Intelligent sensing-based dysuria and urinary incontinence integrated monitoring and diagnosis system

Abstract

The application discloses a dysuria and urinary incontinence integrated monitoring and diagnosing system based on intelligent sensing, comprising: a bladder emptying evaluation module for real-time tracking of bladder shape and volume change and evaluation of whether the bladder is completely emptied; a detrusor contraction function evaluation module for real-time monitoring of the contraction strength and coordination of the detrusor and judgment of whether it works normally; a bladder pressure evaluation module for evaluation of bladder compliance and detrusor function by monitoring the elasticity change and pressure change of the bladder wall; a urinary flow rate determination module for real-time measurement of bladder shape change and urinary flow rate and evaluation of the urinary flow rate; a urethral obstruction and bladder outlet obstruction evaluation module for evaluation of whether there is obstruction in the urethra or bladder outlet by real-time monitoring of the shape change and pressure change of the bladder and urethra; and a data analysis and intelligent diagnosis module for providing dysuria diagnosis and treatment suggestion. The application not only improves the accuracy and operability of dysuria diagnosis, but also optimizes the clinical decision-making process.

Description

Technical Field

[0001] This invention relates to the field of medical monitoring technology, and in particular to an integrated monitoring and diagnostic system for urinary difficulty and incontinence based on intelligent sensing. Background Technology

[0002] Urinary dysfunction is a common urinary system disease involving multiple physiological processes, from bladder storage and urination to urethral discharge. With population aging and lifestyle changes, the incidence of dysuria and urinary incontinence is gradually increasing, significantly impacting patients' quality of life. However, despite advancements in modern medical diagnostic techniques, accurate diagnosis of urinary dysfunction remains challenging. Key technical issues in diagnosing dysuria and urinary incontinence include assessing bladder emptying completeness, detrusor muscle contraction function, bladder pressure, urine flow rate, and the evaluation of urethral and bladder outlet obstruction.

[0003] First, complete bladder emptying is a fundamental issue in diagnosing dysuria. Normal bladder function depends not only on its storage capacity but also on complete emptying during urination. Traditionally, residual urine volume (PVR) assessment has been used to measure complete urination, but this method only provides static results and lacks dynamic and real-time monitoring of bladder emptying, making it difficult to accurately reflect the bladder's emptying function. Therefore, how to accurately assess the completeness of bladder emptying in real time using innovative technologies has become a major challenge in current diagnosis.

[0004] Secondly, the detrusor muscle's contractile function is a key factor in the bladder's emptying process. Normal detrusor muscle contraction is a prerequisite for maintaining smooth urination, but its contraction strength and coordination are often affected by various factors. Current ultrasound and electromyography monitoring technologies cannot accurately measure the detrusor muscle's contraction pattern and its relationship with urination, resulting in many causes of urinary difficulty not being identified and treated in a timely manner. Therefore, how to combine high-resolution dynamic ultrasound and electromyography monitoring to accurately assess the detrusor muscle's contractile function has become a technical challenge that urgently needs to be solved.

[0005] Bladder pressure is another important factor affecting urinary incontinence. Changes in bladder pressure directly reflect its dynamic capacity for urine storage and voiding. Traditional bladder pressure assessment usually relies on invasive methods, such as urodynamic testing, which is not only inconvenient for widespread clinical application but may also cause discomfort to patients. Therefore, how to combine non-invasive ultrasound technology with pressure sensors to monitor bladder pressure changes in real time, and thus assess bladder compliance and detrusor muscle function, is an urgent problem to be solved in the diagnosis of voiding disorders.

[0006] In addition, the measurement of urinary flow rate is of great significance in the diagnosis of voiding disorders, but its accuracy is often affected by factors such as fluctuations in urinary flow and unstable urinary flow velocity. Existing ultrasound technology is difficult to accurately measure urinary flow rate under low or irregular flow conditions, which leads to many cases not being diagnosed accurately.

[0007] Finally, urethral obstruction and bladder outlet obstruction are often the root causes of voiding disorders, but accurately assessing the location and type of obstruction and its impact on urination remains a challenge in clinical practice. While traditional imaging examinations can provide some morphological information, they have significant limitations in dynamic monitoring and real-time assessment of obstruction. Therefore, utilizing contrast-enhanced ultrasound technology and pressure sensors to monitor pressure and morphological changes in the urethra and bladder outlet in real time to help assess the presence of obstruction is key to resolving voiding disorders. Summary of the Invention

[0008] To address the above problems, this invention provides an integrated monitoring and diagnostic system for urinary difficulty and incontinence based on intelligent sensing.

[0009] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0010] An integrated monitoring and diagnostic system for urinary difficulty and incontinence based on intelligent sensors includes:

[0011] Bladder emptying assessment module: used to track changes in bladder shape and capacity in real time and assess whether bladder emptying is complete;

[0012] Detrusor muscle contraction function assessment module: used to monitor the contraction strength and coordination of the detrusor muscle in real time, assess the function of the detrusor muscle, and determine whether it is working normally;

[0013] Bladder pressure assessment module: By monitoring changes in the elasticity and pressure of the bladder wall, the pressure inside the bladder is calculated in real time to assess bladder compliance and detrusor muscle function;

[0014] Uroflowmetry module: Real-time measurement of bladder morphological changes and urine flow rate, calculation of urine flow rate, and assessment of urine flow rate;

[0015] Urethral obstruction and bladder outlet obstruction assessment module: By monitoring the morphological and pressure changes of the bladder and urethra in real time, it assesses whether there is obstruction at the urethra or bladder outlet;

[0016] Data analysis and intelligent diagnosis module: used to provide diagnostic and treatment recommendations for urinary disorders.

