyze the difference between the detected image data and the non-anal fistula disease data in the first difference region; if there is a first difference region in the detected image data that is different from any non-anal fistula disease data, then it is determined that the first difference region is a lesion region;

[0019] Extract the image features of the lesion area and analyze whether there are preset internal orifice features. If so, it is determined that the patient has anal fistula, and the relevant information involving the internal orifice and fistula of the lesion area is extracted to obtain the first anal fistula data.

[0020] In some specific embodiments, the first anal fistula data includes the position of the internal orifice, the shape of the internal orifice, and the starting direction of the fistula.

[0021] The second anal fistula data includes the length of the fistula, the branches of the fistula, and the relationship with the surrounding tissues of the fistula.

[0022] In some specific embodiments, in the anal fistula case database, search for all cases with a similarity degree higher than the preset value in terms of the position of the internal orifice, the shape of the internal orifice, and the starting direction of the fistula of the patient to obtain anal fistula cases.

[0023] Determine the extension direction and extension length of all fistulas in the anal fistula cases, and count the number of various extension directions and extension lengths, so as to predict the length and extension direction of the fistula.

[0024] Analyze the mass characteristics in the symptom manifestation data, set a data statistics method according to the mass characteristics, and count the fistula branch situation and the relationship between the fistula and the surrounding tissues in the anal fistula cases according to the data statistics method, so as to predict the fistula branch and the relationship between the fistula and the surrounding tissues of the patient.

[0025] In some specific embodiments, if in the first anal fistula data, the starting direction of the fistula shows multi-directional extension, the position of the internal orifice is far from the normal position of the anal crypt, or the shape of the internal orifice is irregular, it is determined that the anal fistula of the patient is a complex anal fistula, and medical detection items are increased to obtain the medical detection data.

[0026] The second part, this application proposes an anal fistula model construction system based on an endoscope, including the following:

[0027] An operation unit, configured to obtain the physical data of the patient and the symptom manifestation data related to anal fistula, select a corresponding operation template according to the physical data, and adjust the operation template according to the symptom manifestation data to obtain an operation guide for the electronic colonoscope for this patient.

[0028] An acquisition unit, configured to control the electronic colonoscope to examine the patient according to the operation guide to obtain detection image data; judge whether the patient has anal fistula according to the detection image data and the symptom manifestation data through a preset parsing model.

[0029] An analysis unit, if there is anal fistula, combines the preset non-anal fistula pathological data to parse the first anal fistula data involving the internal orifice and fistula from the detection image data, and searches for relevant anal fistula cases in the anal fistula medical record database based on the first anal fistula data and the symptom manifestation data.

[0030] A prediction unit, configured to predict one or more groups of second anal fistula data through the parsing model according to preset medical detection data, symptom manifestation data, anal fistula cases, and first anal fistula data;

[0031] A model unit, configured to construct a primary three-dimensional model of an anal fistula around the first anal fistula data, and construct a plurality of complete three-dimensional models of anal fistulas on the basis of the primary three-dimensional model in combination with the second anal fistula data.

[0032] Part Three, the present application proposes a computer device, and the computer device includes:

[0033] One or more processors;

[0034] A memory, configured to store one or more programs;

[0035] When the one or more programs are executed by the one or more processors, the one or more processors implement the endoscopic-based anal fistula model construction method as described in any one of the first part.

[0036] Part Four, the present application proposes a computer program product, including executable instructions, which are used to implement the endoscopic-based anal fistula model construction method as described in any one of the first part when executed by a processor.

[0037] Advantageous effects: The present application proposes an endoscopic-based anal fistula model construction method, system and application, which provides comprehensive and multi-dimensional data support for model construction by integrating multiple data types, simplifies the modeling process, overcomes the problem of low efficiency of existing model construction, and meets the needs of clinical rapid diagnosis. After integrating multiple data types, data processing is performed using a preset parsing model and a computer system, and the whole process from data acquisition to model construction can be quickly completed. Compared with traditional manual analysis and modeling methods, the time required for modeling is greatly shortened. By obtaining the patient's body data and symptom manifestation data to select and adjust the operation template, a personalized electronic colonoscopy operation guide is obtained, which helps to perform examinations more targeted and improve the quality and efficiency of obtaining detection image data. At the same time, the preset parsing model can be used to more accurately identify anal fistulas, reducing misdiagnosis and missed diagnosis. It can not only parse the first anal fistula data involving the internal opening and fistula of the anal fistula from the detection image data, but also predict the second anal fistula data including the length of the fistula, the branches of the fistula, and the tissue relationship around the fistula by combining multiple data, so as to comprehensively obtain relevant information of the anal fistula and provide richer and more accurate basis for subsequent model construction and treatment. Searching for relevant cases in the anal fistula medical record database based on the first anal fistula data and symptom manifestation data, and predicting the second anal fistula data accordingly, makes full use of past case experience and improves the accuracy and reliability of predicting complex situations of anal fistulas.

[0038] To make the above objects, features, and advantages of the present application more obvious and understandable, the following presents preferred embodiments in conjunction with the accompanying drawings and provides a detailed description as follows. Description of the Drawings

[0039] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0040] Figure 1 is a schematic flowchart of the method for constructing an anal fistula model of the present application;

[0041] Figure 2 is a schematic diagram of the principle of the method for constructing an anal fistula model of the present application;

[0042] Figure 3 is a schematic flowchart of the process for determining an anal fistula of the present application;

[0043] Figure 4 is a schematic diagram of the system modules for constructing an anal fistula model of the present application.

[0044] Reference Signs: 1 - Operating Unit; 2 - Acquisition Unit; 3 - Analysis Unit; 4 - Prediction Unit; 5 - Model Unit. Detailed Embodiments

[0045] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts fall within the scope of protection of the present application.

[0046] The present application proposes a method for constructing an anal fistula model based on an endoscope, which breaks the dependence on single detection data in the traditional three-dimensional model construction of anal fistulas by integrating patient body data, symptom manifestation data, detection image data, and information in the anal fistula medical record database. The schematic flowchart of the method for constructing an anal fistula model based on an endoscope is as shown in the appendix Figure 1 as shown, and the principle is as shown in the appendix Figure 2 as shown, and the specific solution is as follows:

[0047] A method for constructing an anal fistula model based on an endoscope includes the following:

[0048] 101. Obtain the patient's physical data and data on symptoms related to anal fistula, select the corresponding operation template based on the physical data, and adjust the operation template according to the symptom data to obtain the operation guide for the patient's electronic colonoscope;

[0049] 102. Control the electronic colonoscope to examine the patient according to the operation guide to obtain detection image data; use a preset analysis model to determine whether the patient has an anal fistula based on the detection image data and the symptom data;

[0050] 103. If an anal fistula exists, parse the first anal fistula data involving the internal opening and fistula of the anal fistula from the detection image data in combination with non-anal fistula pathological data, and search for relevant anal fistula cases in the anal fistula medical record database based on the first anal fistula data and the symptom data;

[0051] 104. Use the analysis model to predict one or more groups of second anal fistula data based on preset medical detection data, symptom data, anal fistula cases, and the first anal fistula data;

[0052] 105. Construct a primary three-dimensional model of the anal fistula around the first anal fistula data, and construct multiple complete three-dimensional models of the anal fistula on the basis of the primary three-dimensional model in combination with the second anal fistula data.

