Intelligent PICC intravenous therapy information management system and method

Abstract

The present application provides an intelligent PICC intravenous treatment information management system and method, which relates to the field of computer technology. It includes: preprocessing the PICC catheter image to generate a corrected image, and extracting the feature vector in the corrected image; performing linear combination based on the feature vector, and converting the linear combination result into the first probability of infection risk; performing convolution and pooling processing on the corrected image based on the first probability, and outputting the second probability of the corrected image corresponding to each risk category; generating and displaying analysis and prediction results based on the first probability and the second probability. The present application enhances the model's ability to identify catheter infection risks through precise image preprocessing and feature extraction, uses linear combination and convolution processing to perform automated risk assessment, and provides a more comprehensive infection risk assessment through comprehensive analysis of the first probability and the second probability. The generated and displayed results can intuitively present risk assessments to doctors, improving the monitoring and management efficiency of PICC catheter information.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and more specifically, to an intelligent PICC intravenous therapy information management system and method. Background Art

[0002] With the continuous development of medical technology, PICC (Peripherally Inserted Central Catheter) is increasingly used in clinical practice. It provides patients with medium- and long-term intravenous infusion therapy, reduces the pain of repeated punctures, and improves treatment efficiency. Traditional PICC intravenous treatment management models are mostly manual operations, with problems such as difficulty in information tracing and low management efficiency, which cannot meet the growing clinical needs. Especially during the process of PICC implantation in the body, it cannot be monitored and managed in a timely and effective manner, which leads to problems of improper use. Summary of the invention

[0003] The embodiments of the present application provide an intelligent PICC intravenous treatment information management system and method, which can at least to a certain extent solve the problem of low efficiency in PICC information monitoring and management.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0005] According to one aspect of the present application, a smart PICC intravenous treatment information management method is provided, including: acquiring a catheter image of a PICC through an imaging device; preprocessing the catheter image to generate a corrected image, and extracting a feature vector in the corrected image; performing a linear combination based on the feature vector, and converting the linear combination result into a first probability of infection risk; based on the first probability, performing convolution and pooling processing on the corrected image, and outputting a second probability of the corrected image corresponding to each risk category; based on the first probability and the second probability, generating and displaying an analysis prediction result.

[0006] Furthermore, the catheter image is preprocessed to generate a corrected image, including:

[0007] Performing grayscale equalization on the catheter image to generate a grayscale image;

[0008] Contrast enhancement is performed on the grayscale image to generate the corrected image.

[0009] Furthermore, grayscale equalization is performed on the catheter image to generate a grayscale image, including:

[0010] generating a grayscale histogram of the catheter image;

[0011] Determine the pixel mean based on the pixel values ​​of the pixel points in the grayscale histogram and the frequency of each grayscale level in the grayscale histogram, and calculate the grayscale distribution parameter;

[0012] The equalized grayscale value is determined based on the grayscale distribution parameter and the grayscale level, and a grayscale image is generated according to the grayscale value.

[0013] Further, performing a linear combination based on the feature vector and converting the linear combination result into a first probability of infection risk includes:

[0014] Obtaining a weight vector corresponding to the feature vector;

[0015] Performing a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result;

[0016] The linear combination result is mapped to a probability interval to obtain a first probability of infection risk.

[0017] Further, performing convolution and pooling processing on the corrected image and outputting a second probability of the corrected image corresponding to each risk category includes:

[0018] Performing convolution processing on the pixel value of each pixel point in the corrected image according to the convolution kernel to generate an output feature map;

[0019] Performing pooling processing on the output feature map to generate a pooled feature map;

[0020] Connect neurons based on the pooled feature map to generate a linear combination result;

[0021] A second probability corresponding to each risk category is determined based on the linear combination result.

[0022] Further, based on the first probability and the second probability, generating and displaying analysis and prediction results, including:

[0023] Get the preset form template;

[0024] The first probability, the second probability and the catheter image are written into the form template, and the analysis and prediction results are generated and displayed.