[0017] Furthermore: the bladder emptying assessment module includes:

[0018] Dynamic three-dimensional ultrasound imaging technology is used to continuously scan the bladder. Through a high-frequency ultrasound probe, the three-dimensional structural changes of the bladder are captured in real time, thereby obtaining data on the volume, shape and capacity of the bladder at different time points. After acquiring the three-dimensional ultrasound data of the bladder, computer image processing technology is used to analyze the three-dimensional model of the bladder, thereby calculating the real-time volume of the bladder. Through image segmentation algorithm, the bladder region is separated from the background, the boundary points are extracted, and the volume of the bladder is calculated based on the point cloud data.

[0019] During bladder emptying, the bladder volume data is updated in real time to monitor the bladder emptying process. After acquiring the bladder volume data in real time, the three-dimensional morphological changes of the bladder, the changes in bladder volume during urination, and the time points of the start and end of urination are combined for comprehensive evaluation.

[0020] By combining the output data of the deep learning model, we can predict whether the bladder is completely emptied and estimate the amount of residual urine.

[0021] Furthermore: the detrusor muscle contraction function assessment module includes:

[0022] Dynamic ultrasound imaging is used to image the detrusor muscle in real time. During urination, the dynamic changes of the detrusor muscle and its surrounding tissues are captured by an ultrasound probe to obtain image data of the detrusor muscle during contraction and relaxation. Using a linear array ultrasound probe, combined with real-time three-dimensional imaging and ultrasound dynamic image processing technology, the detrusor muscle image is obtained and the image is converted into detrusor muscle morphology and thickness data.

[0023] Electromyography (EMG) monitoring technology is used to synchronously record the electrical activity of the detrusor muscle. By placing surface electrodes in the perineum or pelvic floor muscle area of ​​the patient, the electrical signals of the detrusor muscle are collected in real time to assess its electrophysiological response during contraction.

[0024] By using ultrasound images to show the morphological and volume changes of the detrusor muscle during contraction, as well as the electrical signals of the detrusor muscle, a comprehensive assessment of the strength and coordination of detrusor muscle contraction can be achieved.

[0025] Furthermore: the bladder pressure assessment module includes:

[0026] Ultrasonic elastography is used to obtain elastic characteristic data of the bladder wall. Ultrasonic elastography calculates the stiffness of the bladder wall by analyzing the changes in the propagation speed of ultrasound waves in the bladder wall tissue.

[0027] A bladder pressure sensor is used to measure the direct pressure inside the bladder in real time, capturing pressure fluctuations within the bladder through a pressure sensor array.

[0028] Once real-time pressure data within the bladder and elasticity data of the bladder wall are obtained, a bladder compliance model is used to assess bladder compliance and detrusor muscle function.

[0029] Furthermore: the urinary flow rate measurement module includes:

[0030] Dynamic ultrasound imaging technology is used to monitor the bladder morphology in real time, capturing changes in the bladder's volume and shape during urination. The ultrasound probe provides data on changes in the bladder during urination by monitoring the bladder's three-dimensional structure and its capacity changes.

[0031] Based on data on bladder morphological changes, a urodynamic monitoring system is set up to monitor the flow rate, volume, and duration of urine flow using urine flow sensors, thereby obtaining instantaneous flow rate data of urine flow.

[0032] By fusing ultrasound morphological change data with urodynamic monitoring data, urine flow rate and urine velocity can be estimated.

[0033] Artificial intelligence will be used to analyze and comprehensively evaluate the acquired urine flow data, further optimizing the urine flow estimation results.

[0034] Furthermore: the urethral obstruction and bladder outlet obstruction assessment module includes:

[0035] The urethral obstruction and bladder outlet obstruction assessment module uses ultrasound contrast imaging technology to dynamically monitor the morphology of the bladder and urethra;

[0036] Pressure sensors are used to monitor pressure changes in the bladder and urethra to obtain data related to bladder outlet and urethral obstruction. The pressure sensors are placed in the bladder and urethral outlet areas to measure pressure fluctuations of urine in real time during the discharge process.

[0037] After collecting morphological and pressure data of the bladder and urethra in real time, a data fusion algorithm is used to analyze the two types of data simultaneously to generate pressure-morphological models of the urethra and bladder outlet, and to infer the specific location and degree of obstruction and its impact on urination.

[0038] By combining the results of fluid dynamics models and data fusion, artificial intelligence algorithms are further utilized to optimize the diagnosis of urethral and bladder outlet obstruction through machine learning.

[0039] Furthermore: the data analysis and intelligent diagnosis module includes:

[0040] Integrate and preprocess the raw data collected from different modules;

[0041] After data integration and preprocessing, feature extraction and data modeling are used to automatically extract diagnostic features from multi-dimensional monitoring data and build mathematical models.

[0042] After feature extraction is completed, deep learning algorithms are used to train the data to generate a model for diagnosing urinary disorders.

[0043] After the AI ​​deep learning model is trained, it can be used to perform real-time analysis and intelligent diagnosis of newly input monitoring data. The system can automatically identify and classify different types of urination disorders.