[0053] Step 101 mainly involves customizing the operation guide for the electronic colonoscope for the patient. The patient's physical data includes information in multiple aspects, such as age, gender, basic physical condition, past medical history, etc. These data are very crucial because different physical conditions will affect the way and risk of electronic colonoscope operation. For example, the intestines of elderly patients may be more fragile, and more caution is needed during the operation; for patients with a history of abdominal surgery, the structure of the intestines may have changed, and special attention needs to be paid to avoid damage during the operation.

[0054] The data on symptoms related to anal fistula are important bases for judging the patient's condition and adjusting the operation template. Common symptom manifestations include pain, swelling, purulent discharge, itching, etc. around the anus, as well as specific information such as the frequency, duration, and severity of the symptoms. For example, patients who frequently have purulent discharge around the anus accompanied by severe pain may have a more serious anal fistula condition, and different strategies need to be adopted during the operation. The sources for obtaining the said symptom data include the patient's self-report, medical history data, doctor's observation, palpation examination, and auxiliary examination; the physical data includes age, basic vital signs, body shape, and nutritional status.

[0055] Based on the obtained patient physical data, select the matching operation template from a series of pre-set operation templates. Each operation template is formulated for people with different physical characteristics and covers the operation process, parameter settings, precautions, and other contents. For example, for patients with relatively healthy bodies and no obvious history of intestinal diseases, a relatively conventional operation template may be selected; while for patients with certain chronic diseases, such as diabetes and hypertension, a special operation template that takes these disease factors into account will be selected to ensure the safety and effectiveness of the operation.

[0056] After selecting the operation template, it is also necessary to adjust it according to the patient's symptom manifestation data. Because even patients with similar physical conditions may have different symptom manifestations of anal fistula, it is necessary to make personalized modifications to the operation template. For example, if the patient's symptom manifestations indicate that the anal fistula may be in a relatively complex state, it is necessary to optimize the operation steps in the operation template, and some inspection details may be added or the inspection order may be adjusted to obtain an electronic colonoscopy operation guide specifically for this patient.

[0057] Regarding the construction of the operation template: Collect detailed information of a large number of patients of different ages, genders, physical conditions, and whether they have underlying diseases, and sort out the detailed records of previous electronic colonoscopy operations. Analyze the symptoms, signs, pathological characteristics, etc. of different types of anal fistulas and related intestinal diseases, and understand the impact of the diseases on electronic colonoscopy operations. According to factors such as the patient's age, gender, and underlying diseases, divide the patients into different categories, summarize the electronic colonoscopy operation processes of different categories of patients, and find out the commonalities and differences. Associate different types of anal fistulas and related intestinal diseases with the corresponding operation processes. According to the results of classification and summarization, formulate detailed electronic colonoscopy operation steps for each category of patients. Define the range of various parameters during the operation, such as the insertion speed of the endoscope, the amount of inflated air, the amount of suction, etc. These parameters should be reasonably set according to the physical conditions and disease characteristics of different patients. For example, for patients with relatively sensitive intestines, the insertion speed of the endoscope should be slow and the amount of inflated air should be appropriately reduced to avoid causing discomfort or intestinal damage to the patient. Formulate corresponding countermeasures for various risks that may occur during the operation.

[0058] The electronic colonoscope is equipped with a high-definition imaging system that can clearly display the internal situation of the intestine on the screen. Doctors can directly observe the color, texture, blood vessel distribution and other fine structures of the intestinal mucosa, and can also clearly see whether there are lesions in the intestine, such as ulcers, polyps, tumors, inflammation, etc., as well as the location, size, shape and other characteristics of the lesions.

[0059] In step 101, a personalized electronic colonoscopy operation guide has been customized based on the patient's physical data and symptom manifestation data. In this step, the operator will strictly follow this operation guide to control the electronic colonoscopy to examine the patient. The operation guide covers detailed contents such as the speed, direction, and depth of the endoscope insertion, as well as the key points of observation and operation techniques in different intestinal parts. For example, if the patient's intestine is relatively narrow or has a bend, the operation guide will instruct the operator to insert the endoscope slowly and adjust the angle to avoid damaging the intestine. During the electronic colonoscopy examination, the device will collect real-time images of the intestinal interior. These images contain rich information, such as the morphology, color, and presence of lesions of the intestinal mucosa. Through advanced imaging techniques, the fine structures in the intestine can be clearly captured, providing an intuitive and accurate data source for subsequent analysis.

[0060] In this application, an analysis model has been established in advance, which integrates a large amount of medical knowledge and clinical experience. The models that can be selected for image analysis and classification in the analysis model include convolutional neural network (CNN), recurrent neural network (RNN), and its variant long short-term memory network (LSTM), etc. By learning and training a large number of anal fistula cases and normal intestinal image data, it is enabled to have the ability to identify anal fistula characteristics. The analysis model will analyze the detected image data and symptom manifestation data at the same time. The symptom manifestation data includes symptom information such as perianal pain, swelling, and pus discharge that the patient has had before. The analysis model will look for anal fistula-related features in the detected image, such as the signs of the internal opening of the anal fistula and the morphology of the fistula tract, and make a comprehensive judgment in combination with the symptom manifestation. For example, if a small hole suspected to be the internal opening of the anal fistula is found in the detected image and the patient has had long-term perianal pus discharge symptoms, then the model will be more inclined to judge that the patient has an anal fistula.

[0061] In some specific embodiments, each operation template corresponds to non-anal fistula pathological data obtained by performing an electronic colonoscopy operation according to the operation template. The anal fistula case data is pre-annotated with pathological features and pathological regions; the non-anal fistula pathological data corresponding to the operation template is adjusted according to the difference between the operation template and the operation guide to obtain reference image data; the local features of the corresponding pathological regions in the detected image data are extracted by the analysis model and compared with the corresponding pathological features to quickly analyze the difference between the detected image data and the reference image data; the comprehensive difference analysis result and the symptom manifestation data are used to judge whether the patient has an anal fistula.