[0025] Furthermore, it also includes:

[0026] Sending the analysis and prediction results to the attending physician;

[0027] The correction information input by the attending physician is obtained, and the analysis prediction result is modified based on the correction information.

[0028] According to one aspect of the present application, a smart PICC intravenous treatment information management system is provided, comprising:

[0029] An acquisition unit, used for acquiring a catheter image of the PICC through an imaging device;

[0030] A feature unit, used for preprocessing the catheter image, generating a corrected image, and extracting a feature vector in the corrected image;

[0031] A linear unit, used for performing a linear combination based on the feature vector and converting the linear combination result into a first probability of infection risk;

[0032] a convolution unit, configured to perform convolution and pooling processing on the corrected image based on the first probability, and output a second probability that the corrected image corresponds to each risk category;

[0033] A display unit is used to generate and display the analysis and prediction results based on the first probability and the second probability.

[0034] According to one aspect of the present application, a computer-readable medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the smart PICC intravenous treatment information management method as described in the above embodiment is implemented.

[0035] According to one aspect of the present application, an electronic device is provided, comprising: one or more processors; a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the smart PICC intravenous treatment information management method as described in the above embodiments.

[0036] In the technical solution of the present application, a catheter image of a PICC is acquired through an imaging device; the catheter image is preprocessed to generate a corrected image, and a feature vector in the corrected image is extracted; a linear combination is performed based on the feature vector, and the linear combination result is converted into a first probability of infection risk; based on the first probability, the corrected image is convoluted and pooled, and a second probability corresponding to each risk category of the corrected image is output; based on the first probability and the second probability, an analysis prediction result is generated and displayed. The technical solution of the present application enhances the model's ability to identify catheter infection risks through precise image preprocessing and feature extraction, and uses linear combination and convolution processing for automated risk assessment, which reduces the need for manual intervention and improves efficiency. Through comprehensive analysis of the first probability and the second probability, a more comprehensive infection risk assessment is provided, and the generated and displayed results can intuitively present risk assessments to doctors, improving the efficiency of monitoring and management of PICC catheter information.

[0037] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The drawings herein are incorporated into the specification and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the specification are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 The flowchart of the intelligent PICC intravenous treatment information management method in one embodiment of the present application is schematically shown.

[0040] Figure 2 The flowchart of generating a grayscale image in one embodiment of the present application is schematically shown.

[0041] Figure 3 The following is a schematic diagram of a smart PICC intravenous treatment information management system in one embodiment of the present application.

[0042] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown. DETAILED DESCRIPTION

[0043] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0044] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the application.

[0045] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0046] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0047] The implementation details of the technical solution of this application are described in detail below:

[0048] Figure 1 FIG. 1 is a flow chart showing a method for managing information of a smart PICC intravenous treatment according to an embodiment of the present application. Figure 1 As shown, the smart PICC intravenous treatment information management method includes at least steps S110 to S150, which are described in detail as follows:

[0049] In step S110, a catheter image of the PICC is acquired by an imaging device.

[0050] In one embodiment of the present application, suitable imaging equipment is selected as needed, such as an X-ray machine, an ultrasound machine, or a computer tomography (CT) machine. These devices can provide detailed images of the catheter. According to the equipment requirements, the patient is placed on the imaging equipment to ensure that the position of the catheter is clearly visible. The position of the catheter can be marked in the imaging equipment to ensure the accuracy of the image.

[0051] In one embodiment of the present application, an imaging device is started and a suitable shooting mode is selected. For example, on an X-ray machine, appropriate exposure parameters and image modes can be selected. An image acquisition operation is performed to obtain an image of the PICC catheter. Ensure that the image includes a complete view of the catheter and is clearly identifiable. The device stores the acquired image data in the system.

[0052] In step S120, the catheter image is preprocessed to generate a corrected image, and a feature vector in the corrected image is extracted.

[0053] In one embodiment of the present application, preprocessing the catheter image to generate a corrected image includes:

[0054] Performing grayscale equalization on the catheter image to generate a grayscale image;

[0055] Contrast enhancement is performed on the grayscale image to generate the corrected image.