[0044] The technological advancements achieved by this invention compared to existing technologies are as follows:

[0045] This invention effectively achieves integrated monitoring and diagnosis of urinary difficulty and incontinence. Firstly, by integrating multiple advanced technologies such as 3D ultrasound imaging, dynamic ultrasound, ultrasound contrast imaging, pressure sensors, electromyography (EMG), and AI deep learning, the system overcomes the limitations of traditional single-monitoring methods, providing a comprehensive and multi-dimensional assessment of urinary function. This not only avoids the errors and limitations that may arise from single detection methods but also tracks and assesses multiple key physiological parameters of the bladder, detrusor muscle, and urethra in real time, providing more accurate and comprehensive diagnostic support for clinical practice. Secondly, the system's non-invasive technology significantly improves patient comfort and safety, avoiding the discomfort and potential risks associated with invasive procedures in traditional urodynamic examinations. By monitoring parameters such as complete bladder emptying, detrusor muscle contraction function, bladder pressure, urine flow rate, and urethral obstruction in real time, the system can comprehensively assess the etiology of urinary disorders, providing a scientific basis for developing personalized treatment plans. Especially in the measurement of uroflowmetry and assessment of urethral obstruction, the system utilizes dynamic ultrasound and AI analysis models to accurately identify abnormal uroflowmetry under low or unstable flow rates, overcoming the limitations of traditional uroflowmetry measurements. Furthermore, the AI ​​deep learning algorithm integrates multidimensional data from various modules, automatically generating diagnostic reports through intelligent analysis, significantly improving diagnostic efficiency and accuracy and reducing the burden on clinicians. Simultaneously, the system features real-time feedback, providing personalized treatment suggestions based on individual patient differences and offering doctors intuitive diagnostic results and treatment plans through a graphical interface. Attached Figure Description

[0046] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof.

[0047] In the attached diagram:

[0048] Figure 1 This is a system structure diagram of the present invention. Detailed Implementation

[0049] The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present invention will now be described with reference to the accompanying drawings.

[0050] like Figure 1 As shown, this invention discloses an integrated monitoring and diagnostic system for urinary difficulty and incontinence based on intelligent sensing, comprising:

[0051] Specifically, the implementation of the bladder emptying assessment module includes:

[0052] The bladder emptying assessment module aims to accurately assess the completeness of bladder emptying, avoiding reliance solely on the static indicator of residual urine volume (PVR). At each stage of the urination process, dynamic three-dimensional ultrasound imaging technology is used to continuously scan the bladder. A high-frequency ultrasound probe captures real-time changes in the bladder's three-dimensional structure, obtaining data on the bladder's volume, shape, and capacity at different time points. The key to this step is the combination of the ultrasound probe and the data acquisition system, continuously adjusting the scanning angle and frequency during urination to obtain high-resolution three-dimensional ultrasound image data. Hundreds of frames are collected per second, ensuring that no detail of each urination moment is missed.

[0053] After acquiring the 3D ultrasound data of the bladder, computer image processing technology is used to analyze the 3D model of the bladder to calculate the real-time volume of the bladder. This process relies on image segmentation algorithms to separate the bladder region from the background, extract boundary points, and calculate the volume of the bladder based on point cloud data.

[0054] V(t)=∫ V(t) f(x,y,z)dxdydz

[0055] Where V(t) represents the volume of the bladder at time t, f(x,y,z) is the local density function of the bladder surface region, and x,t,z are spatial coordinates.

[0056] During bladder emptying, the system updates bladder volume data in real time to monitor the bladder emptying process.

[0057] After acquiring bladder volume data in real time, a deep learning-based AI algorithm is used to further analyze bladder emptying. At this point, the system combines the bladder's three-dimensional morphological changes, bladder volume changes during urination, and the start and end times of urination for a comprehensive evaluation. To this end, this application employs an innovative hybrid model combining convolutional neural networks (CNN) and recurrent neural networks (RNN).

[0058] Convolutional Neural Networks (CNNs): First, they are used to analyze three-dimensional image data of the bladder to extract key features of bladder morphology, such as the thickness and shape of the bladder wall and the pattern of bladder wall contraction. CNNs can extract spatial features from image data and perform preprocessing.

[0059] Recurrent Neural Network (RNN): Next, RNN is used to analyze dynamic data of bladder volume changes over time. RNN is good at processing time series data and can effectively capture the dynamic characteristics of bladder contraction and emptying during urination. Through time series learning, RNN can predict whether the bladder can be completely emptied and determine whether urination is abnormal.

[0060] H(t) = F(H(t-1), X(t), W)

[0061] Where H(t) represents the bladder state (such as bladder capacity, shape, etc.) at time step t, X(t) is the input ultrasound image feature, and W is the weight matrix in the convolutional and recurrent neural network.

[0062] Output results: Through training of the hybrid model, the system can derive the criteria for judging bladder emptying, output the percentage of bladder emptying, and indicate whether there is incomplete emptying.

[0063] By combining the output data of the deep learning model, the bladder emptying assessment module can intelligently predict whether the bladder is completely emptied and estimate the residual urine volume. This process comprehensively analyzes the changes in bladder volume and the volume data at the end of urination, and further uses AI algorithms to infer whether the bladder is not completely emptied, the amount of residual urine, and whether there are any abnormalities during urination (such as difficulty in urination, bladder outlet obstruction, etc.).

[0064] The above process not only breaks through the limitations of traditional static assessments (such as residual urine volume), but also provides more accurate diagnostic evidence for clinical practice, which helps to detect bladder emptying problems early and intervene in urination disorders in a timely manner.

[0065] The specific implementation of the detrusor muscle contraction function assessment module includes:

[0066] The detrusor muscle contraction function assessment module combines high-resolution dynamic ultrasound imaging and electromyography (EMG) monitoring technology to monitor the contraction intensity and coordination of the detrusor muscle in real time, thereby accurately assessing the function of the detrusor muscle and determining whether it is working properly.

