Perineal pelvic floor color ultrasound examination system and use method thereof

Abstract

The invention discloses a perineal pelvic floor color ultrasound examination system and a use method thereof, and relates to the technical field of color ultrasound examination.An image optimization module automatically adjusts gain, contrast, filtering and tissue harmonic imaging modes, and a three-dimensional imaging module is used for capturing changes of pelvic floor muscles in resting and moving states; the data analysis module combines the optimized ultrasonic image data and muscle dynamic information to intelligently evaluate the image quality, automatically calculates the bladder neck activity, the urethra rotation angle and the pelvic floor muscle thickness in a high-quality image, and provides an abnormal marking prompt; the user interaction module realizes visual display of ultrasonic images and analysis results, supports a doctor to input patient information, and improves operation convenience and diagnosis accuracy; the whole system optimizes the visualization ability of an anatomical structure, reduces artifact interference, improves the evaluation accuracy of pelvic floor dysfunction, provides more reliable data support for a personalized treatment scheme, and finally improves the clinical diagnosis and treatment efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of color ultrasound examination, in particular to a transperineal pelvic floor color ultrasound examination system and a use method thereof. BACKGROUND

[0002] The transperineal pelvic floor color ultrasound examination system is a system for visualizing the pelvic floor structure using transperineal ultrasound technology. The system usually includes an ultrasound probe, an imaging device and analysis software, which is used to evaluate the anatomical structure and functional status of the pelvic floor muscles, urethra, bladder, rectum and related tissues, especially in the diagnosis and treatment evaluation of postpartum rehabilitation, stress urinary incontinence, pelvic organ prolapse and other diseases. The use method usually involves the patient taking an appropriate examination position, the operator placing the ultrasound probe in the perineum, obtaining dynamic data of the pelvic floor tissue through real-time imaging, and combining the software analysis results to assist clinical decision-making.

[0003] In the prior art, traditional pelvic floor function evaluation methods mainly include digital rectal examination, pelvic floor electromyography and magnetic resonance imaging (MRI), but these methods have their own shortcomings in resolution, real-time dynamic monitoring and operational convenience. For example, digital rectal examination relies on the subjective judgment of the doctor, electromyography can quantify muscle function but lacks intuitive images, and MRI can provide high-resolution anatomical images, but the cost is high and it is difficult to perform dynamic evaluation. In contrast, transperineal pelvic floor color ultrasound technology can provide high-definition, real-time dynamic images under the premise of non-invasiveness and low cost, so it has been widely used and developed in clinical practice.

[0004] The prior art has the following shortcomings: Ultrasound imaging relies on the propagation and reflection of sound waves between different tissues, but the pelvic floor area contains various tissues (such as muscles, ligaments, connective tissue, fat, etc.), and the interfaces with different densities and acoustic impedances can produce artifacts, affecting image quality. For example, gas in the bladder and rectum can cause sound attenuation or reflection, making it difficult to distinguish some anatomical structures, thereby interfering with the evaluation of key sites such as the urethra, bladder neck and levator ani muscle. In addition, if the artifact leads to misjudgment, it may cause the clinician to misjudge the degree of pelvic floor dysfunction (such as urinary incontinence, organ prolapse, etc.), affecting the development of treatment plans. SUMMARY

[0005] The purpose of the present application is to provide a transperineal pelvic floor color ultrasound examination system and a use method thereof to solve the problems in the background art.

[0006] In order to achieve the above-mentioned purpose, the present application provides the following technical solution: a transperineal pelvic floor color ultrasound examination system, comprising an ultrasound probe module, an imaging module, an image optimization module, a three-dimensional imaging module, a data analysis module and a user interaction module. An ultrasonic probe module, used for transmitting and receiving ultrasonic signals and obtaining echo signals from pelvic floor tissue; An imaging module, connected to the ultrasound probe module, for receiving echo signals and generating real-time ultrasound images; Image optimization module, used to automatically adjust ultrasound imaging parameters, including gain, contrast, filtering, and tissue harmonic imaging mode, to reduce artifacts caused by the complex structure of the pelvic floor tissue; The 3D imaging module is used to perform 3D reconstruction of the pelvic floor tissue and capture the changes in the pelvic floor muscles in static and dynamic states through 4D imaging technology; The data analysis module is used to evaluate the quality of real-time ultrasound images by combining artifact-reduced ultrasound image data with pelvic floor muscle change data. For high-quality real-time ultrasound images, key pelvic floor anatomical parameters, including bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness, are automatically calculated, and abnormal annotation prompts are provided. The user interaction module is used to display real-time ultrasound images and analysis results of the data analysis module, and supports doctors to input patient information.

[0007] Preferably, in the data analysis module, a tissue boundary stability index is generated by measuring whether the pelvic floor tissue boundary is clear and stable in the ultrasound image, wherein the tissue boundary stability index is obtained by: Preprocess the ultrasound image. If the input image is color, convert it to grayscale image. , use Gaussian kernel to smooth the image and calculate the expression: ;in: is the grayscale value of the original ultrasound image, is a two-dimensional Gaussian filter kernel, ∗ represents the convolution operation, is the standard deviation of the Gaussian filter, is the grayscale image after smoothing; Calculate horizontal direction and vertical direction The gradient of , using a Sobel filter: , ; Calculate the gradient magnitude: ; Calculate the gradient direction: ; Along the gradient direction Perform refinement, retain only local maxima, set high threshold Th and low threshold Tl, and filter edges: If , marked as a strong edge point; if , marked as a weak edge point, if it is connected to a strong edge point, it is retained, otherwise it is discarded; if , then discard; Calculate the local contrast of pixels within the boundary area , the expression is: ; Where: N is the number of boundary points (|E|), is the average grayscale value of all boundary points, and the gradient direction consistency value of the boundary points is calculated , E represents the set of edge pixels in the image, and the expression is: ;in: is the average gradient direction of all boundary points; The tissue boundary stability index was obtained by taking the weighted average of the boundary contrast change rate and the gradient consistency value.

