Pelvic floor muscle contraction direction adjusting method and system
By detecting abnormal pelvic floor muscle contraction using ultrasound and image reconstruction algorithms, and combining this with electrode pads to regulate muscle contraction, the problem of cumbersome and low-accuracy pelvic floor muscle detection in existing technologies has been solved, achieving automated regulation and improved accuracy of pelvic floor muscle contraction.
Patent Information
- Application Number
- CN202511077112.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-01
- Publication Date
- 2025-10-31
AI Technical Summary
Existing technologies for detecting pelvic floor muscle movement are cumbersome and have low accuracy. Machine learning measurements require manually creating a large number of samples, which is time-consuming, labor-intensive, and the accuracy is limited by the sample size.
The transducer emits ultrasound waves to obtain signals from the diaphragm and pelvic floor muscles. High-dimensional images are generated using image reconstruction algorithms. Abnormal pelvic floor muscle contraction is determined by combining the respiratory cycle. The muscle contraction is regulated by applying current through electrode pads.
It enables automated and accurate adjustment of the direction of pelvic floor muscle contraction, coordinates the movement of the diaphragm and pelvic floor muscles, helps patients restore normal contraction patterns, and improves detection efficiency and accuracy.
Smart Images
Figure CN120860469A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of prevention and repair, and specifically relates to a method and system for adjusting the direction of pelvic floor muscle contraction. Background Technology
[0002] The pelvic floor muscles are a group of muscles that close the bottom of the pelvis. They support the pelvic organs, maintain their normal position, and prevent prolapse. Furthermore, they can control the urethral and anal sphincter muscles through contraction, thereby maintaining voluntary control of urination and defecation. They also assist in the stability of the abdomen and spine.
[0003] However, detecting pelvic floor muscle movement requires specialized equipment. Currently, there are two methods for ultrasound measurement of the diaphragm: the first is manual operation by a doctor, and the second is measurement using machine learning. Machine learning measurement of the diaphragm requires the doctor to manually create multiple measurement samples beforehand to construct a diaphragm measurement model for testing.
[0004] Regarding the aforementioned technologies, traditional detection methods rely on manual operation, which is not only cumbersome but also has low accuracy. Machine learning measurements still require the manual creation of a large number of measurement samples, which is time-consuming and labor-intensive, and the accuracy is limited by the sample size. Summary of the Invention
[0005] The technical problem to be solved by the present invention is to provide a method and system for adjusting the direction of pelvic floor muscle contraction. By establishing a correlation between the pelvic floor muscles, diaphragm and breathing, the abnormality of pelvic floor muscle contraction can be determined and adjusted, thereby helping the patient's recovery.
[0006] A method for adjusting the direction of pelvic floor muscle contraction includes:
[0007] Ultrasound waves are emitted to the diaphragm and pelvic floor muscles through a transducer to obtain diaphragm reflection signals and pelvic floor muscle signals, and the diaphragm reflection signals and pelvic floor muscle signals are used as signals to be processed.
[0008] The signal to be processed is used to generate a high-dimensional image through an image reconstruction algorithm, and a timestamp is embedded in the high-dimensional image to obtain a frame image;
[0009] The frame image is preprocessed to obtain the processed image;
[0010] The processed image is subjected to feature extraction to obtain extracted features, and the extracted features of consecutive frames of images form a shrinkage curve;
[0011] Obtain respiratory cycles;
[0012] Based on the contraction curve and respiratory cycle, determine whether the breathing pattern is normal. A normal breathing pattern is when the contraction curve rises during exhalation.
[0013] If the breathing pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles through the electrode pads to normalize the contraction of the diaphragm and pelvic floor muscles.