[0067] First, high-resolution dynamic ultrasound imaging technology is used to image the detrusor muscle in real time. During urination, a high-frequency ultrasound probe captures the dynamic changes of the detrusor muscle and its surrounding tissues, and obtains image data of the detrusor muscle during contraction and relaxation. In order to accurately capture the contraction pattern of the detrusor muscle, the ultrasound probe closely coordinates with the dynamic changes of the bladder and urethra, and scans and generates two-dimensional and three-dimensional images of the detrusor muscle in real time.

[0068] This module uses a linear array ultrasound probe, combined with real-time 3D imaging and ultrasound dynamic image processing technology, to ensure the acquisition of high-resolution images. The images are then converted into data on the shape and thickness of the detrusor muscle. The system can monitor the contraction state of the detrusor muscle in real time and optimize image quality through image enhancement technology.

[0069] Assuming that at time t, the volume of the detrusor muscle is V(t), its thickness change can be expressed by the following formula:

[0070] V(t)=∫ 肌肉区域 f(x,y,z)dxdydz

[0071] Where f(x,y,z) is the density function of the detrusor muscle region, and x,y,z are spatial coordinates. The thickness and volume changes of the detrusor muscle will be used for subsequent contraction strength analysis.

[0072] Next, electromyography (EMG) monitoring technology was used to simultaneously record the electrical activity of the detrusor muscle. By placing surface electrodes in the perineum or pelvic floor muscle area of ​​the patient, the electrical signals of the detrusor muscle were acquired in real time to assess its electrophysiological response during contraction. The intensity and frequency of the EMG signal are directly related to the muscle's contraction strength and activity state, and can provide important information about the detrusor muscle's contractile function.

[0073] This process uses surface EMG electrodes, combined with a high-pass filter to remove stray signals, and transmits EMG signals in real time through a data acquisition system. The system monitors the electrical activity of the detrusor muscle in real time, records the muscle contraction pattern and activity intensity, and outputs the EMG signals in the form of time series data, providing the electromyography amplitude (unit: microvolts) at each time point.

[0074] EMG(t)=∫ 肌肉区域 A(x,y,z,t)dxdydz

[0075] Where A(x,y,z,t) is the amplitude of electrical activity at a point on the detrusor muscle at time t, and x,y,z are spatial coordinates.

[0076] By simultaneously combining high-resolution dynamic ultrasound imaging data and EMG signals, the contractile strength of the detrusor muscle can be comprehensively assessed. Specifically, ultrasound images provide information on the morphological and volumetric changes of the detrusor muscle during contraction, while EMG signals reflect the intensity of the muscle's electrical activity. Combining these two sets of data allows for a comprehensive assessment of the contractile strength and coordination of the detrusor muscle.

[0077] This module employs a multimodal data fusion algorithm to combine the morphological changes of the detrusor muscle in ultrasound images with the electrical activity intensity of EMG signals to calculate the detrusor muscle contractility index (CCI). This process uses a weighted average algorithm to generate a detrusor muscle contractility score based on the temporal correlation between ultrasound images and EMG signals. The formula for the contractility index is as follows:

[0078]

[0079] Where V(t) is the volume of the bladder detrusor muscle at time t, and EMG(t) is the amplitude of the EMG signal at time t. max and EMG max ω1 and ω2 are the maximum volume and maximum EMG amplitude, respectively, and the weighting coefficients of ultrasound and EMG signals (adjusted according to specific circumstances). By calculating the contraction intensity index CCI(t), the contraction intensity of the detrusor muscle can be quantitatively evaluated.

[0080] By further analyzing the contraction coordination of the detrusor muscle and combining the temporal relationship between ultrasound data and EMG signals, we can assess whether the contraction of the detrusor muscle is normal and coordinated. Under normal circumstances, the contraction of the detrusor muscle should have a certain degree of synchronicity, and its intensity should gradually increase to the maximum value and then recover rapidly. In the case of detrusor muscle dysfunction, there may be insufficient contraction or poor coordination.

[0081] Using time-series analysis algorithms, such as Dynamic Time Warping (DTW), ultrasound data and EMG signals are time-aligned to assess their temporal consistency. If detrusor muscle contraction in the ultrasound image is out of sync with the electrical activity in the EMG signal, the system marks it as potentially having a coordination problem.

[0082] The specific implementation of the bladder pressure assessment module includes:

[0083] The bladder pressure assessment module combines ultrasound elastography with bladder pressure sensors to monitor real-time changes in bladder wall elasticity and intrabladder pressure, thereby estimating the internal bladder pressure. By combining dynamic ultrasound and pressure sensor data, this module not only assesses bladder compliance but also effectively replaces traditional urodynamic testing, providing real-time and accurate bladder function assessment for clinical use.

[0084] First, the bladder pressure assessment module obtains elastic characteristic data of the bladder wall through ultrasound elastography. Ultrasound elastography calculates the stiffness (elasticity) of the bladder wall by analyzing the changes in the propagation speed of ultrasound waves in the bladder wall tissue. The stiffness of the bladder wall is closely related to the bladder's compliance (i.e., the bladder's ability to respond to pressure). Therefore, this technology can help determine the bladder's compliance and the function of the detrusor muscle.

