Ultrasonic positioning length marking guide wire device

Abstract

The invention relates to the technical field of medical instruments, and discloses an ultrasonic positioning length identification guide wire device which comprises a guide wire and a control module, a filling layer and a lubricating coating are arranged outside the guide wire, the lubricating coating wraps a port of the guide wire, length identifications are arranged on the two sides of the filling layer, the length identifications are scale / number / scale and number combination, and the control module is connected with the filling layer. The control module comprises an ultrasonic assembly and an ultrasonic module, the ultrasonic assembly is electrically connected with the ultrasonic module, the ultrasonic assembly comprises at least three ultrasonic sensors, the three ultrasonic sensors are uniformly arranged on the filling layer, and the ultrasonic acquisition unit is used for setting the acquisition frequencies of the three ultrasonic sensors; and the ultrasonic judgment unit determines a reflected wave signal based on sensor parameters of the three ultrasonic sensors and a tissue propagation model, and judges whether positioning deviation exists or not based on a comparison result of the reflected wave signal and a target echo signal. According to the invention, the stability of distance reading and guide wire positioning is ensured.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and more specifically, to an ultrasound-guided length marking guidewire device. Background Technology

[0002] In endoscopic diagnosis and treatment, guidewire placement is widely used in the diagnosis and treatment of diseases in multiple cavities of organs such as the digestive tract, respiratory tract, and urinary tract. Currently, guidewire placement mainly relies on the operator observing the guidewire advancement status of the endoscope and combining it with their own clinical experience to judge the approximate position of the guidewire. Because the endoscope cannot directly interpret and read the precise position and advancement distance of the guidewire in the body, it is impossible to obtain the spatial information of the guidewire in the body. The operator finds it difficult to accurately determine whether the guidewire has reached the intended lesion area. Furthermore, the lack of an effective positioning and judgment mechanism for the guidewire in the body makes it impossible to monitor the three-dimensional spatial position of the guidewire in real time and accurately. This makes it difficult for the operator to fully understand the direction of the guidewire, which not only affects the accuracy of the surgical operation but also increases the operation time and difficulty.

[0003] Therefore, it is necessary to design an ultrasonic positioning length marking guidewire device to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes an ultrasonic positioning length marking guidewire device, which aims to solve the above-mentioned problems.

[0005] This invention proposes a length marking guidewire device for ultrasonic positioning, comprising: A guidewire, wherein a filler layer and a lubricating coating are provided on the outside of the guidewire, the lubricating coating covers the port of the guidewire, the filler layer and the lubricating coating are fixedly connected, and length markings are provided on both sides of the filler layer, wherein the length markings are scales / numbers / a combination of scales and numbers; The guidewire is made of nickel-titanium alloy / stainless steel; The filler layer is made of polyurethane / polytetrafluoroethylene; The control module includes an ultrasonic component and an ultrasonic module, which are electrically connected. The ultrasonic component includes at least three ultrasonic sensors, which are evenly arranged in the filling layer. The ultrasonic module includes an ultrasonic acquisition unit and an ultrasonic judgment unit. The ultrasonic acquisition unit is used to set the acquisition frequency of the three ultrasonic sensors and determine the target echo signal based on the acquisition frequency; The ultrasound judgment unit determines the reflected wave signal based on the sensor parameters of the three ultrasound sensors and the tissue propagation model, and judges whether there is a positioning deviation based on the comparison result of the reflected wave signal and the target echo signal.

[0006] Furthermore, when setting the acquisition frequencies of the three ultrasonic sensors and determining the target echo signal based on the acquisition frequencies, the process includes: The sampling frequency is directly proportional to the height of the patient to be inserted; The ultrasonic acquisition unit determines three initial echo signals based on the acquisition frequency, performs noise reduction processing on the three initial echo signals to determine the noise-reduced echo signals, and determines the square mean of the noise-reduced echo signals as the echo signal power to obtain the noise power. The echo signal-to-noise ratio is determined based on the echo signal power and the noise power, and the target echo signal is determined based on the echo signal-to-noise ratio to determine whether to compensate the noise-reduced echo signal.

[0007] Furthermore, when determining whether to compensate the denoised echo signal to determine the target echo signal based on the echo signal-to-noise ratio, the process includes: The echo signal-to-noise ratio (SNR) and the echo SNR threshold are compared. When the echo SNR is greater than or equal to the echo SNR threshold, it is determined that no compensation is made to the denoised echo signal, and the denoised echo signal is identified as the target echo signal. When the echo signal-to-noise ratio is less than the echo signal-to-noise ratio threshold, it is determined that the denoised echo signal should be compensated, and the compensated denoised echo signal is determined as the target echo signal.

