A PICC catheterization ultrasound puncture positioning system

Abstract

The present invention discloses a PICC catheterization ultrasonic puncture positioning system, belonging to the technical field of medical devices. A PICC catheterization ultrasonic puncture positioning system includes a data collection module, an identification model, and a positioning module. The present invention solves the problem that the prior art may be affected by factors such as environmental light and spatial layout, affecting its accuracy and practicability. The present invention uses Mel Frequency Cepstral Coefficients for PICC catheterization positioning, which can extract more accurate acoustic wave features, effectively identify and locate the acoustic wave signals of PICC catheterization, thereby improving the positioning accuracy, effectively reducing the interference of background noise on PICC catheterization positioning, improving the accuracy of positioning, ensuring the smooth delivery of drugs, improving the therapeutic effect of drugs, avoiding damage to surrounding tissues, reducing the occurrence of complications such as phlebitis and infection, and protecting the patient's peripheral veins from being corroded by chemotherapy drugs.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and particularly to a PICC catheterization ultrasonic puncture positioning system. Background Technique

[0002] PICC (Peripherally Inserted Central Venous Catheters) is a method of inserting a catheter through a peripheral arm vein directly to the large vein near the heart, avoiding direct contact between chemotherapy drugs and arm veins. Coupled with the very fast blood flow rate in the large vein, it can quickly dilute chemotherapy drugs, prevent drug irritation to blood vessels, so it can effectively protect the upper limb veins, reduce the occurrence of phlebitis, relieve the pain of patients, and improve the quality of life of patients.

[0003] The Chinese patent with the publication number CN118845214A discloses a method for measuring the length of PICC catheterization and tip positioning based on mixed reality technology. By combining the three-dimensional vascular model of the patient with multiple control models in the database, the length of PICC catheterization can be accurately measured and corrected, thereby improving the accuracy and safety of catheterization. Considering individual data such as the patient's arm circumference, body fat percentage, and vascular elasticity, the length of PICC catheterization is more in line with individual physiological characteristics, improving the treatment effect. Using mixed reality technology, the catheterization position can be obtained and adjusted in real time, avoiding errors that may occur in traditional methods. Precise catheterization length and tip positioning reduce complications that may occur during PICC catheterization. The personalized and precise catheterization method reduces the intrusion on patients, improves the comfort and satisfaction of patients, and simplifies the operation process of medical staff and improves work efficiency through automated data processing and model matching.

[0004] In the actual use process of the above patent, mixed reality technology is used to determine the position of PICC catheterization. However, the use of mixed reality technology may be affected by factors such as environmental light and spatial layout, which may affect its accuracy and practicality; therefore, it does not meet the existing requirements, and for this reason, we propose a PICC catheterization ultrasonic puncture positioning system. Summary of the Invention

[0005] The object of the present invention is to provide a PICC catheterization ultrasonic puncture positioning system. Using Mel Frequency Cepstral Coefficients for PICC catheterization positioning can extract more accurate acoustic wave features, effectively identify and locate the acoustic wave signals of PICC catheterization, thereby improving the positioning accuracy. When processing audio signals, it can effectively reduce the interference of background noise on PICC catheterization positioning, improve the accuracy of positioning, and maintain a high positioning accuracy under different environments and conditions. Whether in a noisy environment or a quiet environment, Mel Frequency Cepstral Coefficients can effectively extract the acoustic wave features of PICC catheterization. By positioning the PICC catheter, it can ensure the smooth delivery of drugs, improve the therapeutic effect of drugs. Especially for patients who need long-term infusion or chemotherapy, it can avoid damage to surrounding tissues, reduce the occurrence of complications such as phlebitis and infection, protect the peripheral veins of patients from being corroded by chemotherapy drugs, and solve the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions: A PICC catheterization ultrasonic puncture positioning system, comprising:

[0007] A data collection module, configured to collect the position where the PICC catheter enters and the acoustic wave signals generated during the entry process of the PICC catheter by using an implantable sensor, process the acoustic wave signals to obtain a two-dimensional matrix of Mel Frequency Cepstral Coefficients, and save the two-dimensional matrix in an image format;

[0008] An identification model, configured to establish an acoustic wave signal identification neural network model, and train and optimize the acoustic wave signal identification neural network model;

[0009] A positioning module, configured to extract the fusion features at different scales and different time points in the Mel Frequency Cepstral Coefficient map, and analyze the fusion features by using the acoustic wave signal identification neural network model to obtain the position information of the PICC catheterization.