[0056] like Figure 2 As shown, in one embodiment of the present application, grayscale equalization is performed on the catheter image to generate a grayscale image, including:

[0057] S210: generating a grayscale histogram of the catheter image;

[0058] S220: Determine a pixel mean value based on the pixel values ​​of the pixel points in the grayscale histogram and the frequency of each grayscale level in the grayscale histogram, and calculate a grayscale distribution parameter;

[0059] S230: Determine a grayscale value after equalization based on the grayscale distribution parameter and the grayscale level, and generate a grayscale image according to the grayscale value.

[0060] In one embodiment of the present application, in the above process, a grayscale histogram corresponding to the catheter image is generated. Assume that the total number of pixels of the image is N, and the grayscale range is [0, P-1], where P is the total number of grayscales, and the grayscale is recorded. The frequency of is: .

[0061] The pixel mean and the frequency of each gray level in the gray histogram are determined based on the pixel values ​​of the pixels in the gray histogram, and the gray distribution parameters are calculated. for:

[0062] ;

[0063] Among them, i represents the gray level identifier, k represents the maximum gray level, Indicates grayscale The frequency of represents the frequency corresponding to the pixel mean, represents the pixel value, n represents the pixel identifier, and m represents the maximum pixel value. Represents the pixel factor, and its value is greater than 1. The grayscale distribution parameter calculated by the above process represents the cumulative frequency of pixels less than or equal to the current grayscale level.

[0064] After the grayscale distribution parameters are calculated, the grayscale value after equalization is determined based on the grayscale distribution parameters and the grayscale level. for:

[0065] ;

[0066] Wherein, P represents the total number of gray levels. After the gray values ​​are generated, a gray image is generated according to the gray values.

[0067] In the above process, high-quality images of PICC catheters are obtained through imaging equipment to ensure that subsequent processing is based on accurate data. Image preprocessing (such as denoising, contrast enhancement, and brightness adjustment) can improve image quality and reduce the interference of noise on feature extraction. It improves the clarity and quality of the image and provides reliable input data for subsequent feature extraction and analysis.

[0068] Feature vectors are extracted from the preprocessed images. These feature vectors include key visual information in the image (such as shape, texture, edge, etc.) and are used to describe the characteristics of the catheter. Accurately extracted feature vectors can represent important information in the image and help improve the prediction accuracy and reliability of subsequent models.

[0069] In step S130, a linear combination is performed based on the feature vectors, and the linear combination result is converted into a first probability of infection risk.

[0070] In one embodiment of the present application, performing a linear combination based on the feature vector and converting the linear combination result into a first probability of infection risk includes:

[0071] Obtaining a weight vector corresponding to the feature vector;

[0072] Performing a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result;

[0073] The linear combination result is mapped to a probability interval to obtain a first probability of infection risk.

[0074] In the above process, the feature vector extracted from the corrected image may include information such as age, image texture, and regional features. The corresponding weight vector is obtained based on the above features, which can be obtained by preset corresponding relationships.

[0075] After that, a linear combination is performed based on the feature vector and its corresponding weight vector to generate the linear combination result for:

[0076] ;

[0077] in, represents the feature vector combination, represents a feature vector. represents the weight vector combination, Represents the weight vector corresponding to the feature vector, each weight corresponds to a feature, is the bias term.

[0078] It should be noted that in practical applications, the weight The contribution of each feature to the risk of infection can be explained. A positive weight indicates that the feature increases the risk of infection, and a negative weight indicates that the feature decreases the risk of infection. The model can deduce the main factors affecting the risk of infection for a particular individual by analyzing the feature weights. For example, if The corresponding feature is "age", and If is positive, it means that the older you are, the higher the risk of infection; if The corresponding feature is "Past medical history", and If it is negative, it means that people with a certain medical history have a relatively low risk of infection.

[0079] Afterwards, the linear combination result is mapped to the probability interval to obtain the first probability of infection risk for:

[0080] ;

[0081] After calculating the first probability, the final prediction is determined based on the set threshold. , the infection risk is predicted to be high; otherwise, the infection risk is predicted to be low.