[0008] Furthermore, when compensating the noise-reduced echo signal, the following steps are included: Obtain the echo Doppler frequency of the noise-reduced echo signal and compare the echo Doppler frequency with the Doppler database; The Doppler database includes several historical echo Doppler frequencies and several historical phase compensation values, and each historical echo Doppler frequency corresponds to a historical phase compensation value. The frequency similarity between the echo Doppler frequency and each historical echo Doppler frequency is obtained, and the phase of the echo Doppler frequency is compensated based on the frequency similarity.

[0009] Furthermore, when compensating for the phase of the echo Doppler frequency based on the frequency similarity, the following steps are included: When there are historical echo Doppler frequencies in the Doppler database with a frequency similarity greater than the frequency similarity threshold, if the historical echo Doppler frequency is unique, the phase of the echo Doppler frequency is compensated by the historical phase compensation value corresponding to the historical echo Doppler frequency; if the historical echo Doppler frequencies are not unique, the phase of the echo Doppler frequency is compensated by the average of the historical phase compensation values ​​corresponding to each historical echo Doppler frequency. When there are no historical echo Doppler frequencies in the Doppler database with a frequency similarity greater than the frequency similarity threshold, the phase of the echo Doppler frequencies is compensated based on a clustering algorithm.

[0010] Furthermore, when compensating for the phase of the echo Doppler frequency based on a clustering algorithm, the following steps are included: The echo Doppler frequencies and Doppler database are used as the clustering set. The historical phase compensation value corresponding to each historical echo Doppler frequency in the clustering set is extracted. The expected number of clusters k is determined to be 2. The parameters of the Gaussian distribution are initialized. The probability of each data in the clustering set belonging to each Gaussian distribution is determined to determine the responsibility value. Based on the responsibility value, a cluster set corresponding to the echo Doppler frequency is determined, and the mean of the historical phase compensation values ​​in the cluster set is used to compensate the phase of the echo Doppler frequency.

[0011] Furthermore, when determining the reflected wave signal based on the sensor parameters of the three ultrasonic sensors and the tissue propagation model, the following steps are included: The ultrasound judgment unit constructs a model sample set from the tissue parameters of the patient to be inserted, the tissue parameters of the age group other than the patient to be inserted, and the ultrasound dataset, and divides the model sample set into a training set and a test set. The organization propagation model is determined by finding parameters and constructing a generative adversarial network (GAN) model based on a grid search, training the GAN model on the training set, and testing the trained GAN model on the test set.

[0012] Furthermore, when training the generative adversarial network model based on the training set and testing the trained generative adversarial network model based on the test set to determine the organization propagation model, the process includes: If the iteration step ratio of the currently trained generative adversarial network model is 1:1, then training is stopped, and the currently trained generative adversarial network model is determined as the organization propagation model. If the iteration step ratio of the currently trained generative adversarial network model is not 1:1, then the adjustment direction is determined based on the relationship between D and G, and training continues until the iteration step ratio of the trained generative adversarial network model is 1:1. The reflected wave signal is determined by substituting the sensor parameters into the tissue propagation model.

[0013] Furthermore, when determining the adjustment direction based on the relationship between D and G, it includes: If the discriminative power of D is greater than the generative power of G, then add a regularization term to D; If the discriminative power of D is less than the generative power of G, then increase the depth of the convolutional / fully connected layers of D.

[0014] Furthermore, when determining whether there is a positioning deviation based on the comparison results of the reflected wave signal and the target echo signal, the process includes: If the reflected wave signal is consistent with the target echo signal, then it is determined that there is no positioning deviation; If the reflected wave signal is inconsistent with the target echo signal, it is determined that there is a positioning deviation, and a manual verification is prompted.

[0015] Compared with existing technologies, the advantages of this invention are as follows: The scales, numbers, or combinations thereof on both sides of the guidewire provide an intuitive quantitative reference for length, enabling visualization of the guidewire insertion length and providing length-dimensional data support for the precision of surgical operations. The filling layer uses polyurethane or polytetrafluoroethylene, materials that combine good biocompatibility and structural stability. On the one hand, they protect the internal nickel-titanium alloy or stainless steel guidewire; on the other hand, they provide a stable mounting platform for the ultrasonic sensors. A lubricating coating wraps around the guidewire's ends, reducing frictional resistance during guidewire advancement in cavities such as the digestive and respiratory tracts, improving guidewire insertion smoothness, and reducing the risk of damage to internal tissues. At least three ultrasonic sensors are evenly arranged in the filling layer, and together with the ultrasonic acquisition and judgment units of the ultrasonic module, they construct a spatial positioning system to accurately and in real time determine whether there is any positioning deviation in the guidewire. This achieves real-time monitoring of the guidewire's spatial position within the body, allowing operators to fully grasp the guidewire's trajectory and avoid operational deviations caused by misjudgment of position. Attached Figure Description