[0014] Optionally, preprocessing the frame image to obtain a processed image includes:
[0015] The frame image is subjected to Gaussian filtering to obtain the filtered image, wherein the Gaussian filtering is expressed as:
[0016]
[0017] Where (x, y) are pixel coordinates, the Gaussian convolution kernel is defined as g(i,j), where (i,j) are the offset coordinates of the kernel relative to the center point, the kernel size is (2k+1)×(2k+1)), W is the normalization factor, I is the frame image, and k is the kernel radius;
[0018] Calculate the grayscale histogram of the filtered image;
[0019] Calculate the cumulative distribution function value based on the grayscale histogram and the image size of the filtered image;
[0020] The processed image is obtained based on the cumulative distribution function value and the gray level range of the filtered image.
[0021] Optionally, the step of extracting features from the processed image to obtain extracted features includes:
[0022] A gradient operator is set, which includes a horizontal gradient operator and a vertical gradient operator;
[0023] The gradient component of each pixel in the processed image is obtained based on the gradient operator.
[0024] The gradient magnitude and gradient direction are calculated based on the gradient components.
[0025] Based on the gradient magnitude and gradient direction of each pixel, a gradient magnitude map and a gradient direction map are constructed, and the gradient magnitude map and gradient direction map are used as features for extraction.
[0026] Optionally, the extracted features of the consecutive frame images constitute the shrinkage curve, including:
[0027] Construct a coordinate system with the y-axis from head to feet and the positive direction of the diaphragm moving towards the feet during inhalation, and the Z-axis from the body surface to the chest cavity.
[0028] Based on the extracted features of consecutive frame images, the diaphragm displacement changes are extracted;
[0029] Generate a diaphragm curve based on the diaphragm displacement changes and the coordinate system;
[0030] Similarly, a pelvic floor muscle curve is generated, which serves as the contraction curve for the diaphragm curve and the pelvic floor muscle curve.
[0031] Optionally, determining whether the breathing pattern is normal based on the systolic curve and the respiratory cycle includes:
[0032] The respiratory cycle includes an inspiratory phase and an expiratory phase;
[0033] The contraction curves include the diaphragm curve and the pelvic floor muscle curve;
[0034] Determine whether the diaphragm curve and pelvic floor muscle curve both rise during the inhalation phase, or whether the diaphragm curve and pelvic floor muscle curve both fall during the exhalation phase;
[0035] If both the diaphragm curve and the pelvic floor muscle curve rise during the inhalation phase, or both the diaphragm curve and the pelvic floor muscle curve fall during the exhalation phase, then the breathing pattern is confirmed to be normal.
[0036] Otherwise, an abnormal breathing pattern is confirmed.
[0037] Optionally, if the breathing pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles via electrode pads to normalize their contraction, including:
[0038] Obtain the initial stimulus parameters;
[0039] Acquire real-time electrical signals of the diaphragm and pelvic floor muscles;
[0040] Acquire standard signals;
[0041] Based on the real-time electrical signal and the standard signal, an adjustment signal is applied to the electrode pads to adjust the initial stimulation parameters of the current so that the diaphragm and pelvic floor muscles contract normally.
[0042] Optionally, the initial stimulation parameters include stimulation intensity, stimulation frequency, and pulse width.
[0043] A system for regulating pelvic floor muscle contraction based on the normality of breathing patterns includes:
[0044] The signal conversion module is used to transmit ultrasound waves to the diaphragm and pelvic floor muscles through a transducer, acquire diaphragm reflection signals and pelvic floor muscle signals, and use the diaphragm reflection signals and pelvic floor muscle signals as signals to be processed.
[0045] The signal processing module is used to generate a high-dimensional image from the signal to be processed using an image reconstruction algorithm, and to embed a timestamp into the high-dimensional image to obtain a frame image;
[0046] The preprocessing module is used to preprocess the frame image to obtain a processed image;
[0047] The extraction module is used to extract features from the processed image to obtain extracted features, and the extracted features of consecutive frames of images constitute a contraction curve.
[0048] The acquisition module is used to acquire the respiratory cycle;
[0049] The association module is used to determine whether the breathing pattern is normal based on the contraction curve and the respiratory cycle. A normal breathing pattern is when the contraction curve rises during exhalation.
