Urine flow dynamics diagnosis system based on deep learning

Abstract

The invention relates to the technical field of medical equipment, and provides a urine flow dynamics diagnosis system based on deep learning, the urine flow dynamics diagnosis system comprises a server, a data collection module, an evaluation module, a data analysis module and an interaction module, the data collection module collects urine flow dynamics data of a patient, and the evaluation module analyzes the urine flow dynamics data; the evaluation module evaluates the urodynamic data acquired by the data acquisition module to form an evaluation result, the data analysis module generates an analysis report of the urodynamic data according to the evaluation result, and the interaction module interactively prompts the analysis report to qualified medical personnel or patients. Through mutual cooperation of the evaluation module and the data analysis module, the system can monitor and evaluate urodynamics of a patient, and it is guaranteed that the whole system has the advantages of being efficient in detection process, high in detection accuracy, good in intelligent degree and high in self-learning ability.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment, and in particular to a urodynamic diagnosis system based on deep learning. Background Art

[0002] Currently, urodynamic examination is an important means for urology to diagnose urinary system diseases such as bladder dysfunction and urinary incontinence. However, the existing urodynamic examination methods rely on complex medical equipment and manual data analysis, which is inefficient, and the diagnostic results may be subjective and inaccurate.

[0003] For example, a urodynamic analyzer disclosed in Chinese patent CN117838125A provides a portable collection box for patients to collect urodynamic data, but its accuracy and diagnostic ability are poor and it is not suitable for use in high-precision urodynamic analysis scenarios.

[0004] At the same time, the existing urodynamic examination mainly relies on complex medical equipment and manual data analysis, and has the following major problems:

[0005] 1. The equipment is complex and expensive: The urodynamic examination equipment is large and complex, the operation process is cumbersome, and professional medical staff are required to perform testing and maintenance. The cost is high. The examination process involves multiple devices such as catheter insertion and pressure sensors, which may cause discomfort and infection risks to patients.

[0006] 2. Low data analysis efficiency: The data obtained from urodynamic examinations usually require manual analysis and interpretation by professionals, which is time-consuming and has low diagnostic efficiency. The analysis results may be affected by subjective experience and analysis skills, resulting in certain subjectivity and errors in the diagnostic results.

[0007] 3. Insufficient diagnostic accuracy and standardization: Since data analysis and interpretation rely on the doctor's personal experience and knowledge, the diagnostic results lack standardization, and there may be misdiagnosis or missed diagnosis. Some urinary system diseases have complex symptoms, and traditional urodynamic examinations are difficult to accurately identify, resulting in low diagnostic accuracy;

[0008] 4. Difficulty in patient data management and follow-up: Traditional urodynamic examination data are mostly stored offline, which makes it difficult to carry out systematic management and follow-up tracking, and it is difficult to conduct long-term evaluation of the patient's treatment effect.

[0009] The present invention is made to solve the common problems in this field, such as complicated detection process, strong subjectivity, insufficient diagnostic accuracy, difficult data management, lack of interaction, low intelligence and low detection efficiency. Summary of the invention

[0010] The purpose of the present invention is to propose a urodynamic diagnosis system based on deep learning to address the current deficiencies.

[0011] In order to overcome the shortcomings of the prior art, the present invention adopts the following technical solutions:

[0012] A urodynamic diagnosis system based on deep learning, the urodynamic diagnosis system comprising a server, the urodynamic diagnosis system further comprising a data acquisition module, an evaluation module, a data analysis module and an interaction module, the server being connected to the data acquisition module, the evaluation module, the data analysis module and the interaction module respectively;

[0013] The data acquisition module acquires the patient's urodynamic data, the evaluation module evaluates the urodynamic data acquired by the data acquisition module to form an evaluation result, the data analysis module generates an analysis report of the urodynamic data according to the evaluation result, and the interactive module interactively prompts the analysis report to qualified medical staff or patients;

[0014] The data acquisition module includes a bladder capacity measuring unit and a urine flow rate measuring unit, wherein the bladder capacity measuring unit measures the bladder capacity, and the urine flow rate measuring unit measures the flow rate and flow rate of the patient's urine;

[0015] The bladder capacity measuring unit is placed against the patient's bladder to measure the patient's bladder capacity, and the urine flow rate measuring unit receives urine from the patient during urination and measures its flow rate and flow rate.

[0016] Optionally, the bladder capacity measurement unit includes a bladder ultrasound scanner, an action member, a support member, a first sliding member, and a second sliding member, wherein the action member is used to adjust the position of the bladder ultrasound scanner, the support member supports the action member, the first sliding member, the second sliding member, and the bladder ultrasound scanner, and the first sliding member and the second sliding member respectively adjust the position of the action member;

[0017] The supporting member presses the action member, the first sliding member, the second sliding member and the bladder ultrasound scanner against the abdomen of the patient, and triggers the action member, the first sliding member and the second sliding member to slowly slide the position of the bladder ultrasound scanner to obtain bladder capacity and residual urine volume data through the bladder ultrasound scanner.

[0018] Optionally, the urine flow rate measurement unit includes a loading member and a flow rate measurement member, the loading member carries urine discharged by the patient, the flow rate measurement member is arranged in the loading member, and measures the flow rate and flow rate of urine discharged by the patient;

[0019] The loading component includes a urine loading bag and a contact pipe, one end of the contact pipe is for contacting the urethra of the patient, one end of the contact pipe is connected to the urine loading bag, and the contact pipe is used to guide the discharged urine and store the discharged urine in the urine loading bag;

[0020] Wherein, the outer wall of the contact pipe is provided with a measuring window and a clip-on track, and the clip-on track is detachably connected to the flow rate measuring component so that the flow rate measuring component is placed exactly opposite to the measuring window and measures the flow rate and speed of urine discharged by the patient in a non-contact manner.

[0021] Optionally, the evaluation module obtains the bladder capacity and residual urine volume data measured by the bladder capacity measurement unit, and the flow rate and speed of urine discharged by the patient measured by the urine flow rate measurement unit, and calculates the patient's urodynamic index UDI according to the following formula:

[0022]

[0023] Wherein, BC is the maximum bladder capacity measured by a bladder ultrasound scanner, PVR is the residual urine volume of the patient, Q_max is the maximum urine flow rate of the patient when urinating, UQ is the average urine flow rate of the patient when urinating, and T is the urination time, which is the total time from the start of urination to the end of urination;

[0024] After the evaluation module measures the urodynamic index UDI, the urodynamic index UDI is transmitted to the data analysis module.