[0085] This module employs a focused ultrasound array probe and uses ultrasound elastography algorithms (such as Shear Wave Elastography, SWE) to measure the deformation of the bladder wall under different pressures. SWE technology calculates the elastic modulus (E) of the bladder wall, i.e., the stiffness of the bladder wall, by measuring the shear wave velocity (SWS) of the bladder wall under stress.

[0086] E=ρ·SWS 2

[0087] Where ρ is the density of the tissue and SWS is the shear wave velocity. By monitoring different pressure changes, the system can calculate the elastic modulus of the bladder wall in real time, thereby indirectly reflecting bladder compliance.

[0088] At the same time, bladder pressure sensors are used to measure the direct pressure inside the bladder in real time. These sensors are placed inside the bladder or via a urethral catheter, and an array of pressure sensors captures pressure fluctuations within the bladder, transmitting the data in real time to a computing system. The bladder pressure data provides specific information about bladder compression status, detrusor muscle function, and changes in bladder capacity.

[0089] The bladder pressure sensor uses miniature sensors (such as pressure microsensors or membrane sensors) that can accurately sense pressure changes within the bladder and have the characteristics of high sensitivity and fast response. The sensor data is synchronized with the main control system in real time through a wireless transmission module to ensure the real-time nature and accuracy of the pressure data.

[0090] The change of bladder internal pressure P(t) with time t can be expressed by the following formula:

[0091] P(t) = P0 + ΔP(t)

[0092] Where P0 is the static pressure (baseline) of the bladder, and ΔP(t) is the instantaneous change in pressure within the bladder.

[0093] Through data fusion algorithms, the bladder pressure assessment module combines bladder wall elasticity data provided by ultrasound elastography and pressure data provided by bladder pressure sensors to calculate the pressure state inside the bladder in real time. This combination method can effectively improve the accuracy and real-time performance of bladder pressure assessment, while also enabling dynamic observation of changes in the bladder wall and pressure fluctuations within the bladder.

[0094] The system uses a weighted fusion algorithm to integrate the bladder wall elastic modulus (E) measured by ultrasound and the real-time pressure data (P) provided by a pressure sensor, and calculates the overall pressure state of the bladder using a weighted formula. The algorithm sets weights between the two data sources and dynamically adjusts the weights based on the reliability and accuracy of each data source.

[0095] Bladder internal pressure P total (t) can be calculated using the following formula:

[0096] P total (t)=ω1·E(t)+ω2·P(t)

[0097] Where E(t) is the elastic modulus of the bladder wall, P(t) is the internal pressure of the bladder, and ω1 and ω2 are the weighting coefficients of ultrasound data and pressure data, respectively. Through this weighting method, the system can comprehensively consider the influence of both and obtain a more accurate estimate of bladder pressure.

[0098] Once real-time data on bladder pressure and bladder wall elasticity are obtained, the system uses a bladder compliance model to assess bladder compliance and detrusor muscle function. Bladder compliance refers to the bladder's ability to adapt to pressure during urination, reflecting the health of bladder wall elasticity and urination function. Low bladder compliance may indicate problems such as detrusor muscle dysfunction or bladder outlet obstruction. Bladder compliance (C) can be calculated using the following formula:

[0099]

[0100] ΔV represents the change in bladder capacity (measured via ultrasound imaging), and ΔP represents the change in bladder pressure (measured via a pressure sensor). Low compliance may indicate bladder wall stiffness or abnormal detrusor muscle contraction.

[0101] Based on changes in bladder pressure and compliance, the system can infer the function of the detrusor muscle. Poor bladder compliance and a rapid increase in pressure may indicate detrusor muscle dysfunction or bladder outlet obstruction.

[0102] The specific implementation of the urine flow rate measurement module includes:

[0103] The urinary flow rate measurement module combines dynamic ultrasound imaging and urodynamic monitoring technology to measure changes in bladder morphology and urinary flow rate in real time. Based on fluid dynamics models and artificial intelligence (AI) analysis technology, it can accurately calculate urinary flow rate, thereby comprehensively assessing urinary flow rate.

[0104] The first step of the uroflowmetry module is to monitor the bladder morphology in real time using dynamic ultrasound imaging technology, capturing changes in the bladder's volume and shape during urination. The ultrasound probe provides data on changes in the bladder during urination by monitoring the bladder's three-dimensional structure and its capacity changes.

[0105] This module utilizes a high-frequency linear array ultrasound probe, combined with 3D ultrasound imaging technology, to acquire real-time data on bladder morphology and capacity changes. During urination, the system captures bladder contraction patterns and records real-time changes in bladder volume. Through 3D ultrasound image processing algorithms, changes in bladder morphology can be mapped in real-time to volume data V(t), representing the bladder's capacity change at different time points. The change in bladder volume V(t) can be expressed by the following formula:

[0106] V(t)=∫ 膀胱区域 f(x,y,z,t)dxdydz

[0107] Where g(x,y,z,t) represents the density distribution of the bladder at various locations at time t, and x,y,z are three-dimensional coordinates.

[0108] Based on data on bladder morphological changes, a urodynamic monitoring system is used to measure urine flow rate in real time. This system monitors the velocity, volume, and duration of urine flow using a urine flow sensor. By accurately measuring the time-varying flow rate, the system obtains instantaneous flow rate data and provides raw data for subsequent urine flow rate calculations.