[0016] Various other advantages and benefits will become apparent to those skilled in the art upon reading the following detailed description of preferred embodiments. The accompanying drawings are for illustrative purposes only and are not intended to limit the invention. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings: Figure 1 This is a schematic diagram of the structure of an ultrasonic positioning length marking guidewire device provided in an embodiment of the present invention; Figure 2 A cross-sectional view of the middle portion of an ultrasonic positioning length marking guidewire device provided in an embodiment of the present invention; Figure 3 A cross-sectional view of the guide wire port provided in an embodiment of the present invention; Figure 4 This is a schematic diagram of the structure of the control module provided in an embodiment of the present invention; The components include: 1. Guide wire; 2. Filler layer; 3. Lubricating coating; 4. Length marking. Detailed Implementation

[0017] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the disclosure to those skilled in the art. It should be noted that, unless otherwise specified, embodiments and features in the embodiments of the present invention can be combined with each other. The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0018] See Figure 1-4 As shown in some embodiments of this application, an ultrasonic positioning length marking guidewire device includes: a guidewire 1, with a filling layer 2 and a lubricating coating 3 disposed on the outside of the guidewire 1, the lubricating coating 3 covering the port of the guidewire 1, the filling layer 2 and the lubricating coating 3 being fixedly connected, length markings 4 being disposed on both sides of the filling layer 2, the length markings 4 being scales / numbers / a combination of scales and numbers, the guidewire 1 being made of nickel-titanium alloy / stainless steel, the filling layer 2 being made of polyurethane / polytetrafluoroethylene, and a control module, the control module including an ultrasonic component and an ultrasonic module, the ultrasonic component and the ultrasonic module being electrically connected, the ultrasonic component including at least three ultrasonic sensors, the three ultrasonic sensors being evenly arranged on the filling layer 2, the ultrasonic module including an ultrasonic acquisition unit and an ultrasonic judgment unit, the ultrasonic acquisition unit being used to set the acquisition frequency of the three ultrasonic sensors and determine the target echo signal based on the acquisition frequency, the ultrasonic judgment unit determining the reflected wave signal based on the sensor parameters of the three ultrasonic sensors and the tissue propagation model, and judging whether there is a positioning deviation based on the comparison result of the reflected wave signal and the target echo signal.

[0019] Specifically, guidewire 1 is made of nickel-titanium alloy or stainless steel. These materials combine excellent flexibility and strength. The flexibility allows guidewire 1 to conform to the natural curvature of cavities such as the digestive, respiratory, and urinary tracts, allowing it to be smoothly inserted into the body. The strength ensures that guidewire 1 is not prone to breakage during advancement, laying the foundation for subsequent diagnostic and treatment procedures. The filling layer 2, made of polyurethane or polytetrafluoroethylene, wraps around the guidewire 1. On one hand, it protects the internal guidewire 1, reducing direct friction between the guidewire 1 and internal tissues, thus reducing damage. On the other hand, the filling layer 2 provides a mounting carrier for the length marker 4 and the ultrasonic sensor, allowing the length marker 4 to be stably distributed on both sides of the filling layer 2, and enabling the ultrasonic sensor to be evenly distributed on the surface of the filling layer 2. This ensures the stability of the component positions, laying the foundation for accurate length reading and ultrasonic positioning. A lubricating coating 3 wraps around the end of guidewire 1 and is fixedly connected to the filling layer 2. Its function is to reduce the friction between the guidewire 1 port and the internal cavity tissues (such as mucosa, tube walls, etc.), making the guidewire 1 insertion smoother and reducing stimulation and damage to the cavity tissues. It also facilitates the operator's advance and adjustment of the guidewire 1. Length markers 4 are located on both sides of the filling layer 2, and can be in the form of graduations, numbers, or a combination of graduations and numbers. During operation, the operator can visually read the length of the guidewire 1 inside the body through the length markers 4, thereby roughly determining the position of the guidewire 1 within the body and helping to determine whether the guidewire 1 is close to the predetermined lesion area. This compensates for the inability of traditional endoscopes to directly read the guidewire 1 advancement distance. The control module includes an ultrasound component and an ultrasound module. The ultrasound component includes at least three ultrasound sensors evenly arranged in the filling layer 2. Multiple ultrasound sensors emit and receive target echo signals from different angles, thereby comprehensively capturing information about the internal tissues surrounding the guidewire 1, providing multi-dimensional data support for determining the three-dimensional spatial position of the guidewire 1. The ultrasound acquisition unit is used to set the acquisition frequency of the three ultrasound sensors and determine the target echo signal based on this frequency. Setting a uniform acquisition frequency ensures consistency and comparability in the operation of the ultrasonic sensors. The ultrasonic judgment unit determines the reflected wave signal based on the sensor parameters of the three ultrasonic sensors (reflecting the sensor's own performance characteristics) and the tissue propagation model (summarizing the propagation law of ultrasound in different tissues in the body). By comparing the reflected wave signal with the target echo signal, it dynamically judges whether there is a positioning deviation of guidewire 1, realizing real-time monitoring of the spatial position of guidewire 1 in the body. This allows the operator to clearly grasp the direction of guidewire 1, avoiding accidental contact with normal tissue or deviation from the lesion area. It not only solves the problem of the inability to quantify the advancement distance of traditional guidewire 1, but also makes up for the deficiency of the inability to monitor the spatial direction. The operator obtains basic advancement information through length marker 4, and then uses ultrasonic positioning to grasp the three-dimensional position and deviation of guidewire 1 in real time, comprehensively improving the accuracy, safety and efficiency of guidewire 1 placement operation.