[0025] Optionally, the data analysis module generates an analysis report according to the following steps:

[0026] S1. Data collection and preprocessing, obtaining the urodynamic data including the maximum bladder capacity BC measured by a bladder ultrasound scanner, the residual urine volume PVR of the patient, the maximum urine flow rate Q_max when the patient urinates, the urine flow rate UQ when the patient urinates, the urination time T and the urodynamic index UDI;

[0027] S2, inputting the collected urodynamic data into the deep learning model, establishing an input matrix in the input layer of the deep learning model, and performing deep learning and calculation in the hidden layer;

[0028] S3, outputting the comprehensive scoring result in the output layer of the deep model;

[0029] S4. Generate a urodynamic analysis report based on the comprehensive scoring results.

[0030] Optionally, the interaction module includes an interaction unit and a prompting unit, wherein the interaction unit interacts with qualified medical staff or patients and generates a pass code, and the prompting unit prompts the qualified medical staff and patients according to the pass code;

[0031] The interactive unit includes an interactive verifier and a qualified passer, wherein the interactive verifier verifies the identity IDs of the medical staff and the patient and forms a verification result, and if the verification is passed, the qualified passer is triggered to generate a pass code according to the identity IDs of the medical staff and the patient;

[0032] The medical staff and patients read or query the corresponding urodynamic analysis report according to the access code.

[0033] Optionally, the measuring member comprises a support seat, a laser emitter, an optical sensor and a data storage device, wherein the laser emitter and the optical sensor are arranged on the support seat at intervals so that an angle θ is formed between the laser emitter and the flow direction of the patient's urine;

[0034] Wherein, a sliding groove is provided on the support seat body and is slidably engaged with the engaging track.

[0035] Optionally, the supporting member includes a connecting seat, a standing seat, a loose-leaf and a magnetic member, the magnetic member is used to adsorb the connecting seat on the bed, the connecting seat supports the standing seat, the connecting seat and the standing seat are connected together through the loose-leaf so that the standing seat can be placed above the abdomen of the patient, and the body of the standing seat is provided with an action cavity, and the action cavity is used to place the action member and the bladder ultrasound scanner;

[0036] Wherein, the bladder ultrasound scanner is pressed against the abdomen of the patient under the drive of the action component to detect the bladder capacity and residual urine volume data.

[0037] Optionally, the action component includes a sliding seat, an α action rod, a β action rod, an α action driving mechanism and a β action driving mechanism, one end of the α action rod is connected to the sliding seat, the other end of the α action rod is drivingly connected to the α action driving mechanism to form an α action portion, the α action portion is connected to the inner wall of the action cavity, one end of the β action rod is connected to the sliding seat, the other end of the β action rod is drivingly connected to the β action driving mechanism to form a β action portion, and the β action portion is connected to the inner wall of the action cavity;

[0038] The axes of the α action rod and the β action rod are perpendicular to each other, so that the α action rod and the β action rod can adjust the position of the sliding seat at the peripheral side of the sliding seat.

[0039] Optionally, the identity ID includes an identity card, a work permit, a medical card or a hospitalization card.

[0040] The beneficial effects achieved by the present invention are:

[0041] 1. Through the cooperation of the evaluation module and the data analysis module, the system can monitor and evaluate the patient's urodynamics, ensuring that the entire system has the advantages of efficient detection process, high detection accuracy, good intelligence, and strong self-learning ability;

[0042] 2. Collect the patient's performance parameters through the data acquisition module to improve the accuracy and reliability of the patient's urodynamic assessment;

[0043] 3. Through the cooperation between the data acquisition module and the evaluation module, the patient's urodynamic test is more accurate, which also changes the defects of the existing subjective judgment, ensuring that the whole system has the advantages of high diagnostic accuracy, high data management security, high intelligence and high detection efficiency;

[0044] 4. Through the cooperation of the interactive unit and the prompt unit, medical staff and patients can view the urodynamic analysis report while taking into account the safety of the patient's report, ensuring that the entire system has the advantages of high interactive comfort, good privacy protection, high intelligence, strong automatic operation capability and precise data management. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate the same parts.

[0046] Figure 1 It is an overall block diagram of the present invention.

[0047] Figure 2 It is a block diagram of the data acquisition module and the evaluation module of the present invention.

[0048] Figure 3 It is a flowchart diagram of the interaction unit and the prompt unit of the present invention.

[0049] Figure 4 It is a schematic structural diagram of a patient, a bladder capacity measuring unit and a hospital bed of the present invention.

[0050] Figure 5 for Figure 4 A magnified schematic diagram of center A.

[0051] Figure 6 It is a front view schematic diagram of the bladder capacity measuring unit of the present invention.

[0052] Figure 7 for Figure 6 Schematic cross-sectional view at CC in the middle.

[0053] Figure 8 It is a schematic structural diagram of an action chamber, an action component, a bladder ultrasound scanner, a first sliding component and a second sliding component in the stand of the present invention.

[0054] Fig. 9 It is a schematic diagram of the partial structure and details of the contact pipe and urine loading bag of the present invention.

[0055] Fig.10 for Fig. 9 A magnified schematic diagram of point B in the middle.

[0056] Fig.11 It is a schematic structural diagram of the standing urinal of the present invention.

[0057] Fig.12 Schematic diagram of the scenario of using a standing urinal for female patients.

[0058] Fig.13 This is a schematic diagram of the analysis report format illustrated in the present invention.

[0059] Explanation of the accompanying drawings: 1. Patient; 2. Bed; 3. Magnetic element; 4. Loose-leaf; 5. Connecting seat; 6. Standing seat; 7. Action chamber; 8. Standing urinal; 9. Software system; 10. Bladder ultrasound scanner; 11. Pressure sensor; 12. Holding rod; 13. Sliding seat; 14. α action rod; 15. First sliding track; 16. First moving seat; 17. Range of movement; 18. Second sliding track; 19. Second moving seat; 20. β action rod; 21. Magnetic seat; 22. Adjustment rod; 23. Urine loading bag; 24. Snap-on track; 25. Contact pipe; 26. Support seat; 27. Laser emitter; 28. Optical sensor; 29. ​​Measuring window. DETAILED DESCRIPTION

[0060] The following is an explanation of the embodiments of the present invention through specific embodiments. Those skilled in the art can understand the advantages and effects of the present invention from the contents disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and the details in this specification can also be modified and changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. In addition, the drawings of the present invention are only simple schematic illustrations and are not depicted according to actual sizes. It is stated in advance. The following embodiments will further explain the relevant technical contents of the present invention in detail, but the disclosed contents are not intended to limit the scope of protection of the present invention.