[0050] The adjustment module is used to apply current to the diaphragm and pelvic floor muscles through electrode pads if the breathing pattern is abnormal, so as to make the diaphragm and pelvic floor muscles contract normally.
[0051] A terminal device includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor loads and executes the computer program, it employs a method for adjusting the direction of pelvic floor muscle contraction.
[0052] A computer-readable storage medium storing a computer program that, when loaded and executed by a processor, employs a method for adjusting the direction of pelvic floor muscle contraction.
[0053] The beneficial effects of this invention are:
[0054] This invention utilizes ultrasound to acquire signals from the diaphragm and pelvic floor muscles. These signals are then used to generate high-dimensional images via image reconstruction algorithms. Timestamps are embedded in these high-dimensional images to obtain frame images. These frame images are preprocessed to obtain processed images. Feature extraction is performed on the processed images to obtain extracted features. The extracted features from consecutive frame images constitute a contraction curve. The respiratory cycle is acquired. Based on the contraction curve and respiratory cycle, the normality of the respiratory pattern is determined. A normal respiratory pattern is indicated by an upward curve during exhalation. If the respiratory pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles via electrode pads to normalize their contraction. This application establishes a correlation between the diaphragm, pelvic floor muscles, and respiration. The pelvic floor muscles and diaphragm are connected via the celiac fascia, forming a "respiration-pelvic floor muscle linkage axis." Their coordinated movement involves the diaphragm contracting and descending, increasing abdominal pressure, while the pelvic floor muscles simultaneously relax slightly to buffer the pressure. Conversely, the diaphragm relaxes and rises, decreasing abdominal pressure, and the pelvic floor muscles subsequently contract slightly to maintain pelvic organ stability. When abnormalities are detected, an electric current is applied to stimulate the muscles to return to normal contraction, aiding in patient rehabilitation or preventing abnormal pelvic floor muscle contraction. Attached Figure Description
[0055] Figure 1 This is a flowchart illustrating a method for adjusting the direction of pelvic floor muscle contraction according to the present invention. Detailed Implementation
[0056] A method for adjusting the direction of pelvic floor muscle contraction, such as Figure 1 As shown, the present invention includes:
[0057] S1. Ultrasound waves are emitted to the diaphragm and pelvic floor muscles through a transducer to obtain diaphragm reflection signals and pelvic floor muscle signals, and the diaphragm reflection signals and pelvic floor muscle signals are used as signals to be processed.
[0058] Specifically, the transducer is integrated into a wearable device. This wearable device (using a patch type) consists of a diaphragm patch and a pelvic floor muscle patch. Each patch contains an electrode and an ultrasound detector. The transducer in the patch-type ultrasound detection device emits ultrasound waves towards the diaphragm or pelvic floor muscles. The ultrasound waves propagate through muscles and other tissues, and are reflected, refracted, and scattered when they encounter different tissue interfaces. The transducer receives these reflected waves and converts them into electrical signals.
[0059] Specifically, it includes the launch phase and the reception phase.
[0060] 1. Transmission stage: The flexible piezoelectric element array (high-performance lead-free mKNN ceramic) in the patch receives electrical pulse signals from the driving circuit, generates mechanical vibration through the inverse piezoelectric effect, and then emits ultrasonic waves (frequency is usually 2-10MHz).
[0061] 2. Receiving stage: After ultrasound waves penetrate human tissue, they encounter interfaces with differences in acoustic impedance (such as organ boundaries or muscle layers), generating reflected echoes. These echoes act on piezoelectric elements, converting mechanical vibrations into electrical signals (microvolts) through the positive piezoelectric effect.
[0062] S2. The signal to be processed is processed by an image reconstruction algorithm to generate a high-dimensional image, and the high-dimensional image is embedded with a timestamp to obtain a frame image;
[0063] Specifically, the purpose of adding a timestamp is to synchronize with the breathing cycle over time. In this application, a two-dimensional image is generated.
