Intelligent self-adaptive arteriopuncture decompression monitoring system

Abstract

The invention relates to the technical field of medical monitoring, in particular to an intelligent self-adaptive arteriopuncture decompression monitoring system. The image acquisition module is used for acquiring image information of a punctured limb in real time; the image processing module is used for preprocessing the acquired image and enhancing the image contrast; segmenting the blood vessel; the deviation condition of the blood vessel center curve is detected, and the deviation amount or the deviation direction is output; the judgment module is used for establishing a prediction model, generating a decompression demand according to a blood vessel image analysis result, and generating a control command to adjust the position and pressure of the compressor according to the decompression demand; and the pressure reduction control module is used for adjusting the pressure of the compressor or sending a monitoring prompt according to the control command. According to the technical scheme, the arterial puncture decompression monitoring effect and safety can be improved.

Description

Technical Field

[0001] The invention relates to the technical field of medical monitoring, and in particular to an intelligent adaptive arterial puncture decompression monitoring system. Background Art

[0002] In medical practice, arterial puncture is a common diagnostic and treatment method, widely used in various medical scenarios such as hemodialysis, angiography, and interventional surgery. However, after arterial puncture, in order to prevent bleeding and maintain stable blood flow, it is usually necessary to compress the puncture point to stop bleeding. In this process, the strength and duration of compression are crucial: insufficient compression may cause continuous bleeding, while excessive compression may cause complications such as limb ischemia and nerve damage.

[0003] Currently, decompression monitoring after arterial puncture mainly relies on the experience and manual operation of medical staff, which is achieved by regularly observing and adjusting the position and pressure of the compressor. However, this method has many shortcomings. First, manual monitoring is difficult to ensure continuity and accuracy, and medical staff may suffer from poor monitoring effects due to fatigue, negligence or differences in judgment. Second, for patients who require long-term monitoring, manual monitoring not only increases the workload of medical staff, but may also affect the normal progress of other medical work.

[0004] In recent years, with the rapid development of medical imaging technology and computer technology, image processing and machine learning algorithms have been widely used in the medical field, providing new solutions for arterial puncture decompression monitoring. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent adaptive arterial puncture decompression monitoring system, which can improve the effect and safety of arterial puncture decompression monitoring.

[0006] To achieve the above-mentioned purpose, the embodiment of the present disclosure provides an intelligent adaptive arterial puncture decompression monitoring system, including an image acquisition module for real-time acquisition of image information of the punctured limb; The image processing module is used to pre-process the collected images, enhance the image contrast, segment the blood vessels, detect the deviation of the blood vessel center curve, and output the deviation amount or deviation direction; The judgment module is used to establish a prediction model, generate a decompression requirement based on the vascular image analysis results, and generate a control command to adjust the position and pressure of the compressor based on the decompression requirement; The decompression control module is used to adjust the compressor pressure or issue a monitoring reminder according to the control command.

[0007] Beneficial effects of the basic solution: The image acquisition module captures the image information of the punctured limb in real time, and the high-precision image preprocessing and vascular segmentation technology of the image processing module are combined to monitor the vascular status. The judgment module uses a prediction model to dynamically generate decompression requirements based on the results of vascular image analysis, which helps reduce complications such as thrombosis and bleeding, promote faster recovery of patients, and is suitable for monitoring different patients.

[0008] The decompression control module automatically adjusts the position and pressure of the compressor according to the control command generated by the judgment module, eliminating the need for frequent manual adjustments and reducing the workload. At the same time, the system can issue monitoring reminders and promptly notify medical staff to take intervention measures to ensure patient safety when abnormal deviations are detected.

[0009] As an implementable preferred solution, the image processing module adjusts the grayscale distribution of the image through histogram equalization; stretches the contrast range of the image through contrast stretching; and enhances the edge information of the image through sharpening.

[0010] As an implementable preferred solution, the image processing module performs blood vessel segmentation by one of the following methods: Based on the threshold, the pixels in the image are divided into foreground and background by setting the threshold. For the vascular image, the threshold is set as the grayscale difference between the blood vessel and the surrounding tissue. Segmentation based on regions; by calculating the neighborhood information of each pixel in the image, pixels with similar features are grouped into the same region; Edge-based segmentation detects edge information in the image and extracts the boundary between the blood vessel and the surrounding tissue, thereby achieving blood vessel segmentation.