[0082] Further, after the first probability is calculated, step S140 is performed based on the judgment result between the first probability and the set threshold. , it is predicted that the infection risk is high, and step S140 is executed to specifically determine the risk category corresponding to the catheter image.

[0083] The feature vectors are weighted by linear combination to calculate the first probability of infection risk. This process can integrate multiple feature information into a probability value. The linear combination method can effectively combine multiple features to provide a preliminary infection risk assessment.

[0084] In step S140, based on the first probability, convolution and pooling processing is performed on the corrected image, and a second probability that the corrected image corresponds to each risk category is output.

[0085] In one embodiment of the present application, performing convolution and pooling processing on the corrected image and outputting a second probability that the corrected image corresponds to each risk category includes:

[0086] Performing convolution processing on the pixel value of each pixel point in the corrected image according to the convolution kernel to generate an output feature map;

[0087] Performing pooling processing on the output feature map to generate a pooled feature map;

[0088] Connect neurons based on the pooled feature map to generate a linear combination result;

[0089] A second probability corresponding to each risk category is determined based on the linear combination result.

[0090] In one embodiment of the present application, image analysis is used to process and analyze image data of a PICC catheter, identify the position and shape of the catheter through edge detection, detect whether there is displacement or other abnormalities, classify the image, and identify catheter-related features or abnormalities.

[0091] Specifically, for the input rectified image and convolution kernel Perform convolution processing to generate output feature maps The pixel value is:

[0092] ;

[0093] in, is the output feature map at position The pixel value of is the corrected image at position The pixel value of is the convolution kernel at position The weight of and is the height and width of the convolution kernel.

[0094] Then, it is pooled to reduce the dimension of the feature map while retaining the main features to obtain the pixel value corresponding to the pooled feature map. for:

[0095] ;

[0096] in, It is the feature map after pooling at position The pixel value of Is the pooling window in the input feature map The range of sliding up, Indicates that the feature map is at position The pixel value of .

[0097] After generating the pooled feature map, the neurons are connected based on the pooled feature map to generate a linear combination result. for:

[0098] ;

[0099] in, is the activation function; It is The linear combination of neurons is Is the connection The input and The weight of a neuron, is the width of the convolution kernel. It is The activation value of the input. It is The bias parameters of each neuron.

[0100] Afterwards, the second probability corresponding to each risk category is determined based on the linear combination result. Specifically, the second probability is classified and outputted, and the probability corresponding to each risk category is calculated as:

[0101] ;

[0102] in, is the input feature Belong to The probability of a risk category, is the fully connected layer for the Class rating, is the total number of infection risk categories, It is the score of the Kth category by the fully connected layer.

[0103] Based on the first probability, the corrected image is convolved and pooled to obtain deeper features of the image and calculate the second probability of each risk category. The above process can automatically learn and extract complex features. Convolution and pooling can capture subtle features and patterns in the image and improve the ability to classify infection risks. CNN's automatic feature learning can adapt to complex image data, making risk assessment more accurate.

[0104] In step S150, based on the first probability and the second probability, an analysis and prediction result is generated and displayed.

[0105] In one embodiment of the present application, based on the first probability and the second probability, generating and displaying an analysis prediction result includes:

[0106] Get the preset form template;

[0107] The first probability, the second probability and the catheter image are written into the form template, and the analysis and prediction results are generated and displayed.

[0108] In one embodiment of the present application, in the above process, a preset form template is first read from a storage medium (such as a file system, a database, or a network). The form template exists in the form of an electronic file, such as a PDF, a Word document, an HTML, or an XML file. The template file is then parsed. Template files of different formats use corresponding parsing libraries or tools. For example, a PDF template can use a PDF parsing library, a Word document can use a special Word processing library, and an HTML template can use an HTML parser.