[0064] S3. Preprocess the frame image to obtain the processed image;
[0065] The frame image is preprocessed to obtain the processed image, which includes:
[0066] The frame image is subjected to Gaussian filtering to obtain the filtered image. Gaussian filtering is represented as:
[0067]
[0068] Where (x, y) are pixel coordinates, the Gaussian convolution kernel is defined as g(i,j), where (i,j) are the offset coordinates of the kernel relative to the center point, the kernel size is (2k+1)×(2k+1)), W is the normalization factor, I is the frame image, and k is the kernel radius;
[0069]
[0070] Where σ is the standard deviation of the Gaussian function (controlling the smoothness of the filter, σ>0), the larger the value, the stronger the smoothing effect, k is the kernel radius, usually chosen according to σ, and W ensures that the weights of the kernel sum to 1.
[0071] This formula effectively reduces Gaussian noise and some speckle noise by weighted averaging of neighboring pixels (the weights are determined by a Gaussian function), while maintaining relatively clear image edges.
[0072] Calculate the grayscale histogram of the filtered image;
[0073] Specifically, if the gray level range of the input image G is [0, L-1], then the gray level histogram h(r) = the number of pixels whose pixel values are equal to r, where r is the gray level.
[0074] Calculate the cumulative distribution function value based on the grayscale histogram and the image size of the filtered image;
[0075]
[0076] Specifically,
[0077] Where p(r) is the cumulative distribution function value, and M and N are the image sizes.
[0078]
[0079] Where CDF(r) is the cumulative distribution function value, s is a temporary variable, and s = 1, 2, 3...r.
[0080] The processed image is obtained based on the cumulative distribution function value and the gray level range of the filtered image.
[0081] s r =round((L-1)·CDF(r))
[0082] Specifically,
[0083] Among them, s r This is the new value after mapping the grayscale level r, and round means rounding to the nearest integer.
[0084] By remapping pixel values using CDF, the dynamic range of the image is stretched, thereby enhancing contrast and making the anatomical structures of the diaphragm and pelvic floor muscles easier to identify.
[0085] S4. Extract features from the processed image to obtain extracted features. The extracted features of consecutive frames of images form a contraction curve.
[0086] The processed image undergoes feature extraction, yielding the following features:
[0087] Define gradient operators, including horizontal gradient operators and vertical gradient operators;
[0088] Specifically, in the analysis of ultrasound images of the diaphragm and pelvic floor muscles, feature extraction needs to capture both edge structures (such as the diaphragm boundary) and texture characteristics (such as muscle tissue state).
[0089] The preprocessed image is I(x,y).
[0090] Define the horizontal gradient operator G x and the vertical gradient operator G y .
[0091] In this embodiment,
[0092] Based on the gradient operator, the gradient components of each pixel in the processed image are obtained;
[0093] Specifically, the gradient components of each pixel (x, y) are calculated as follows:
[0094]
[0095] The gradient magnitude and gradient direction are calculated based on the gradient components.
[0096] Specifically, the gradient magnitude is calculated as follows:
[0097]
[0098] The gradient direction is calculated as follows:
[0099]
[0100] Based on the gradient magnitude and gradient direction of each pixel, a gradient magnitude map and a gradient direction map are constructed, and these maps are used as features for extraction.
[0101] Specifically, the gradient magnitude map G(x,y) highlights the diaphragm boundary, while the gradient direction map θ(x,y) describes the boundary orientation. After calculating the gradient magnitude map and gradient direction map, the diaphragm and pelvic floor muscles can be accurately identified.
[0102] The extracted features from consecutive frames of images constitute the contraction curve, including:
[0103] Construct a coordinate system with the y-axis from head to feet and the positive direction of the diaphragm moving towards the feet during inhalation, and the Z-axis from the body surface to the chest cavity.