[0010] Preferably, the data collection module includes:

[0011] An implantable sensor, disposed inside the PICC catheter, for acquiring the position where the PICC catheter enters and the acoustic wave signals generated during the entry process of the PICC catheter;

[0012] A processing module, configured to process the acquired acoustic wave signals, extract the acoustic wave signal features, obtain a two-dimensional matrix of Mel Frequency Cepstral Coefficients, and save the two-dimensional matrix in an image format.

[0013] Preferably, the processing module includes:

[0014] A feature extraction module, which is used to perform filtering, pre-emphasis, framing, and window function processing on the acquired acoustic wave signals, and extract acoustic wave signal features from the converted acoustic wave signals to obtain a two-dimensional matrix of Mel-frequency cepstral coefficients;

[0015] A picture conversion module, which is used to save the two-dimensional matrix of Mel-frequency cepstral coefficients in an image format, where the rows represent the number of Mel filters and the columns represent the time frames.

[0016] Preferably, the processing module specifically includes:

[0017] Perform pre-emphasis processing using a first-order high-pass filter, frame the leaked acoustic wave signals after pre-emphasis processing, and window each frame by multiplying it by a window function;

[0018] Perform a fast Fourier transform on each framed and windowed signal to obtain the spectrum of each frame, convert the actual frequency length to the Mel-frequency length, configure a triangular filter bank, and calculate the output after filtering the signal amplitude spectrum by each triangular filter;

[0019] Perform a logarithmic operation on the outputs of all filters, and further perform a discrete cosine transform to obtain a two-dimensional matrix of Mel-frequency cepstral coefficients, and save the two-dimensional matrix of Mel-frequency cepstral coefficients in an image format.

[0020] Preferably, the recognition module includes:

[0021] A model construction module, which is used to establish an acoustic wave signal recognition neural network model using the deep learning algorithm of a neural network, and divide the acoustic wave signal features into a training set and a validation set;

[0022] A model training module, which is used to train the acoustic wave signal recognition neural network model using the training set, and adjust the hyperparameters of the acoustic wave signal recognition neural network model through the backpropagation algorithm;

[0023] A model evaluation module, which is used to evaluate the performance of the acoustic wave signal recognition neural network model using the validation set, adjust the parameters of the acoustic wave signal recognition neural network model according to the evaluation results, and optimize the performance of the acoustic wave signal recognition neural network model.

[0024] Preferably, the model construction module specifically includes:

[0025] Establish an acoustic wave signal recognition neural network model using the deep learning algorithm of a neural network. The neural network model consists of an input layer, a hidden layer, and an output layer;

[0026] The dataset required by the input layer is sourced from the time-domain signals and time-frequency spectrum signals of measured acoustic waves under different working conditions, and is divided into a training set and a validation set in an appropriate proportion;

[0027] The hidden layer is responsible for the extraction and learning of acoustic wave features, and includes a convolutional layer, a feature extraction and sampling layer, a pooling layer, and a fully connected layer;

[0028] The output layer is responsible for exporting the acceleration curve recognized as the train acoustic wave and using it as the recognition result;

[0029] Preferably, the positioning module includes:

[0030] A feature fusion module for extracting fusion features at different scales and different time points in the mel-frequency cepstrum coefficient map;

[0031] A position determination module for inputting the extracted fusion features into the acoustic wave signal recognition neural network model to analyze the fusion features, and outputting the position information of PICC catheterization according to the analysis results;

[0032] A real-time monitoring module for real-time monitoring of the hemodynamic parameters in the patient's body, and giving corresponding warnings when the hemodynamic parameters in the patient's body are abnormal.

[0033] Preferably, the extraction of the fusion features of the mel-frequency cepstrum coefficient map specifically includes

[0034] Concatenating several mel-frequency cepstrum coefficient feature vectors of different scales into a high-dimensional vector and inputting it into a compressed delay network;

[0035] Taking the output of the compressed delay network as the acoustic wave feature and concatenating it with several mel-frequency cepstrum coefficient feature vectors at different time points to obtain a mixed feature;

[0036] Processing the mixed feature using a convolutional neural network, and learning the mixed feature through the convolutional layer to fuse several mel-frequency cepstrum coefficient features at different scales and different time points to obtain the fusion feature of the mel-frequency cepstrum coefficient map.