[0008] Preferably, in the data analysis module, the pelvic floor muscle dynamic deformation index is generated by measuring the consistency and repeatability of the deformation of the pelvic floor muscle under different physiological states, wherein the pelvic floor muscle dynamic deformation index is obtained by: Preprocess the ultrasound image sequence. If the ultrasound image is in RGB format, convert it to grayscale image , calculate the horizontal direction and vertical direction The gradient of , using a Sobel filter: , ; Calculate the time gradient: ; Calculate the movement speed of each pixel. The basic equation of optical flow is: ; Where: u is the displacement velocity in the x direction, v is the displacement velocity in the y direction, 、 is the spatial gradient, is the time gradient; Assuming that the speed of the local pixel block remains consistent within the window size W, we have: ; ; Solve u, v to get the displacement vector of each pixel; Calculate the average motion speed of all pixels in the pelvic floor muscle area, and calculate the expression: ;in: Represents the local deformation velocity of the pelvic floor muscle, u and v are the movement velocities in the horizontal and vertical directions respectively, and the pelvic floor muscle dynamic deformation index PFDC is calculated using the following expression: ; Where M is the total number of pixels in the pelvic floor muscle area, is the deformation speed of each pixel.

[0009] Preferably, in the data analysis module, the organization boundary stability index and the pelvic floor muscle dynamic deformation index are converted into a comprehensive feature vector, the comprehensive feature vector is taken as an input of a machine learning model, the machine learning model takes a quality analysis value label of the real-time ultrasound image as a prediction target, minimizes a sum of prediction errors of the quality analysis value labels of all real-time ultrasound images as a training target, and trains the machine learning model until the sum of prediction errors converges, and then stops the model training, and finally determines the quality analysis value of the real-time ultrasound image according to an output result of the model, wherein the machine learning model is a polynomial regression model.

[0010] Preferably, in the data analysis module, the quality analysis value of the acquired real-time ultrasound image is compared with a quality analysis value reference threshold value preset according to historical data, if the quality analysis value of the real-time ultrasound image is greater than or equal to the preset quality analysis value reference threshold value, it is indicated that the quality of the acquired real-time ultrasound image is high, and the real-time ultrasound image is divided into a high-quality real-time ultrasound image, the pelvic floor key anatomical parameters including bladder neck activity, urethral rotation angle and pelvic floor muscle thickness are automatically calculated for the high-quality real-time ultrasound image, and an abnormality annotation prompt is provided, and if the quality analysis value of the real-time ultrasound image is less than the preset quality analysis value reference threshold value, it is indicated that the quality of the acquired real-time ultrasound image is low, and the real-time ultrasound image is divided into a low-quality real-time ultrasound image, and the image needs to be reacquired or the ultrasound parameters need to be adjusted.

[0011] The application also provides a use method of the transperineal pelvic floor color ultrasound examination, comprising: S1: the patient takes a supine position or a lateral position, relaxes the pelvic floor muscles, and prepares for the examination; S2: the operator places the ultrasound probe coated with a coupling agent on the perineum of the patient, adjusts the angle of the probe, and obtains the best imaging angle; S3: the imaging device displays the ultrasound image of the pelvic floor tissue in real time, and the image optimization module performs enhancement processing to reduce the interference of artifacts; S4: the three-dimensional imaging module is enabled, three-dimensional reconstruction images of the pelvic floor muscle group are acquired, and key anatomical structures are analyzed; S5: the quality of the real-time ultrasound image is evaluated in combination with the ultrasound image data after the reduction of artifacts and the pelvic floor muscle change data, the pelvic floor function parameters are calculated, and the abnormality prompt is provided in combination with the patient's symptoms; S6: the doctor determines whether the patient has pelvic floor dysfunction according to the ultrasound image and the analysis result, and formulates a corresponding treatment or rehabilitation scheme.

[0012] Preferably, in S2, the operator places the ultrasound probe coated with a coupling agent on the perineum of the patient, adjusts the angle of the probe, and obtains the best imaging angle, and specifically comprises: Let the angle of the current ultrasound probe be The dynamic adjustment of the probe angle is represented as: ; wherein: is the current ultrasound probe angle, is the adjusted ultrasound probe angle, Q is a quality analysis value of the real-time ultrasound image, which is calculated by the data analysis module, is a gradient of the image quality analysis value to the probe angle, that is, a quality change rate at the current angle, is a learning rate for controlling the adjustment amplitude; The partial derivative of the probe angle is obtained as: ; wherein: , is a weight coefficient, which is set as ; is an influence of the probe angle on the stability of the tissue boundary, if the boundary is blurred, the partial derivative is small, and the probe angle needs to be adjusted; is an influence of the probe angle on the dynamic deformation evaluation of the pelvic floor muscle, if the profile deformation of the pelvic floor muscle is abnormal, the partial derivative is small, and the probe angle needs to be adjusted.