[0104] Based on the extracted features of consecutive frame images, the diaphragm displacement changes are extracted;
[0105] Generate a diaphragm curve based on the diaphragm displacement changes and the coordinate system;
[0106] Similarly, a pelvic floor muscle curve is generated, which serves as the contraction curve for the diaphragm curve and the pelvic floor muscle curve.
[0107] Specifically, since the image changes continuously from frame to frame, and the extracted features are retrieved, a contraction curve can be generated in the coordinate system based on the displacement changes of the extracted features over continuous time. The specific structure is as follows:
[0108] The patch synchronously emits ultrasound waves from the same clock source, embedding a timestamp (accurate to milliseconds) in each frame to ensure the app can align the motion sequences of both images along the timeline during image reconstruction. The mobile app allows for left-right or top-bottom split-screen display; the left side shows the diaphragm ultrasound image (sagittal section along the mid-axillary line), and the right side shows the pelvic floor muscle ultrasound image (sagittal section or cross-section of the perineum). A "Synchronous Pause / Play" button is provided for easy frame-by-frame comparison of the motion directions of both images within the same respiratory cycle. Secondly, a unified coordinate system is established: with the probe placement point as the origin, the vertical direction (Y-axis, diaphragm movement towards the foot during inspiration) is the head-to-foot direction; the depth direction (Z-axis, ultrasound incidence direction) is the body surface-to-thoracic cavity direction. The pelvic floor muscle coordinate system is: with the perineum center point as the origin, the vertical direction (Y-axis, pelvic floor muscle contraction towards the head) is the head-to-tail direction; the depth direction (Z-axis) is the body surface-to-pelvic cavity direction.
[0109] S5. Obtain the respiratory cycle;
[0110] Specifically, the respiratory cycle refers to the time it takes for a person to complete one inhalation and exhalation action. By using timestamps, the changes in the diaphragm and pelvic floor muscles corresponding to a person's inhalation and exhalation actions are linked.
[0111] S6. Based on the systolic curve and respiratory cycle, determine whether the breathing pattern is normal. A normal breathing pattern is when the systolic curve rises during exhalation.
[0112] Determining whether a breathing pattern is normal based on the systolic curve and respiratory cycle includes:
[0113] The respiratory cycle includes the inhalation phase and the exhalation phase;
[0114] The contraction curves include the diaphragm curve and the pelvic floor muscle curve;
[0115] Determine whether the diaphragm curve and pelvic floor muscle curve both rise during the inhalation phase, or whether they both fall during the exhalation phase.
[0116] If both the diaphragm curve and the pelvic floor muscle curve rise during inhalation, or both fall during exhalation, then the breathing pattern is considered normal.
[0117] Otherwise, an abnormal breathing pattern is confirmed.
[0118] Specifically, to assess synergy, during the inspiratory phase: when the diaphragm curve rises (increased foot-side displacement), the pelvic floor muscle curve rises synchronously (increased head-side displacement), which is considered to be in the same direction; during the expiratory phase: when the diaphragm curve descends (returning to the resting position), the pelvic floor muscle curve descends synchronously (relaxing back to its original position), which is considered to be in the same direction; abnormal signals: if the two curves show opposite trends during inspiration / expiration (e.g., the diaphragm moves towards the foot side, and the pelvic floor muscles move towards the tail side), it suggests synergy disorder.
[0119] It can also be combined with displacement amplitude detection. Diaphragm detection is performed in the sagittal section along the midaxillary line, measuring the distance the diaphragm moves towards the foot. Normal breathing is 1-2 cm, deep breathing is 3-7 cm, abnormal breathing is <1 cm, and deep breathing is <2 cm. Pelvic floor muscle detection is performed to measure cephalic displacement: the distance the pelvic floor muscles are lifted towards the head during maximum contraction (normal ≥1.5 cm); changes in anteroposterior diameter: the angle between the puborectalis muscles decreases during contraction (normal angle is about 90°~110°, which can decrease to 60°~80° during contraction); abnormal cephalic displacement is <1.0 cm, and the anteroposterior diameter is unchanged or increased.
