Remaining needle work intelligent identification method and system based on enhanced examination image

Abstract

The invention relates to the technical field of intelligent nursing, in particular to an intelligent indwelling needle work identification method and system based on an enhanced examination image, and during patient examination, a timing system identifies a photograph of an image (CT or MRI enhanced examination) in a patient folder (discovering angiography image features such as angiography color, texture and the like); a timing system is intelligently triggered to start timing; and when the needle withdrawal time is up, sending out a needle withdrawal notice of the corresponding patient. Therefore, needle withdrawal detection and reminding in CT or MRI enhanced examination in the imaging department can be intelligently realized, a head nurse does not need to carry out remaining needle withdrawal detection at a patient for a long time, the system can intelligently detect the enhanced examination condition and calculate the remaining time, the enhanced examination patient and nurses can be intelligently managed and served, and the system is convenient to use and popularize. The management efficiency of the imaging department enhanced examination patient is improved, excessive occupation of nursing resources is avoided, medical errors and infection risks are reduced, and the medical experience of the patient is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent nursing technology, and in particular to an intelligent identification method and system for indwelling needle operation based on enhanced examination images and electronic equipment. Background Art

[0002] In the field of intelligent nursing technology, it mainly uses technologies such as artificial intelligence and big data to make nursing services more intelligent. Through machine learning and data analysis, the system can automatically identify and process a large amount of medical data, assist decision-making, reduce human errors, and improve nursing quality and efficiency. The key to enhanced examination of CT or magnetic resonance imaging is the use of contrast agents. Contrast agents enter the body through intravenous injection, which can highlight abnormal areas such as blood vessels, inflammation, and tumors, making the image clearer. In order to ensure that the contrast agent can enter the body smoothly and quickly, patients need to have a retention needle when doing enhanced CT or MRI. The puncture process of the retention needle is to insert the steel needle and the catheter into the blood vessel at the same time, fix the puncture needle, and then pull out the steel needle, leaving the catheter in the blood vessel, so the retention needle left on the patient in the end does not have a "needle". Therefore, when doing CT or MRI examinations, the retention needle is the main way to inject drugs when enhancing patient examinations.

[0003] During the examination, medical staff can quickly and safely inject contrast agent through an indwelling needle without the need for repeated punctures, reducing the patient's pain and the risk of complications.

[0004] The enhanced examination guidance system of the imaging department is an injection service system provided by the hospital for patients who need injections. It can provide patients with full-process intelligent guidance including registration, injection number calling, re-queueing, re-calling in the examination room, needle removal reminders, and electronic management of patient documents. It also supports re-entering the examination queue list after injection.

[0005] Although the patient examination assistance systems provided by these hospitals can provide patients with corresponding injection queuing and other management services when they receive indwelling needles, there are still the following clinical management issues for patients with indwelling needles:

[0006] First, after the contrast medium is quickly and safely injected through the indwelling needle, the patient has concerns and worries about the examination. He does not know how long the examination will take to be completed, whether the indwelling needle needs to be kept in place, and he cannot know the remaining injection time, that is, the remaining time for needle removal.

[0007] Secondly, the existing needle removal timing work needs to be continuously supervised by clinical nurses, so clinical nurses are required to guard or appear next to the patient for a long time and multiple times to monitor the remaining time for needle removal, which will take up a lot of nursing time and nursing resources, and reduce the management efficiency after the enhanced injection examination. In addition, many patients remove the indwelling needle in advance without examination. Summary of the invention

[0008] On the one hand, the present application proposes an intelligent identification method for an indwelling needle based on enhanced inspection images, comprising the following steps:

[0009] Obtain the patient's enhanced CT or MRI examination images and write them into the patient's folder;

[0010] The patient folder is monitored in real time by a timing system, and the CT or MRI enhanced examination image is identified. When a needle removal feature image is found in the CT or MRI enhanced examination image, the timing is triggered and the remaining time for needle removal is calculated, wherein the needle removal feature image is an image contrast feature in the CT or MRI enhanced examination image identified by the enhanced image detection model; and the needle removal monitoring system is notified at the same time;

[0011] The needle removal monitoring system generates a timing QR code of the needle removal time in real time, and saves it to the patient's folder after adding a timestamp;

[0012] Scan the timing QR code to check the remaining time for needle removal. When the needle removal time is reached, a needle removal notification is issued to the corresponding patient.