[0109] The urodynamic monitoring system is equipped with a high-precision urine flow sensor, which records the urine flow rate (m / s) and volume (ml / s) in real time via a sensor array. The urine flow data is transmitted to the central control unit in real time via a digital signal processor (DSP). The urine flow sensor can capture the urine flow velocity u(t) and urine volume Q(t) in real time and provide highly accurate flow-time curves. The relationship between urine flow rate u(t) and urine volume Q(t) can be expressed by the following formula:

[0110] Q(t) = A·u(t)

[0111] Where A is the cross-sectional area of ​​the urethra (unit: cm²) 2 U(t) is the urine flow velocity (unit: cm / s), and Q(t) is the urine flow rate (unit: ml / s).

[0112] By fusing ultrasound morphological change data with urodynamic monitoring data, accurate estimation of urine flow rate and velocity can be achieved. Simultaneously combining these two types of data allows for a more accurate assessment of the relationship between flow velocity and bladder morphological changes during urine excretion.

[0113] This module uses a multimodal data fusion algorithm to combine bladder volume change V(t) and urine flow rate u(t) data. Through dynamic time series analysis algorithms (such as Kalman filters or particle filters), it integrates bladder morphology changes with urine flow velocity data to calculate the instantaneous urine flow rate Q(t). Through this fusion process, the system can calculate the urine expulsion rate in real time, taking into account the influence of factors such as bladder pressure, morphology, and urethral resistance on urine flow. Considering both bladder capacity V(t) and urine flow rate u(t), the urine flow rate Q(t) can be expressed as:

[0114]

[0115] Wherein, T(t) is the urination time period, representing the duration of bladder urination. The system uses data fusion and time alignment algorithms to ensure the synchronization and accuracy of these data on the same time scale.

[0116] To further improve the accuracy of urine flow estimation, the system will use a fluid dynamics model to model and simulate factors such as pressure, urine flow rate, and bladder wall compliance during bladder emptying. The fluid dynamics model can effectively simulate the flow state of urine in the bladder and the relationship between bladder pressure and urine flow rate.

[0117] This module uses the Navier-Stokes equations to simulate urine flow within the bladder, considering factors such as urethral morphology, bladder pressure, and urine flow rate. In the fluid dynamics model, changes in bladder pressure and morphology affect urine velocity and flow rate. Therefore, the model combines pressure-volume relationships with urine flow dynamics equations to accurately calculate the flow state of urine. In the model, the governing equations for urine flow can be expressed using the Navier-Stokes equations:

[0118]

[0119] Where u is the flow velocity vector, p is the urine pressure, μ is the liquid viscosity, and ρ is the urine density. By solving this equation, the system can accurately simulate the flow state of urine and calculate the urine flow rate Q(t).

[0120] Finally, the system will use artificial intelligence (AI) analysis to comprehensively evaluate the acquired urine flow data and further optimize the urine flow estimation results. AI models (such as deep neural networks or support vector machines) can learn the complex relationship between bladder morphological changes, urine flow rate and fluid dynamics models, thereby improving the prediction accuracy of urine flow rate.

[0121] The AI ​​model is trained on historical data to optimize the predictive relationship between urine flow rate and bladder capacity, bladder pressure, and urethral morphology. During training, the system uses a supervised learning algorithm to adjust the model's parameters by minimizing an error function, enabling it to accurately predict urine flow rate. In the prediction process, the AI ​​model can predict the trend of urine flow rate changes based on current bladder volume and pressure variations. The AI ​​prediction model can be represented as:

[0122]

[0123] in, For the urine flow rate predicted by the AI ​​model, f AI It is a mapping function generated by an AI algorithm, with inputs including factors such as bladder capacity V(t), bladder pressure P(t), and urine flow rate u(t).

[0124] The specific implementation of the urethral obstruction and bladder outlet obstruction assessment module includes:

[0125] The urethral obstruction and bladder outlet obstruction assessment module combines contrast-enhanced ultrasound with pressure sensors to provide accurate assessments of urethral and bladder outlet obstruction by monitoring real-time morphological and pressure changes in the bladder and urethra. The core objective of this module is to promptly identify and quantify obstruction issues through comprehensive analysis of structural and functional data from the urethra and bladder outlet, providing decision support for clinical treatment.

[0126] First, the urethral obstruction and bladder outlet obstruction assessment module uses contrast-enhanced ultrasound (CEUS) to dynamically monitor the morphology of the bladder and urethra. CEUS combines ultrasound imaging with contrast agents. By injecting microbubble contrast agents, the contrast of ultrasound images is significantly enhanced, thus more clearly depicting the structural details of the bladder and urethra and helping to identify the obstruction area.

[0127] An appropriate amount of ultrasound contrast agent (such as barium sulfate microbubble solution) is injected into the bladder, and real-time scanning is performed using a high-resolution ultrasound probe. The microbubble signals in the ultrasound images enhance the visualization of the bladder and urethra, clearly demonstrating bladder wall movement and urethral patency. Ultrasound image processing software, through image segmentation and dynamic tracking algorithms, accurately extracts the morphological information of the bladder and urethra. By comparing morphological changes in normal and abnormal states, the presence of obstruction can be inferred. The change in bladder volume V(t) can be expressed as:

[0128] V(t)=∫ 膀胱区域 f(x,y,z,t)dxdydz

[0129] Where f(x,y,z,t) represents the density distribution of bladder tissue, and x,y,z represent three-dimensional coordinates.

[0130] By tracking the flow of contrast agent through urine in the bladder and urethra, the system can assess whether there is a significant area of ​​obstruction in the urethra and quantify the extent of the obstruction.

[0131] Meanwhile, the module monitors pressure changes in the bladder and urethra through pressure sensors to obtain key data related to bladder outlet and urethral obstruction. The pressure sensors are placed in the bladder and urethral outlet areas to measure pressure fluctuations of urine in real time during the discharge process.