[0011] As an implementable preferred solution, the image processing module detects the deviation of the blood vessel center curve by one of the following methods: Detection based on feature points: by extracting feature points from the blood vessel image and calculating the matching degree between the feature points, the deviation of the blood vessel center curve can be determined. Detection is performed based on template matching, by matching the blood vessel image with the preset template and calculating the matching degree, thereby determining the deviation of the blood vessel center curve; The detection is performed based on the model, and the automatic detection of the deviation of the blood vessel center curve is realized by training the model.

[0012] As an implementable preferred solution, the judgment module is used to establish a prediction model, and generate a decompression requirement according to the vascular image analysis result, and generate a control command to adjust the position and pressure of the compressor according to the decompression requirement, including the following contents: Collect a large amount of vascular image data, including images of normal blood vessels, high-pressure blood vessels, and low-pressure blood vessels in different states; pre-process the images, including denoising, contrast enhancement, and extracting key features in the images, including vascular diameter, blood flow velocity, and vascular wall thickness; Set thresholds or rules for determining whether blood vessels need decompression, use a large amount of preprocessed historical feature data and corresponding decompression demand labels as training sets, use machine learning algorithms for training and learning, train the prediction model, and establish a prediction model.

[0013] As an implementable preferred solution, the decompression control module includes a pressure sensor and a solenoid valve. The opening of the solenoid valve is controlled according to the control command to adjust the pressure of the compressor. At the same time, the pressure value of the compressor is monitored through the pressure sensor. The pressure of the compressor is fine-tuned according to the feedback pressure value and control instructions. The decompression control module is also used to issue monitoring reminders.

[0014] As an implementable preferred solution, it also includes a data recording module for recording key data during arterial puncture decompression, including image data, pressure data and time data.

[0015] As an implementable preferred solution, the image acquisition module also includes a parameter adjustment submodule, which monitors the ambient lighting information in real time through a light sensor, the lighting information including light intensity, light distribution and light color, and adjusts the acquisition parameters of the image acquisition module according to the lighting information.

[0016] As an implementable preferred solution, the image acquisition module also includes a skin color monitoring submodule, which detects the skin color through a skin color recognition algorithm; the image acquisition module adjusts the color temperature of the light source of the image acquisition module through a color temperature adjustment algorithm according to the actual color temperature of the environment and the skin color, so that it matches the skin color.

[0017] As an implementable preferred solution, the image processing module is used to check and correct the skin color in the captured image according to the skin color detection result of the image acquisition module, and match different vascular image preprocessing strategies according to the skin color. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 This is a schematic diagram of the architecture of the intelligent adaptive arterial puncture decompression monitoring system. DETAILED DESCRIPTION

[0019] In order to make the technical solution and advantages of the present application clearer, the technical solution of the present invention will be further described in detail below in conjunction with the accompanying drawings. It will be understood that the specific embodiments described herein are only partial embodiments of the present invention, which are only used to explain the present application, rather than to limit the present application. It should be noted that the technical features or combinations of technical features described in the following embodiments should not be considered isolated, and they can be combined with each other to achieve better technical effects. The same reference numerals appearing in the drawings of the following embodiments represent the same features or components, which can be applied to different embodiments.

[0020] In addition, unless otherwise defined, the technical terms or scientific terms used in the description of the present invention should have the common meanings understood by those skilled in the art in the art to which the present invention belongs.

[0021] The present invention is further described in detail below in conjunction with the accompanying drawings: Embodiment 1 Reference Figure 1 , an intelligent adaptive arterial puncture decompression monitoring system, including an image acquisition module, an image processing module, a judgment module, a decompression control module and a data recording module.

[0022] The image acquisition module is used to collect image information of the punctured limb in real time. It is preferred to use a high-precision sensor, such as a high-definition camera, to ensure that the collected image is clear and accurate. The high-definition camera has high resolution and high sensitivity, and can capture detailed information such as blood vessels and skin, providing a reliable data basis for subsequent image processing. The high-definition camera is installed in a suitable position so that the image of the punctured limb can be clearly captured. At the same time, the camera and the image processing module are connected by wire or wireless means to ensure real-time transmission of image data.