[0037] Preferably, the PICC catheterization ultrasonic puncture positioning system further includes:

[0038] A model construction module for constructing a position marking model based on the position information of the PICC catheter and the pre-configured human body model of the patient;

[0039] The data collection module further includes:

[0040] A signal receiving module for receiving the acoustic wave signal of the implantable sensor;

[0041] Among them, the signal receiving module is configured as at least two ultrasonic receivers arranged at different positions; a positioning module is configured beside the ultrasonic receivers, and the ultrasonic receivers are respectively configured at the end of a manipulator;

[0042] When constructing the position marking model, the model construction module identifies the ultrasonic receiver into the position marking model according to the positioning module;

[0043] The controller of the manipulator performs the following operations:

[0044] Track the position of the end of the PICC catheter in the position marking model and generate the position sequence of the end of the PICC catheter in the human body;

[0045] Determine the prediction sequence according to the position sequence and the pre-configured position prediction library;

[0046] Determine the deployment area of the receiver corresponding to each predicted position in the prediction sequence according to the preset deployment area library;

[0047] Take the center point of the intersection area of the deployment areas corresponding to each predicted position as the target position of the end of the manipulator to control the movement of the manipulator.

[0048] Preferably, the PICC catheterization ultrasonic puncture positioning system further includes: a risk assessment module for performing real-time assessment on the operation risk of the PICC catheter and outputting;

[0049] Among them, the risk assessment module performs the following operations:

[0050] Obtain the position relationship between the implementer and the patient and call the corresponding personnel model according to the current action of the implementer;

[0051] Construct a simulation scenario based on the position marking model, the position relationship and the personnel model;

[0052] Track the actions of the implementer, determine the risk parts and mark them on the personnel model in the simulation scenario;

[0053] Mark the movement trajectory of the manipulator in the simulation scenario and calculate the first risk value according to the position relationship between each trajectory point and the risk part; The calculation formula of the first risk value is as follows:

[0054]

[0055] In the formula, represents the first risk value; represents the th trajectory point and the th sampling point on the risk part distance value; represents the th trajectory point and the th sampling point on the risk part corresponding preset risk coefficient;

[0056] Evaluate the moving speed of the end of the PICC catheter and the position of the prediction sequence to obtain a second risk value. The calculation formula of the second risk value is as follows:

[0057]

[0058] In the formula, represents the second risk value; represents the risk value of the th prediction position; represents the preset weight coefficient of the th prediction position; represents the moving speed of the end of the PICC catheter; is the preset risk conversion coefficient corresponding to the speed; is the configured standard speed;

[0059] Output the first risk value and the second risk value.

[0060] Compared with the prior art, the beneficial effects of the present invention are:

[0061] The present invention uses Mel Frequency Cepstral Coefficients for PICC catheter placement positioning, which can extract more accurate acoustic wave features, effectively identify and locate the acoustic wave signals of PICC catheter placement, thereby improving the positioning accuracy. When processing audio signals, it can effectively reduce the interference of background noise on PICC catheter placement positioning, improve the positioning accuracy, and maintain a high positioning accuracy under different environments and conditions. Whether in a noisy environment or a quiet environment, Mel Frequency Cepstral Coefficients can effectively extract the acoustic wave features of PICC catheter placement. By positioning the PICC catheter, it can ensure the smooth delivery of drugs, improve the therapeutic effect of drugs, especially for patients who need long-term infusion or chemotherapy, it can avoid damage to surrounding tissues, reduce the occurrence of complications such as phlebitis and infection, and protect the patient's peripheral veins from being corroded by chemotherapy drugs. Brief Description of the Drawings

[0062] Figure 1 is a schematic diagram of a PICC catheter placement ultrasound puncture positioning system of the present invention;

[0063] Figure 2 is a schematic diagram of a method of a PICC catheter placement ultrasound puncture positioning system of the present invention. Detailed Embodiments

[0064] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0065] In order to solve the problem that in the actual use process of existing patents, mixed reality technology is used to determine the position of PICC catheterization, but the use of mixed reality technology may be affected by factors such as environmental light and spatial layout, which may affect its accuracy and practicability. Please refer to Figure 1 - Figure 2 this embodiment provides the following technical solutions