[0061] Embodiment 1: According to Figure 1 , Figure 2 , Figure 3, Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 , Fig. 9 , Fig.10 , Fig.11 , Fig.12 and Fig.13 As shown, this embodiment provides a urodynamic diagnosis system based on deep learning, the urodynamic diagnosis system includes a server, the urodynamic diagnosis system also includes a data acquisition module, an evaluation module, a data analysis module and an interaction module, the server is connected to the data acquisition module, the evaluation module, the data analysis module and the interaction module respectively, and the intermediate data and process data of the data acquisition module, the evaluation module, the data analysis module and the interaction module are stored in the server for query or call;

[0062] The data acquisition module acquires the urodynamic data of the patient 1, the evaluation module evaluates the urodynamic data acquired by the data acquisition module to form an evaluation result, the data analysis module generates an analysis report of the urodynamic data according to the evaluation result, and the interactive module interactively prompts the analysis report to a qualified medical staff or the patient 1;

[0063] The urodynamic diagnosis system also includes a central processor, which is respectively connected to the data acquisition module, the evaluation module, the data analysis module and the interaction module, and centrally controls the data acquisition module, the evaluation module, the data analysis module and the interaction module based on the central processor, and stores the control data of the central processor in the database of the server, so as to improve the accuracy of the whole system in diagnosing and evaluating the urinary flow dynamics of the patient 1;

[0064] The data acquisition module includes a bladder capacity measuring unit and a urine flow rate measuring unit, wherein the bladder capacity measuring unit measures the bladder capacity, and the urine flow rate measuring unit measures the flow rate and flow rate of the urine of the patient 1;

[0065] The bladder capacity measuring unit is placed against the bladder of the patient 1 to measure the bladder capacity of the patient 1, and the urine flow rate measuring unit receives urine from the patient 1 during urination and measures its flow rate and flow rate;

[0066] Optionally, the bladder capacity measurement unit includes a bladder ultrasound scanner 10, an action member, a support member, a first sliding member, and a second sliding member, wherein the action member is used to adjust the position of the bladder ultrasound scanner 10, the support member supports the action member, the first sliding member, the second sliding member, and the bladder ultrasound scanner 10, and the first sliding member and the second sliding member respectively adjust the position of the action member;

[0067] The supporting member presses the action member, the first sliding member, the second sliding member and the bladder ultrasound scanner 10 against the abdomen of the patient 1, and triggers the action member, the first sliding member and the second sliding member to slowly slide the position of the bladder ultrasound scanner 10, so as to obtain bladder capacity and residual urine volume data through the bladder ultrasound scanner 10;

[0068] Optionally, the supporting member includes a connecting seat 5, a standing seat 6, a loose-leaf 4 and a magnetic member 3, the magnetic member 3 is used to adsorb the connecting seat 5 on the bed 2, the connecting seat 5 supports the standing seat 6, the connecting seat 5 and the standing seat 6 are connected together through the loose-leaf 4, so that the standing seat 6 can be placed above the abdomen of the patient 1, and the body of the standing seat 6 is provided with an action cavity 7, and the action cavity 7 is used to place the action member and the bladder ultrasound scanner 10;

[0069] Wherein, the bladder ultrasound scanner 10 is driven by the action member to rest against the abdomen of the patient 1 to detect the bladder capacity and residual urine volume data;

[0070] In this embodiment, the stand 6 and the connecting seat 5 are connected by the hinge 4, and the stand 6 is just located above the abdomen of the patient 1. Through the action of the action member, the bladder ultrasound scanner 10 is placed against the abdomen of the patient 1 to measure or explore the abdomen of the patient 1.

[0071] In addition, during the detection process of the bladder ultrasound scanner 10, the medical staff needs to apply the ultrasound coupling agent to the detection position of the patient 1 (the detection position is set to the position of the bladder);

[0072] Optionally, the action component includes a sliding seat 13, an α action rod 14, a β action rod 20, an α action driving mechanism and a β action driving mechanism, one end of the α action rod 14 is connected to the sliding seat 13, the other end of the α action rod 14 is drivingly connected to the α action driving mechanism to form an α action portion, the α action portion is connected to the first sliding member, one end of the β action rod 20 is connected to the sliding seat 13, the other end of the β action rod 20 is drivingly connected to the β action driving mechanism to form a β action portion, and the β action portion is connected to the second sliding member;

[0073] The axes of the α action rod 14 and the β action rod 20 are perpendicular to each other, so that the α action rod 14 and the β action rod 20 can adjust the position of the sliding seat 13 at the peripheral side of the sliding seat 13;

[0074] The first sliding member and the second sliding member are arranged on the side wall of the action chamber 7, and drive the α action part and the β action part respectively;

[0075] The first sliding member further includes a first moving seat 16, a first sliding track 15, and a first sliding drive mechanism. The first moving seat 16 is slidably connected to the first sliding track 15, and slides along the direction of the first sliding track 15 under the drive of the first sliding drive mechanism.

[0076] The second sliding member includes a second moving seat 19, a second sliding track 18 and a second sliding drive mechanism. The second moving seat 19 is slidably connected to the second sliding track 18 and slides along the direction of the second sliding track 18 under the drive of the second sliding drive mechanism.

[0077] The bladder ultrasound scanner 10 is arranged on the sliding seat 13, and detects the bladder capacity of the patient 1 under the adjustment of the α action part and the β action part;

[0078] The range of motion 17 of the bladder ultrasound scanner 10 is as follows: Figure 7 As shown (as Figure 7 As shown in the curved ellipse in the figure), and under the adjustment of the first sliding part and the second sliding part, reciprocating motion is performed in the range of motion 17 to detect the capacity of the bladder of the patient 1;

[0079] In this embodiment, a method for detecting and determining bladder capacity is provided, and the specific steps are as follows:

[0080] S11, prepare equipment: use a bladder ultrasound scanner 10 (Bladder Ultrasound Scanner), the equipment includes an ultrasound probe, a display and a software system 9;

[0081] S12. Preparation of patient 1: Ensure that the bladder of patient 1 is full before the examination and avoid emptying the bladder. Patient 1 lies flat on the examination bed with the abdomen exposed. Patient 1 needs to remain relaxed during the examination to avoid abdominal muscle tension affecting the measurement results.