[0023] The image processing module is used to perform preprocessing, segmentation, center curve offset detection, etc. on the collected images to extract key vascular information, including an image enhancement submodule, a vascular segmentation submodule, and an offset detection submodule.

[0024] The image enhancement submodule is used to enhance the contrast of the image, improve the visibility of the blood vessels, and make the boundary between the blood vessels and the surrounding tissues clearer, which is convenient for subsequent segmentation and detection. In this embodiment, the grayscale distribution of the image is adjusted by histogram equalization to make the grayscale value of the image more uniform, thereby enhancing the contrast of the image. By contrast stretching, the contrast range of the image is stretched to make the details of the image more prominent. By sharpening, the edge information of the image is enhanced to make the edge of the blood vessel clearer.

[0025] The vascular segmentation submodule is used to segment the blood vessels. The threshold-based segmentation method divides the pixels in the image into foreground and background by setting a threshold. For vascular images, the threshold is set to the grayscale difference between the blood vessels and the surrounding tissues, thereby achieving blood vessel segmentation. The region-based segmentation method calculates the neighborhood information of each pixel in the image and classifies pixels with similar features into the same region, thereby achieving blood vessel segmentation. The edge-based segmentation method extracts the boundary between the blood vessels and the surrounding tissues by detecting the edge information in the image, thereby achieving blood vessel segmentation.

[0026] The offset detection submodule is used to detect the offset of the vascular center curve and output information such as the offset amount and / or offset direction. Specifically, the offset of the vascular center curve is determined by extracting feature points in the vascular image and calculating the matching degree between the feature points. The offset of the vascular center curve can also be determined by matching the vascular image with a preset template and calculating the matching degree. The automatic detection of the offset of the vascular center curve can also be achieved by training the model.

[0027] The judgment module is used to judge whether decompression is needed based on the vascular image analysis results sent by the image processing module, and adjust the position and pressure of the compressor according to the offset and / or offset direction. A large amount of data is trained and learned to establish a prediction model, judge the decompression requirement based on the vascular analysis image, and generate corresponding control commands based on the decompression requirement, including the following: Collect a large amount of vascular image data, including images of normal blood vessels, high-pressure blood vessels, low-pressure blood vessels, etc. Perform preprocessing on the images, including denoising, contrast enhancement, cropping, etc., to improve image quality. Extract key features in the image, such as blood vessel diameter, blood flow velocity, and blood vessel wall thickness.

[0028] Set thresholds or rules for determining whether blood vessels need decompression, use a large amount of preprocessed historical feature data and corresponding decompression demand labels (such as decompression degree, decompression type, etc.) as training sets, use machine learning algorithms for training and learning, train the prediction model, and establish a prediction model.

[0029] The decompression control module is used to adjust the compressor according to the control command, including hardware devices such as pressure sensors and solenoid valves to achieve precise control of the compressor pressure. When the judgment module outputs a decompression command, the decompression control module can reduce the pressure of the compressor by controlling the opening of the solenoid valve. At the same time, the pressure value of the compressor is monitored in real time through the pressure sensor. The decompression control module fine-tunes the compressor pressure according to the real-time feedback pressure value and control instructions to ensure accurate and timely decompression.

[0030] The decompression control module is also used to issue a monitoring reminder. When receiving the control command from the judgment module to adjust the compressor position, the decompression control module will promptly issue a monitoring reminder to instruct the compressor position to be adjusted. The monitoring reminder sends a sound, light signal or text message through a buzzer, indicator light or display screen.

[0031] The data recording module is used to record key data during arterial puncture decompression, including image data, pressure data, time data, etc., to facilitate subsequent analysis, auditing, scientific research and other work.

[0032] Embodiment 2 The technical feature that distinguishes this embodiment from the above-mentioned embodiments is that the image acquisition module also includes a parameter adjustment submodule, which monitors the lighting information of the environment in real time through a light sensor, the lighting information including light intensity, light distribution and light color (color temperature), and adjusts the acquisition parameters of the image acquisition module according to the lighting information.