[0066] A PICC catheterization ultrasonic puncture positioning system, comprising:

[0067] A data collection module, configured to collect the position where the PICC catheter enters and the acoustic wave signals generated during the entry of the PICC catheter by using an implantable sensor, process the acoustic wave signals to obtain a two-dimensional matrix of mel-frequency cepstral coefficients, and save the two-dimensional matrix in an image format;

[0068] An identification model, configured to establish an acoustic wave signal identification neural network model, and train and optimize the acoustic wave signal identification neural network model;

[0069] A positioning module, configured to extract the fusion features at different scales and different time points in the mel-frequency cepstral coefficient map, and analyze the fusion features by using the acoustic wave signal identification neural network model to obtain the position information of the PICC catheterization.

[0070] The data collection module includes:

[0071] An implantable sensor, disposed in the PICC catheter, for obtaining the position where the PICC catheter enters and the acoustic wave signals generated during the entry of the PICC catheter;

[0072] A processing module, configured to process the obtained acoustic wave signals, extract the acoustic wave signal features, obtain a two-dimensional matrix of mel-frequency cepstral coefficients, save the two-dimensional matrix in an image format, capture key features and improve the analysis accuracy. When processing audio signals, the signals will be preprocessed, including operations such as windowing, denoising, and smoothing, to remove interference factors such as noise and burst sounds, which can effectively reduce the interference of background noise on PICC catheterization positioning and improve the positioning accuracy. It can maintain a high positioning accuracy in different environments and conditions. Whether in a noisy environment or a quiet environment, the mel-frequency cepstral coefficients can effectively extract the acoustic wave features of the PICC catheter, so as to achieve accurate positioning.

[0073] A processing module, including:

[0074] A feature extraction module, which is used to filter, pre-emphasize, frame, and window the acquired acoustic signal, and extract the acoustic signal features from the transformed acoustic signal to obtain a two-dimensional matrix of Mel-frequency cepstral coefficients;

[0075] A picture conversion module, which is used to save the two-dimensional matrix of Mel-frequency cepstral coefficients in an image format, where the rows represent the number of Mel filters and the columns represent the time frames. This matrix can be directly regarded as a grayscale image, and the value of each pixel corresponds to an element value in the Mel spectrogram. Therefore, by simply saving the matrix data of the Mel spectrogram in an image format, a picture representing the Mel-frequency cepstral coefficients can be obtained. Converting the Mel-frequency cepstral coefficients into an image makes the features more intuitive, facilitating human understanding and analysis. The features in image form can be more easily visualized, thus helping researchers better understand the features of the acoustic signal. After converting the Mel-frequency cepstral coefficients into an image, the computational efficiency is relatively high, which can reduce the computational cost, speed up the training and inference speed of the model, and improve the processing efficiency.

[0076] The processing module specifically includes:

[0077] Perform pre-emphasis processing using a first-order high-pass filter, frame the leaked acoustic signal after pre-emphasis processing, and window each frame by multiplying it with a window function;

[0078] Perform a fast Fourier transform on each frame of the windowed signal after framing to obtain the spectrum of each frame, convert the actual frequency length to the Mel frequency length, configure a triangular filter bank, and calculate the output of each triangular filter after filtering the signal amplitude spectrum;

[0079] Perform a logarithmic operation on the outputs of all filters and further perform a discrete cosine transform to obtain a two-dimensional matrix of Mel-frequency cepstral coefficients, and save the two-dimensional matrix of Mel-frequency cepstral coefficients in an image format.

[0080] By filtering, pre-emphasizing, framing, and windowing the acquired acoustic signal, the clarity and quality of the signal are improved. The filter can effectively remove high-frequency or low-frequency noise in the signal, thereby improving the clarity and quality of the signal, which can help extract and analyze the features of the acoustic signal.

[0081] An identification module, including:

[0082] A model construction module, which is used to establish an acoustic signal recognition neural network model using the deep learning algorithm of the neural network and divide the acoustic signal features into a training set and a validation set;

[0083] A model training module is used to train the acoustic signal recognition neural network model using a training set, and adjust the hyperparameters of the acoustic signal recognition neural network model through a back propagation algorithm;

[0084] The model evaluation module is used to evaluate the performance of the acoustic signal recognition neural network model using the validation set, adjust the parameters of the acoustic signal recognition neural network model according to the evaluation results, and optimize the performance of the acoustic signal recognition neural network model.