[0013] Furthermore, after the needle removal monitoring system generates a timing QR code of the needle removal time in real time and saves it to the patient folder after adding a timestamp, it also includes:

[0014] The generated timing QR code of each patient is sent to the patient's user end APP in real time;

[0015] or,

[0016] The generated timing QR code of each patient is sent to the QR code display terminal in real time.

[0017] Furthermore, the patient's enhanced CT or MRI examination images are obtained and written into the patient folder of the HIS system, including:

[0018] Log in to the enhanced examination guidance system of the imaging department and generate the patient's electronic medical record file, i.e., the patient folder, in the HIS system;

[0019] Through CT or MRI enhanced examination equipment, according to the preset sampling frequency, the patient's CT or MRI enhanced examination image photos are checked and collected and uploaded to the HIS system. The HIS system writes the CT or MRI enhanced examination image photos into the patient's electronic medical record file and binds it to the patient's medical ID.

[0020] Furthermore, the patient folder is monitored in real time by a timing system, and the CT or MRI enhanced examination image is identified, including:

[0021] Configuring the image detection frequency for the timing system to keep it synchronized with the sampling frequency;

[0022] The timing system sequentially monitors the CT or MRI enhanced examination images of the patient, and detects whether a needle removal feature image appears in the CT or MRI enhanced examination images based on an enhanced image detection model:

[0023] If it appears, go to the next step and trigger the timing;

[0024] Otherwise, continue monitoring.

[0025] Furthermore, the method for generating the enhanced image detection model includes:

[0026] Prepare a number of CT or MRI enhanced examination images with and without contrast, and CT or MRI ordinary examination images;

[0027] Perform feature engineering to extract CT or MRI enhanced image features and CT or MRI image features from the CT or MRI enhanced examination image photos and the CT or MRI ordinary examination image photos, respectively, and construct a training set;

[0028] Dividing the training set into corresponding training sets and validation sets according to a preset ratio;

[0029] Importing the training set into the CNN model, training and learning the CNN model according to preset optimization iteration conditions, and constructing the enhanced image detection model;

[0030] The enhanced image detection model is verified using the verification set:

[0031] If the enhanced image detection model is capable of distinguishing the CT or MRI enhanced image features from the CT or MRI image features, deploying the enhanced image detection model into the timing system;

[0032] Otherwise, retrain according to the above steps.

[0033] On the other hand, the present application proposes a system for intelligently identifying the operation of an indwelling needle based on enhanced inspection images, which is implemented based on the method for intelligently identifying the operation of an indwelling needle based on enhanced inspection images, and includes:

[0034] The enhanced examination guidance system of the imaging department is used by administrators to log in and generate electronic medical records of patients in the HIS system, namely patient folders;

[0035] CT or MRI enhanced examination equipment, used to examine and collect CT or MRI enhanced examination images of patients according to a preset sampling frequency and upload them to the HIS system, and the HIS system writes the CT or MRI enhanced examination images into the patient's electronic medical record and binds them to the patient's medical ID;

[0036] A timing system is used to monitor the patient folder in real time and identify the CT or MRI enhanced examination image photos. When a needle removal feature image is found in the CT or MRI enhanced examination image photos, the timing is triggered and the remaining time for needle removal is calculated, wherein the needle removal feature image is an image contrast feature in the CT or MRI enhanced examination image photos identified by the enhanced image detection model; the needle removal monitoring system is notified at the same time; and when the needle removal time is reached, a needle removal notification corresponding to the patient is sent to the user-side APP or nursing terminal;

[0037] The needle removal monitoring system is used to generate a timing QR code of the needle removal time in real time, and save it to the patient's folder after adding a timestamp;

[0038] The user-side APP is used to display the timing QR code to the QR code scanning terminal at the needle removal site, and the QR code scanning terminal scans the timing QR code and displays the remaining time for needle removal.

[0039] Furthermore, it also includes:

[0040] The QR code screen display terminal is used to display the patient's timing QR code. The user-side APP scans the timing QR code and displays the remaining time for needle removal on the user-side APP.

[0041] In another aspect, the present application further provides an electronic device, comprising:

[0042] processor;

[0043] a memory for storing processor-executable instructions;

[0044] Wherein, the processor is configured to implement the intelligent identification method of indwelling needle operation based on enhanced examination images when executing the executable instructions.