[0020] In some embodiments of this application, when setting the acquisition frequency of three ultrasonic sensors and determining the target echo signal based on the acquisition frequency, the process includes: the acquisition frequency being proportional to the height of the patient to be inserted; the ultrasonic acquisition unit determining three initial echo signals based on the acquisition frequency; performing noise reduction processing on the three initial echo signals to determine a noise-reduced echo signal; determining the square mean of the noise-reduced echo signal as the echo signal power; acquiring the noise power; determining the echo signal-to-noise ratio based on the echo signal power and the noise power; and determining whether to compensate the noise-reduced echo signal based on the echo signal-to-noise ratio to determine the target echo signal.

[0021] In some embodiments of this application, when determining whether to compensate the denoised echo signal to determine the target echo signal based on the echo signal-to-noise ratio (SNR), the method includes: comparing the echo SNR with an echo SNR threshold; when the echo SNR is greater than or equal to the echo SNR threshold, determining that no compensation is needed for the denoised echo signal and determining the denoised echo signal as the target echo signal; when the echo SNR is less than the echo SNR threshold, determining that compensation is needed for the denoised echo signal and determining the compensated denoised echo signal as the target echo signal.

[0022] Specifically, when setting the acquisition frequencies of the three ultrasound sensors and determining the target echo signal, the acquisition frequency is first set according to the height of the patient to be inserted. Patients of different heights have varying depths and path lengths of their internal organs (such as the digestive and respiratory tracts). Since ultrasound waves propagate through tissue paths of different lengths, the appropriate frequency differs. Taller patients may have longer tissue paths, requiring a higher acquisition frequency to ensure signal propagation efficiency; conversely, shorter patients require a lower frequency. Therefore, the acquisition frequency is proportional to height to accommodate individual differences. The ultrasound acquisition unit acquires three initial echo signals through the acquisition frequency and performs noise reduction processing on the initial echo signals to filter out potential interference noise, determining a relatively pure noise-reduced echo signal. The square mean of the noise-reduced echo signal is calculated to determine the echo signal power. The noise power is determined during the period when the ultrasound sensors do not receive the initial echo signal. Specifically, the signal period can be selected during the idle time before the ultrasound sensors emit ultrasound waves or when guidewire 1 is in a uniform tissue area with no significant reflection. The signal during this period is mainly composed of various interference noises, thus obtaining the noise power. The echo signal-to-noise ratio is determined by the following formula:

[0023] Wherein, SNR represents the echo signal-to-noise ratio, P represents the echo signal power, and P0 represents the noise power. The signal power is calculated based on the squared mean of the denoised echo signal. The echo SNR is compared with a preset echo SNR threshold. If the echo SNR is greater than or equal to the echo SNR threshold, it indicates that the signal quality of the denoised echo signal meets the standard, and it is directly identified as the target echo signal. If the echo SNR is less than the echo SNR threshold, it indicates that the signal quality of the denoised echo signal does not meet the standard, and the denoised echo signal needs to be compensated to ensure the reliability of the target echo signal. This provides an accurate benchmark for the subsequent ultrasonic judgment unit to compare the reflected wave signal with the target echo signal to determine the positioning deviation.