[0109] Gather the data that needs to be filled in, including the first probability, second probability, and catheter image. The data may come from user input, calculation results, or database queries. Format the data to meet the field requirements in the template. For example, convert the probability value to an appropriate format (such as decimal, percentage) and convert the image to a format suitable for insertion into the template.

[0110] Use the template engine library to populate data into the form template. For example, if it is an HTML template, you can use the server-side template engine to dynamically insert data into the HTML. If it is a PDF template, you can use the PDF manipulation library to fill data into predefined fields. Insert the catheter image into the form template. The image needs to be converted to the appropriate format and embedded in the specified location of the template. Image processing may include resizing, cropping, or format conversion. Generate the final file from the filled form template. The generated file may be a PDF document, HTML page, or other format.

[0111] In terms of display methods, it includes displaying the result page in the web application, providing a download link to allow users to download the generated file, or sending the generated result file via email. Through the above steps, the computer system can generate a final file containing the analysis and prediction results from the template and display it to the user in an appropriate manner.

[0112] The above process combines the first probability and the second probability to generate the final analysis and prediction results and display them. This result includes a comprehensive assessment of the risk of infection and the specific probability distribution of different risk categories. The comprehensive analysis provides a comprehensive risk assessment result that can help doctors better understand and make decisions. The display method can be optimized according to actual needs, such as generating reports, charts or visual interfaces, which are convenient for doctors and medical staff to use and understand.

[0113] In one embodiment of the present application, it also includes:

[0114] Sending the analysis and prediction results to the attending physician;

[0115] The correction information input by the attending physician is obtained, and the analysis prediction result is modified based on the correction information.

[0116] In one embodiment of the present application, an email service can be used to send a file to the email address of the attending physician. Alternatively, a notification or message is generated in a web application to prompt the attending physician to download or view the results. By generating a download link or file viewing interface in the application, ensure that the attending physician has access. Create a form in the web application for the attending physician to enter the correction information. The form can include input controls such as text boxes, drop-down menus, check boxes, etc. In the web form, the attending physician submits the entered correction information. The system verifies the validity of the input (such as format, required fields, etc.).

[0117] Parse the correction information into a format that the system can understand. For example, the correction value may be a new probability value, a modified image, or other parameters. Modify the data of the prediction result according to the correction information. For example, if it is a PDF file, update the content through the PDF editing library; if it is an HTML file, the corresponding HTML content needs to be updated. Refill the modified data into the template to generate an updated file. Save the updated file to the storage medium, replacing the original file or saving it as a new file. Through these steps, the computer system can efficiently handle the sending and correction of analysis results, ensuring that the attending physician can obtain accurate and updated prediction results.

[0118] In the technical solution of the present application, a catheter image of a PICC is acquired through an imaging device; the catheter image is preprocessed to generate a corrected image, and a feature vector in the corrected image is extracted; a linear combination is performed based on the feature vector, and the linear combination result is converted into a first probability of infection risk; based on the first probability, the corrected image is convoluted and pooled, and a second probability corresponding to each risk category of the corrected image is output; based on the first probability and the second probability, an analysis prediction result is generated and displayed. The technical solution of the present application enhances the model's ability to identify catheter infection risks through precise image preprocessing and feature extraction, and uses linear combination and convolution processing for automated risk assessment, which reduces the need for manual intervention and improves efficiency. Through comprehensive analysis of the first probability and the second probability, a more comprehensive infection risk assessment is provided, and the generated and displayed results can intuitively present risk assessments to doctors, improving the efficiency of monitoring and management of PICC catheter information.

[0119] The following describes an embodiment of the device of the present application, which can be used to execute the intelligent PICC intravenous treatment information management method in the above embodiment of the present application. It can be understood that the device can be a computer program (including program code) running in a computer device, for example, the device is an application software; the device can be used to execute the corresponding steps in the method provided in the embodiment of the present application. For details not disclosed in the embodiment of the device of the present application, please refer to the embodiment of the intelligent PICC intravenous treatment information management method in the above embodiment of the present application.

[0120] Figure 3 A block diagram of a smart PICC intravenous treatment information management system according to an embodiment of the present application is shown.