[0045] Technical effects of the present invention:

[0046] This application uses a machine learning model to establish an enhanced image detection model, so that when the patient is examined, the timing system can identify the CT or MRI enhanced examination image photos in the patient's folder (discover the contrast image features in the image, such as contrast color, texture, etc.), and intelligently trigger the timing system to start timing. Through the timing system, the patient folder is monitored in real time, and the CT or MRI enhanced examination image photos are identified. When the needle removal feature image appears in the CT or MRI enhanced examination image photos, the timing is triggered and the remaining time for needle removal is calculated, and the needle removal monitoring system is notified at the same time; when the needle removal time is reached, the needle removal notification corresponding to the patient is sent to the user-side APP or nursing terminal.

[0047] Therefore, it can intelligently realize needle removal detection and reminders in CT or MRI enhanced examinations, without the need for nurses to accompany patients for a long time to perform indwelling needle detection. The system can intelligently detect the contrast conditions and calculate the remaining time. It can intelligently manage and serve contrast detection patients and nurses, improve the management efficiency of enhanced injection examinations, and avoid excessive occupation of nursing resources. By judging the completion of the examination and starting the countdown and reminder of needle removal for patients, the management efficiency and safety of enhanced injection examinations can be improved, medical errors and infection risks can be reduced, and the patient's medical experience can be improved.

[0048] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0050] Figure 1 It is shown as a schematic diagram of the implementation process of the present invention;

[0051] Figure 2 Shown is a schematic diagram of an application system of the present invention;

[0052] Figure 3 Schematic diagram showing contrast-enhanced CT or MRI examination images (the upper figure is darker in color) and common CT or MRI examination images (the lower figure is lighter in color) collected by the present invention;

[0053] Figure 4 A schematic diagram of the model training process of the present invention is shown;

[0054] Figure 5 It is a schematic diagram showing the application of the electronic device of the present invention. DETAILED DESCRIPTION

[0055] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0056] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0057] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0058] Example 1

[0059] like Figure 1 As shown, on the one hand, the present application proposes an intelligent identification method for indwelling needle work based on enhanced inspection images, comprising the following steps:

[0060] S1. Obtain the patient's CT or MRI enhanced examination images and write them into the patient's folder;

[0061] S2. Real-time monitoring of the patient folder by a timing system, and identification of the CT or MRI enhanced examination image photos. When a needle removal feature image is found in the CT or MRI enhanced examination image photos, the timing is triggered and the remaining time for needle removal is calculated, wherein the needle removal feature image is an image contrast feature in the CT or MRI enhanced examination image photos identified by the enhanced image detection model; and the needle removal monitoring system is notified at the same time;

[0062] S3, the needle removal monitoring system generates a timing QR code of the needle removal time in real time, adds a timestamp and saves it to the patient's folder;

[0063] S4. Scan the timing QR code to check the remaining time for needle removal, and when the needle removal time is reached, issue a needle removal notification to the corresponding patient.

[0064] The present invention proposes a solution for needle removal timing based on intelligent recognition of contrast images. When a patient is examined, the timing system identifies the image photos of CT or MRI enhanced examination in the patient's folder and intelligently triggers the timing system to start timing; the needle removal timing starts according to the change of the patient's examination status.

[0065] Patients can check the remaining time for needle removal through the obtained QR code.

[0066] Specifically, at the time of the examination, the time starts when the patient's status changes from registered to matched after the examination in the examination room. Half an hour later, it will be displayed on the screen to remind the patient to remove the needle.

[0067] The enhanced patient examination timing process is as follows:

[0068] 1. Calling numbers

[0069] The examining doctor can call the patient who needs enhanced examination to the designated room to complete the relevant examination through the call page.

[0070] When the patient is examined, the timing system will identify the image photos in the patient's folder, intelligently trigger the timing system to start timing, and generate a QR code at the same time. There are two ways to obtain the QR code:

[0071] The first method: print it out through a printer;

[0072] The second method: push it to patients through the system.

[0073] 2. Needle removal reminder

[0074] Patients can check the remaining time for needle removal through the obtained QR code. There are two ways to check the QR code:

[0075] The first method is to set up a QR code scanning terminal at the needle removal site, where the patient scans the QR code and the terminal displays the remaining time.