[0024] In some embodiments of this application, when compensating for the denoised echo signal, the method includes: obtaining the echo Doppler frequency of the denoised echo signal, comparing the echo Doppler frequency with a Doppler database, wherein the Doppler database includes several historical echo Doppler frequencies and several historical phase compensation values, and each historical echo Doppler frequency corresponds to a historical phase compensation value, obtaining the frequency similarity between the echo Doppler frequency and each historical echo Doppler frequency, and compensating for the phase of the echo Doppler frequency based on the frequency similarity.

[0025] In some embodiments of this application, when compensating for the phase of echo Doppler frequencies based on frequency similarity, the method includes: when there are historical echo Doppler frequencies in the Doppler database with a frequency similarity greater than a frequency similarity threshold, if the historical echo Doppler frequency is unique, then the phase of the echo Doppler frequency is compensated by the historical phase compensation value corresponding to that historical echo Doppler frequency; if the historical echo Doppler frequencies are not unique, then the phase of the echo Doppler frequency is compensated by the average of the historical phase compensation values ​​corresponding to each historical echo Doppler frequency; when there are no historical echo Doppler frequencies in the Doppler database with a frequency similarity greater than a frequency similarity threshold, then the phase of the echo Doppler frequency is compensated based on a clustering algorithm.

[0026] Specifically, although the denoised echo signal removes some noise, the phase of its echo Doppler frequency may shift due to relative motion such as guidewire 1 advancement and tissue peristalsis, leading to signal quality distortion. The echo Doppler frequency reflects the signal characteristic changes caused by the relative motion between guidewire 1 and surrounding tissue. By comparing the echo Doppler frequency with a Doppler database, which stores several historical echo Doppler frequencies and their corresponding historical phase compensation values, each historical frequency has a unique matching phase compensation record, frequency similarity comparison can quickly match compensation experience for similar scenarios, ensuring the targetedness and consistency of the compensation. Frequency similarity can be determined based on cosine similarity and Euclidean distance. In this embodiment, the frequency similarity threshold is preferably 0.85. When there are historical echo Doppler frequencies in the Doppler database with a frequency similarity exceeding the frequency similarity threshold, if there is only one historical echo Doppler frequency that meets the condition, then its corresponding historical phase compensation value can be directly used to compensate the phase of the current echo Doppler frequency. If there are multiple historical echo Doppler frequencies that meet the condition, then the average of the historical phase compensation values ​​corresponding to these historical echo Doppler frequencies is taken as the compensation basis. When there are no historical frequencies in the Doppler database with a frequency similarity exceeding the frequency similarity threshold, then a clustering algorithm is used to classify the echo Doppler frequencies with data that have similar characteristics to the data in the Doppler database. Based on the common characteristics of the data of the same type, a compensation value is generated to compensate the phase. By matching the data in the Doppler database and performing phase compensation, historical compensation schemes can be quickly reused, improving compensation efficiency and accuracy, reducing signal distortion caused by phase shift, and further improving the accuracy of guidewire 1 positioning and the safety of surgical operation.

[0027] In some embodiments of this application, when compensating for the phase of echo Doppler frequencies based on a clustering algorithm, the following steps are included: taking the echo Doppler frequencies and the Doppler database as a set to be clustered, extracting the historical phase compensation value corresponding to each historical echo Doppler frequency in the set to be clustered, determining the expected number of clusters k as 2, initializing the parameters of the Gaussian distribution, determining the probability that each data in the set to be clustered belongs to each Gaussian distribution to determine the responsibility value, determining the cluster set corresponding to the echo Doppler frequency based on the responsibility value, and compensating for the phase of the echo Doppler frequencies using the mean of the historical phase compensation values ​​in the cluster set.

[0028] Specifically, by analyzing the Doppler database using clustering algorithms, even in the absence of directly similar historical data, the cluster set most closely related to the current surgical conditions can still be found based on data feature associations. This improves the accuracy of phase compensation for echo Doppler frequencies, thereby maintaining the stability and efficiency of the positioning process, enhancing the overall automation level and reliability. The average of historical phase compensation values ​​in the cluster set is used to compensate for the phase of the echo Doppler frequencies, balancing individual differences between data, reducing the impact of single data biases, and ensuring the reliability of the compensation results.

[0029] In some embodiments of this application, when determining the reflected wave signal based on the sensor parameters of three ultrasonic sensors and the tissue propagation model, the process includes: the ultrasound judgment unit constructing a model sample set from the tissue parameters of the patient to be inserted, the tissue parameters of the age group of the non-patient to be inserted, and the ultrasound dataset, dividing the model sample set into a training set and a test set, searching for and establishing parameters based on grid search and constructing a generative adversarial network model, training the generative adversarial network model based on the training set, and testing the trained generative adversarial network model based on the test set to determine the tissue propagation model.