[0013] Preferably, in S2, in order to realize dynamic adjustment, an iterative optimization strategy is adopted, which includes: setting an initial probe angle between 30° and 60°; calculating using the current image; obtaining a change rate of the quality to the angle, and updating the probe angle: ; if the image quality change is less than a set threshold ε, stop adjusting; otherwise, continue iteration.

[0014] In the above technical solution, the present application has the following technical effects and advantages: 1. The present application realizes precise evaluation of the pelvic floor function through the collaborative optimization of the ultrasound probe module, the imaging module, the image optimization module, the three-dimensional imaging module, the data analysis module, and the user interaction module. The system adopts automatic artifact suppression, three-dimensional / 4D dynamic imaging, intelligent image quality analysis, and parameter optimization technologies, and overcomes the problems of low image quality, large diagnostic errors, and the like caused by tissue complexity, acoustic attenuation, and reflection in existing ultrasound examinations. In particular, the data analysis module introduces a tissue boundary stability index (TBSI) and a pelvic floor muscle dynamic deformation index (PFDC), combines a machine learning polynomial regression model, automatically evaluates the image quality, and dynamically adjusts the probe angle according to the analysis result, to ensure imaging clarity, improve the measurement accuracy of key anatomical parameters such as bladder neck activity, urethral rotation angle, and pelvic floor muscle thickness, and provide abnormal annotations to assist doctors in precise diagnosis.

[0015] 2. This system utilizes intelligent image quality optimization and dynamic probe adjustment to automatically screen high-quality ultrasound images and accurately calculate key pelvic floor functional parameters, significantly improving the reliability and ease of use of ultrasound examinations. Physicians can intuitively view real-time images, data analysis results, and anomaly annotations through a user-interactive module, and input patient medical history for personalized diagnosis. This system not only reduces the risk of misdiagnosis due to artifacts or improper ultrasound angles, but also improves the efficiency of screening and follow-up for pelvic floor disorders (such as stress urinary incontinence and pelvic organ prolapse), providing clinicians with a more accurate, intelligent, and efficient pelvic floor ultrasound examination solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments described in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0017] Figure 1 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0019] For examples, see Figure 1 As shown, the transperineal pelvic floor color Doppler ultrasound examination system described in this embodiment includes an ultrasound probe module, an imaging module, an image optimization module, a three-dimensional imaging module, a data analysis module, and a user interaction module; An ultrasonic probe module, used for transmitting and receiving ultrasonic signals and obtaining echo signals from pelvic floor tissue; An imaging module, connected to the ultrasound probe module, for receiving echo signals and generating real-time ultrasound images; Image optimization module, used to automatically adjust ultrasound imaging parameters, including gain, contrast, filtering, and tissue harmonic imaging mode, to reduce artifacts caused by the complex structure of the pelvic floor tissue; The 3D imaging module is used to perform 3D reconstruction of the pelvic floor tissue and capture the changes in the pelvic floor muscles in static and dynamic states through 4D imaging technology; The data analysis module is used to evaluate the quality of real-time ultrasound images by combining artifact-reduced ultrasound image data with pelvic floor muscle change data. For high-quality real-time ultrasound images, key pelvic floor anatomical parameters, including bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness, are automatically calculated, and abnormal annotation prompts are provided. The user interaction module is used to display real-time ultrasound images and analysis results of the data analysis module, and supports doctors to input patient information.

[0020] The ultrasound probe module is the core component of the transperineal pelvic floor color Doppler ultrasound examination system. It is mainly used to transmit and receive ultrasonic signals and transmit the echo signals to the imaging module to generate ultrasound images of the pelvic floor tissue. This module generally includes the following key parts: Transducer Array: Made of piezoelectric materials (such as PZT or PMN-PT), it converts electrical signals into ultrasound waves. Transducer arrays can be linear, convex, or phased array to suit different pelvic floor examination needs.

[0021] Operating frequency: Typically in the 5MHz to 12MHz range, adjustable based on imaging depth requirements. High frequencies (>8MHz) provide higher resolution and are suitable for superficial tissues (e.g., urethra, bladder neck), while low frequencies (<7MHz) can penetrate deeper tissues (e.g., levator ani muscles, rectum).

[0022] Dynamic focus adjustment: The ultrasound probe supports electronic focusing and dynamic receiving focusing technology to optimize imaging clarity at different depths and reduce blurring caused by focus mismatch.

[0023] Signal transmission and noise suppression: The probe is integrated with a low-noise amplifier (LNA), which can improve the detection sensitivity of weak echo signals and reduce the impact of electromagnetic interference on ultrasonic signals.

[0024] The imaging module is the core computing module of the transperineal pelvic floor color ultrasound system, responsible for receiving the echo signals collected by the ultrasound probe and converting them into real-time ultrasound images. The main functions and technical features include: Signal Reception and Preprocessing: Multi-channel High Dynamic Range (HDR) signal reception effectively captures the contrast between strong echoes (such as bone) and weak echoes (such as soft tissue), enhancing image detail. Adaptive Gain Control (TGC) automatically adjusts signal gain at different depths to avoid overly dark or overexposed images.

[0025] Real-time image processing: Tissue Harmonic Imaging (THI): Utilizes high-order harmonic signals to improve resolution, reduce artifacts, and enhance the clarity of pelvic floor tissue boundaries. Adaptive Filtering (Speckle Reduction Algorithm, SRA): Removes speckle noise, enhances image contrast, and makes the pelvic floor muscle layers more clearly visible. Spatial Composite Imaging: Acquires ultrasound signals from multiple angles and fuses them into a single image to improve the visualization of key pelvic floor structures (such as urethral rotation angle and bladder neck mobility). Automatic Tissue Segmentation: Based on artificial intelligence (AI) algorithms, it can automatically identify pelvic floor muscle groups, urethra, bladder and other tissues, and annotate key anatomical parameters, such as pelvic floor muscle thickness, urethral rotation angle, etc.