[0062] Each pre-set operation template for an electronic colonoscope is associated with a set of non-fistula pathological data obtained during operations according to this template. These data represent the characteristic information of the intestine when it is normal or suffering from non-fistula diseases under a specific operation process, serving as a reference benchmark for subsequent analysis. This corresponding relationship provides a standardized reference basis for the analysis of detection images, enabling doctors and analysis models to compare and analyze the detection results of different patients based on a unified specification. Since the operation guidelines are obtained by adjusting the operation template according to the physical data and symptom data of individual patients. Therefore, it is necessary to make corresponding adjustments to the non-fistula pathological data corresponding to the operation template according to the differences between the two, so as to obtain reference image data that better fits the actual situation of the patient. Through this personalized adjustment, it is ensured that the reference image data matches the individual situation of the patient, improving the accuracy of subsequent detection image analysis. For example, for a patient with a history of abdominal surgery, special attention should be paid to the intestinal adhesion site in the operation guidelines. At this time, based on the non-fistula pathological data of the corresponding operation template, images of the possible changes in the intestinal morphology caused by intestinal adhesion, such as intestinal tube distortion and local stenosis, are added to obtain the reference image data.

[0063] Using a pre-trained analysis model, extract the local features of specific pathological regions in the detection image data, and compare them with the pathological features of the corresponding pathological regions in the reference image data, so as to quickly analyze the differences between the two. With the powerful feature extraction and comparison capabilities of the analysis model, efficient analysis of the detection image is achieved, providing objective data support for judging whether the patient has a fistula. For example, in the anorectal region of the detection image, the analysis model extracts features such as the texture and color of this region. If the texture of the normal mucosa in this region is clear and the color is uniform in the reference image, while there are characteristic differences such as local mucosal roughness and dark red color in the detection image, this provides clues for further judging the fistula.

[0064] Combine the results of the differential analysis with the symptom data of the patient to comprehensively judge whether the patient has a fistula from multiple dimensions, avoiding the one-sidedness brought by single-data judgment. This comprehensive analysis method makes full use of the detection image information and the patient's clinical symptom information, significantly improving the accuracy of fistula diagnosis.

[0065] When analyzing new detected image data, since the known pathological features and pathological regions are available, there is no need to conduct a comprehensive and undifferentiated analysis of the entire image data. Instead, it is possible to directly focus on specific regions that may be related to anal fistulas. For example, among a large number of intestinal images taken by an electronic colonoscope, it is possible to quickly locate the area around the anus and the possible presence of fistulas, avoiding wasting time in irrelevant regions, thereby greatly improving the data processing speed. For the parsing model, the pre-annotated information provides it with prior knowledge, enabling it to directly compare the features of the detected images extracted with the annotated pathological features and make a judgment quickly, reducing the calculation steps and time consumption of the model.

[0066] In practical applications, the annotation work is carried out by experienced pathologists, anorectal surgeons, or medically trained technical personnel. High-quality image data of anal fistula cases are collected, including electronic colonoscope images, MRI images, ultrasound images, etc. If there are different layers or structures in the pathological region, such as the wall and lumen of the fistula, as well as the surrounding inflammatory tissues, different colors or annotation symbols can be used for differentiation to record the lesion information in more detail. According to medical knowledge and clinical experience, various pathological features of anal fistulas in the images are identified. Common pathological features include the morphology of the fistula (such as curved, straight, uneven thickness, etc.), the thickness of the wall (whether thickened), the signal intensity (in MRI or ultrasound images), the inflammatory reaction of the surrounding tissues (such as edema, exudation, etc.), and the presence or absence of calcification.

[0067] In some specific embodiments, non-anal fistula pathological data are divided into healthy data and non-anal fistula disease data; the healthy data include the morphological data of healthy intestinal mucosa and histological pathological data detected in sequence according to the operation template, and the non-anal fistula disease data include the image data of inflammatory bowel disease, intestinal polyp images, and intestinal tumor images detected in sequence according to the operation template.

[0068] Healthy data:

[0069] Morphological data of healthy intestinal mucosa: It refers to the data on the appearance, morphology, etc. of normal intestinal mucosa obtained when detecting according to a specific operation template. For example, normal intestinal mucosa should exhibit features such as smoothness, uniform color, and clear texture, and these features will be converted into specific data for recording, such as the roughness value of the mucosa and the RGB values of the color.

[0070] Histological pathological data: This is the data obtained by detecting healthy intestinal tissue from a histological perspective. After processing the intestinal tissue by slicing, staining, etc., the morphology, structure, arrangement, etc. of cells are observed under a microscope, and these observation results are quantified into data, such as the size of cells, the nuclear-cytoplasmic ratio, and the density of tissue structure. These data can reflect the normal physiological state of intestinal tissue at the microscopic level.

[0071] Data of non-anal fistula diseases:

[0072] Image data of inflammatory bowel disease: Inflammatory bowel disease includes ulcerative colitis, Crohn's disease, etc. When detected according to the operation template, the image data of the intestine in the inflammatory state will be recorded. These images can show the pathological features such as congestion, edema, ulcer, erosion, etc. of the intestinal mucosa. The image data can be two-dimensional or three-dimensional, containing information such as the location, scope, and degree of the lesion. For example, through image analysis, quantitative data such as the area of the ulcer and the degree of mucosal congestion can be obtained. Under the electronic colonoscope, inflammatory bowel disease has specific image features, such as continuous or segmental distribution of the lesion, blurred mucosal vascular texture, brittle and easy to bleed, etc. These features can be used as the basis for classifying the image data of inflammatory bowel disease.

[0073] Image data of intestinal polyps: Intestinal polyps are elevated lesions on the surface of the intestinal mucosa. During the detection process, the image data of the polyps will be obtained. These data describe the morphology (such as flat, spherical, pedunculated or sessile, etc.), size, color, surface features, etc. of the polyps. Intestinal polyps generally show round or oval elevations under the electronic colonoscope, with a smooth surface or lobulated shape, pedunculated or sessile. Different types of polyps have different characteristics in imaging and pathology, and based on this, the image data of intestinal polyps can be classified.

[0074] Image data of intestinal tumors: For intestinal tumors, their image data will also be recorded. These data can reflect the growth pattern of the tumor (such as infiltrative growth, expansive growth, etc.), whether the boundary is clear, and the presence of necrosis foci and other characteristics. Under the electronic colonoscope, intestinal tumors have unique image features, such as cauliflower-like masses, ulcerative masses, intestinal lumen stenosis, etc. Combining the discovery of cancer cells or dysplastic cells through pathological examination can be used as the basis for classifying the image data of intestinal tumors.