[0033] For example, in the case of insufficient light, the parameter adjustment submodule controls the lighting equipment to increase the light intensity to ensure the clarity of image acquisition. In the case of excessive light, the parameter adjustment submodule adjusts the exposure parameters of the acquisition equipment to avoid overexposure and loss of image information, thereby improving the image quality and reducing the subsequent preprocessing steps. At the same time, the effect of preprocessing will also be improved due to more appropriate image illumination.

[0034] Since the technical solution makes targeted adjustments to the exposure of the captured image during the acquisition phase to ensure that the exposure of the captured image is normal, if a deep learning model is subsequently trained for blood vessel segmentation or centerline detection, there is no need to conduct targeted training for images under different lighting conditions, thus saving computing resources. For the recognition method described in Example 1, the normal exposure of the captured image can also ensure the effectiveness of the method and the accuracy of the results.

[0035] Embodiment 3 The technical features of this embodiment that differ from the above embodiments are that multiple light source parameters are added and the fusion recognition method is When adjusting the acquisition parameters, the image acquisition module takes pictures to obtain multi-light source parameter image data under different illumination information, and uses a high-resolution camera to take pictures of the target under different illumination information parameter combinations.

[0036] Train the corresponding image recognition models under a variety of different acquisition parameters, recognize the image data under each parameter respectively, and obtain the recognition results.

[0037] The acquisition parameters and recognition results of all images are combined to form an input, which is input into the fusion neural network model, and the final recognition result is output, which is used as the reference result for the initial acquisition and recognition; When the recognition is subsequently performed under the normal adjusted light source, the normal image and the reference result are input and the recognition result is output.

[0038] This technical solution makes full use of the dimming process and integrates the results under multiple light source parameters to improve recognition accuracy. In the subsequent processing process, the movement of personnel or doctors and the adjustment of acquisition parameters may cause changes in the color or lighting environment of local image acquisition. The fusion neural network model will use the reference results of the initial acquisition and recognition to dynamically adjust and optimize to improve the recognition accuracy in this case.

[0039] Embodiment 4 The technical feature that distinguishes this embodiment from the above-mentioned embodiment is that the image acquisition module further includes a skin color monitoring submodule, which detects the skin color through a skin color recognition algorithm, specifically including the following contents: First, the image is preprocessed, including grayscale and denoising operations, to improve the image quality, and the preprocessed image is converted from RGB color space to YCbCr color space. The formula is as follows:

[0040]

[0041]

[0042] In the YCbCr color space, each pixel in the image is judged according to the parameters of the skin color model to determine whether it belongs to the skin color area. The skin color model is a model established based on the statistical data of a large number of samples to determine whether the distribution pattern of skin color belongs to skin color or is similar to skin color. In this embodiment, a threshold range is set according to the skin color model, and the chromaticity value of the pixel is compared with the threshold range to determine whether it belongs to the skin color area.

[0043] The segmented skin color area is post-processed to eliminate mis-segmentation and noise. The post-processing steps include morphological processing and connected region analysis. Morphological processing includes operations such as dilation, erosion, opening and closing operations to smooth and fill the skin color area. Connected region analysis performs connectivity analysis on the segmented skin color area to remove isolated noise points and small areas.

[0044] The processed skin color area is output, and the skin color is recognized.

[0045] The image acquisition module uses a color temperature adjustment algorithm to automatically adjust the color temperature of the light source of the image acquisition module according to the actual color temperature of the environment and skin color, so that it matches the human skin color, thereby reducing image color distortion, capturing skin texture more clearly, and improving image quality.

[0046] In addition, by segmenting the skin color area, the area that needs to be processed by the blood vessel segmentation submodule is further reduced, thereby improving the processing speed and accuracy.

[0047] The image processing module is also used to check and correct the skin color in the collected image according to the skin color detection result of the image acquisition module, so as to restore the accuracy of the color of the collected image and ensure the accuracy of blood vessel information extraction and recognition.

[0048] The image processing module will also match different vascular image preprocessing strategies according to skin color. For darker skin colors, the brightness or contrast will be increased to enhance details; for lighter skin colors, the brightness or contrast will be reduced to avoid overexposure.

[0049] The disclosed embodiment also provides an intelligent adaptive arterial puncture decompression monitoring method, which utilizes the above-mentioned intelligent adaptive arterial puncture decompression monitoring system.