[0076] The second method: Scan the QR code through WeChat on your mobile phone, and scan the QR code on the screen through the APP to enter the system to check the remaining time.

[0077] 3. Large screen reminder

[0078] When the needle removal time arrives, the large screen at the needle removal site will display the name of the needle that can be removed as a reminder.

[0079] The following will be combined with the attached Figure 2 The implementation principle of the present invention is specifically described with reference to the system.

[0080] In this embodiment, the CT or MRI enhanced inspection equipment or system can be provided by the hospital, and the user-side APP can be provided by the hospital and guide the patient to download it. Through the user-side APP, you can log in to the background imaging department enhanced inspection guidance system (a management system provided by the hospital background) to perform corresponding patient management. And administrators such as nursing staff can log in to the background imaging department enhanced inspection guidance system through nursing terminals such as PDA terminals or EDA terminal devices to perform corresponding enhanced inspection management.

[0081] The system is deployed with HIS electronic medical record system and timing system. The electronic medical record system is mainly used to generate electronic medical record files of patients and record the corresponding examination data; while the timing system is equipped with an enhanced image detection model, which can perform image recognition on CT or MRI enhanced examination images based on CNN convolutional neural network, so as to judge the contrast image features in the enhanced examination film, so as to judge whether to start injection of contrast agent: when the contrast image features appear in the image, it is determined that the injection of contrast agent has started, and the timing mechanism is triggered at this time, the timing system starts timing, and notifies the needle removal monitoring system to start needle removal monitoring.

[0082] In the present invention, a QR code is used to notify the remaining time for needle removal. The needle removal monitoring system can generate a QR code under the corresponding timestamp sequence through the timestamp system, and continuously keep the information updated. A QR code scanning terminal or a QR code screen display terminal can be set up next to the bed. The QR code scanning terminal can interact with the user-side APP. The user-side APP can log in to the system to view its own timing QR code and display it to the QR code scanning terminal. The QR code scanning terminal scans the code to obtain the patient's remaining time for needle removal. Another way is to display the patient's timing QR code through a QR code screen display terminal, and the user-side APP scans the QR code on the screen to display the remaining time for needle removal on the user-side APP.

[0083] The database in the system can be used for data storage of the background system, and the message middleware is mainly based on the message queue mechanism such as the KAFKA mechanism to queue and dispatch various message data.

[0084] The steps for timestamping can be:

[0085] Open the document or picture to which you want to add a timestamp;

[0086] Select the location where you want to add a timestamp;

[0087] Click the "Insert" menu and select the "Timestamp" option;

[0088] In the pop-up timestamp dialog box, select the appropriate time format;

[0089] After confirmation, click the "Insert" button and the timestamp will be added to the specified location.

[0090] Furthermore, after the needle removal monitoring system generates a timing QR code of the needle removal time in real time and saves it to the patient folder after adding a timestamp, it also includes:

[0091] The generated timing QR code of each patient is sent to the patient's user end APP in real time;

[0092] or,

[0093] The generated timing QR code of each patient is sent to the QR code display terminal in real time.

[0094] See the above description for details.

[0095] Furthermore, the patient's enhanced CT or MRI examination images are obtained and written into the patient folder of the HIS system, including:

[0096] Log in to the enhanced examination guidance system of the imaging department and generate the patient's electronic medical record file, i.e., the patient folder, in the HIS system;

[0097] Through CT or MRI enhanced examination equipment, according to the preset sampling frequency, the patient's CT or MRI enhanced examination image photos are checked and collected and uploaded to the HIS system. The HIS system writes the CT or MRI enhanced examination image photos into the patient's electronic medical record file and binds it to the patient's medical ID.

[0098] Build the patient's electronic medical record file, which can be operated by nurses and other administrators.

[0099] The sampling frequency of CT or MRI enhanced inspection equipment can be set by the administrator and the corresponding inspection work can be performed.

[0100] Furthermore, the patient folder is monitored in real time by a timing system, and the CT or MRI enhanced examination image is identified, including:

[0101] Configuring the image detection frequency for the timing system to keep it synchronized with the sampling frequency;

[0102] The timing system sequentially monitors the CT or MRI enhanced examination images of the patient, and detects whether a needle removal feature image appears in the CT or MRI enhanced examination images based on an enhanced image detection model:

[0103] If it appears, go to the next step and trigger the timing;

[0104] Otherwise, continue monitoring.