[0026] Dynamic Image Storage and Analysis: Equipped with real-time 4D ultrasound imaging, the system records dynamic changes in the pelvic floor during rest, Valsalva maneuvers, and coughing, enabling assessment of stress urinary incontinence and pelvic organ prolapse. A built-in image storage and playback system enables post-examination analysis and supports DICOM format export for remote consultations and post-operative follow-up.

[0027] The image optimization module automatically adjusts ultrasound imaging parameters in the transperineal pelvic floor color ultrasound examination system to improve imaging quality, reduce artifact interference caused by the complex structure of the pelvic floor tissue (such as muscles, ligaments, connective tissue, fat, etc.), and ensure clear visualization of key anatomical structures.

[0028] Because the pelvic floor contains different types of tissue (e.g., hyperechoic ligaments and hypoechoic muscles), improper gain adjustment can result in an image that is too bright (high gain) or too dark (low gain), impairing visualization of key anatomical structures (e.g., the urethra, bladder neck, and levator ani muscles). This module automatically adjusts gain (TGC - Time Gain Compensation) based on the distribution of echo intensity, ensuring uniform brightness across tissues at varying depths. In the near field (near the probe), gain is reduced to avoid signal overexposure; in the far field (deep tissue), gain is increased to enhance signal strength, ensuring clear visualization of deep pelvic floor structures (e.g., the puborectalis and levator ani muscles).

[0029] The low echo contrast of pelvic floor tissue, especially at the demarcation points between pelvic floor muscle groups, can make it difficult to distinguish different structures, such as the blurred boundary between the urethra and bladder wall. Dynamic Range Optimization automatically adjusts the grayscale level of the image to highlight details in low-contrast areas, improving the distinction between muscles, ligaments, and connective tissue. Tissue-Specific Contrast Enhancement uses AI to identify key pelvic floor structures and automatically adjust local contrast to make the target area clearer.

[0030] Traditional ultrasound imaging can be affected by artifacts, such as reflections from bladder and rectal gas, which can obscure some tissue structures. Tissue harmonic imaging (THI) utilizes the second harmonic of ultrasound, rather than the fundamental wave, for imaging. This allows the high-frequency signal to be more focused on soft tissue areas, reducing near-field artifacts and improving image clarity. This module automatically selects the optimal harmonic frequency based on the patient's pelvic floor anatomy to optimize imaging quality.

[0031] Pelvic floor ultrasound images are often affected by speckle noise, which can cause granular speckling and reduce the resolution of tissues such as muscles and ligaments. Adaptive multi-scale filtering (MAF) technology is used to smooth images and remove noise while preserving tissue boundary details. Combined with AI algorithms, it performs region-specific noise reduction on different pelvic floor tissue areas, avoiding image distortion caused by over-smoothing.

[0032] The three-dimensional imaging module is an important component of the transperineal pelvic floor color ultrasound examination system. It is mainly used to perform three-dimensional reconstruction of the pelvic floor tissue and capture the changing data of the pelvic floor muscles in static and dynamic states through 4D imaging technology (i.e. real-time three-dimensional ultrasound) to improve the accuracy of pelvic floor function assessment.

[0033] Traditional two-dimensional ultrasound can only provide single-section images, which makes it difficult to fully display the three-dimensional structure of the pelvic floor muscles, such as the overall shape of the levator ani muscles, the spatial relationship between the urethra and bladder neck, etc., affecting the doctor's accurate assessment of pelvic floor dysfunction (such as urinary incontinence and pelvic organ prolapse).

[0034] By employing 3D Ultrasound Imaging technology, an ultrasound probe collects data from multiple angles and processes it through a computer to construct a high-resolution 3D image of the pelvic floor. Combined with volume rendering, this enhances the visualization of different tissues (such as the pelvic floor muscles, ligaments, urethra, and rectum), allowing doctors to observe the pelvic floor anatomy from multiple angles.

[0035] The diagnosis of pelvic floor dysfunction relies not only on static structures but also on observing the movement of the pelvic floor muscles in different states. For example, dynamic changes in the bladder neck, urethra, and rectum during the Valsalva maneuver (increasing abdominal pressure, such as coughing or breath-holding) or sphincter contraction are key indicators for urinary incontinence and pelvic organ prolapse. However, traditional two-dimensional ultrasound only provides single-frame images, making it difficult to intuitively reflect the dynamic movement patterns of tissues.

[0036] By utilizing 4D ultrasound technology (real-time 3D ultrasound), it is possible to continuously acquire 3D imaging data and display in real time the movement changes of the pelvic floor tissue under different physiological conditions. Time Sequence Analysis: This records the movement trajectory of the pelvic floor muscles at different time points, quantifies the dynamic changes of the urethra, bladder neck, and levator ani muscles, and provides objective functional assessment data.

[0037] The data analysis module is used to evaluate the quality of real-time ultrasound images by combining artifact-reduced ultrasound image data and pelvic floor muscle change data. For high-quality real-time ultrasound images, it automatically calculates key pelvic floor anatomical parameters, including bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness, and provides abnormal annotation prompts.