[0082] S13, ultrasound probe position selection: apply an appropriate amount of ultrasound coupling agent on the lower abdomen of the patient 1 to improve the transmission of ultrasound signals, place the ultrasound probe above the pubic bone, and gently apply pressure to the ultrasound probe at the abdominal detection position of the patient 1 through the action member and the support member to obtain a clear bladder image;

[0083] S14, scanning and measuring: scanning the bladder area by ultrasound to observe the shape, size and capacity of the bladder, marking the boundary of the bladder on the ultrasound image, and calculating the bladder capacity using software, or manually reading the bladder capacity data on the screen on the display;

[0084] S15. Post-Void Residual Measurement: After patient 1 urinates, the bladder area is rescanned to measure the post-void residual urine volume (PVR).

[0085] S16. Data recording and analysis: record the maximum bladder capacity, residual urine volume, bladder wall thickness and morphology, and input the data into the diagnostic system. Use three-dimensional imaging technology to measure the maximum bladder capacity and residual urine volume after urination (at the same time, the thickness and morphology of the bladder wall can also be observed to determine whether there are abnormal conditions such as bladder thickening, stones or tumors);

[0086] Among them, by inputting data into the diagnostic system and performing three-dimensional imaging technology, measuring the maximum capacity of the bladder and the residual urine volume after urination is a technical means well known to those skilled in the art. Those skilled in the art can refer to relevant technical manuals to learn about the technology, so it will not be described in detail in this embodiment;

[0087] In this embodiment, when the patient 1 urinates, the urine flow rate measuring unit is carried to measure the flow rate and flow rate of urine discharged by the patient 1;

[0088] Optionally, the urine flow rate measurement unit includes a loading member and a flow rate measurement member, the loading member carries urine discharged by the patient 1, the flow rate measurement member is arranged in the loading member, and measures the flow rate and flow rate of urine discharged by the patient 1;

[0089] The loading member includes a urine loading bag 23 and a contact pipe 25, one end of which is for contacting the urethra of the patient 1, and one end of which is connected to the urine loading bag 23, and the contact pipe 25 is used to divert or adjust the discharged urine and store the discharged urine in the urine loading bag 23;

[0090] The outer wall of the contact pipe 25 is provided with a measuring window 29 and a clamping track 24, and the clamping track 24 is detachably connected to the flow rate measuring member, so that the flow rate measuring member is placed exactly opposite to the measuring window 29, and measures the flow rate and speed of urine discharged by the patient 1 in a non-contact manner;

[0091] In addition, the loading component also includes a standing urinal 8, which is used by the female patient 1 and can be detachably connected to the inlet of the contact pipe 25, so that the female patient 1 can conveniently stand and introduce urine into the contact pipe 25, and finally into the urine loading bag 23;

[0092] At the same time, the contact pipe 25, the standing urinal 8 and the urine loading bag 23 are all disposable consumables to prevent cross infection between different patients 1;

[0093] Optionally, the measuring component includes a support seat 26, a laser emitter 27, an optical sensor 28 and a data storage device. The laser emitter is used to generate a laser beam, which is directed to the direction of urine flow. The optical sensor is used to receive the laser beam reflected by the urine and measure the speed of the object by analyzing the frequency change of the laser beam. The laser emitter 27 and the optical sensor 28 are arranged on the support seat 26 at intervals so that the angle of the light emitted by the laser emitter 27 forms an angle θ with the urine flow direction of the patient 1, as shown in FIG. Fig.10 As shown;

[0094] The support seat 26 body is provided with a sliding groove, and is slidably engaged with the engaging track 24; when the connection is detachable, the laser emitter and the optical sensor 28 are just facing the detection window.

[0095] In this embodiment, the flow rate and flow rate of urine are calculated by the Doppler effect, specifically:

[0096] The urine flow rate index is calculated by the following formula:

[0097]

[0098] In the formula, v is the flow rate index of urine, f dis the Doppler frequency shift, f0 is the frequency of the laser source, θ is the angle between the laser beam emitted by the laser transmitter and the direction of urine flow, and c is the laser light speed;

[0099] The flow rate of urine is calculated by the following formula:

[0100]

[0101] Where UQ is the flow rate of urine, v(t) is the function of the urine flow rate index with respect to time t (the function of the urine flow rate index v and time t), and T is the time of urination;

[0102] Of course, it can also be calculated by bladder capacity and residual urine volume, that is: UQ = BC-PVR, where BC is the maximum bladder capacity measured by a bladder ultrasound scanner, and PVR is the residual urine volume of the patient, which is measured in step S15;

[0103] The performance parameters of the patient are collected by the data collection module to improve the accuracy and reliability of the patient's urodynamic assessment;

[0104] Optionally, the evaluation module obtains the bladder capacity and residual urine volume data measured by the bladder capacity measurement unit, and the flow rate and speed of urine discharged by the patient measured by the urine flow rate measurement unit, and calculates the patient's urodynamic index UDI according to the following formula:

[0105]

[0106] Wherein, BC is the maximum bladder capacity measured by a bladder ultrasound scanner, PVR is the residual urine volume of the patient, Q_max is the maximum urine flow rate of the patient when urinating, UQ is the average urine flow rate of the patient when urinating, and T is the urination time, which is the total time from the start of urination to the end of urination;

[0107] After the evaluation module measures the urodynamic index UDI, the urodynamic index UDI is transmitted to the data analysis module;

[0108] Optionally, the data analysis module generates an analysis report according to the following steps:

[0109] S1. Data collection and preprocessing, obtaining the urodynamic data including the maximum bladder capacity BC measured by a bladder ultrasound scanner, the residual urine volume PVR of the patient, the maximum urine flow rate Q_max when the patient urinates, the urine flow rate UQ when the patient urinates, the urination time T and the urodynamic index UDI;

[0110] S2, inputting the collected urodynamic data into the deep learning model, establishing an input matrix in the input layer of the deep learning model, and performing deep learning and calculation in the hidden layer;

[0111] Specifically, the input of the deep learning module is urodynamic data: maximum bladder capacity (BC, BladderCapacity), residual urine volume (PVR, Post-Void Residual), maximum urine flow rate (Q_max, Maximum UrineFlow Rate), urine flow (UQ, Urine Flow), urination time (T, Time), urodynamic index (UDI, UrodynamicIndex);

[0112] Each layer in the deep learning model consists of the following parts:

[0113] Weight matrix: A coefficient matrix connecting input and output, used to linearly combine input data;

[0114] Bias vector: used to adjust the results of linear combination and increase the flexibility of the model;

[0115] Activation function: a nonlinear function that helps the model learn complex mapping relationships;

[0116] The deep learning model structure: input layer: 6 input features, hidden layer 1: 64 nodes, activation function ReLU, hidden layer 2: 32 nodes, activation function ReLU, hidden layer 3: 16 nodes, activation function ReLU, output layer: 1 node, used to generate a comprehensive score;