[0085] Model building modules, including:

[0086] Use the deep learning algorithm of neural network to establish a neural network model for acoustic signal recognition. The neural network model consists of an input layer, a hidden layer, and an output layer.

[0087] The data set required by the input layer is derived from the time domain signals and time-frequency spectrum signals of the measured sound waves under different working conditions, and is divided into training sets and validation sets in appropriate proportions;

[0088] The hidden layer is responsible for extracting and learning the sound wave features, including the convolution layer, feature extraction sampling layer, pooling layer and fully connected layer;

[0089] The output layer is responsible for exporting the acceleration curve identified as the train sound wave as the recognition result;

[0090] Positioning module, including:

[0091] The feature fusion module is used to extract fusion features of different scales and different time points in the Mel frequency cepstral coefficient map, and use the Mel frequency cepstral coefficient to locate the PICC catheter. By converting the audio signal into a set of feature vectors, it can better simulate the characteristics of the human auditory system, thereby extracting more accurate sound wave features, so that the Mel frequency cepstral coefficient has higher robustness when processing sound wave signals, and can effectively identify and locate the sound wave signals of the PICC catheter, thereby improving the positioning accuracy;

[0092] The position determination module is used to input the extracted fusion features into the acoustic signal recognition neural network model to analyze the fusion features, and output the position information of the PICC catheter according to the analysis results. By positioning the PICC catheter, it can ensure the smooth delivery of drugs and improve the therapeutic effect of drugs, especially for patients who need long-term infusion or chemotherapy, it can avoid damage to surrounding tissues, reduce the occurrence of complications such as phlebitis and infection, and protect the patient's peripheral veins from corrosion by chemotherapy drugs;

[0093] The real-time monitoring module is used to monitor the patient's blood flow dynamic parameters in real time. When the patient's blood flow dynamic parameters are abnormal, corresponding warnings are issued to achieve continuous monitoring and management of the patient's condition.

[0094] Extract the fusion features of the Mel-frequency cepstral coefficient map, specifically including

[0095] Concatenate several Mel-frequency cepstral coefficient feature vectors of different scales into a high-dimensional vector and input it into the compressed delay network;

[0096] Use the output of the compressed delay network as the acoustic wave feature and concatenate it with several Mel-frequency cepstral coefficient feature vectors at different time points to obtain the mixed feature;

[0097] Use a convolutional neural network to process the mixed feature, and learn the mixed feature through the convolutional layer to fuse several Mel-frequency cepstral coefficient features at different scales and different time points to obtain the fusion feature of the Mel-frequency cepstral coefficient map.

[0098] Working principle: When using a PICC catheterization ultrasonic puncture positioning system of the present invention, according to Figure 1 and Figure 2 , it includes the following steps:

[0099] Step 1: Use the implantable sensor to collect the position where the PICC catheter enters and the acoustic wave signals generated during the entry of the PICC catheter, process the acoustic wave signals to obtain a two-dimensional matrix of Mel-frequency cepstral coefficients, and save the two-dimensional matrix in image format;

[0100] Step 2: Use the deep learning algorithm of the neural network to establish an acoustic wave signal recognition neural network model, and divide the acoustic wave signal features into a training set and a validation set;

[0101] Step 3: Use the training set to train the acoustic wave signal recognition neural network model, adjust the hyperparameters of the acoustic wave signal recognition neural network model through the backpropagation algorithm, use the validation set to evaluate the performance of the acoustic wave signal recognition neural network model, and adjust the parameters of the acoustic wave signal recognition neural network model according to the evaluation results to optimize the performance of the acoustic wave signal recognition neural network model;

[0102] Step 4: Concatenate several Mel-frequency cepstral coefficient feature vectors of different scales into a high-dimensional vector and concatenate it with several Mel-frequency cepstral coefficient feature vectors at different time points to obtain the mixed feature, and fuse several Mel-frequency cepstral coefficient features at different scales and different time points through the convolutional layer to obtain the fusion feature of the Mel-frequency cepstral coefficient map;

[0103] Step 5: Input the extracted fusion features into the acoustic wave signal recognition neural network model to analyze the fusion features, and output the position information of the PICC catheterization according to the analysis results.