[0075] These diseases may have similarities with anal fistula in terms of symptoms and colonoscopic manifestations. Incorporating their image data into the detection helps doctors in differential diagnosis when diagnosing anal fistula and avoids misdiagnosing anal fistula as other diseases. For example, inflammatory bowel disease may cause ulcers and inflammation of the intestinal mucosa, which has a certain similarity with the local inflammation of anal fistula. However, through the analysis of details such as the scope and distribution characteristics of the lesions in the image data, it can help doctors accurately judge the condition. Intestinal polyps and tumors may also cause local abnormal changes in the intestine, confusing some manifestations with those of anal fistula. By comparing and analyzing the image data characteristics of these diseases, the unique image features of anal fistula can be more accurately identified. In addition, patients may have both anal fistula and other intestinal diseases, such as inflammatory bowel disease, intestinal polyps or tumors. Incorporating the image data of these diseases into the detection can help doctors comprehensively understand the patient's intestinal condition, timely discover possible co-existing diseases, and provide a basis for formulating a comprehensive treatment plan.

[0076] Step 103 is to further explore and utilize the existing data to search for relevant cases on the basis of determining that the patient has anal fistula, so as to provide support for the subsequent prediction of anal fistula condition and model construction. The non-anal fistula pathological data includes healthy data and non-anal fistula disease data. Using these data as a reference helps to more accurately distinguish the characteristics belonging to the internal orifice and fistula tract of anal fistula from the detection image data. The parsing model will compare the detection image data with the non-anal fistula pathological data, exclude the characteristics belonging to normal tissues or other non-anal fistula diseases, and thus extract the key information related to the internal orifice and fistula tract of anal fistula, that is, the first anal fistula data. The first anal fistula data usually covers the content such as the position of the internal orifice, the shape of the internal orifice, and the starting direction of the fistula tract. Taking the information such as the position of the internal orifice, the shape of the internal orifice, and the starting direction of the fistula tract in the first anal fistula data, as well as the symptom manifestation data (such as the degree of pain around the anus, the situation of purulent discharge, etc.) as the retrieval conditions, a matching search is carried out in the anal fistula medical record database. Those cases in the database that are highly similar to the current patient in these aspects will be screened out as relevant anal fistula cases.

[0077] Searching for relevant cases in the anal fistula medical record database is to draw on the experience of previous similar cases and provide a reference for the condition prediction and treatment plan formulation of the current patient. Similar cases may have certain commonalities in aspects such as the development process and treatment effect of anal fistula. By analyzing these cases, the condition of the current patient can be better understood.

[0078] In some specific embodiments, the first difference region is obtained by analyzing the difference between the detection image data and the healthy data through the parsing model; the difference in the first difference region between the detection image data and the non-anal fistula disease data is analyzed; if there is a certain first difference region in the detection image data that is different from any non-anal fistula disease data, then it is determined that this first difference region is the diseased region; the image features of the diseased region are extracted and analyzed to determine whether there are preset internal orifice features. If so, it is determined that the patient has anal fistula, and the relevant information related to the internal orifice and fistula tract of anal fistula in this diseased region is extracted to obtain the first anal fistula data. The principle is as shown in the appendix Figure 3As shown. The analysis model is a tool constructed based on machine learning or other data analysis algorithms, and it has the ability to identify and analyze the characteristics of image data. Through comparison, the model will find the areas in the detected image data that do not match the healthy data, and these areas are defined as the first difference areas. For example, healthy intestinal mucosa should be smooth and have uniform color. If there are rough or color-changing conditions in a certain part of the mucosa in the detected image, then this part of the area will be identified as the first difference area. The first difference area reflects the parts in the detected image that may have abnormalities. After determining the first difference area, the analysis model will continue to conduct in-depth analysis on these areas. At this time, the characteristics of the detected image data in the first difference area are compared with non-anal fistula disease data (such as inflammatory bowel disease image data, intestinal polyp image data, intestinal tumor image data, etc.). Through this comparison, the model attempts to find the differences between the characteristics of the first difference area and the characteristics of various non-anal fistula diseases. For example, inflammatory bowel disease usually has the characteristics of extensive mucosal congestion and edema. If the characteristics of the first difference area do not match the typical characteristics of inflammatory bowel disease, then further analysis of other differences is required.

[0079] If there is a certain first difference area in the detected image data, and its characteristics are different from the characteristics of all non-anal fistula disease data, this means that the abnormality in this area is not caused by common non-anal fistula diseases. Based on this situation, this first difference area is identified as the lesion area. The lesion area is defined in this way because the possibility of anal fistula-related lesions in it is relatively high. By excluding the possibility of common non-anal fistula diseases, the scope of the cause of the abnormal area is narrowed, thus making it more likely to point to anal fistula. Once the lesion area is determined, the analysis model will extract detailed image characteristics from this area, including characteristics in terms of texture, color, shape, etc. These characteristics can describe the situation of the lesion area in more detail. Then, the model will conduct a comparative analysis of the extracted characteristics with the preset anal fistula internal orifice characteristics. The preset internal orifice characteristics are the typical characteristics of the anal fistula internal orifice summarized based on a large number of anal fistula cases. For example, the internal orifice may appear as a small hole, and there may be an inflammatory reaction in the surrounding mucosa, etc. If the situation conforming to the preset internal orifice characteristics is found in the lesion area, then there is a greater possibility of identifying that the patient has anal fistula. When the preset internal orifice characteristics are detected in the lesion area, it can be determined that the patient has anal fistula. This is a diagnostic conclusion based on data analysis and feature comparison. At the same time, relevant information involving the anal fistula internal orifice and fistula is extracted from the lesion area, such as the location and shape of the internal orifice, the starting direction of the fistula, etc. These information constitute the first anal fistula data. The first anal fistula data has important reference value for further understanding the specific situation of anal fistula and formulating treatment plans in the future.