[0105] Each time a CT or MRI enhanced examination is performed (continuous contrast examination or multiple contrast examinations are required, which is determined by the clinician), the system will save the CT or MRI enhanced examination images of the corresponding frequency. Therefore, the timing system also needs a needle removal feature image, which can specifically include corresponding contrast features such as whether the corresponding contrast image color appears in the image, the gray value changes, texture changes, etc. Because the image features such as texture and color are different before and after the contrast injection is completed and not injected, the timing system can identify the contrast injection of the indwelling needle based on the image detection results recognized by the model. When it is found that the image features (texture, color, gray value, etc.) in the image begin to change, it indicates that the contrast has begun. The timing system can synchronously update the timing QR code based on the image recognition results detected by the model. In the early stage, when the corresponding needle removal image features begin to appear in the first recognized image, it indicates that the contrast injection has begun, and the timing system starts timing. In the system, when the timing starts, the administrator can also pre-configure the corresponding injection time in the system, and the system automatically calculates the remaining time for needle removal. The information in the QR code can be continuously updated, and the system is responsible for maintenance and data update.

[0106] like Figure 4 As shown, further, the method for generating the enhanced image detection model includes:

[0107] Prepare a number of CT or MRI enhanced examination images with and without contrast, and CT or MRI ordinary examination images;

[0108] Perform feature engineering to extract CT or MRI enhanced image features and CT or MRI image features from the CT or MRI enhanced examination image photos and the CT or MRI ordinary examination image photos, respectively, and construct a training set;

[0109] Dividing the training set into corresponding training sets and validation sets according to a preset ratio;

[0110] Importing the training set into the CNN model, training and learning the CNN model according to preset optimization iteration conditions, and constructing the enhanced image detection model;

[0111] The enhanced image detection model is verified using the verification set:

[0112] If the enhanced image detection model is capable of distinguishing the CT or MRI enhanced image features from the CT or MRI image features, deploying the enhanced image detection model into the timing system;

[0113] Otherwise, retrain according to the above steps.

[0114] like Figure 3Shown are the collected CT or MRI enhanced examination images with and without contrast (the upper image is darker in color) and CT or MRI ordinary examination images (the lower image is lighter in color).

[0115] The steps for image feature training using machine learning models such as CNN can be:

[0116] Data preparation: Collect image datasets and preprocess the data, including normalization, resizing, data augmentation, etc.

[0117] Design network structure: determine the structure of the convolutional neural network, including convolutional layers, pooling layers, fully connected layers, etc.;

[0118] Build a model: Use a deep learning framework (such as TensorFlow or PyTorch) to build a convolutional neural network model;

[0119] Loss function and optimizer: Choose a loss function (such as cross entropy loss) and an optimizer (such as Adam or SGD);

[0120] Training model: Divide the data set into a training set and a validation set, use the training set to train the model, and monitor the performance of the validation set;

[0121] Model tuning: Adjust model parameters such as learning rate, batch size, network structure, etc. according to the performance of the validation set;

[0122] Model evaluation: Use the test set to evaluate the model’s performance indicators such as accuracy and recall;

[0123] Model saving and deployment: Save the trained model as a file and deploy it in actual applications.

[0124] In this embodiment, the specific CT or MRI enhanced examination images with and without contrast (the upper image is darker in color) and the CT or MRI ordinary examination images (the lower image is lighter in color) are prepared by the administrator. The feature engineering, extracting image features from the image, can be performed using the CNN method.

[0125] The specific model training is completed by the administrator, and can be implemented in combination with the architecture, training, and application principles of the CNN model. This embodiment will not be described in detail.

[0126] Therefore, the present application utilizes CNN, i.e., convolutional neural network, to train and learn the CT or MRI enhanced image features and the CT or MRI image features in the CT or MRI enhanced examination image photos and the CT or MRI ordinary examination image photos, respectively, and trains and constructs an enhanced image detection model that can distinguish between CT or MRI enhanced examination image photos and CT or MRI ordinary examination image photos (feature recognition). In this way, when examining a patient, the timing system can intelligently trigger the timing system to start timing by identifying the CT or MRI enhanced examination image photos in the patient's folder (discovering the contrast image features in the image, such as contrast color, texture, etc.).