[0117] The workflow of the deep learning module is as follows:

[0118] 1) Input features:

[0119] Input features: X = [BC, PVR, Q_max, UQ, T, UDI];

[0120] 2) Hidden layer 1:

[0121] Calculate the output of hidden layer 1: y1 = ReLU(W1·X+b1);

[0122] Among them, W1 is the weight matrix and b1 is the bias vector;

[0123] 3) Hidden layer 2:

[0124] Calculate the output of hidden layer 2: y2 = ReLU(W2 y1 + b2);

[0125] Among them, W2 is the weight matrix and b2 is the bias vector;

[0126] 4) Hidden layer 3:

[0127] Calculate the output of hidden layer 2: y3 = ReLU (W3 y2 + b3);

[0128] Among them, W3 is the weight matrix and b3 is the bias vector;

[0129] 5) Output layer:

[0130] Calculate the comprehensive score: Score = W4 y4 + b4;

[0131] Where W4 is the weight matrix and b4 is the bias vector;

[0132] Through the above steps (1-5), the deep learning model continuously adjusts the weight matrix and bias vector to minimize the error between the predicted score and the actual score. This process is called training. Through repeated iterations and adjustment of coefficients, the scoring results of the deep learning model are made more accurate.

[0133] Among them, the ReLU (Rectified Linear Unit) activation function is a commonly used activation function in deep learning. Its main function is to introduce nonlinearity in the training process of the neural network, so that the network can learn and represent more complex patterns and functions; the ReLU function achieves this goal by setting all negative values ​​in the input to zero and keeping the positive values ​​unchanged;

[0134] In this embodiment, the weight matrix (W1, W2, W3, W4) and the bias vector (b1, b2, b3, b4) are determined through a training process. i : The weight matrix b of the i-th layer i : Bias vector of the i-th layer;

[0135] S3, outputting the comprehensive scoring result in the output layer of the deep model;

[0136] S4. Generate a urodynamic analysis report based on the comprehensive scoring results;

[0137] In this embodiment, a determination process of a weight matrix (W1, W2, W3, W4) and a bias vector (b1, b2, b3, b4) is provided, specifically:

[0138] S21. Initialize weights and biases

[0139] For the weight matrix: the weight matrix is ​​a matrix that connects the input and output nodes between each layer. The initial value is generally initialized randomly to break the symmetry and ensure that the weight of each neuron is different. Normal distribution or uniform distribution is usually used for random initialization. It can also be initialized using standardized methods, such as Xavier initialization or He initialization.

[0140] For the bias vector: the bias vector is used to adjust the activation threshold of the neuron to make the model more flexible, and is usually initialized to zero or a very small value;

[0141] S22, Forward Propagation

[0142] The forward propagation calculates the output result through each layer;

[0143] Hidden Layer 1:

[0144] Calculate the output of hidden layer 1: y1 = ReLU(W1·X+b1);

[0145] Among them, W1 is the weight matrix and b1 is the bias vector;

[0146] Hidden Layer 2:

[0147] Calculate the output of hidden layer 2: y2 = ReLU(W2 y1 + b2);

[0148] Among them, W2 is the weight matrix and b2 is the bias vector;

[0149] Hidden Layer 3:

[0150] Calculate the output of hidden layer 2: y3 = ReLU (W3 y2 + b3);

[0151] Among them, W3 is the weight matrix and b3 is the bias vector;

[0152] Output layer:

[0153] Calculate the comprehensive score: Score = W4 y4 + b4;

[0154] Where W4 is the weight matrix and b4 is the bias vector;

[0155] S23. Loss Calculation

[0156] Use the loss function to measure the error between the model's predicted output value (Scroe) and the actual value (i.e., the actual score Scroe value); commonly used loss functions include mean square error (MSE) and cross entropy loss;

[0157] Mean Squared Error (MSE) loss function:

[0158]

[0159] In the formula, is the output value predicted by the model (Scroe), y i is the actual output value (i.e. the actual score Scroe value), and N is the total number of samples;

[0160] S24. Backpropagation

[0161] The gradient of the loss to the weight matrix and bias vector is calculated through back propagation to obtain the direction and amplitude of adjusting the weight matrix and bias vector;

[0162] 1) Output layer gradient calculation:

[0163]

[0164] In the formula, δ4 is the gradient of the output layer with respect to the loss function. For each sample, a δ4 is calculated, which represents the contribution of the error of the sample prediction output to the loss. is the output value (Scroe) predicted by the model, y is the actual output value (i.e. the actual score Scroe value), i is the index of the sample in the batch, m is the size of the batch, i.e. the number of samples contained in the batch, and δ 4i is the output layer gradient of the ith sample, is the transposed matrix of the bias vector a3, a3 is the activation output of the third hidden layer; dW4 is an overall symbol, which represents the gradient matrix of the loss function with respect to the weight matrix W4. By calculating this gradient matrix and using it to update the weights, the neural network can be trained to continuously improve its performance. db4 is the gradient vector of the loss function with respect to the bias vector b4;

[0165] 2) Hidden layer 3 gradient calculation:

[0166]

[0167] Where δ3 is the gradient of the hidden layer with respect to the loss function, δ4 is the gradient of the output layer with respect to the loss function, ReLU′ is the derivative of the ReLU activation function, y3 is the output of hidden layer 3, and δ 3i is the output layer gradient of the ith sample, is the transposed matrix of the bias vector a2, a2 ​​is the activation output of the third hidden layer; dW3 is an overall symbol, which represents the gradient matrix of the loss function with respect to the weight matrix W3. By calculating this gradient matrix and using it to update the weights, the neural network can be trained to continuously improve its performance. db3 is the gradient vector of the loss function with respect to the bias vector b3;

[0168] 3) Hidden layer 2 gradient calculation:

[0169]

[0170] Where δ2 is the gradient of the hidden layer with respect to the loss function, δ3 is the gradient of the output layer with respect to the loss function, ReLU′ is the derivative of the ReLU activation function, y2 is the output of hidden layer 2, and δ 2i is the output layer gradient of the ith sample, is the transposed matrix of the bias vector a1, a1 is the activation output of the third hidden layer; dW2 is an overall symbol, which represents the gradient matrix of the loss function with respect to the weight matrix W2. By calculating this gradient matrix and using it to update the weights, the neural network can be trained to continuously improve its performance. db2 is the gradient vector of the loss function with respect to the bias vector b2;

[0171] 4) Hidden layer 1 gradient calculation:

[0172]