[0104] In summary, a PICC catheterization ultrasound puncture positioning system of the present invention uses Mel-frequency cepstral coefficients for PICC catheterization positioning. By converting the audio signal into a set of feature vectors, it can better simulate the characteristics of the human auditory system, thereby extracting more accurate acoustic wave features. This makes the Mel-frequency cepstral coefficients have high robustness when processing acoustic wave signals, and can effectively identify and locate the acoustic wave signals of PICC catheterization, thus improving the positioning accuracy. When processing the audio signal, it will preprocess the signal, including operations such as windowing, denoising, and smoothing, to remove interference factors such as noise and burst sounds, which can effectively reduce the interference of background noise on PICC catheterization positioning and improve the positioning accuracy. It can maintain a high positioning accuracy under different environments and conditions. Whether in a noisy environment or a quiet environment, the Mel-frequency cepstral coefficients can effectively extract the acoustic wave features of PICC catheterization, thereby achieving accurate positioning. By positioning the PICC catheter, it can ensure the smooth delivery of drugs and improve the therapeutic effect of drugs. Especially for patients who need long-term infusion or chemotherapy, it can avoid damage to surrounding tissues, reduce the occurrence of complications such as phlebitis and infection, and protect the patient's peripheral veins from being corroded by chemotherapy drugs.

[0105] In order to achieve a more intuitive positioning observation, in one embodiment, the PICC catheterization ultrasound puncture positioning system further includes:

[0106] A model construction module, configured to construct a position marking model based on the position information of the PICC catheter and a pre-configured human model of the patient; the position marking model marks the movement trajectory of the PICC catheter;

[0107] The data collection module further includes:

[0108] A signal receiving module, configured to receive the acoustic wave signals of the implantable sensor;

[0109] Among them, the signal receiving module is configured as at least two ultrasonic receivers arranged at different positions; a positioning module is configured beside the ultrasonic receivers, and each ultrasonic receiver is configured at the end of a manipulator;

[0110] When constructing the position marking model, the model construction module identifies the ultrasonic receivers into the position marking model according to the positioning module;

[0111] The controller of the manipulator performs the following operations:

[0112] Track the position of the end of the PICC catheter in the position marking model and generate a position sequence of the end of the PICC catheter in the human body; the position sequence is composed of the coordinates of the positions of the ends of a preset number (any one from 2 to 10) of PICC catheters; for example, the first position in the position sequence is the position of the nearest PICC catheter, and then successively the positions of the PICC catheters at the previous moment;

[0113] Determine a prediction sequence based on the position sequence and a pre-configured position prediction library; in the position prediction library, the position sequences and the prediction sequences are in one-to-one correspondence;

[0114] Determine the deployment area of the receiver corresponding to each predicted position in the prediction sequence according to a preset deployment area library; in the deployment area library, the predicted positions and the deployment areas are in one-to-one correspondence;

[0115] Take the center point of the intersection area of the deployment areas corresponding to each predicted position as the target position of the end of the manipulator to control the movement of the manipulator. By tracking the position of the PICC catheter to adjust the position of the receiver, the effectiveness and accuracy of signal reception are further ensured;

[0116] In order to realize real-time risk analysis to remind the implementer to pay attention to risks, the PICC catheterization ultrasound puncture positioning system further includes: a risk assessment module for performing real-time assessment on the operation risks of the PICC catheter and outputting;

[0117] Among them, the risk assessment module performs the following operations:

[0118] Obtain the position relationship of the implementer relative to the patient and call the corresponding personnel model according to the current action of the implementer;

[0119] Construct a simulation scenario based on the position marking model, the position relationship and the personnel model;

[0120] Track the actions of the implementer, determine the risk parts and mark them on the personnel model in the simulation scenario; the determination of the risk parts is first to determine the distance between each part of the implementer and the end of the manipulator; when the distance is less than or equal to a preset threshold and the distance is gradually decreasing, it is determined that this part is a risk part;

[0121] Mark the movement trajectory of the manipulator in the simulation scenario and calculate the first risk value according to the position relationship between each trajectory point and the risk parts; the calculation formula of the first risk value is as follows:

[0122]