[0127] It should be noted that although CNN is used as an example, those skilled in the art will understand that the present disclosure should not be limited thereto. In fact, users can flexibly set machine learning models such as RNN or random forest according to actual application scenarios, as long as the technical functions of the present application can be implemented according to the above technology.

[0128] Obviously, those skilled in the art should understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory (Flash Memory), a hard disk (Hard Disk Drive, abbreviated as: HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above-mentioned types of memory.

[0129] Example 2

[0130] Based on the implementation principle of Example 1, on the other hand, the present application proposes an intelligent recognition system for indwelling needle work based on enhanced inspection images, which is implemented based on the intelligent recognition method for indwelling needle work based on enhanced inspection images described in Example 1, including:

[0131] The enhanced examination guidance system of the imaging department is used by administrators to log in and generate electronic medical records of patients in the HIS system, namely patient folders;

[0132] CT or MRI enhanced examination equipment, used to examine and collect CT or MRI enhanced examination images of patients according to a preset sampling frequency and upload them to the HIS system, and the HIS system writes the CT or MRI enhanced examination images into the patient's electronic medical record and binds them to the patient's medical ID;

[0133] A timing system is used to monitor the patient folder in real time and identify the CT or MRI enhanced examination image photos. When a needle removal feature image is found in the CT or MRI enhanced examination image photos, the timing is triggered and the remaining time for needle removal is calculated, wherein the needle removal feature image is an image contrast feature in the CT or MRI enhanced examination image photos identified by the enhanced image detection model; the needle removal monitoring system is notified at the same time; and when the needle removal time is reached, a needle removal notification corresponding to the patient is sent to the user-side APP or nursing terminal;

[0134] The needle removal monitoring system is used to generate a timing QR code of the needle removal time in real time, and save it to the patient's folder after adding a timestamp;

[0135] The user-side APP is used to display the timing QR code to the QR code scanning terminal at the needle removal site, and the QR code scanning terminal scans the timing QR code and displays the remaining time for needle removal.

[0136] Furthermore, it also includes:

[0137] The QR code screen display terminal is used to display the patient's timing QR code. The user-side APP scans the timing QR code and displays the remaining time for needle removal on the user-side APP.

[0138] The modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0139] Example 3

[0140] like Figure 5 As shown, further, in another aspect, the present application also proposes an electronic device, including:

[0141] processor;

[0142] a memory for storing processor-executable instructions;

[0143] Wherein, the processor is configured to implement the method for intelligently identifying the operation of an indwelling needle based on enhanced examination images as described in Example 1 when executing the executable instructions.

[0144] The electronic device of the embodiment of the present disclosure includes a processor and a memory for storing processor executable instructions. The processor is configured to implement the method for intelligently identifying the operation of an indwelling needle based on enhanced inspection images described in the first embodiment above when executing the executable instructions.

[0145] Here, it should be noted that the number of processors can be one or more. At the same time, the electronic device in the embodiment of the present disclosure may also include an input device and an output device. Among them, the processor, memory, input device and output device may be connected through a bus or in other ways, which are not specifically limited here.

[0146] The memory, as a computer-readable storage medium, can be used to store software programs, computer executable programs and various modules, such as the program or module corresponding to the method for intelligently identifying the operation of an indwelling needle based on enhanced inspection images in the embodiment of the present disclosure. The processor executes various functional applications and data processing of the electronic device by running the software programs or modules stored in the memory.

[0147] The input device can be used to receive input numbers or signals. The signal can be a key signal related to user settings and function control of the device / terminal / server. The output device can include a display device such as a display screen.

[0148] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for intelligently identifying indwelling needle work based on enhanced inspection images, characterized in that: The steps include: Obtain the patient's enhanced CT or MRI examination images and write them into the patient's folder; The patient folder is monitored in real time by a timing system, and the CT or MRI enhanced examination image is identified. When a needle removal feature image is found in the CT or MRI enhanced examination image, the timing is triggered and the remaining time for needle removal is calculated, wherein the needle removal feature image is an image contrast feature in the CT or MRI enhanced examination image identified by the enhanced image detection model; and the needle removal monitoring system is notified at the same time; The needle removal monitoring system generates a timing QR code of the needle removal time in real time, and saves it to the patient's folder after adding a timestamp; Scan the timing QR code to check the remaining time for needle removal. When the needle removal time is reached, a needle removal notification is issued to the corresponding patient.