[0173] Where δ1 is the gradient of the hidden layer with respect to the loss function, δ2 is the gradient of the output layer with respect to the loss function, ReLU′ is the derivative of the ReLU activation function, y1 is the output of hidden layer 1, and δ 1i is the output layer gradient of the i-th sample, X T is the transposed matrix of the matrix corresponding to the input feature X; dW1 is an overall symbol, which represents the gradient matrix of the loss function to the weight matrix W1. By calculating this gradient matrix and using it to update the weights, the neural network can be trained to continuously improve its performance. db1 is the gradient vector of the loss function to the bias vector b1;

[0174] 5) Update weights and biases

[0175] Use an optimization algorithm (such as gradient descent or the Adam optimizer) to update the weights and biases according to the gradients:

[0176]

[0177] Where W new is the new weight matrix, W old is the original weight matrix, b new is the new bias vector, b old is the original bias vector, α is the learning rate, dW is the gradient matrix of the loss function with respect to the weight matrix W (the partial derivative of the loss function with respect to each weight parameter), and db is the gradient vector of the loss function with respect to the bias vector b (indicating the partial derivative of the loss function with respect to each bias parameter);

[0178] In this embodiment, the learning rate (α) is a hyperparameter in the deep learning model training, which is usually set by the operator. The learning rate determines the magnitude of the weight update at each iteration of the model. In simple terms, it is a parameter for adjusting the learning speed of the model. The learning rate (α) generally ranges from 0.0001 to 0.1.

[0179] Learning rate is too high: the model is prone to skipping the optimal solution of the loss function during training, resulting in instability and divergence, causing the loss function to suddenly increase or oscillate during training;

[0180] Learning rate is too low: Model training converges very slowly, and it may take a very large number of iterations to get a satisfactory result, resulting in a very slow decrease in the loss function.

[0181] In this embodiment, the setting can be based on experience. Common empirical values ​​are 0.001, 0.01 or 0.1. Try several common values ​​and observe the training results.

[0182] Of course, the gradual attenuation method is also used for adjustment:

[0183] That is, adjust the learning rate α according to the following formula:

[0184]

[0185] In the formula, α t is the learning rate of the tth iteration, α0 is the initial learning rate, t is the number of iterations, and Times is the total number of training rounds;

[0186] In this embodiment, a specific classification standard is provided:

[0187] Score>900: bladder function is healthy, without obvious impairment;

[0188] 700<Score≤900: Mild bladder dysfunction, occasional urinary incontinence or urgency may occur;

[0189] 400<Score≤700: moderate bladder dysfunction, symptoms include frequent urination, urgency, nocturia, etc.;

[0190] Score < 400: severe bladder dysfunction, including severe urinary incontinence, urinary retention or other severe symptoms;

[0191] The above classification standards can also be adjusted or set according to actual conditions. This is a technical means well known to those skilled in the art, so it will not be described in detail in this embodiment.

[0192] The comprehensive scoring classification process is based on the following steps:

[0193] S31. Obtain comprehensive score: comprehensive score (Score) calculated by deep learning model;

[0194] S32. Classification criteria: Determine the patient's bladder function status according to the above classification criteria;

[0195] S33, Diagnosis and recommendations: Provide diagnosis and recommendations based on the comprehensive scoring classification results;

[0196] In this embodiment, an analysis report format is provided, such as Fig.12 As shown;

[0197] Through the cooperation between the data acquisition module and the evaluation module, the patient's urodynamic test is more accurate, which also changes the defects of the existing subjective judgment, ensuring that the whole system has the advantages of high diagnostic accuracy, high data management security, high intelligence and high detection efficiency;

[0198] Through the cooperation between the evaluation module and the data analysis module, the system can monitor and evaluate the patient's urodynamics, ensuring that the entire system has the advantages of efficient detection process, high detection accuracy, good intelligence, and strong self-learning ability;

[0199] Optionally, the interaction module includes an interaction unit and a prompting unit, wherein the interaction unit interacts with qualified medical staff or patients and generates a pass code, and the prompting unit prompts the qualified medical staff and patients according to the pass code;

[0200] The interactive unit includes an interactive verifier and a qualified passer, wherein the interactive verifier verifies the identity IDs of the medical staff and the patient and forms a verification result, and if the verification is passed, the qualified passer is triggered to generate a pass code according to the identity IDs of the medical staff and the patient;

[0201] The medical staff and the patient can access or query the corresponding urodynamic analysis report according to the pass code;

[0202] In this embodiment, the so-called qualified refers to the medical staff and patients who have established a medical association or mapping relationship during the hospitalization or treatment process, which is generally the patient's attending physician or managing physician;

[0203] Optionally, the identity ID includes an identity card, a work card, a medical card or a hospitalization card, and has a unique identity identifier (i.e., a card or document with a unique identity verification ID);

[0204] The verification process includes: comparing the identity IDs of the medical staff and the patient with the identity IDs pre-stored in the server, and if the comparison is the same, the verification is passed;

[0205] The qualified passer generates a pass code according to the following formula (assuming the pass code has k bits):

[0206] C(i)=((D m +i·N)·(D p +i·N)mod10000)mod10;

[0207] Where C(i) is the value corresponding to the i-th digit of the passcode, and D m D is the last four digits extracted from the medical staff's ID. p is the last four digits extracted from the patient's identity ID, i is the bit index (1 to k) i∈k of the pass code, k is the total number of digits of the pass code, i.e., i is the position i corresponding to the current i-th pass code; N is the number of historical verifications of the patient;

[0208] After the prompting unit prompts the medical staff and the patient, the medical staff and the patient are allowed to print or view the urodynamic analysis report according to the prompt;

[0209] Through the cooperation of the interaction unit and the prompt unit, the medical staff and patients can view the urodynamic analysis report while taking into account the security of the patient's report, ensuring that the entire system has the advantages of high interaction comfort, good privacy protection effect, high intelligence, strong automatic operation capability and precise data management.

[0210] Embodiment 2: This embodiment should be understood to include all the features of any of the above embodiments, and further improve upon them. Figure 1 , Figure 2 , Figure 3 , Figure 4 , Figure 5 , Figure 6 , Figure 7 , Figure 8 , Fig. 9 , Fig.10 , Fig.11 , Fig.12 and Fig.13 As shown, the bladder capacity measurement unit further includes a force adjustment subunit, a force analysis subunit and a force acquisition subunit. The force acquisition subunit acquires the pressing force data applied by the medical staff. The force analysis subunit analyzes the force of the sliding seat 13 in a direction perpendicular to the detection position according to the data of the force acquisition subunit to form an analysis result, and triggers the force adjustment subunit to adjust the position of the sliding seat 13, thereby realizing the adjustment of the contact force between the bladder ultrasound scanner 10 and the detection position;

[0211] The force adjustment subunit adjusts the position of the sliding seat 13 perpendicular to the detection position direction (such as Figure 8 shown);

[0212] The force acquisition subunit includes a gripping rod 12 and at least one pressure sensor 11 disposed on the gripping rod 12. The gripping rod 12 is for medical personnel to hold and is used to respond to the position adjustment amount of the sliding seat 13 in a direction perpendicular to the detection position.