[0080] In some specific embodiments, the first anal fistula data includes the position of the internal orifice, the shape of the internal orifice, and the starting direction of the fistula tract; the second anal fistula data includes the length of the fistula tract, the branches of the fistula tract, and the relationship with the surrounding tissues. The internal orifice is the primary site of anal fistula infection, and its position and shape are crucial for judging the type of anal fistula, the source of infection, and formulating the surgical plan. The starting direction of the fistula tract determines the extension path of the fistula tract in the body, helping the doctor understand the direction and scope of infection spread. The length of the fistula tract, the branches of the fistula tract, and the relationship with the surrounding tissues further supplement the detailed information of the anal fistula. The length of the fistula tract affects the scope of fistula tract resection or treatment during the operation; the situation of the fistula tract branches is related to whether the infection focus can be completely removed during the operation to avoid recurrence; the relationship with the surrounding tissues involves the difficulty and risk of the operation, as well as the impact on the functions of the surrounding tissues. By clarifying these data, doctors can more accurately judge the complexity and severity of anal fistula. For example, the internal orifice of a high anal fistula is at a higher position, the fistula tract may be longer and have more branches, and it has a close relationship with important surrounding tissues such as sphincters, so the operation difficulty and risk are relatively large. While the internal orifice of a low anal fistula is at a lower position, the fistula tract is relatively simple, and the choice of treatment plan may be relatively more straightforward. These data can also provide precise guidance for formulating the surgical plan. Doctors can select the appropriate surgical approach and method based on the position of the internal orifice, the direction of the fistula tract, and the relationship with the surrounding tissues, minimize the damage to normal tissues as much as possible, improve the success rate of the operation, and reduce the recurrence rate.

[0081] The first anal fistula data mainly involves some basic and intuitive information about the internal opening and fistula tract of the anal fistula, such as the location, shape of the internal opening, and the starting direction of the fistula tract. This information is relatively clear, can be directly observed through detection means such as electronic colonoscopy, and has relatively clear characteristic manifestations on images. Using the preset analysis model, it can be relatively accurately directly analyzed from the detection image data. The second anal fistula data includes information such as the length of the fistula tract, the branching situation, and the relationship with the surrounding tissues. This information not only involves the complex structure of the anal fistula itself but also is closely related to the surrounding physiological environment. The length of the fistula tract may vary due to individual differences and different stages of the disease development. The fistula tract branches may be relatively hidden and may not be fully clearly shown in the detection images. Moreover, the relationship between the fistula tract and the surrounding tissues requires considering multiple factors comprehensively, with high complexity and uncertainty, and it is difficult to accurately obtain from the detection images directly. Due to its complexity and uncertainty, more information needs to be combined for prediction. The anal fistula case database contains complete anal fistula information of a large number of previous patients. By finding cases similar to the current patient, the second anal fistula data in these cases can be used for reference. Using the analysis model to comprehensively consider various factors such as the preset medical detection data, symptom manifestation data, anal fistula cases, and the first anal fistula data, a more comprehensive and reasonable prediction of the second anal fistula data of the current patient can be made, so as to construct a complete three-dimensional model of the anal fistula that more conforms to the actual situation of the patient. In this way, the empirical information in the historical data can be fully utilized to make up for the deficiencies of the current detection data and improve the accuracy and reliability of the model.

[0082] Step 104 is to further predict the anal fistula situation of the patient based on the data obtained in the previous steps with the help of the analysis model to obtain more comprehensive anal fistula-related information. By comprehensively analyzing the preset medical detection data, symptom manifestation data, anal fistula cases, and the first anal fistula data, other characteristics of the patient's anal fistula are predicted, so as to obtain one or more sets of second anal fistula data, providing more detailed information for the subsequent construction of a complete three-dimensional model of the anal fistula. The patient's own symptom manifestation data is an important basis for reflecting their condition. The symptom manifestation data includes the patient's subjective feelings, such as the degree, frequency of pain around the anus, whether accompanied by itching, etc., and objective manifestations, such as whether there is purulent discharge, the size and location of the mass, etc. These symptoms are closely related to the pathological characteristics of the anal fistula. The analysis model can further understand information such as the severity and development stage of the patient's anal fistula by analyzing these symptoms, so as to make a more accurate prediction. For example, frequent purulent discharge may indicate more branches of the fistula tract or a deeper location of the internal opening.

[0083] The analytical model uses its built-in algorithms and rules to comprehensively analyze and process the above-mentioned various types of data. The model will identify the associations and patterns among the data, and through methods such as comparison and reasoning, predict the second anal fistula data of the patient, such as the length of the fistula, the branches of the fistula, and the relationship between the fistula and the surrounding tissues. For example, the model may predict the range of the fistula length of the patient based on the relationship between the position of the internal opening and the fistula length in similar cases and the position of the internal opening of the current patient; by analyzing the characteristics of the mass in the symptom manifestation data and the starting direction of the fistula in the first anal fistula data, and combining the situation of similar cases, predict the branching situation of the fistula.

[0084] In some specific embodiments, in the anal fistula case database, search for all cases with a similarity degree higher than a preset value in terms of the position of the internal opening, the shape of the internal opening, and the starting direction of the fistula of the patient, and obtain anal fistula cases; determine the extension direction and extension length of all fistulas in the anal fistula cases, and count the number of various extension directions and extension lengths, so as to predict the fistula length and extension direction; analyze the mass characteristics in the symptom manifestation data, set a data statistics method according to the mass characteristics, and count the fistula branching situation and the relationship between the fistula and the surrounding tissues in the anal fistula cases according to the data statistics method, and then predict the fistula branches and the relationship between the fistula and the surrounding tissues of the patient.

[0085] A large number of past anal fistula case information is stored in the anal fistula case database, and each case contains key data such as the position of the internal opening, the shape of the internal opening, and the starting direction of the fistula. When facing a new patient, by searching for cases with a relatively high similarity degree in these key aspects of the patient, and using the existing information such as the fistula length, extension direction, branching situation, and the relationship between the fistula and the surrounding tissues in these similar cases, to predict the corresponding situation of the new patient. At the same time, combined with the symptom manifestation data (such as mass characteristics) of the new patient itself, adjust the statistics method to make the prediction result more in line with the actual situation of the patient.

[0086] In the anal fistula case database, compare the data such as the position of the internal opening, the shape of the internal opening, and the starting direction of the fistula of the new patient with the existing cases in the database, and calculate the similarity degree. Set a preset value, and find all cases with a similarity degree higher than the preset value. These cases form the set of anal fistula cases for subsequent analysis. For example, if the preset value is 80%, then cases with a similarity degree of 80% or more in the above key aspects with the new patient will be screened out. For the screened anal fistula cases, determine the extension direction (such as horizontal, vertical, oblique, etc.) and extension length of all fistulas. Then count the number of various extension directions and extension lengths. For example, count how many cases the fistula extension direction is horizontal and how many cases the length is in a certain interval among these similar cases. Through this statistical analysis, obtain the most likely fistula length and extension direction as the prediction result for the new patient.