[0121] Reference Figure 3 As shown, according to an embodiment of the present application, a smart PICC intravenous treatment information management system includes:

[0122] An acquisition unit 310 is used to acquire a catheter image of the PICC through an imaging device;

[0123] A feature unit 320, configured to preprocess the catheter image, generate a corrected image, and extract a feature vector from the corrected image;

[0124] A linear unit 330, configured to perform a linear combination based on the feature vectors and convert the linear combination result into a first probability of infection risk;

[0125] A convolution unit 340 is used to perform convolution and pooling processing on the corrected image based on the first probability, and output a second probability that the corrected image corresponds to each risk category;

[0126] The display unit 350 is used to generate and display the analysis and prediction results based on the first probability and the second probability.

[0127] In the present application, based on the above-mentioned scheme, the catheter image is preprocessed to generate a corrected image, including: grayscale equalization of the catheter image to generate a grayscale image; contrast enhancement of the grayscale image to generate the corrected image.

[0128] In the present application, based on the aforementioned scheme, the catheter image is grayscale equalized to generate a grayscale image, including: generating a grayscale histogram of the catheter image; determining the pixel mean and the frequency of each grayscale level in the grayscale histogram based on the pixel values ​​of the pixel points in the grayscale histogram, and calculating the grayscale distribution parameters; determining the grayscale value after equalization based on the grayscale distribution parameters and the grayscale level, and generating a grayscale image according to the grayscale value.

[0129] In the present application, based on the aforementioned scheme, a linear combination is performed based on the feature vector, and the linear combination result is converted into a first probability of infection risk, including: obtaining a weight vector corresponding to the feature vector; performing a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result; mapping the linear combination result to a probability interval to obtain a first probability of infection risk.

[0130] In the present application, based on the aforementioned scheme, the corrected image is convolved and pooled, and the second probability of the corrected image corresponding to each risk category is output, including: performing convolution processing on the pixel value of each pixel point in the corrected image according to the convolution kernel to generate an output feature map; performing pooling processing on the output feature map to generate a pooled feature map; performing neuron connection based on the pooled feature map to generate a linear combination result; and determining the second probability corresponding to each risk category based on the linear combination result.

[0131] In the present application, based on the aforementioned scheme, based on the first probability and the second probability, an analysis prediction result is generated and displayed, including: obtaining a preset form template; writing the first probability, the second probability and the catheter image into the form template, generating an analysis prediction result and displaying it.

[0132] In the present application, based on the above-mentioned scheme, it also includes: sending the analysis and prediction results to the attending physician; obtaining correction information input by the attending physician, and modifying the analysis and prediction results based on the correction information.

[0133] In the technical solution of the present application, a catheter image of a PICC is acquired through an imaging device; the catheter image is preprocessed to generate a corrected image, and a feature vector in the corrected image is extracted; a linear combination is performed based on the feature vector, and the linear combination result is converted into a first probability of infection risk; based on the first probability, the corrected image is convoluted and pooled, and a second probability corresponding to each risk category of the corrected image is output; based on the first probability and the second probability, an analysis prediction result is generated and displayed. The technical solution of the present application enhances the model's ability to identify catheter infection risks through precise image preprocessing and feature extraction, and uses linear combination and convolution processing for automated risk assessment, which reduces the need for manual intervention and improves efficiency. Through comprehensive analysis of the first probability and the second probability, a more comprehensive infection risk assessment is provided, and the generated and displayed results can intuitively present risk assessments to doctors, improving the efficiency of monitoring and management of PICC catheter information.

[0134] Figure 4 A schematic diagram of the structure of a computer system suitable for implementing an electronic device of an embodiment of the present application is shown.

[0135] It should be noted that the computer system 400 of the electronic device shown in the figure is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0136] The computer system 400 includes a central processing unit (CPU) 401, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 402 or the program loaded from the storage part 408 to the random access memory (RAM) 403, such as executing the method described in the above embodiment. Various programs and data required for system operation are also stored in the RAM 403. The CPU 401, the ROM 402 and the RAM 403 are connected to each other through the bus 404. The input / output (I / O) interface 405 is also connected to the bus 404.