[0132] This module utilizes diaphragm pressure sensors (such as miniature pressure sensor arrays), which can detect real-time pressure fluctuations in the bladder and urethra with extremely high accuracy. Pressure data is transmitted in real-time to the central processing unit via a wireless transmission module. By analyzing the trends in bladder and urethral pressure changes, the system can identify abnormal pressure increases and indicate potential obstruction. The pressure change formula is: Instantaneous pressure in the bladder P... bladder (t) and urethral pressure P irethra (t) can be expressed by the following formula:

[0133] P(t) = P0 + ΔP(t)

[0134] Wherein, P0 is the baseline pressure (i.e., the pressure when there is no urine flow), and ΔP(t) is the pressure increment of the bladder or urethra during urination. If there is abnormal pressure increase in the bladder or urethral inlet area (such as a rapid increase in pressure in a short period of time), it may indicate obstruction.

[0135] After collecting morphological and pressure data of the bladder and urethra in real time, the system will use a data fusion algorithm to analyze these two types of data simultaneously. By combining ultrasound contrast imaging data with pressure sensor data, the system can more accurately assess the obstruction of the urethra or bladder outlet.

[0136] The system uses multimodal data fusion algorithms (such as Kalman filters or particle filters) to jointly analyze the three-dimensional morphological information of the bladder and urethra obtained by ultrasound imaging with real-time pressure data provided by pressure sensors. Through this fusion process, the system can generate pressure-morphology models of the urethra and bladder outlet, and infer the specific location and degree of obstruction, as well as its impact on urination.

[0137] To improve the accuracy of obstruction assessment, the system incorporates a fluid dynamics model to simulate urine flow within the bladder. This model integrates bladder morphological changes, urethral pressure data, and urine flow characteristics to accurately predict the presence or absence of obstruction.

[0138] The fluid dynamics model simulates urine flow based on the Navier-Stokes equations and the Hagen-Boselli formula (used to calculate the flow resistance of fluid through a pipe). The system calculates the urine flow velocity based on pressure data in the bladder and urethra, and identifies abrupt changes in urine flow, indicating areas of obstruction. The fluid dynamics model of the bladder voiding process can be described by the following Navier-Stokes equations:

[0139]

[0140] Where u is the urine flow velocity, ρ is the pressure, μ is the urine viscosity, and ρ is the urine density, the system can determine the fluid characteristics of the bladder and urethra and identify the flow velocity changes caused by obstruction by solving this equation.

[0141] Combining the results of fluid dynamics models and data fusion, the system further utilizes artificial intelligence (AI) algorithms to optimize the diagnosis of urethral and bladder outlet obstruction through machine learning. The AI ​​algorithm can identify different types of obstruction based on training data and provide quantitative assessments.

[0142] AI models use convolutional neural networks (CNNs) or support vector machines (SVMs) to learn the complex relationship between bladder morphology, pressure data, and urine flow. Through training on a large amount of historical case data, the AI ​​system can accurately classify obstruction types (such as urethral stricture, bladder outlet obstruction, etc.) and provide corresponding obstruction severity scores. The output of the AI ​​algorithm can be represented as:

[0143]

[0144] in, f represents the degree of obstruction predicted by the AI ​​model. AI The diagnostic function generated for the AI ​​model takes as input a comprehensive stress P. total Data such as bladder capacity V(t) and urine flow rate u(t).

[0145] The specific implementation of the data analysis and intelligent diagnosis module includes:

[0146] The data analysis and intelligent diagnosis module is a core component of the integrated monitoring and diagnosis system for urinary difficulty and incontinence. It mainly uses AI deep learning algorithms to intelligently analyze monitoring data from other modules and generate detailed diagnostic reports, providing accurate diagnoses of urinary disorders and personalized treatment suggestions for clinicians. The core objective of this module is to provide real-time, accurate, and actionable clinical decision support based on the analysis of large amounts of data.

[0147] In the initial stage of the data analysis and intelligent diagnosis module, it is first necessary to integrate and preprocess the raw data collected from different modules (such as the bladder emptying assessment module, detrusor muscle contraction function assessment module, bladder pressure assessment module, uroflowmetry module, and urethral obstruction and bladder outlet obstruction assessment module). The data provided by each module is usually presented in different formats, including image data, time series data, and scalar data.

[0148] The module receives data streams from various modules through a data interface (such as JSON or Protobuf format) and uses data cleaning algorithms (such as missing value imputation, outlier detection, standardization, and normalization) to ensure data consistency and quality. For example, for bladder capacity and urine flow rate data, z-score normalization is used to unify the data to the same units; for ultrasound image data, image preprocessing algorithms (such as denoising and edge detection) are used to improve image quality.

[0149] After data integration and preprocessing, the module automatically extracts diagnostically meaningful features from multi-dimensional monitoring data using feature extraction and data modeling techniques, and constructs mathematical models. These features include the rate of change of bladder capacity, fluctuations in urine flow rate, the contraction strength of the detrusor muscle, and pressure changes in the bladder and urethra. These features will serve as input for subsequent AI deep learning model training and prediction.

[0150] The feature extraction process includes using time series analysis (such as Fourier transform or wavelet transform) to extract dynamic change features of the bladder and urethra; image analysis (such as convolutional neural network (CNN)) to extract morphological features of the bladder and urethra in ultrasound images; and pressure waveform analysis (such as dynamic time warping (DTW)) to extract features of pressure changes during urine flow.