[0038] The ultrasound signal in the pelvic floor region is significantly affected by tissue heterogeneity. Some areas (such as those around the bladder) may have artifacts or blurred boundaries, affecting the clarity of tissue demarcations. Traditional ultrasound imaging relies primarily on the physician's subjective judgment of tissue boundary clarity. By measuring the clarity and stability of pelvic floor tissue boundaries (such as the urethra, bladder neck, and puborectalis muscle) in ultrasound images, a tissue boundary stability index is generated to automatically assess boundary quality. The method for obtaining the organizational boundary stability index is as follows: Preprocess the ultrasound image. If the input image is color (RGB), convert it to grayscale image. , use Gaussian kernel to smooth the image to reduce the effect of speckle noise, and calculate the expression: ;in: is the grayscale value of the original ultrasound image, is a two-dimensional Gaussian filter kernel, and ∗ represents a convolution operation. is the standard deviation of the Gaussian filter (typical value = 1.0 to 2.0). is the grayscale image after smoothing.

[0039] Calculate horizontal direction and vertical direction The gradient of , using a Sobel filter: , ; Calculate the gradient magnitude: ; Calculate the gradient direction: ; Along the gradient direction Refine and retain only local maxima, double threshold processing: set high threshold Th and low threshold Tl, filter edge: if , marked as a strong edge point; if , marked as a weak edge point, if it is connected to a strong edge point, it is retained, otherwise it is discarded; if , then discard; Calculate the local contrast of pixels within the boundary area , the expression is: ; Where: N is the number of boundary points (|E|), is the average grayscale value of all boundary points, and the gradient direction consistency value of the boundary points is calculated , E represents the set of edge pixels in the image, and the expression is: ;in: is the average gradient direction of all boundary points.

[0040] The tissue boundary stability index is calculated by taking the weighted average of the boundary contrast change rate and the gradient consistency value. The higher the tissue boundary stability index, the clearer and more stable the boundary and the better the ultrasound image quality.

[0041] The dynamic changes of the pelvic floor muscles are important indicators for functional assessment. However, the muscle echo signal is easily affected by artifacts and motion artifacts, leading to measurement errors. Traditional assessment methods rely solely on doctors observing changes in muscle morphology. By measuring the consistency and repeatability of pelvic floor muscle deformation under different physiological states (such as resting, Valsalva maneuver, coughing, etc.), a pelvic floor muscle dynamic deformation index is generated to evaluate the quality of real-time ultrasound images. Among them, the method for obtaining the dynamic deformation index of the pelvic floor muscle is: Preprocess the ultrasound image sequence. If the ultrasound image is in RGB format, convert it to grayscale image (Two adjacent ultrasound frames). Obtain image spatial and temporal gradient information to calculate pixel motion. Calculate horizontal and vertical direction The gradient of , using a Sobel filter: , ; Calculate the temporal gradient (pixel value change between frames): .

[0042] Calculate the movement speed of each pixel (motion vector of the pelvic floor muscle), the basic equation of optical flow: ; Where: u is the displacement velocity in the x direction (horizontal movement), v is the displacement velocity in the y direction (vertical movement), 、 is the spatial gradient, is the time gradient.

[0043] Assuming that the speed of the local pixel block remains consistent within the window size W, we have: ; ; Solve u, v to get the displacement vector of each pixel.

[0044] Calculate the average motion velocity of all pixels in the pelvic floor muscle area to evaluate the overall dynamic deformation of the muscle. The calculation expression is: ;in: Represents the local deformation velocity of the pelvic floor muscle, u and v are the movement velocities in the horizontal and vertical directions respectively. The pelvic floor muscle dynamic deformation index PFDC is calculated using the following expression: ; Where M is the total number of pixels in the pelvic floor muscle area, is the deformation speed of each pixel.

[0045] The tissue boundary stability index and the pelvic floor muscle dynamic deformation index are converted into comprehensive feature vectors, which are used as inputs of the machine learning model. The machine learning model predicts the quality analysis value label of the real-time ultrasound image for each set of comprehensive feature vectors as the prediction target, and minimizes the sum of the prediction errors of the quality analysis value labels of all real-time ultrasound images as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence, and the model training is stopped. The quality analysis value of the real-time ultrasound image is determined based on the model output results. The machine learning model is a polynomial regression model.

[0046] The method for obtaining the quality analysis value of real-time ultrasound images is to obtain the corresponding function expression from the comprehensive feature vector training data of the trained machine learning model: Where, is the output function of the model, TBSI is the tissue boundary stability index, PFDC is the pelvic floor muscle dynamic deformation index, It is the quality analysis value of real-time ultrasound image.

[0047] The quality analysis value of the acquired real-time ultrasound image is compared with the quality analysis value reference threshold pre-set based on historical data. If the quality analysis value of the real-time ultrasound image is greater than or equal to the pre-set quality analysis value reference threshold, it indicates that the quality of the acquired real-time ultrasound image is high and it is classified as a high-quality real-time ultrasound image. For high-quality real-time ultrasound images, key pelvic floor anatomical parameters, including bladder neck mobility, urethral rotation angle and pelvic floor muscle thickness, are automatically calculated, and abnormality annotation prompts are provided. If the quality analysis value of the real-time ultrasound image is less than the pre-set quality analysis value reference threshold, it indicates that the quality of the acquired real-time ultrasound image is low and it is classified as a low-quality real-time ultrasound image, and the image needs to be re-acquired or the ultrasound parameters need to be adjusted.