[0137] The following components are connected to the I / O interface 405: an input section 406 including a keyboard, a mouse, etc.; an output section 407 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 408 including a hard disk, etc.; and a communication section 409 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 409 performs communication processing via a network such as the Internet. A drive 410 is also connected to the I / O interface 405 as needed. A removable medium 411, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 410 as needed so that a computer program read therefrom is installed into the storage section 408 as needed.

[0138] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 409, and / or installed from a removable medium 411. When the computer program is executed by the central processing unit (CPU) 401, various functions defined in the system of the present application are executed.

[0139] It should be noted that the computer-readable medium shown in the embodiment of the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate, or transmit programs for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0140] The flowchart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present application. Wherein, each box in the flowchart or block diagram can represent a module, a program segment, or a part of the code, and the above-mentioned module, program segment, or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0141] The units involved in the embodiments described in this application may be implemented by software or hardware, and the units described may also be set in a processor. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0142] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0143] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiment; or may exist independently without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiment.

[0144] It should be noted that, although several modules or units of the equipment for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into being embodied by multiple modules or units.

[0145] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the implementation method of the present application.

[0146] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the embodiments disclosed herein. The present application is intended to cover any variations, uses or adaptations of the present application, which follow the general principles of the present application and include common knowledge or customary technical means in the art that are not disclosed in the present application.

[0147] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A smart PICC intravenous treatment information management method, characterized in that: include: Obtain the catheter image of the PICC through imaging equipment; Preprocessing the catheter image to generate a corrected image, and extracting a feature vector from the corrected image; Performing a linear combination based on the feature vector and converting the linear combination result into a first probability of infection risk; specifically, obtaining a weight vector corresponding to the feature vector; performing a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result; mapping the linear combination result to a probability interval to obtain a first probability of infection risk; The method of performing a linear combination based on the feature vector and converting the linear combination result into a first probability of infection risk includes: Obtain a weight vector corresponding to the feature vector; perform a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result ;in, represents the feature vector combination, represents the feature vector; represents the weight vector combination, Represents the weight vector corresponding to the feature vector, where each weight corresponds to a feature, is a bias term; the linear combination result is mapped to a probability interval to obtain a first probability of infection risk; Based on the first probability, the corrected image is convolved and pooled to output a second probability of the corrected image corresponding to each risk category; specifically, the pixel value of each pixel in the corrected image is convolved according to the convolution kernel to generate an output feature map; the output feature map is pooled to generate a pooled feature map; neurons are connected based on the pooled feature map to generate a linear combination result; based on the linear combination result, the second probability corresponding to each risk category is determined; The correction image is convolved and pooled to output the second probability of the correction image corresponding to each risk category, including: and convolution kernel Perform convolution processing to generate output feature maps The pixel value is: ； in, is the output feature map at position The pixel value of is the corrected image at position The pixel value of is the convolution kernel at position The weight of and is the height and width of the convolution kernel; the output feature map is pooled to generate pixel values ​​corresponding to the pooled feature map for: ； in, It is the feature map after pooling at position The pixel value of Is the pooling window in the input feature map The range of sliding up, Indicates that the feature map is at position The pixel value of Based on the pooled feature map, neurons are connected to generate linear combination results for: ； in, is the activation function; It is The linear combination of neurons is Is the connection The input and The weight of a neuron, is the width of the convolution kernel; It is The activation value of the input; It is The bias parameters of each neuron; The second probability corresponding to each risk category is determined based on the linear combination result: ； in, is the input feature Belong to The probability of a risk category, is the fully connected layer for the Class rating, is the total number of infection risk categories, is the score of the Kth category given by the fully connected layer; Based on the first probability and the second probability, an analysis prediction result is generated and displayed; specifically, a form template in a preset electronic file format is read from a storage medium; the first probability, the second probability and the catheter image are written into the form template, and an analysis prediction result is generated and displayed.