[0120] Abdominal breathing detection: The probe is placed at the 7th to 9th intercostal spaces along the mid-axillary line to display the thoracic and abdominal lateral movement trajectory of the diaphragm. Typical abdominal breathing on ultrasound shows the diaphragm moving downwards with inspiration, and the liver / stomach moving towards the feet with the diaphragm (a phenomenon known as "liver sliding sign"). Simultaneous observation of the abdominal wall (which can be combined with M-mode ultrasound) is also performed. During inspiration, the rectus abdominis and external oblique muscles bulge outwards, consistent with the direction of diaphragmatic movement. Abnormal breathing patterns, such as thoracic breathing, show minimal diaphragmatic movement (<1 cm), significant contraction of accessory respiratory muscles such as the intercostal muscles and sternocleidomastoid muscle (high-frequency contraction of upper chest muscles visible on ultrasound), and simultaneous immobility or inward retraction of the abdominal wall during inspiration (paradoxical movement), indicating diaphragmatic inhibition and respiratory power dependent on chest wall rise and fall.
[0121] S7. If the breathing pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles through the electrode pads to make the diaphragm and pelvic floor muscles contract normally.
[0122] If the breathing pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles through electrode pads to normalize their contraction, including:
[0123] Obtain the initial stimulus parameters;
[0124] Initial stimulation parameters include stimulation intensity, stimulation frequency, and pulse width.
[0125] Acquire real-time electrical signals of the diaphragm and pelvic floor muscles;
[0126] Acquire standard signals;
[0127] Based on real-time electrical signals and standard signals, adjustment signals are applied to the electrode pads to adjust the initial stimulation parameters of the current so that the diaphragm and pelvic floor muscles contract normally.
[0128] Specifically, if there is an abnormal breathing pattern, i.e., the diaphragm and pelvic floor muscles contract in different directions, an electric current will be applied using electrode pads for intervention, and ultrasound imaging will be used to determine whether the contraction direction has improved. Since muscle contraction is essentially a process of motor neuron excitation → muscle fiber depolarization → calcium ion release → myofibril sliding, and during depolarization, ions (Na+) inside and outside the muscle cell membrane... + K + The flow of Cl- generates weak action potentials (approximately 0.1–5 mV), which are then superimposed to form electromyography (EMG signals). These signals can be collected through surface or implanted electrodes, thus integrating an electromyography (EMG) sensor to monitor muscle electrical activity in real time, assess muscle tone and contraction force, and automatically adjust stimulation parameters based on feedback to ensure consistent muscle contraction frequency.
[0129] A system for regulating pelvic floor muscle contraction based on the normality of breathing patterns includes:
[0130] The signal conversion module is used to transmit ultrasound waves to the diaphragm and pelvic floor muscles through a transducer, acquire diaphragm reflection signals and pelvic floor muscle signals, and use the diaphragm reflection signals and pelvic floor muscle signals as signals to be processed.
[0131] The signal processing module is used to generate a high-dimensional image from the signal to be processed using an image reconstruction algorithm, and to embed a timestamp into the high-dimensional image to obtain a frame image;
[0132] The preprocessing module is used to preprocess the frame image to obtain the processed image;
[0133] The extraction module is used to extract features from the processed image to obtain extracted features. The extracted features of consecutive frames of images form a contraction curve.
[0134] The acquisition module is used to acquire the respiratory cycle;
[0135] The correlation module is used to determine whether the breathing pattern is normal based on the systolic curve and respiratory cycle. A normal breathing pattern is when the systolic curve rises during exhalation.
[0136] The adjustment module is used to apply current to the diaphragm and pelvic floor muscles through electrode pads if the breathing pattern is abnormal, so as to make the diaphragm and pelvic floor muscles contract normally.
[0137] This application also discloses a terminal device, including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor loads and executes the computer program, it employs a method for adjusting the direction of pelvic floor muscle contraction.