[0030] Specifically, the tissue parameters of the patients to be inserted include tissue density, tissue elasticity (which determines the intensity of ultrasound reflection), and tissue thickness (such as the thickness of the esophageal and tracheal walls) of cavity organs (such as the esophagus / intestine in the digestive tract, the trachea / bronchus in the respiratory tract, and the ureter / bladder in the urinary tract). The tissue parameters of non-patients of different age groups are consistent with those of the patients to be inserted in terms of type and dimension. The core purpose is to provide a reference for tissue characteristics of different age groups to reduce the interference of individual differences on the model, thereby taking into account both individual specificity and group commonality. The ultrasound dataset includes ultrasound emission intensity, ultrasound propagation time (corresponding to propagation path length) in different tissues (such as normal mucosa, muscle layer, and adipose tissue), and the degree of energy attenuation during propagation (directly related to tissue density and thickness). Integrating these three types of data into the model sample set ensures the generalization ability of the model. The model sample set is divided into a training set and a test set, typically in a 4:1 ratio. The training set is used for model learning, while the test set is used to verify the model's performance. Grid search searches for the optimal setup parameters (i.e., the model's configuration information) in the parameter space. Based on these setup parameters, a generative adversarial network (GAN) model is constructed. GAN models excel at capturing the mapping relationships between complex data and are suitable for simulating the dynamic process of ultrasound interacting with different tissues. The GAN model is trained using the training set to learn the propagation laws of ultrasound under different tissue parameters. The test set is then used to verify the output performance of the trained model. Through verification and adjustment, the tissue propagation model is finally determined, further improving the accuracy of guidewire 1 positioning.

[0031] In some embodiments of this application, when training a generative adversarial network (GAN) model based on a training set and testing the trained GAN model based on a test set to determine the organization propagation model, the process includes: if the iteration step ratio of the currently trained GAN model is 1:1, then training is stopped and the currently trained GAN model is determined as the organization propagation model; if the iteration step ratio of the currently trained GAN model is not 1:1, then the adjustment direction is determined based on the relationship between D and G, and training continues until the iteration step ratio of the trained GAN model is 1:1, and the sensor parameters are substituted into the organization propagation model to determine the reflected wave signal.

[0032] In some embodiments of this application, when determining the adjustment direction based on the relationship between D and G, the following steps are included: if the discriminative ability of D is greater than the generative ability of G, then a regularization term is added to D; if the discriminative ability of D is less than the generative ability of G, then the depth of the convolutional layer / fully connected layer of D is increased.

[0033] Specifically, when training a generative adversarial network (GAN) model based on a training set, the GAN model consists of a generator (G) and a discriminator (D). These two components learn the propagation patterns of ultrasound waves in tissues through adversarial game. During training, the iteration step ratio reflects the overall performance level of the model. If the current iteration step ratio is 1:1, the simulated data generated by G closely approximates the ultrasound propagation characteristics in real tissues, and D can objectively determine the authenticity of the data. The model can accurately capture the tissue propagation patterns and has reached the expected training level. At this point, training can be stopped, and the currently trained GAN model can be identified as the tissue propagation model. If the iteration step ratio is not 1:1, it indicates that the capabilities of the two components are not balanced. If D is too strong, it will easily identify the simulated data generated by G, causing G to be unable to effectively learn the real propagation patterns. If the propagation pattern (G) is too strong, the generated simulated data may "fool" the model (D), causing the model to learn patterns that deviate from reality. Therefore, the model needs to be adjusted based on the relationship between the capabilities of D and G. During adjustment, if D's discriminative ability (the ability to distinguish between real data and simulated data generated by G) is stronger than G's generative ability (the ability to generate ultrasound propagation data that closely resembles reality), a regularization term is added to D to limit its overfitting of the training data and weaken its discriminative ability. If D's discriminative ability is weaker than G's generative ability, the depth of D's convolutional or fully connected layers is increased to enhance its ability to extract and discriminate data features. This process of repeated training and adjustment continues until the iteration ratio reaches 1:1, avoiding the risk of model failure due to one side being too strong, thus improving the stability and efficiency of model training. This allows the model to determine the reflected wave signal based on the tissue propagation model, ensuring the reliability of guidewire 1 positioning.