2. The intelligent PICC intravenous treatment information management method according to claim 1 is characterized in that: Preprocessing the catheter image to generate a corrected image includes: Performing grayscale equalization on the catheter image to generate a grayscale image; Contrast enhancement is performed on the grayscale image to generate the corrected image.

3. The intelligent PICC intravenous treatment information management method according to claim 2 is characterized in that: Performing grayscale equalization on the catheter image to generate a grayscale image includes: generating a grayscale histogram of the catheter image; Determine the pixel mean based on the pixel values ​​of the pixel points in the grayscale histogram and the frequency of each grayscale level in the grayscale histogram, and calculate the grayscale distribution parameter; The equalized grayscale value is determined based on the grayscale distribution parameter and the grayscale level, and a grayscale image is generated according to the grayscale value.

4. The intelligent PICC intravenous treatment information management method according to claim 1 is characterized in that: Also includes: Sending the analysis and prediction results to the attending physician; The correction information input by the attending physician is obtained, and the analysis prediction result is modified based on the correction information.

5. A smart PICC intravenous treatment information management system, characterized in that: include: An acquisition unit, used for acquiring a catheter image of the PICC through an imaging device; A feature unit, used for preprocessing the catheter image, generating a corrected image, and extracting a feature vector in the corrected image; A linear unit is used to perform a linear combination based on the feature vector and convert the linear combination result into a first probability of infection risk; specifically, obtain a weight vector corresponding to the feature vector; perform a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result; map the linear combination result to a probability interval to obtain a first probability of infection risk; The method of performing a linear combination based on the feature vector and converting the linear combination result into a first probability of infection risk includes: Obtain a weight vector corresponding to the feature vector; perform a linear combination based on the feature vector and its corresponding weight vector to generate a linear combination result ;in, represents the feature vector combination, represents the feature vector; represents the weight vector combination, Represents the weight vector corresponding to the feature vector, where each weight corresponds to a feature, is a bias term; the linear combination result is mapped to a probability interval to obtain a first probability of infection risk; A convolution unit is used to perform convolution and pooling processing on the corrected image based on the first probability, and output the second probability of the corrected image corresponding to each risk category; specifically, convolution processing is performed on the pixel value of each pixel point in the corrected image according to the convolution kernel to generate an output feature map; pooling processing is performed on the output feature map to generate a pooling feature map; based on the pooling feature map, neurons are connected to generate a linear combination result; based on the linear combination result, the second probability corresponding to each risk category is determined; The correction image is convolved and pooled to output the second probability of the correction image corresponding to each risk category, including: and convolution kernel Perform convolution processing to generate output feature maps The pixel value is: ； in, is the output feature map at position The pixel value of is the corrected image at position The pixel value of is the convolution kernel at position The weight of and is the height and width of the convolution kernel; the output feature map is pooled to generate pixel values ​​corresponding to the pooled feature map for: ； in, It is the feature map after pooling at position The pixel value of Is the pooling window in the input feature map The range of sliding up, Indicates that the feature map is at position The pixel value of Based on the pooled feature map, neurons are connected to generate linear combination results for: ； in, is the activation function; It is The linear combination of neurons is Is the connection The input and The weight of a neuron, is the width of the convolution kernel; It is The activation value of the input; It is The bias parameters of each neuron; The second probability corresponding to each risk category is determined based on the linear combination result: ； in, is the input feature Belong to The probability of a risk category, is the fully connected layer for the Class rating, is the total number of infection risk categories, is the score of the Kth category given by the fully connected layer; A display unit is used to generate and display the analysis and prediction results based on the first probability and the second probability; specifically, read a form template in the form of a preset electronic file from a storage medium; write the first probability, the second probability and the catheter image into the form template, generate and display the analysis and prediction results.

6. A computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the smart PICC intravenous treatment information management method according to any one of claims 1 to 4 is implemented.

7. An electronic device, characterized in that: include: one or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to implement the smart PICC intravenous treatment information management method as described in any one of claims 1 to 4.

Images