[0123] In the formula, represents the first risk value; represents the th trajectory point and the The distance value between sampling points; Indicating the th trajectory point and the preset risk coefficient corresponding to the th sampling point on the risk site; Is the total number of trajectory points; Is the total number of sampling points; The sampling rule for the risk site is pre-configured, that is, sampling points are obtained by sampling the risk site according to the sampling rule; For example: the sampling rule for the hand is the end, the phalangeal joint, and the wrist joint, etc.; In addition, the trajectory points are obtained by sampling the movement trajectory according to the pre-configured trajectory sampling rule;

[0124] Evaluate the moving speed of the end of the PICC catheter and the position of the prediction sequence to obtain the second risk value; The calculation formula of the second risk value is as follows:

[0125]

[0126] In the formula, Represents the second risk value; Represents the th risk value of the prediction position; Indicates the th preset weight coefficient of the prediction position; Represents the moving speed of the end of the PICC catheter; Is the preset risk conversion coefficient corresponding to the speed; Is the configured standard speed;

[0127] Output the first risk value and the second risk value. Among them, the first risk value indicates the interference of the implementer's action on the positioning system, and the second risk value indicates that there is a risk in the puncture action of the PICC catheter. Marking both can remind the implementer to perform the operation more attentively.

[0128] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the term "including", "comprising" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0129] Although embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention.

Claims

1. A PICC catheterization ultrasound puncture positioning system, characterized in that, Including: A data collection module, which is used to collect the entry position of the PICC catheter and the acoustic wave signals generated during the entry process of the PICC catheter by using an implantable sensor, process the acoustic wave signals to obtain a two-dimensional matrix of Mel frequency cepstral coefficients, and save the two-dimensional matrix in an image format; An identification module, which is used to establish an acoustic wave signal identification neural network model, and train and optimize the acoustic wave signal identification neural network model; A positioning module, which is used to extract the fusion features at different scales and different time points in the Mel frequency cepstral coefficient map, and analyze the fusion features by using the acoustic wave signal identification neural network model to obtain the position information of PICC catheterization; A risk assessment module, which is used to perform real-time assessment of the operation risks of the PICC catheter and output them; Among them, the risk assessment module performs the following operations: Obtain the position relationship of the implementer relative to the patient and retrieve the corresponding personnel model according to the current action of the implementer; Construct a simulation scenario based on the position marking model, the position relationship, and the personnel model; Track the actions of the implementer, determine the risk parts and mark them on the personnel model in the simulation scenario; Mark the movement trajectory of the manipulator in the simulation scenario and calculate the first risk value according to the position relationship between each trajectory point and the risk parts. The calculation formula of the first risk value is as follows: ； In the formula, represents the first risk value; represents the distance value between the th trajectory point and the th sampling point on the risk part; represents the preset risk coefficient corresponding to the th trajectory point and the th sampling point on the risk part; is the total number of trajectory points; is the total number of sampling points; Evaluate the moving speed of the end of the PICC catheter and the position of the prediction sequence to obtain the second risk value. The calculation formula of the second risk value is as follows: ； In the formula, represents the second risk value; Indicates The hazard value of each predicted location; Indicates The preset weight coefficients of the predicted positions; Indicates the movement speed of the PICC catheter tip; is the risk conversion factor of the preset corresponding speed; is the standard speed configured; Output the first risk value and the second risk value.

2. The PICC catheterization ultrasound puncture positioning system according to claim 1, wherein: The data collection module includes: An implantable sensor, which is arranged in the PICC catheter and is used to obtain the entry position of the PICC catheter and the acoustic wave signals generated during the entry process of the PICC catheter; A processing module, which is used to process the obtained acoustic wave signals, extract the acoustic wave signal features, obtain a two-dimensional matrix of Mel frequency cepstral coefficients, and save the two-dimensional matrix in an image format.

3. The PICC catheterization ultrasonic puncture positioning system according to claim 2, wherein: The processing module includes: A feature extraction module, which is used to perform filtering, pre-emphasis, framing, and window function processing on the obtained acoustic wave signals, and extract the acoustic wave signal features from the converted acoustic wave signals to obtain a two-dimensional matrix of Mel frequency cepstral coefficients; A picture conversion module, which is used to save the two-dimensional matrix of Mel frequency cepstral coefficients in an image format, where the rows represent the number of Mel filters and the columns represent the time frames.