[0087] Analyze the mass characteristics in the patient's symptom data, such as the size, location, hardness of the mass, etc. Set corresponding data statistics methods according to these characteristics. For example, if the mass is large and located close to the anal sphincter, more attention may be paid to the relationship between the fistula and the sphincter, and this aspect of information will be focused on when counting the tissue relationship around the fistula in anal fistula cases. According to the set data statistics method, count the fistula branch situation (such as the number of branches, branch directions, etc.) and the tissue relationship around the fistula (such as the adjacent relationship with tissues such as muscles, blood vessels, nerves, etc.) in anal fistula cases, and then predict the fistula branch and the tissue relationship around the fistula of new patients.

[0088] By referring to the information of a large number of similar cases, it is possible to more comprehensively understand the possible situations of anal fistulas, avoid one-sided judgments based only on the limited own data of new patients, and thus improve the accuracy of diagnosis in aspects such as the length, extension direction, branch situation of the fistula, and the tissue relationship around the fistula. Adjust the statistical method by combining the patient's own symptom data, making the prediction result more personalized and more in line with the actual condition of the patient, reflecting the concept of personalized medicine and improving the quality and effect of medical services.

[0089] In practical applications, the process of the model obtaining the second anal fistula data is a comprehensive analysis of various data. Pre-collect medical test data, symptom data, anal fistula cases, and the first anal fistula data, and perform feature extraction on the data to convert various data into numerical features that the model can process. For example, quantify the pain level in symptoms as 1, 2, 3 for mild, moderate, and severe respectively; represent different shapes of the internal orifice such as round and oval with different codes; extract and quantify features such as the signal intensity and edge clarity of the fistula from MRI images. Through these operations, various types of data are unified into digital feature vectors, facilitating the model to perform calculations and analyses. According to the characteristics of the data and the requirements of the prediction task, select appropriate machine learning or deep learning models, such as decision trees, random forests, neural networks, etc. Taking neural networks as an example, it has a powerful non-linear mapping ability and can handle complex data relationships and feature interactions. Use historical anal fistula case data as the training set, use the preset medical test data, symptom data, and the first anal fistula data as input features, and the corresponding second anal fistula data (fistula length, fistula branches, tissue relationship around the fistula, etc.) as output labels to train the model. During the training process, the model continuously adjusts its own parameters to learn the mapping relationship between the input features and the output labels to improve the accuracy of prediction

[0090] In some specific embodiments, if in the first anal fistula data, the starting direction of the fistula shows multi-directional extension, the position of the internal orifice is far from the normal position of the anal crypt, or the shape of the internal orifice is irregular, it is determined that the patient's anal fistula is a complex anal fistula, and additional medical test items are added to obtain medical test data.

[0091] The fistula tract of a normal anal fistula has a relatively single direction, while the multi-directional extension of the starting direction of the fistula tract means that the diffusion path of infection in the perianal tissues is complex, and there may be multiple branches or complex connections with the surrounding tissues, increasing the difficulty of diagnosis and treatment. The anal crypt is a common site for the internal opening of an anal fistula. If the position of the internal opening is far from the normal position of the anal crypt, it indicates that the cause of the anal fistula may be relatively special, or the condition has developed to a more complex level, which may involve deeper tissue infections or the formation of abnormal channels. The normal shape of the internal opening is relatively regular, while an irregular shape often indicates that the tissues around the internal opening have been severely damaged by inflammation, or are affected by multiple pathogenic factors, causing changes in the structure and shape of the internal opening, which is also an indication of the complexity of the anal fistula condition. For complex anal fistulas, relying solely on routine examinations may not provide a comprehensive understanding of the condition, and additional medical examination items are needed to obtain more detailed medical examination data for accurate diagnosis and formulation of a reasonable treatment plan. Since the electronic colonoscope is excluded, the following examination items can be selected:

[0092] Magnetic Resonance Imaging (MRI) examination: The principle is to utilize the phenomenon of nuclear magnetic resonance that occurs when hydrogen protons in the human body are excited by radiofrequency pulses in a magnetic field, generating signals, which are then reconstructed into images by a computer. It can clearly display the anatomical structure of the perianal soft tissues, including the course, branches of the fistula tract, its relationship with the surrounding muscles and organs, and the accurate position of the internal opening, etc. It has high value for the diagnosis of complex anal fistulas, and can help doctors comprehensively understand the condition and formulate precise surgical plans.

[0093] Endorectal Ultrasound examination: By inserting an ultrasound probe into the rectal cavity and using the principle of ultrasound reflection to scan and image the perianal tissues. It can accurately detect the position, depth, shape of the fistula tract and its relationship with the anal sphincter, and also plays an important role in detecting some hidden fistula branches and determining the position of the internal opening, providing important basis for the diagnosis and treatment of complex anal fistulas.

[0094] Fistulography examination: Inject a contrast agent into the fistula tract, and then perform examinations through imaging means such as X-ray or CT. The contrast agent can fill the fistula tract and clearly display the course, branches of the fistula tract and its communication with the surrounding tissues, helping to detect complex fistula tract structures that are difficult to detect by routine examinations and providing detailed anatomical information for surgical treatment.

[0095] Step 105 is to construct a three-dimensional model of the anal fistula based on the first anal fistula data and the second anal fistula data obtained from the previous steps, which is of great significance for doctors to intuitively understand the specific situation of the anal fistula and formulate a precise treatment plan. First, construct a primary three-dimensional model around the first anal fistula data, and then construct multiple complete three-dimensional models of the anal fistula based on the primary three-dimensional model in combination with the second anal fistula data.

[0096] The first anal fistula data contains key basic information about the internal opening and fistula tract of the anal fistula, such as the position of the internal opening, the shape of the internal opening, and the starting direction of the fistula tract. This information provides the core elements for constructing the initial shape of the anal fistula. Using 3D modeling technology, with the patient's body structure as the basic framework, according to the position of the internal opening in the first anal fistula data, the specific coordinates of the internal opening are determined in 3D space; based on the shape of the internal opening, the 3D shape of the internal opening is shaped; combined with the starting direction of the fistula tract, the extension direction of the starting part of the fistula tract in 3D space is initially depicted. Through these operations, a preliminary 3D model that can reflect the basic characteristics of the anal fistula is constructed. For example, if the position of the internal opening is at a specific height and circumferential position in the rectum, the internal opening is marked at the corresponding position in the 3D model; if the shape of the internal opening is circular, a circular internal opening model is constructed with that position as the center; and then according to the starting direction of the fistula tract, an initial fistula tract model is extended from the internal opening.