[0151] Assume that the spectral characteristics of the time series data of bladder emptying velocity v(t) and urine flow rate u(t) obtained by Fourier transform are F v (ω) and F u (ω), then:

[0152] F v(ω)=F[v(t)]

[0153] F u (ω)=F[u(t)]

[0154] Where F represents the Fourier transform operation, and ω is the frequency variable.

[0155] After feature extraction, the module uses deep learning algorithms (such as Convolutional Neural Networks (CNN), Long Short-Term Memory Networks (LSTM), or Graph Neural Networks (GNN)) to train the data and generate a model for diagnosing urinary disorders. The training process of the deep learning model uses a labeled dataset, including known urinary disorder symptoms and normal urination samples. The system continuously adjusts the model's weight parameters to minimize the loss function.

[0156] First, cross-validation is used to evaluate the model's generalization ability. Second, the deep learning network is trained using the Adam optimization algorithm or SGD optimization algorithm, and the learning rate and regularization parameters are adjusted based on the training data. During training, Dropout can be used to prevent overfitting and improve the model's stability and robustness. The loss function L(θ) of the AI ​​model can be expressed as:

[0157]

[0158] Where N is the number of samples, y i For the actual label, f(x) i ,θ) is the model output, λ is the regularization parameter, ||θ|| 2 This is an L2 regularization term.

[0159] After the AI ​​deep learning model is trained, the system uses the trained model to perform real-time analysis and intelligent diagnosis of newly input monitoring data. The system can automatically identify and classify different types of urination disorders, such as urinary flow obstruction, detrusor muscle dysfunction, and bladder outlet obstruction, and generate corresponding diagnostic results. In addition, the system also has anomaly detection function, which can identify potential abnormal urination behaviors or potential pathological problems.

[0160] The system inputs real-time monitoring data (such as changes in bladder capacity, fluctuations in urine flow rate, and intrabladder pressure) into an AI model to obtain output results. The model learns the characteristics of different voiding disorders from the input data through multi-layer nonlinear transformations and maps them to specific diagnostic categories, such as "urethral obstruction" and "overactive bladder." The model also incorporates anomaly detection algorithms (such as Isolation Forest or One-Class SVM) to analyze the data and identify potential abnormal patterns. Assuming the model's output diagnosis is... If the corresponding category is C, then:

[0161]

[0162] X is the model's predicted output, and X is the input dataset. The diagnostic category C obtained by the model through deep learning can be "normal", "urethral obstruction", "bladder outlet obstruction" or other types of urinary disorders.

[0163] After completing the intelligent diagnosis, the module generates a detailed diagnostic report. The report not only includes the diagnostic results, but also automatically generates personalized treatment suggestions based on the patient's specific circumstances (such as age, gender, medical history, etc.). The treatment suggestions include recommended examinations, possible drug treatments, surgical interventions, or physical therapies. After the report is generated, the system will display it to the doctor through a graphical user interface (GUI) to support further clinical decision-making.

[0164] Treatment recommendations are generated based on a combination of a rule engine and an AI model. The rule engine generates treatment recommendations based on the diagnosis category and existing medical literature. For example, if the diagnosis is "bladder outlet obstruction", it will automatically recommend "bladder outlet pressure measurement" or "bladder dilation therapy".

[0165] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. An integrated monitoring and diagnostic system for urinary difficulty and incontinence based on intelligent sensing, characterized in that, include: Bladder emptying assessment module: used to track changes in bladder shape and capacity in real time and assess whether bladder emptying is complete; Detrusor muscle contraction function assessment module: used to monitor the contraction strength and coordination of the detrusor muscle in real time, assess the function of the detrusor muscle, and determine whether it is working normally; Bladder pressure assessment module: By monitoring changes in bladder wall elasticity and pressure, it calculates intrabladder pressure in real time, assesses bladder compliance and detrusor muscle function, including: The deformation of the bladder wall under different pressures was measured using a focused ultrasound array probe and an ultrasound elastography algorithm. Specifically, the ultrasound elastography algorithm calculated the elastic modulus of the bladder wall, i.e., the stiffness, by measuring the shear wave velocity of the bladder wall under stress. in, It is the density of the tissue. It is the shear wave velocity. By monitoring different pressure changes, the elastic modulus of the bladder wall is calculated in real time, thereby indirectly reflecting bladder compliance. At the same time, a bladder pressure sensor is used to measure the direct pressure inside the bladder in real time. The bladder pressure sensor is inserted into the bladder or placed through a urethral catheter. The pressure sensor array captures pressure fluctuations within the bladder. Over time The change is expressed by the following formula: in, It is the static pressure of the bladder. It is the instantaneous change in pressure within the bladder; Using a weighted fusion algorithm, the bladder wall elastic modulus measured by ultrasound and the real-time pressure data provided by the pressure sensor are integrated through a weighted formula to calculate the overall pressure state of the bladder and the internal pressure of the bladder. The following formulas are used for comprehensive calculation: in, The elastic modulus of the bladder wall. For the pressure inside the bladder, and These are the weighting coefficients for ultrasound data and pressure data, respectively. Uroflowmetry module: Real-time measurement of bladder morphological changes and urine flow rate, calculation of urine flow rate, and assessment of urine flow rate; Urethral obstruction and bladder outlet obstruction assessment module: By monitoring the morphological and pressure changes of the bladder and urethra in real time, it assesses whether there is obstruction at the urethra or bladder outlet; Data analysis and intelligent diagnosis module: used to provide diagnostic and treatment recommendations for urinary disorders.

Images