[0034] In some embodiments of this application, when determining whether there is a positioning deviation based on the comparison results of the reflected wave signal and the target echo signal, the method includes: if the reflected wave signal is consistent with the target echo signal, it is determined that there is no positioning deviation; if the reflected wave signal is inconsistent with the target echo signal, it is determined that there is a positioning deviation, and a reminder is given to perform manual verification.

[0035] Specifically, the target echo signal is the real-time feedback reflecting the actual status of guidewire 1, while the reflected wave signal is a reference optimized through multiple stages. When judging the positioning deviation, the target echo signal is used as the benchmark. This signal is an ultrasonic signal reflecting the actual position on guidewire 1 after noise reduction and compensation processing. The reflected wave signal output by the tissue propagation model reflects the ultrasonic signal of the expected position of guidewire 1. The comparison between the two can directly correlate the expected and actual positions of guidewire 1. If the characteristics of the two match perfectly, it means that the actual position of guidewire 1 is consistent with the expected position, and it is determined that there is no positioning deviation. If the characteristics of the two are different, such as phase and amplitude not coinciding, it means that the actual position of guidewire 1 deviates from the expectation, and it is determined that there is a positioning deviation. At the same time, the reminder mechanism is triggered to prompt the operator to perform manual verification, thereby realizing the rapid judgment of positioning deviation and forming a dual guarantee of comparative judgment and manual verification, ensuring the accuracy and reliability of guidewire 1 positioning and distance reading.

[0036] In summary, the beneficial effects of this invention are as follows: the scales, numbers, or combinations thereof on both sides of the guidewire provide an intuitive quantitative reference for length, enabling visualization of the guidewire insertion length and providing length-dimensional data support for the precision of surgical operations. The filling layer uses polyurethane or polytetrafluoroethylene, materials that combine good biocompatibility and structural stability. On the one hand, they protect the internal nickel-titanium alloy or stainless steel guidewire; on the other hand, they provide a stable mounting carrier for the ultrasonic sensors. The lubricating coating wrapped around the guidewire's ends reduces frictional resistance during guidewire advancement in cavities such as the digestive and respiratory tracts, improving the smoothness of guidewire insertion and reducing the risk of damage to internal tissues. At least three ultrasonic sensors are evenly arranged in the filling layer, and together with the ultrasonic acquisition and judgment units of the ultrasonic module, they construct a spatial positioning system to accurately and in real time determine whether there is any positioning deviation of the guidewire. This achieves real-time monitoring of the guidewire's spatial position within the body, allowing operators to fully grasp the guidewire's trajectory and avoid operational deviations caused by misjudgment of position.

[0037] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program goods. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program goods embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0038] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0039] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0040] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0041] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A length-marking guidewire device for ultrasonic positioning, characterized in that, include: A guidewire, wherein a filler layer and a lubricating coating are provided on the outside of the guidewire, the lubricating coating covers the port of the guidewire, the filler layer and the lubricating coating are fixedly connected, and length markings are provided on both sides of the filler layer, wherein the length markings are scales / numbers / a combination of scales and numbers; The guidewire is made of nickel-titanium alloy / stainless steel; The filler layer is made of polyurethane / polytetrafluoroethylene; The control module includes an ultrasonic component and an ultrasonic module, which are electrically connected. The ultrasonic component includes at least three ultrasonic sensors, which are evenly arranged in the filling layer. The ultrasonic module includes an ultrasonic acquisition unit and an ultrasonic judgment unit. The ultrasonic acquisition unit is used to set the acquisition frequency of the three ultrasonic sensors and determine the target echo signal based on the acquisition frequency; The ultrasound judgment unit determines the reflected wave signal based on the sensor parameters of the three ultrasound sensors and the tissue propagation model, and judges whether there is a positioning deviation based on the comparison result of the reflected wave signal and the target echo signal.

2. The ultrasonic positioning length marking guidewire device according to claim 1, characterized in that, When setting the acquisition frequencies of the three ultrasonic sensors and determining the target echo signal based on the acquisition frequencies, the process includes: The sampling frequency is directly proportional to the height of the patient to be inserted; The ultrasonic acquisition unit determines three initial echo signals based on the acquisition frequency, performs noise reduction processing on the three initial echo signals to determine the noise-reduced echo signals, and determines the square mean of the noise-reduced echo signals as the echo signal power to obtain the noise power. The echo signal-to-noise ratio is determined based on the echo signal power and the noise power, and the target echo signal is determined based on the echo signal-to-noise ratio to determine whether to compensate the noise-reduced echo signal.