[0097] The second anal fistula data further supplements the detailed information of the fistula tract, including the length of the fistula tract, the branches of the fistula tract, and the tissue relationship around the fistula tract. This information makes the shape of the anal fistula more complete and specific. Since there may be certain uncertainties in predicting the second anal fistula data, different combinations of prediction results may produce different shapes of the anal fistula. To comprehensively consider various possible situations, multiple complete 3D models of the anal fistula are constructed. Based on the preliminary 3D model, according to the length of the fistula tract in the second anal fistula data, the fistula tract in the preliminary model is extended accordingly; based on the branch situation of the fistula tract, branches are added to the fistula tract to simulate the directions and connection methods of different branches; combined with the tissue relationship around the fistula tract, the relative position and spatial relationship between the anal fistula model and the surrounding tissues (such as the anal sphincter, blood vessels, nerves, etc.) are adjusted. By processing different combinations of the second anal fistula data, multiple complete 3D models of the anal fistula are constructed to display various possible shapes of the anal fistula.

[0098] Multiple complete 3D models of the anal fistula can help doctors observe and understand the specific situation of the anal fistula from different angles and different possibilities, more accurately judge the complexity and severity of the anal fistula, and avoid misdiagnosis or missed diagnosis caused by a single perspective or insufficient information. Doctors can intuitively plan the surgical path, evaluate the surgical difficulty and risk, and formulate coping strategies in advance based on these 3D models. For example, by observing the relationship between the fistula tract and the surrounding important tissues, an appropriate surgical approach is selected to reduce damage to the surrounding tissues and improve the success rate of the surgery. The 3D model can visually show the patient's condition to the patient, enabling the patient to better understand their own disease situation and enhancing the patient's understanding and cooperation with the treatment plan.

[0099] This application also proposes an anal fistula model construction system based on an endoscope, as shown in the appendix Figure 4 and includes the following:

[0100] The operation unit 1 is used to obtain the physical data of the patient and the symptom data related to anal fistula, select the corresponding operation template according to the physical data, and adjust the operation template according to the symptom data to obtain the operation guide for the electronic colonoscope of this patient;

[0101] The acquisition unit 2 is used to control the electronic colonoscope to examine the patient according to the operation guide to obtain the detection image data; and judge whether the patient has anal fistula according to the detection image data and the symptom data through a preset parsing model;

[0102] The parsing unit 3, if there is an anal fistula, combines the non-anal fistula pathological data to parse the first anal fistula data involving the internal opening and fistula of the anal fistula from the detection image data, and searches for relevant anal fistula cases in the anal fistula medical record database based on the first anal fistula data and the symptom data;

[0103] The prediction unit 4 is used to predict one or more groups of second anal fistula data through the parsing model according to the preset medical detection data, symptom data, anal fistula cases and the first anal fistula data;

[0104] The model unit 5 is used to construct a primary three-dimensional model of the anal fistula around the first anal fistula data, and construct multiple complete three-dimensional models of the anal fistula on the basis of the primary three-dimensional model in combination with the second anal fistula data.

[0105] This application provides a computer program product, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a method for constructing an anal fistula model based on an endoscope. Applying a method for constructing an anal fistula model based on an endoscope to a computer program product is convenient for execution.

[0106] This application also provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of a method for constructing an anal fistula model based on an endoscope as described above are realized.

[0107] The computer storage medium of the present application may adopt any combination of one or more computer-readable media. The computer-readable media may be computer-readable signal media or computer-readable storage media. The computer-readable storage media may be, for example, but not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, the computer-readable storage media may be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, device, or component. The present application applies a method for constructing an anal fistula model based on an endoscope to a computer-readable storage medium, on which a computer program is stored. When this program is executed by a processor, it implements the steps of the clothing simulation method provided by the present application, which is simple, fast, easy to store, and not easily lost.

[0108] The present application proposes a method, system, and application for constructing an anal fistula model based on an endoscope. By integrating multiple data types, it provides comprehensive and multi-dimensional data support for model construction, simplifies the modeling process, overcomes the problem of low efficiency in existing model construction, and meets the needs of rapid clinical diagnosis. After integrating multiple data types, using a preset parsing model and a computer system for data processing can quickly complete the whole process from data acquisition to model construction. Compared with traditional manual analysis and modeling methods, it greatly shortens the time required for modeling. By obtaining the patient's body data and symptom manifestation data to select and adjust the operation template, a personalized electronic colonoscopy operation guide is obtained, which helps to conduct examinations more targeted and improves the quality and efficiency of obtaining detection image data. At the same time, using the preset parsing model can more accurately identify anal fistulas, reducing misdiagnosis and missed diagnosis. It can not only parse the first anal fistula data related to the internal opening and fistula of the anal fistula from the detection image data, but also predict the second anal fistula data including the length of the fistula, the branches of the fistula, and the tissue relationship around the fistula by combining multiple data, so as to comprehensively obtain the relevant information of the anal fistula and provide richer and more accurate basis for subsequent model construction and treatment. Based on the first anal fistula data and symptom manifestation data, relevant cases are searched in the anal fistula medical record database, and the second anal fistula data is predicted accordingly, making full use of the previous case experience and improving the accuracy and reliability of predicting the complex situation of anal fistulas.

[0109] Those of ordinary skill in the art should understand that the various modules of the present application described above can be implemented using a general-purpose computing system. They can be centralized on a single computing system or distributed across a network composed of multiple computing systems. Optionally, they can be implemented using program code executable by a computer system, so that they can be stored in a storage system and executed by the computing system, or they can be separately fabricated into individual integrated circuit modules, or multiple modules or steps among them can be fabricated into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0110] Note that the above is only the preferred embodiment of the present application and the technical principles applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments here, and various obvious changes, re-adjustments, and substitutions can be made by those skilled in the art without departing from the protection scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments only. Without departing from the concept of the present application, more other equivalent embodiments can be included, and the scope of the present application is determined by the scope of the appended claims.

[0111] The above discloses only several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by those skilled in the art should fall within the protection scope of the present application.