[0138] The terminal device can be a computer device such as a desktop computer, a laptop computer, or a cloud server. The terminal device includes, but is not limited to, a processor and a memory. For example, the terminal device may also include input / output devices, network access devices, and buses.
[0139] The processor can be a central processing unit (CPU). Of course, depending on the actual use, it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), off-the-shelf programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor, etc., and this application does not limit it in this regard.
[0140] The memory can be an internal storage unit of the terminal device, such as a hard disk or RAM of the terminal device, or an external storage device of the terminal device, such as a plug-in hard disk, smart memory card (SMC), secure digital card (SD), or flash memory card (FC) equipped on the terminal device. Furthermore, the memory can be a combination of internal storage units and external storage devices of the terminal device. The memory is used to store computer programs and other programs and data required by the terminal device. The memory can also be used to temporarily store data that has been output or will be output. This application does not limit this.
[0141] In this terminal device, a method for adjusting the direction of pelvic floor muscle contraction in the above embodiments is stored in the memory of the terminal device and loaded and executed on the processor of the terminal device for convenient use.
[0142] This application also discloses a computer-readable storage medium, which stores a computer program, wherein when the computer program is executed by a processor, it employs a pelvic floor muscle contraction direction adjustment method described in the above embodiments.
[0143] The computer program can be stored in a computer-readable medium. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or certain middleware. The computer-readable medium includes any entity or device capable of carrying computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the computer-readable medium includes, but is not limited to, the above-mentioned components.
[0144] The above-described method for adjusting the direction of pelvic floor muscle contraction is stored in the computer-readable storage medium and loaded and executed on the processor to facilitate the storage and application of the above method.
[0145] Those skilled in the art should understand that the discussion of any of the above embodiments is merely exemplary and is not intended to imply that the scope of protection of this application is limited to these examples; within the framework of this application, the technical features of the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations of different aspects of one or more embodiments of this application as described above, which are not provided in detail for the sake of brevity.
[0146] One or more embodiments in this application are intended to cover all such substitutions, modifications, and variations that fall within the broad scope of this application. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of one or more embodiments in this application should be included within the protection scope of this application.
Claims
1. A method for adjusting the direction of pelvic floor muscle contraction, characterized in that, include: Ultrasound waves are emitted to the diaphragm and pelvic floor muscles through a transducer to obtain diaphragm reflection signals and pelvic floor muscle signals, and the diaphragm reflection signals and pelvic floor muscle signals are used as signals to be processed. The signal to be processed is used to generate a high-dimensional image through an image reconstruction algorithm, and a timestamp is embedded in the high-dimensional image to obtain a frame image; The frame image is preprocessed to obtain the processed image; The processed image is subjected to feature extraction to obtain extracted features, and the extracted features of consecutive frames of images form a contraction curve; Obtain respiratory cycles; Based on the contraction curve and respiratory cycle, determine whether the breathing pattern is normal. A normal breathing pattern is when the contraction curve rises during exhalation. If the breathing pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles through the electrode pads to normalize the contraction of the diaphragm and pelvic floor muscles.
2. The method for adjusting the direction of pelvic floor muscle contraction as described in claim 1, characterized in that, The step of preprocessing the frame image to obtain the processed image includes: The frame image is subjected to Gaussian filtering to obtain the filtered image, wherein the Gaussian filtering is expressed as: Where (x, y) are pixel coordinates, the Gaussian convolution kernel is defined as g(i,j), where (i,j) are the offset coordinates of the kernel relative to the center point, the kernel size is (2k+1)×(2k+1)), W is the normalization factor, I is the frame image, and k is the kernel radius; Calculate the grayscale histogram of the filtered image; Calculate the cumulative distribution function value based on the grayscale histogram and the image size of the filtered image; The processed image is obtained based on the cumulative distribution function value and the gray level range of the filtered image.