3. The ultrasonic positioning length marking guidewire device according to claim 2, characterized in that, When determining whether to compensate the denoised echo signal to determine the target echo signal based on the echo signal-to-noise ratio, the process includes: The echo signal-to-noise ratio (SNR) and the echo SNR threshold are compared. When the echo SNR is greater than or equal to the echo SNR threshold, it is determined that no compensation is made to the denoised echo signal, and the denoised echo signal is identified as the target echo signal. When the echo signal-to-noise ratio is less than the echo signal-to-noise ratio threshold, it is determined that the denoised echo signal should be compensated, and the compensated denoised echo signal is determined as the target echo signal.

4. The ultrasonic positioning length marking guidewire device according to claim 3, characterized in that, Compensating the noise-reduced echo signal includes: Obtain the echo Doppler frequency of the noise-reduced echo signal and compare the echo Doppler frequency with the Doppler database; The Doppler database includes several historical echo Doppler frequencies and several historical phase compensation values, and each historical echo Doppler frequency corresponds to a historical phase compensation value. The frequency similarity between the echo Doppler frequency and each historical echo Doppler frequency is obtained, and the phase of the echo Doppler frequency is compensated based on the frequency similarity.

5. The ultrasonic positioning length marking guidewire device according to claim 4, characterized in that, When compensating for the phase of the echo Doppler frequency based on the frequency similarity, the following steps are included: When there are historical echo Doppler frequencies in the Doppler database with a frequency similarity greater than the frequency similarity threshold, if the historical echo Doppler frequency is unique, the phase of the echo Doppler frequency is compensated by the historical phase compensation value corresponding to the historical echo Doppler frequency; if the historical echo Doppler frequencies are not unique, the phase of the echo Doppler frequency is compensated by the average of the historical phase compensation values ​​corresponding to each historical echo Doppler frequency. When there are no historical echo Doppler frequencies in the Doppler database with a frequency similarity greater than the frequency similarity threshold, the phase of the echo Doppler frequencies is compensated based on a clustering algorithm.

6. The ultrasonic positioning length marking guidewire device according to claim 5, characterized in that, When compensating for the phase of the echo Doppler frequency based on a clustering algorithm, the following steps are included: The echo Doppler frequencies and Doppler database are used as the clustering set. The historical phase compensation value corresponding to each historical echo Doppler frequency in the clustering set is extracted. The expected number of clusters k is determined to be 2. The parameters of the Gaussian distribution are initialized. The probability of each data in the clustering set belonging to each Gaussian distribution is determined to determine the responsibility value. Based on the responsibility value, a cluster set corresponding to the echo Doppler frequency is determined, and the mean of the historical phase compensation values ​​in the cluster set is used to compensate the phase of the echo Doppler frequency.

7. The ultrasonic positioning length marking guidewire device according to claim 6, characterized in that, When determining the reflected wave signal based on the sensor parameters of the three ultrasonic sensors and the tissue propagation model, the following steps are included: The ultrasound judgment unit constructs a model sample set from the tissue parameters of the patient to be inserted, the tissue parameters of the age group other than the patient to be inserted, and the ultrasound dataset, and divides the model sample set into a training set and a test set. The organization propagation model is determined by finding parameters and constructing a generative adversarial network (GAN) model based on a grid search, training the GAN model on the training set, and testing the trained GAN model on the test set.

8. The ultrasonic positioning length marking guidewire device according to claim 7, characterized in that, When training the generative adversarial network model based on the training set and testing the trained generative adversarial network model based on the test set to determine the organization propagation model, the process includes: If the iteration step ratio of the currently trained generative adversarial network model is 1:1, then training is stopped, and the currently trained generative adversarial network model is determined as the organization propagation model. If the iteration step ratio of the currently trained generative adversarial network model is not 1:1, then the adjustment direction is determined based on the relationship between D and G, and training continues until the iteration step ratio of the trained generative adversarial network model is 1:

1. The reflected wave signal is determined by substituting the sensor parameters into the tissue propagation model.

9. The ultrasonic positioning length marking guidewire device according to claim 8, characterized in that, When determining the adjustment direction based on the relationship between D and G, the following is included: If the discriminative power of D is greater than the generative power of G, then add a regularization term to D; If the discriminative power of D is less than the generative power of G, then increase the depth of the convolutional / fully connected layers of D.

10. The ultrasonic positioning length marking guidewire device according to claim 9, characterized in that, When determining whether there is a positioning error based on the comparison results of the reflected wave signal and the target echo signal, the following steps are included: If the reflected wave signal is consistent with the target echo signal, then it is determined that there is no positioning deviation; If the reflected wave signal is inconsistent with the target echo signal, it is determined that there is a positioning deviation, and a manual verification is prompted.

Images