4. The PICC catheterization ultrasound puncture positioning system according to claim 3, characterized in that: Specifically, the processing module includes: Perform pre-emphasis processing by using a first-order high-pass filter, frame the leaked acoustic wave signals after pre-emphasis processing, and window each frame by multiplying it by a window function; Perform fast Fourier transform on each frame of the framed and windowed signals to obtain the spectrum of each frame, convert the actual frequency length to the Mel frequency length, configure a triangular filter bank and calculate the output of each triangular filter after filtering the signal amplitude spectrum; Perform logarithmic operation on the outputs of all filters, and further perform discrete cosine transform to obtain a two-dimensional matrix of Mel frequency cepstral coefficients, and save the two-dimensional matrix of Mel frequency cepstral coefficients in an image format.

5. The PICC catheterization ultrasound puncture positioning system according to claim 1, wherein: The identification module includes: A model construction module, which is used to establish a neural network model for acoustic signal recognition by using the deep learning algorithm of a neural network, and divide the acoustic signal features into a training set and a validation set; A model training module, which is used to train the neural network model for acoustic signal recognition by using the training set, and adjust the hyperparameters of the neural network model for acoustic signal recognition through the backpropagation algorithm; A model evaluation module, which is used to evaluate the performance of the neural network model for acoustic signal recognition by using the validation set, adjust the parameters of the neural network model for acoustic signal recognition according to the evaluation results, and optimize the performance of the neural network model for acoustic signal recognition.

6. The PICC catheterization ultrasonic puncture positioning system according to claim 5, wherein: The model construction module specifically includes: Establish a neural network model for acoustic signal recognition by using the deep learning algorithm of a neural network. The neural network model consists of an input layer, a hidden layer, and an output layer; The data set required by the input layer is derived from the time-domain signals and time-frequency spectrum signals of measured acoustic waves under different working conditions, and is divided into a training set and a validation set in an appropriate proportion; The hidden layer is responsible for the extraction and learning of acoustic features, and includes a convolutional layer, a feature extraction sampling layer, a pooling layer, and a fully connected layer; The output layer is responsible for exporting the acceleration curve recognized as the train acoustic wave and using it as the recognition result.

7. A PICC catheterization ultrasound puncture positioning system according to claim 1, characterized in that: The positioning module includes: A feature fusion module, which is used to extract the fusion features at different scales and different time points in the mel-frequency cepstrum coefficient map; A position determination module, which is used to input the extracted fusion features into the neural network model for acoustic signal recognition to analyze the fusion features, and output the position information of PICC catheterization according to the analysis results; A real-time monitoring module, which is used to monitor the hemodynamic parameters in the patient's body in real time, and give corresponding warnings when the hemodynamic parameters in the patient's body are abnormal.

8. A PICC catheterization ultrasound puncture positioning system according to claim 7, characterized in that: The extraction of the fusion features of the mel-frequency cepstrum coefficient map specifically includes Concatenate several mel-frequency cepstrum coefficient feature vectors of different scales into a high-dimensional vector, and input it into the compressed delay network; Use the output of the compressed delay network as the acoustic feature, and concatenate it with several mel-frequency cepstrum coefficient feature vectors at different time points to obtain a mixed feature; Process the mixed feature by using a convolutional neural network, and learn the mixed feature through the convolutional layer to fuse several mel-frequency cepstrum coefficient features at different scales and different time points to obtain the fusion feature of the mel-frequency cepstrum coefficient map.

9. The PICC catheterization ultrasound puncture positioning system according to claim 1, wherein: It also includes: A model construction module, which is used to construct a position marking model according to the position information of the PICC catheter and the pre-configured human model of the patient; The data collection module also includes: A signal receiving module, which is used to receive the acoustic signals of the implantable sensor; Among them, the signal receiving module is configured as at least two ultrasonic receivers arranged at different positions; a positioning module is configured beside the ultrasonic receivers, and each ultrasonic receiver is configured at the end of a manipulator; When constructing the position marking model, the model construction module marks the ultrasonic receivers into the position marking model according to the positioning module; The controller of the manipulator performs the following operations: Track the position of the end of the PICC catheter in the position marking model, and generate the position sequence of the end of the PICC catheter in the human body; Determine the prediction sequence according to the position sequence and the pre-configured position prediction library; Determine the layout area of the receiver corresponding to each prediction position in the prediction sequence according to the preset layout area library; Use the center point of the intersection area of the layout areas corresponding to each prediction position as the target position of the end of the manipulator to control the movement of the manipulator.

Images