[0048] For high-quality, real-time ultrasound images, the system automatically calculates key anatomical parameters, including bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness, to accurately assess pelvic floor function. Bladder neck mobility refers to the displacement of the bladder neck between resting and exertion during a Valsalva maneuver (e.g., coughing or breath-holding), and can be used to assess the risk of stress urinary incontinence. Urethral rotation angle indicates changes in urethral inclination under different physiological conditions and is a key indicator for assessing urethral hypermobility. Pelvic floor muscle thickness reflects the muscular condition of the pelvic floor muscles; weakness or uneven thickening may indicate muscle atrophy, dysfunction, or the effects of postoperative scar tissue.

[0049] After obtaining these anatomical parameters, the system will combine them with normal reference ranges to provide abnormal annotation prompts. Excessive bladder neck mobility may indicate a risk of urinary incontinence; urethral rotation angles outside the normal range may be associated with pelvic organ prolapse; and significantly low or locally uneven pelvic floor muscle thickness may indicate decreased muscle strength or injury. The system will provide intuitive feedback to physicians through color coding, warning signs, or risk scores to assist in clinical decision-making, ensuring the accuracy of diagnosis and the rationality of treatment plans.

[0050] The user interaction module is a key component of the transperineal pelvic floor color Doppler ultrasound system. It displays real-time ultrasound images, presents analysis results from the data analysis module, and supports physician input of patient information. Through its intuitive interface and interactive design, this module enhances the convenience of ultrasound examinations, enabling physicians to efficiently complete image evaluation, data entry, and diagnostic decision-making.

[0051] Real-time ultrasound image display provides clear and smooth ultrasound images so that doctors can observe the anatomical structure and functional changes of the pelvic floor in real time. High-definition real-time ultrasound display: supports 2D grayscale ultrasound, color Doppler (CFD), tissue harmonic imaging (THI) and other modes, and can dynamically adjust parameters such as brightness, contrast, and gain. 4D ultrasound playback: can pause and replay dynamic images so that doctors can analyze the changes in pelvic floor tissue under different physiological states, such as Valsalva maneuver, cough test, etc. Multi-angle switching: supports 3D / 4D image reconstruction from different angles to obtain complete structural information of the bladder neck, urethra, and pelvic floor muscles. AI-assisted boundary annotation: automatically outlines the contours of the bladder neck, urethra, and pelvic floor muscles, and can be manually adjusted to improve annotation accuracy.

[0052] The data analysis results display intuitively presents key anatomical parameters and quality assessment results calculated by the data analysis module to assist physicians in decision-making. Automatic calculation and visualization of key pelvic floor anatomical parameters: Bladder Neck Mobility: Displays bladder neck displacement with numerical values ​​and dynamic graphics, and provides a normal reference range. Urethral Rotation Angle: Displays changes in urethral inclination with angle values ​​and dynamic graphics, and marks abnormalities. Pelvic Floor Muscle Thickness: Displays muscle thickness measurements and compares them with historical data.

[0053] Image quality scores (1-10) are calculated by the data analysis module. High-quality images are annotated (green) and low-quality images are indicated (red), allowing physicians to quickly determine whether re-image acquisition is necessary. Abnormal parameters (such as bladder neck mobility outside the normal range) are highlighted. Color coding (green / yellow / red) visually identifies ultrasound assessment results. An intelligent risk score (based on AI) predicts the presence of pelvic floor dysfunction and recommends further testing or treatment options.

[0054] Physician input and patient information management facilitate the entry of patient information, supporting data storage and historical comparison to enhance follow-up management capabilities. Basic patient information entry includes name, age, medical history, and symptom description. Electronic medical record (EMR) integration allows direct access to hospital database information.

[0055] Image data is automatically matched to patient information for easy subsequent review. Supporting the DICOM standard, it can be connected to PACS image storage systems for remote consultation or long-term follow-up.

[0056] Doctors can adjust AI-calculated markers for the bladder neck, urethra, and pelvic floor muscles to ensure accuracy. Customized diagnostic assessment: Doctors can manually enter diagnostic conclusions and store them in the patient's file. Voice input support: Reduces the burden of manual input for doctors and improves work efficiency.

[0057] The interactive interface is optimized for ultrasound equipment's touchscreen, allowing for quick menu selection and parameter adjustment. One-touch switching between ultrasound images, data analysis, and patient information improves operational fluidity. Doctors can remotely access images and data via tablets or mobile devices, enhancing follow-up convenience.

[0058] In this embodiment, high-precision ultrasonic imaging and intelligent analysis of pelvic floor tissue are achieved by integrating an ultrasound probe module, an imaging module, an image optimization module, a three-dimensional imaging module, a data analysis module, and a user interaction module. The ultrasound probe module is responsible for transmitting and receiving ultrasonic signals, the imaging module processes echo signals and generates real-time images, and the image optimization module reduces artifact interference and improves image quality by automatically adjusting gain, contrast, filtering, and tissue harmonic imaging mode. The three-dimensional imaging module supports three-dimensional reconstruction and 4D imaging, capturing changes in the pelvic floor muscles in static and dynamic states. The data analysis module performs quality assessment on the optimized ultrasound images and automatically calculates bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness in high-quality images, providing abnormal annotation prompts. The user interaction module is used to display real-time images and analysis results, and supports doctors to input patient information, achieving accurate and intelligent pelvic floor function assessment and clinical decision support.