2. According to claim 1, a method for intelligently identifying indwelling needle operation based on enhanced inspection images is characterized in that: After the needle removal monitoring system generates a timing QR code of the needle removal time in real time and saves it to the patient folder after adding a timestamp, it also includes: The generated timing QR code of each patient is sent to the patient's user end APP in real time; or, The generated timing QR code of each patient is sent to the QR code display terminal in real time.

3. According to claim 1, a method for intelligently identifying indwelling needle operation based on enhanced inspection images is characterized in that: Obtain the patient's enhanced CT or MRI examination images and write them into the patient folder of the HIS system, including: Log in to the enhanced examination guidance system of the imaging department and generate the patient's electronic medical record file, i.e., the patient folder, in the HIS system; Through CT or MRI enhanced examination equipment, according to the preset sampling frequency, the patient's CT or MRI enhanced examination image photos are checked and collected and uploaded to the HIS system. The HIS system writes the CT or MRI enhanced examination image photos into the patient's electronic medical record file and binds it to the patient's medical ID.

4. The method for intelligently identifying the operation of an indwelling needle based on enhanced inspection images according to claim 3 is characterized in that: The patient folder is monitored in real time by a timing system, and the CT or MRI enhanced examination image photographs are identified, including: Configuring the image detection frequency for the timing system to keep it synchronized with the sampling frequency; The timing system sequentially monitors the CT or MRI enhanced examination images of the patient, and detects whether a needle removal feature image appears in the CT or MRI enhanced examination images based on an enhanced image detection model: If it appears, go to the next step and trigger the timing; Otherwise, continue monitoring.

5. The method for intelligently identifying the operation of an indwelling needle based on enhanced inspection images according to claim 4 is characterized in that: The method for generating the enhanced image detection model comprises: Prepare a number of CT or MRI enhanced examination images with and without contrast, and CT or MRI ordinary examination images; Perform feature engineering to extract CT or MRI enhanced image features and CT or MRI image features from the CT or MRI enhanced examination image photos and the CT or MRI ordinary examination image photos, respectively, and construct a training set; Dividing the training set into corresponding training sets and validation sets according to a preset ratio; Importing the training set into the CNN model, training and learning the CNN model according to preset optimization iteration conditions, and constructing the enhanced image detection model; The enhanced image detection model is verified using the verification set: If the enhanced image detection model is capable of distinguishing the CT or MRI enhanced image features from the CT or MRI image features, deploying the enhanced image detection model into the timing system; Otherwise, retrain according to the above steps.

6. An intelligent recognition system for indwelling needle operation based on enhanced inspection images, implemented based on the intelligent recognition method for indwelling needle operation based on enhanced inspection images as described in any one of claims 1 to 5, characterized in that: include: The enhanced examination guidance system of the imaging department is used by administrators to log in and generate electronic medical records of patients in the HIS system, namely patient folders; CT or MRI enhanced examination equipment, used to examine and collect CT or MRI enhanced examination images of patients according to a preset sampling frequency and upload them to the HIS system, and the HIS system writes the CT or MRI enhanced examination images into the patient's electronic medical record and binds them to the patient's medical ID; A timing system is used to monitor the patient folder in real time and identify the CT or MRI enhanced examination image photos. When a needle removal feature image is found in the CT or MRI enhanced examination image photos, the timing is triggered and the remaining time for needle removal is calculated, wherein the needle removal feature image is an image contrast feature in the CT or MRI enhanced examination image photos identified by the enhanced image detection model; the needle removal monitoring system is notified at the same time; and when the needle removal time is reached, a needle removal notification corresponding to the patient is sent to the user-side APP or nursing terminal; The needle removal monitoring system is used to generate a timing QR code of the needle removal time in real time, and save it to the patient's folder after adding a timestamp; The user-side APP is used to display the timing QR code to the QR code scanning terminal at the needle removal site, and the QR code scanning terminal scans the timing QR code and displays the remaining time for needle removal.

7. The intelligent recognition system for indwelling needle operation based on enhanced inspection images according to claim 6 is characterized in that: Also includes: The QR code screen display terminal is used to display the patient's timing QR code. The user-side APP scans the timing QR code and displays the remaining time for needle removal on the user-side APP.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; Wherein, the processor is configured to implement an intelligent method for identifying the operation of an indwelling needle based on enhanced examination images as described in any one of claims 1 to 5 when executing the executable instructions.

Images