3. The method for adjusting the direction of pelvic floor muscle contraction as described in claim 1, characterized in that, The step of extracting features from the processed image to obtain the extracted features includes: A gradient operator is set, which includes a horizontal gradient operator and a vertical gradient operator; The gradient component of each pixel in the processed image is obtained based on the gradient operator. The gradient magnitude and gradient direction are calculated based on the gradient components. Based on the gradient magnitude and gradient direction of each pixel, a gradient magnitude map and a gradient direction map are constructed, and the gradient magnitude map and gradient direction map are used as features for extraction.
4. The method for adjusting the direction of pelvic floor muscle contraction as described in claim 1, characterized in that, The extracted features of the consecutive frames of images constitute the contraction curve, including: Construct a coordinate system with the y-axis from head to feet and the positive direction of the diaphragm moving towards the feet during inhalation, and the Z-axis from the body surface to the chest cavity. Based on the extracted features of consecutive frame images, the diaphragm displacement changes are extracted; Generate a diaphragm curve based on the diaphragm displacement changes and the coordinate system; Similarly, a pelvic floor muscle curve is generated, which serves as the contraction curve for the diaphragm curve and the pelvic floor muscle curve.
5. The method for adjusting the direction of pelvic floor muscle contraction as described in claim 1, characterized in that, The step of determining whether the breathing pattern is normal based on the contraction curve and the respiratory cycle includes: The respiratory cycle includes an inspiratory phase and an expiratory phase; The contraction curves include the diaphragm curve and the pelvic floor muscle curve; Determine whether the diaphragm curve and pelvic floor muscle curve both rise during the inhalation phase, or whether the diaphragm curve and pelvic floor muscle curve both fall during the exhalation phase; If both the diaphragm curve and the pelvic floor muscle curve rise during the inhalation phase, or both the diaphragm curve and the pelvic floor muscle curve fall during the exhalation phase, then the breathing pattern is confirmed to be normal. Otherwise, an abnormal breathing pattern is confirmed.
6. The method for adjusting the direction of pelvic floor muscle contraction as described in claim 1, characterized in that, If the breathing pattern is abnormal, an electric current is applied to the diaphragm and pelvic floor muscles via electrode pads to normalize their contraction, including: Obtain the initial stimulus parameters; Acquire real-time electrical signals of the diaphragm and pelvic floor muscles; Acquire standard signals; Based on the real-time electrical signal and the standard signal, an adjustment signal is applied to the electrode pads to adjust the initial stimulation parameters of the current so that the diaphragm and pelvic floor muscles contract normally.
7. The method for adjusting the direction of pelvic floor muscle contraction as described in claim 1, characterized in that, The initial stimulation parameters include stimulation intensity, stimulation frequency, and pulse width.
8. A system for regulating pelvic floor muscle contraction based on the normality of breathing patterns, characterized in that... include: The signal conversion module is used to transmit ultrasound waves to the diaphragm and pelvic floor muscles through a transducer, acquire diaphragm reflection signals and pelvic floor muscle signals, and use the diaphragm reflection signals and pelvic floor muscle signals as signals to be processed. The signal processing module is used to generate a high-dimensional image from the signal to be processed using an image reconstruction algorithm, and to embed a timestamp into the high-dimensional image to obtain a frame image; The preprocessing module is used to preprocess the frame image to obtain a processed image; The extraction module is used to extract features from the processed image to obtain extracted features, and the extracted features of consecutive frames of images constitute a contraction curve. The acquisition module is used to acquire the respiratory cycle; The association module is used to determine whether the breathing pattern is normal based on the contraction curve and the respiratory cycle. A normal breathing pattern is when the contraction curve rises during exhalation. The adjustment module is used to apply current to the diaphragm and pelvic floor muscles through electrode pads if the breathing pattern is abnormal, so as to make the diaphragm and pelvic floor muscles contract normally.
9. A terminal device, comprising a memory and a processor, characterized in that, The memory stores a computer program that can run on a processor, and when the processor loads and executes the computer program, it employs the method described in any one of claims 1 to 7.
10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it employs the method described in any one of claims 1 to 7.