[0059] Example 2: A method for using transperineal pelvic floor color Doppler ultrasound examination as described in this example includes: S1: The patient lies supine or lateral, relaxes the pelvic floor muscles, and prepares for examination. S2: The operator coats the ultrasound probe with coupling agent and places it on the patient's perineum. The operator also adjusts the probe angle to obtain the best imaging perspective. S3: The ultrasound image of the pelvic floor tissue is displayed in real time by the imaging device and enhanced by the image optimization module to reduce artifact interference; S4: Enable the 3D imaging module to obtain 3D reconstructed images of the pelvic floor muscles and analyze key anatomical structures; S5: Combine the artifact-reduced ultrasound image data and pelvic floor muscle change data to evaluate the quality of real-time ultrasound images, calculate pelvic floor function parameters, and provide abnormal prompts based on patient symptoms; S6: The doctor determines whether the patient has pelvic floor dysfunction based on ultrasound images and analysis results, and formulates a corresponding treatment or rehabilitation plan.

[0060] In step S2, the operator coats the ultrasound probe with coupling agent and places it on the patient's perineum, and adjusts the probe angle to obtain the best imaging perspective, specifically including: In order to optimize the ultrasound probe angle and ensure high-quality real-time ultrasound images, the probe angle is adjusted based on the ultrasound image quality assessment results (quality analysis value Q). Dynamic adjustment. By building a feedback control system, the probe angle is adaptively adjusted in the direction of optimal image quality, reducing artifacts and enhancing tissue boundary clarity.

[0061] Assume that the current angle of the ultrasound probe is (angle after the nth adjustment), the dynamic adjustment of the probe angle is expressed as: ; wherein: is the current ultrasound probe angle (unit: degree). is the adjusted ultrasound probe angle (unit: degree). Q is the quality analysis value of real-time ultrasound image, which is calculated by the data analysis module (range: 0≤Q≤1), is the gradient of image quality analysis value to probe angle, i.e. the quality change rate at the current angle, is the learning rate (step coefficient), which is used to control the adjustment amplitude, and the typical value is 0.1-0.5 to prevent oscillation or slow convergence.

[0062] The partial derivative of the probe angle is obtained as: ; wherein: , is the weight coefficient, which determines the contribution of TBSI and PFDC in the calculation of image quality, and is usually set to .

[0063] is the influence of the probe angle on the stability of the tissue boundary. If the boundary is blurred, the partial derivative is smaller, and the probe angle needs to be adjusted. is the influence of the probe angle on the dynamic deformation evaluation of the pelvic floor muscle. If the pelvic floor muscle profile deformation is abnormal, the partial derivative is smaller, and the probe angle needs to be adjusted.

[0064] In order to realize dynamic adjustment, an iterative optimization strategy is adopted: Initial angle setting: set the initial probe angle , which is usually between 30°-60°.

[0065] Calculate the image quality analysis value : calculate using the current image.

[0066] Calculate the gradient : find the change rate of quality to angle.

[0067] Update the probe angle: .

[0068] Convergence judgment: ; if the image quality change is less than the set threshold value e (such as 0.01), stop adjusting; otherwise, continue iteration.

[0069] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A transperineal pelvic floor color Doppler ultrasound examination system, characterized by: It includes ultrasound probe module, imaging module, image optimization module, three-dimensional imaging module, data analysis module and user interaction module; An ultrasonic probe module, used for transmitting and receiving ultrasonic signals and obtaining echo signals from pelvic floor tissue; An imaging module, connected to the ultrasound probe module, for receiving echo signals and generating real-time ultrasound images; Image optimization module, used to automatically adjust ultrasound imaging parameters, including gain, contrast, filtering, and tissue harmonic imaging mode, to reduce artifacts caused by the complex structure of the pelvic floor tissue; The 3D imaging module is used to perform 3D reconstruction of the pelvic floor tissue and capture the changes in the pelvic floor muscles in static and dynamic states through 4D imaging technology; The data analysis module is used to evaluate the quality of real-time ultrasound images by combining artifact-reduced ultrasound image data with pelvic floor muscle change data. For high-quality real-time ultrasound images, key pelvic floor anatomical parameters, including bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness, are automatically calculated, and abnormal annotation prompts are provided. The user interaction module is used to display real-time ultrasound images and analysis results of the data analysis module, and supports doctors to input patient information.

2. The transperineal pelvic floor color Doppler ultrasound examination system according to claim 1, characterized in that: In the data analysis module, the tissue boundary stability index is generated by measuring whether the pelvic floor tissue boundary is clear and stable in the ultrasound image. The tissue boundary stability index is obtained as follows: Preprocess the ultrasound image. If the input image is color, convert it to grayscale image. , use Gaussian kernel to smooth the image and calculate the expression: ;in: is the grayscale value of the original ultrasound image, is a two-dimensional Gaussian filter kernel, ∗ represents the convolution operation, is the standard deviation of the Gaussian filter, is the grayscale image after smoothing; Calculate horizontal direction and vertical direction The gradient of , using a Sobel filter: , ; Calculate the gradient magnitude: ; Calculate the gradient direction: ; Along the gradient direction Perform refinement, retain only local maxima, set high threshold Th and low threshold Tl, and filter edges: If , marked as a strong edge point; if , marked as a weak edge point, if it is connected to a strong edge point, it is retained, otherwise it is discarded; if , then discard; Calculate the local contrast of pixels within the boundary area , the expression is: ; Where: N is the number of boundary points, is the average grayscale value of all boundary points, E represents the edge pixel set in the image, and the gradient direction consistency value of the boundary points is calculated , the expression is: ;in: is the average gradient direction of all boundary points; The tissue boundary stability index was obtained by taking the weighted average of the boundary contrast change rate and the gradient consistency value.