Claims

1. A method for constructing an anal fistula model based on endoscope, characterized in that: These include: Acquire the patient's physical data and symptom data related to anal fistula, select a corresponding operation template according to the physical data, and adjust the operation template according to the symptom data to obtain an operation guide for the electronic colonoscope for the patient; Controlling the electronic colonoscope to examine the patient according to the operation guide to obtain detection image data; judging whether the patient has an anal fistula according to the detection image data and the symptom manifestation data through a preset analytical model; If anal fistula exists, first anal fistula data involving the internal opening and fistula of the anal fistula is parsed from the detection image data in combination with the preset non-anal fistula pathological data, and related anal fistula cases are searched in an anal fistula medical record database based on the first anal fistula data and the symptom manifestation data; Predicting one or more groups of second anal fistula data according to preset medical test data, symptom data, anal fistula cases and first anal fistula data through the analytical model; Constructing a primary three-dimensional model of anal fistula based on the first anal fistula data, and constructing multiple complete three-dimensional models of anal fistula based on the primary three-dimensional model and combining the second anal fistula data; Among them, the three-dimensional modeling technology is used, with the patient's body structure as the basic framework, and according to the position of the internal opening in the first anal fistula data, the specific coordinates of the internal opening are determined in the three-dimensional space; according to the internal opening morphology, the three-dimensional shape of the internal opening is shaped; combined with the starting direction of the fistula, the extension direction of the starting part of the fistula in the three-dimensional space is preliminarily depicted, and a preliminary primary three-dimensional model that can reflect the basic characteristics of the anal fistula is constructed; On the basis of the primary three-dimensional model, the fistula in the primary model is extended accordingly according to the length of the fistula in the second anal fistula data; branches are added to the fistula according to the branching of the fistula to simulate the direction and connection method of different branches; the relative position and spatial relationship between the anal fistula model and the surrounding tissues are adjusted in combination with the relationship of the surrounding tissues of the fistula; and multiple complete anal fistula three-dimensional models are constructed by processing different combinations of the second anal fistula data to show the possible various forms of anal fistula.

2. The method for constructing anal fistula model according to claim 1, characterized in that: Each operation template corresponds to non-anal fistula pathological data obtained by performing electronic colonoscopy according to the operation template, and the anal fistula case data is pre-labeled with pathological features and pathological areas; According to the difference between the operation template and the operation guide, the non-anal fistula pathology data corresponding to the operation template is adjusted to obtain reference image data; Extracting local features of the corresponding pathological area in the detection image data by using the analytical model, and comparing them with the corresponding pathological features, so as to quickly analyze the difference between the detection image data and the reference image data; The difference analysis results and the symptom data are combined to determine whether the patient has anal fistula.

3. The method for constructing anal fistula model according to claim 2, characterized in that: The non-anal fistula pathology data is divided into health data and non-anal fistula disease data; The health data includes healthy intestinal mucosal morphology data and histological pathology data detected in sequence according to the operation template, and the non-anal fistula disease data includes inflammatory bowel disease image data, intestinal polyp image data and intestinal tumor image data detected in sequence according to the operation template.

4. The method for constructing anal fistula model according to claim 3, characterized in that: Analyzing the difference between the detection image data and the health data by the analytical model to obtain a first difference area; Analyze the difference between the detection image data and the non-anal fistula disease data in the first difference area; if a first difference area in the detection image data is different from any non-anal fistula disease data, identify the first difference area as a lesion area; The image features of the lesion area are extracted and analyzed to see whether there is a preset internal opening feature. If so, it is determined that the patient has an anal fistula, and relevant information related to the internal opening and fistula of the anal fistula in the lesion area is extracted to obtain the first anal fistula data.

5. The method for constructing anal fistula model according to claim 1, characterized in that: The first anal fistula data includes the position of the internal opening, the shape of the internal opening and the starting direction of the fistula; The second anal fistula data includes the length of the fistula, the branches of the fistula, and the relationship between the tissues around the fistula.

6. The method for constructing anal fistula model according to claim 5, characterized in that: In the anal fistula case database, all cases with a similarity with the patient in terms of the internal opening position, internal opening shape, and fistula starting direction higher than a preset value are searched to obtain anal fistula cases; Determine the extension direction and extension length of all fistulas in the anal fistula case, and count the number of various extension directions and extension lengths, so as to predict the length and extension direction of the fistula; Analyze the mass characteristics in the symptom manifestation data, set a data statistical method according to the mass characteristics, and use the data statistical method to count the fistula branches and the relationship between the tissues around the fistula in the anal fistula case, so as to predict the relationship between the fistula branches and the tissues around the fistula of the patient.

7. The method for constructing anal fistula model according to claim 5, characterized in that: If in the first anal fistula data, the starting direction of the fistula extends in multiple directions, the internal opening is far away from the normal position of the anal crypt, or the internal opening is irregular in shape, the patient's anal fistula is determined to be a complex anal fistula, and additional medical examination items are added to obtain the medical examination data.

8. An endoscope-based anal fistula model construction system, characterized in that: These include: An operation unit, used to obtain the patient's physical data and symptom data related to anal fistula, select a corresponding operation template according to the physical data, and adjust the operation template according to the symptom data to obtain an operation guide for the electronic colonoscope for the patient; An acquisition unit is used to control the electronic colonoscope to examine the patient according to the operation guide to obtain detection image data; and to determine whether the patient has an anal fistula according to the detection image data and the symptom manifestation data through a preset analytical model; The parsing unit, if an anal fistula exists, parses the detected image data to obtain first anal fistula data related to the anal fistula internal opening and fistula tract in combination with the preset non-anal fistula pathological data, and searches for related anal fistula cases in an anal fistula medical record database based on the first anal fistula data and the symptom manifestation data; A prediction unit, configured to predict one or more groups of second anal fistula data according to preset medical test data, symptom data, anal fistula cases and first anal fistula data through the analytical model; A model unit is used to construct a primary three-dimensional model of anal fistula around the first anal fistula data, and to construct multiple complete three-dimensional models of anal fistula based on the primary three-dimensional model and in combination with the second anal fistula data; wherein the three-dimensional modeling technology is used to determine the specific coordinates of the internal opening in the three-dimensional space according to the position of the internal opening in the first anal fistula data, based on the patient's body structure as a basic framework; the three-dimensional shape of the internal opening is shaped according to the morphology of the internal opening; the extension direction of the starting part of the fistula in the three-dimensional space is preliminarily depicted in combination with the starting direction of the fistula, so as to construct a preliminary primary three-dimensional model that can reflect the basic characteristics of the anal fistula; On the basis of the primary three-dimensional model, the fistula in the primary model is extended accordingly according to the length of the fistula in the second anal fistula data; branches are added to the fistula according to the branching of the fistula to simulate the direction and connection method of different branches; the relative position and spatial relationship between the anal fistula model and the surrounding tissues are adjusted in combination with the relationship of the surrounding tissues of the fistula; and multiple complete anal fistula three-dimensional models are constructed by processing different combinations of the second anal fistula data to show the possible various forms of anal fistula.

9. A computer device, characterized in that: The computer device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the endoscope-based anal fistula model construction method as described in any one of claims 1-7.

10. A computer program product, characterized in that It includes executable instructions for implementing the endoscope-based anal fistula model construction method as described in any one of claims 1-7 when executed by a processor.

Images