[0213] One end of the holding rod 12 is connected to the upper end surface of the stand 6, and the other end of the holding rod 12 extends vertically toward a side away from the upper end surface of the stand 6;

[0214] At the same time, at least one pressure sensor 11 is distributed at equal intervals on the outer peripheral wall of the gripping rod 12;

[0215] The force analysis subunit obtains the force data collected by the force collection subunit, and calculates the force feedback index ACT according to the following formula:

[0216]

[0217] In the formula, is the average force, σ is the standard deviation of the force data, P min is the minimum strength value, S is the skewness, and K is the kurtosis;

[0218] For average strength Calculate according to the following formula:

[0219]

[0220] In the formula, p i is the pressure reading value of the pressure sensor corresponding to the i-th position on the grip rod, and n is the total number of pressure sensors;

[0221] The force data standard deviation σ is calculated according to the following formula:

[0222]

[0223] In the formula, is the average force, p i is the pressure reading value of the pressure sensor corresponding to the i-th position on the grip rod, and n is the total number of pressure sensors;

[0224] Minimum force value P min The minimum value is obtained from the sequence of pressure readings acquired;

[0225] The skewness S is calculated according to the following formula:

[0226]

[0227] In the formula, is the average force, p i is the pressure reading value of the pressure sensor corresponding to the i-th position on the grip rod, and n is the total number of pressure sensors;

[0228] The kurtosis K is calculated according to the following formula:

[0229]

[0230] In the formula, is the average force, p i is the pressure reading value of the pressure sensor corresponding to the i-th position on the grip rod, and n is the total number of pressure sensors;

[0231] Here, the numerator is the average of the fourth power of the data deviation from its mean, and the denominator is the fourth power of the standard deviation. The minus 3 is to make the kurtosis of the normal distribution zero.

[0232] The force adjustment subunit includes an adjustment rod 22, an adjustment drive mechanism, an extension detection member and a magnetic seat 21, wherein the extension detection member detects the extension amount of the adjustment rod 22, one end of the adjustment rod 22 is connected to the main body of the sliding seat 13, and the other end of the adjustment rod 22 is driven and connected to the adjustment drive mechanism to form an adjustment portion, and the adjustment portion is arranged on the magnetic seat 21, and the adjustment portion is arranged on the magnetic seat 21, and the magnetic seat 21 is slidably connected to the inner wall surface of the action cavity 7, so that the magnetic seat 21 is adsorbed on the inner wall surface of the action cavity 7, and when the α action portion and the β action portion are adjusted, the sliding seat 13 can be adjusted following the adjustment of the position of the magnetic seat 21;

[0233] When the adjusting part performs a telescopic action, the sliding seat 13 is adjusted in a direction perpendicular to the detection position, that is, the position of the bladder ultrasound scanner 10 is moved closer to the detection position of the patient 1 to achieve different levels of pressing, thereby improving the accurate measurement of the bladder ultrasound scanner 10;

[0234] The force analysis subunit obtains the feedback index and calculates the adjustment amount D of the adjustment rod 22 according to the following formula:

[0235] D = λ·(Target-ACT)+B;

[0236] In the formula, λ is the proportional coefficient, and its value is set by the operator according to the actual situation of the patient. Target is the target force feedback index expected by the system, which is determined according to the ACT value when the contact between the device and the patient reaches the best state, which is equivalent to the known value. B is the baseline offset, and its value usually reflects the default position of the adjustment rod when there is no external pressure, that is, the default extension of the adjustment rod when no action is performed, which is equivalent to the known value.

[0237] The value of the proportionality factor λ may range from very small values ​​(such as 0.1) to relatively large values ​​(such as 50 or more), depending on the response sensitivity of the adjustment lever and the requirements of the operating environment;

[0238] In this embodiment, an example of a value of the proportionality coefficient λ is provided, specifically:

[0239] 1) Routine bladder examination

[0240] In daily clinics, routine bladder examinations usually do not require overly fine adjustments, because the main purpose is to evaluate the size, shape and basic function of the bladder. In routine examinations, the required adjustments are relatively small and the adjustment speed does not need to be very fast. The proportionality factor λ = 10 provides sufficient adjustment sensitivity to quickly obtain good image quality without causing discomfort.

[0241] 2) Bladder tumor localization

[0242] Accuracy is critical in bladder tumor localization because it affects subsequent treatment decisions, such as planning for surgery or radiotherapy.

[0243] In cases where precise tumor positioning is required, the proportionality factor λ needs to be high to ensure that even subtle operational feedback can be responded to quickly and accurately. λ = 30 can help the device make more detailed adjustments to ensure the best image quality and position accuracy.

[0244] 3) Bladder function assessment (such as urodynamic testing)

[0245] During urodynamic testing, a finely tuned bladder ultrasound scanner is used to track bladder activity, such as changes in urine flow rate and bladder pressure;

[0246] This type of test requires the device to be able to sensitively respond to changes in the patient's bladder activity. λ = 20 provides a balance between adjustment speed and accuracy, which can quickly reflect the patient's physiological changes, but will not be too sensitive, causing the device to be repeatedly adjusted, affecting the continuity of the test;

[0247] The force analysis subunit transmits the adjustment amount D obtained by analysis to the force adjustment subunit, and controls the adjustment unit to increase the force of the adjustment amount D through the central processor, thereby achieving precise control of the detection force;

[0248] Through the mutual cooperation among the force adjustment subunit, the force analysis subunit and the force collection subunit, the detection force of urine flow force can be precisely controlled, thereby improving the comfort of patient diagnosis or evaluation and ensuring that the entire system has the advantages of high intelligence, high detection efficiency, good comfort and high intelligence.

[0249] The contents disclosed above are only preferred feasible embodiments of the present invention, and do not limit the protection scope of the present invention. Therefore, all equivalent technical changes made using the contents of the present invention specification and drawings are included in the protection scope of the present invention. In addition, the elements therein can be updated as technology develops.