3. The transperineal pelvic floor color Doppler ultrasound examination system according to claim 2, characterized in that: In the data analysis module, the pelvic floor muscle dynamic deformation index is generated by measuring the consistency and repeatability of the deformation of the pelvic floor muscle under different physiological states. The method for obtaining the pelvic floor muscle dynamic deformation index is as follows: Preprocess the ultrasound image sequence. If the ultrasound image is in RGB format, convert it to grayscale image , calculate the horizontal direction and vertical direction The gradient of , using a Sobel filter: , ; Calculate the time gradient: ; Calculate the movement speed of each pixel. The basic equation of optical flow is: ; Where: u is the displacement velocity in the x direction, v is the displacement velocity in the y direction, 、 is the spatial gradient, is the time gradient; Assuming that the speed of the local pixel block remains consistent within the window size W, we have: ; Solve u and v to get the displacement vector of each pixel; calculate the average movement speed of all pixels in the pelvic floor muscle area, and calculate the expression: ;in: Represents the local deformation velocity of the pelvic floor muscle, u and v are the movement velocities in the horizontal and vertical directions respectively, and the pelvic floor muscle dynamic deformation index PFDC is calculated using the following expression: ; Where M is the total number of pixels in the pelvic floor muscle area, is the deformation speed of each pixel.

4. The transperineal pelvic floor color Doppler ultrasound examination system according to claim 3, characterized in that: In the data analysis module, the tissue boundary stability index and the pelvic floor muscle dynamic deformation index are converted into comprehensive feature vectors, which are used as inputs to the machine learning model. The machine learning model predicts the quality analysis value label of the real-time ultrasound image for each set of comprehensive feature vectors as the prediction target, and minimizes the sum of the prediction errors of the quality analysis value labels of all real-time ultrasound images as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The quality analysis value of the real-time ultrasound image is determined based on the model output results. The machine learning model is a polynomial regression model.

5. The transperineal pelvic floor color Doppler ultrasound examination system according to claim 4, characterized in that: In the data analysis module, the quality analysis value of the acquired real-time ultrasound image is compared with the quality analysis value reference threshold pre-set based on historical data. If the quality analysis value of the real-time ultrasound image is greater than or equal to the pre-set quality analysis value reference threshold, it indicates that the quality of the acquired real-time ultrasound image is high and it is classified as a high-quality real-time ultrasound image. For high-quality real-time ultrasound images, key pelvic floor anatomical parameters, including bladder neck mobility, urethral rotation angle, and pelvic floor muscle thickness, are automatically calculated, and abnormal annotation prompts are provided; If the quality analysis value of the real-time ultrasound image is less than a preset quality analysis value reference threshold, it indicates that the quality of the acquired real-time ultrasound image is low, and the image is classified as a low-quality real-time ultrasound image, and the image needs to be reacquired or the ultrasound parameters need to be adjusted.

6. A method for using transperineal pelvic floor color Doppler ultrasound examination, characterized by: The method of use adopts a transperineal pelvic floor color Doppler ultrasound examination system according to any one of claims 1 to 5, comprising: S1: The patient lies supine or lateral, relaxes the pelvic floor muscles, and prepares for examination. S2: The operator coats the ultrasound probe with coupling agent and places it on the patient's perineum. The operator also adjusts the probe angle to obtain the best imaging perspective. S3: The ultrasound image of the pelvic floor tissue is displayed in real time by the imaging device and enhanced by the image optimization module to reduce artifact interference; S4: Enable the 3D imaging module to obtain 3D reconstructed images of the pelvic floor muscles and analyze key anatomical structures; S5: Combine the artifact-reduced ultrasound image data and pelvic floor muscle change data to evaluate the quality of real-time ultrasound images, calculate pelvic floor function parameters, and provide abnormal prompts based on patient symptoms; S6: The doctor determines whether the patient has pelvic floor dysfunction based on ultrasound images and analysis results, and formulates a corresponding treatment or rehabilitation plan.

7. The method for using transperineal pelvic floor color Doppler ultrasound examination according to claim 6, characterized in that: In S2, the operator coats the ultrasound probe with coupling gel and places it on the patient's perineum. The operator then adjusts the probe angle to obtain the optimal imaging perspective, including: Assume that the current angle of the ultrasound probe is , then the dynamic adjustment of the probe angle is expressed as: ;in: is the current ultrasound probe angle, is the adjusted ultrasound probe angle, Q is the quality analysis value of the real-time ultrasound image, which is calculated by the data analysis module. is the gradient of the image quality analysis value to the probe angle, that is, the quality change rate at the current angle, is the learning rate, which is used to control the adjustment amplitude; Taking the partial derivative of the probe angle, we get: ;in: , is the weight coefficient, set to ; is the effect of the probe angle on the stability of the tissue boundary. If the boundary is blurred, the partial derivative is small and the probe angle needs to be adjusted. This is the influence of the probe angle on the evaluation of dynamic deformation of the pelvic floor muscles. If the pelvic floor muscle contour deformation is abnormal, the partial derivative of this item is small and the probe angle needs to be adjusted.

8. The method for using transperineal pelvic floor color Doppler ultrasound examination according to claim 7, characterized in that: In S2, in order to achieve dynamic adjustment, an iterative optimization strategy is adopted, which includes: Set the initial probe angle , between 30°-60°; calculated using the current image ; Calculate the rate of change of mass with respect to angle and update the probe angle: If the image quality change is less than the set threshold ϵ, stop adjusting; otherwise, continue iterating.

Images