[0050] A person of ordinary skill in the art can understand that the implementation of all or part of the process in an intelligent adaptive arterial puncture decompression monitoring method can be completed by instructing related hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the process of each embodiment of an intelligent adaptive arterial puncture decompression monitoring method. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0051] The above contents are only embodiments of the present invention. The common sense such as the known specific structures and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to explain the content of the claims.

Claims

1. An intelligent adaptive arterial puncture decompression monitoring system, characterized in that: include: The image acquisition module is used to collect image information of the punctured limb in real time; The image processing module is used to pre-process the collected images and enhance the image contrast; Segment the blood vessels; detect the deviation of the blood vessel center curve, and output the deviation amount or deviation direction; The judgment module is used to establish a prediction model, generate a decompression requirement based on the vascular image analysis results, and generate a control command to adjust the position and pressure of the compressor based on the decompression requirement; The decompression control module is used to adjust the compressor pressure or issue a monitoring reminder according to the control command.

2. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: The image processing module adjusts the grayscale distribution of the image through histogram equalization; stretches the contrast range of the image through contrast stretching; and enhances the edge information of the image through sharpening.

3. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: The image processing module performs blood vessel segmentation by one of the following methods: Based on the threshold, the pixels in the image are divided into foreground and background by setting the threshold. For the vascular image, the threshold is set as the grayscale difference between the blood vessel and the surrounding tissue. Segmentation based on regions; by calculating the neighborhood information of each pixel in the image, pixels with similar features are grouped into the same region; Edge-based segmentation detects edge information in the image and extracts the boundary between the blood vessel and the surrounding tissue, thereby achieving blood vessel segmentation.

4. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: The image processing module detects the deviation of the blood vessel center curve by one of the following methods: Detection based on feature points: by extracting feature points from the blood vessel image and calculating the matching degree between the feature points, the deviation of the blood vessel center curve can be determined. Detection is performed based on template matching, by matching the blood vessel image with the preset template and calculating the matching degree, thereby determining the deviation of the blood vessel center curve; The detection is performed based on the model, and the automatic detection of the deviation of the blood vessel center curve is realized by training the model.

5. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: The judgment module is used to establish a prediction model and generate a decompression requirement based on the results of vascular image analysis. The control command is generated according to the decompression requirement to adjust the position and pressure of the compressor, including the following: Collect a large amount of vascular image data, including images of normal blood vessels, high-pressure blood vessels, and low-pressure blood vessels in different states; pre-process the images, including denoising, contrast enhancement, and extracting key features in the images, including vascular diameter, blood flow velocity, and vascular wall thickness; Set thresholds or rules for determining whether blood vessels need decompression, use a large amount of preprocessed historical feature data and corresponding decompression demand labels as training sets, use machine learning algorithms for training and learning, train the prediction model, and establish a prediction model.

6. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: The decompression control module includes a pressure sensor and a solenoid valve, which controls the opening of the solenoid valve according to the control command to adjust the pressure of the compressor. At the same time, the pressure value of the compressor is monitored through the pressure sensor, and the pressure of the compressor is fine-tuned according to the feedback pressure value and control instructions. The decompression control module is also used to issue monitoring reminders.

7. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: It also includes a data recording module for recording key data during the arterial puncture decompression process, including image data, pressure data and time data.

8. The intelligent adaptive arterial puncture decompression monitoring system according to claim 1 is characterized in that: The image acquisition module also includes a parameter adjustment submodule, which monitors the lighting information of the environment in real time through a light sensor. The lighting information includes light intensity, light distribution and light color, and adjusts the acquisition parameters of the image acquisition module according to the lighting information.

9. The intelligent adaptive arterial puncture decompression monitoring system according to claim 8, characterized in that: The image acquisition module also includes a skin color monitoring submodule, which detects the skin color through a skin color recognition algorithm; the image acquisition module uses a color temperature adjustment algorithm to adjust the color temperature of the light source of the image acquisition module according to the actual color temperature of the environment and the skin color to match the skin color.

10. The intelligent adaptive arterial puncture decompression monitoring system according to claim 9, characterized in that: The image processing module is used to check and correct the skin color in the collected image according to the skin color detection result of the image acquisition module, and match different blood vessel image preprocessing strategies according to the skin color.

Images