Claims

1. A urodynamic diagnosis system based on deep learning, the urodynamic diagnosis system comprising a server, It is characterized in that The urodynamic diagnosis system further comprises a data acquisition module, an evaluation module, a data analysis module and an interaction module, and the server is respectively connected to the data acquisition module, the evaluation module, the data analysis module and the interaction module in communication; The data acquisition module acquires the patient's urodynamic data, the evaluation module evaluates the urodynamic data acquired by the data acquisition module to form an evaluation result, the data analysis module generates an analysis report of the urodynamic data according to the evaluation result, and the interactive module interactively prompts the analysis report to qualified medical staff or patients; The data acquisition module includes a bladder capacity measuring unit and a urine flow rate measuring unit, wherein the bladder capacity measuring unit measures the bladder capacity, and the urine flow rate measuring unit measures the flow rate and flow rate of the patient's urine; The bladder capacity measuring unit is placed against the patient's bladder to measure the patient's bladder capacity, and the urine flow rate measuring unit receives urine from the patient during urination and measures its flow rate and flow rate.

2. The deep learning-based urodynamic diagnostic system according to claim 1, It is characterized in that The bladder capacity measurement unit comprises a bladder ultrasound scanner, an action member, a support member, a first sliding member and a second sliding member, wherein the action member is used to adjust the position of the bladder ultrasound scanner, the support member supports the action member, the first sliding member, the second sliding member and the bladder ultrasound scanner, and the first sliding member and the second sliding member respectively adjust the position of the action member; The supporting member presses the action member, the first sliding member, the second sliding member and the bladder ultrasound scanner against the abdomen of the patient, and triggers the action member, the first sliding member and the second sliding member to slowly slide the position of the bladder ultrasound scanner to obtain bladder capacity and residual urine volume data through the bladder ultrasound scanner.

3. The deep learning-based urodynamic diagnostic system according to claim 2, It is characterized in that The urine flow rate measurement unit comprises a loading member and a flow rate measurement member, wherein the loading member carries urine discharged by the patient, and the flow rate measurement member is arranged in the loading member and measures the flow rate and flow rate of the urine discharged by the patient; The loading component includes a urine loading bag and a contact pipe, one end of the contact pipe is for contacting the urethra of the patient, one end of the contact pipe is connected to the urine loading bag, and the contact pipe is used to guide the discharged urine and store the discharged urine in the urine loading bag; Wherein, the outer wall of the contact pipe is provided with a measuring window and a clip-on track, and the clip-on track is detachably connected to the flow rate measuring component so that the flow rate measuring component is placed exactly opposite to the measuring window and measures the flow rate and speed of urine discharged by the patient in a non-contact manner.

4. The deep learning-based urodynamic diagnostic system according to claim 3, It is characterized in that The evaluation module obtains the bladder capacity and residual urine volume data measured by the bladder capacity measurement unit, and the flow rate and speed of urine discharged by the patient measured by the urine flow rate measurement unit, and calculates the patient's urodynamic index UDI according to the following formula: Wherein, BC is the maximum bladder capacity measured by a bladder ultrasound scanner, PVR is the residual urine volume of the patient, Q_max is the maximum urine flow rate of the patient when urinating, UQ is the average urine flow rate of the patient when urinating, and T is the urination time, which is the total time from the start of urination to the end of urination; After the evaluation module measures the urodynamic index UDI, the urodynamic index UDI is transmitted to the data analysis module.

5. The deep learning-based urodynamic diagnostic system according to claim 4, It is characterized in that The data analysis module generates an analysis report according to the following steps: S1. Data collection and preprocessing, obtaining the urodynamic data including the maximum bladder capacity BC measured by a bladder ultrasound scanner, the residual urine volume PVR of the patient, the maximum urine flow rate Q_max when the patient urinates, the urine flow rate UQ when the patient urinates, the urination time T and the urodynamic index UDI; S2, inputting the collected urodynamic data into the deep learning model, establishing an input matrix in the input layer of the deep learning model, and performing deep learning and calculation in the hidden layer; S3, outputting the comprehensive scoring result in the output layer of the deep model; S4. Generate a urodynamic analysis report based on the comprehensive scoring results.

6. The deep learning-based urodynamic diagnostic system according to claim 5, It is characterized in that The interaction module includes an interaction unit and a prompting unit, wherein the interaction unit interacts with qualified medical staff or patients and generates a pass code, and the prompting unit prompts the qualified medical staff and patients according to the pass code; The interactive unit includes an interactive verifier and a qualified passer, wherein the interactive verifier verifies the identity IDs of the medical staff and the patient and forms a verification result, and if the verification is passed, the qualified passer is triggered to generate a pass code according to the identity IDs of the medical staff and the patient; The medical staff and patients read or query the corresponding urodynamic analysis report according to the access code.

7. The deep learning-based urodynamic diagnostic system according to claim 6, It is characterized in that The measuring member comprises a support seat, a laser emitter, an optical sensor and a data storage device, wherein the laser emitter and the optical sensor are arranged on the support seat at intervals so that an angle θ is formed between the laser emitter and the flow direction of the patient's urine; Wherein, a sliding groove is provided on the support seat body and is slidably engaged with the engaging track.

8. The deep learning-based urodynamic diagnostic system according to claim 7, It is characterized in that The supporting member includes a connecting seat, a standing seat, a loose-leaf and a magnetic member, the magnetic member is used to adsorb the connecting seat on the bed, the connecting seat supports the standing seat, the connecting seat and the standing seat are connected together through the loose-leaf so that the standing seat can be placed above the abdomen of the patient, and the main body of the standing seat is provided with an action cavity, and the action cavity is used to place the action member and the bladder ultrasound scanner; Wherein, the bladder ultrasound scanner is pressed against the abdomen of the patient under the drive of the action component to detect the bladder capacity and residual urine volume data.

9. The deep learning-based urodynamic diagnostic system according to claim 8, It is characterized in that The action member includes a sliding seat, an α action rod, a β action rod, an α action driving mechanism and a β action driving mechanism, one end of the α action rod is connected to the sliding seat, the other end of the α action rod is drivingly connected to the α action driving mechanism to form an α action portion, the α action portion is connected to the first sliding member, one end of the β action rod is connected to the sliding seat, the other end of the β action rod is drivingly connected to the β action driving mechanism to form a β action portion, and the β action portion is connected to the second sliding member; The axes of the α action rod and the β action rod are perpendicular to each other, so that the α action rod and the β action rod can adjust the position of the sliding seat at the peripheral side of the sliding seat.

10. The deep learning-based urodynamic diagnostic system according to claim 9, It is characterized in that The identity ID includes an identity card, a work permit, a medical card or a hospitalization card.

Images