Acites drainage monitoring method and device

Abstract

The invention is suitable for the technical field of ascites drainage, and particularly relates to an ascites drainage monitoring method and equipment, and the method comprises the steps: obtaining the ascites drainage data and drainage image data of a target monitoring object, and providing an accurate basis for the subsequent safety evaluation. And based on the ascites drainage data of the target monitoring object, determining first monitoring information of the target monitoring object, and identifying a potential drainage problem. And second monitoring information of the target monitoring object is obtained based on the drainage image data of the target monitoring object, and potential risks in the drainage process are monitored and identified through visual features. According to the first monitoring information and the second monitoring information of the target monitoring object, the ascites drainage process of the target monitoring object is evaluated, the safety state of the target monitoring object is determined, the ascites drainage monitoring cost is reduced, and the consistency and accuracy of monitoring results are improved.

Description

Technical Field

[0001] The present application belongs to the technical field of ascites drainage, and in particular, relates to an ascites drainage monitoring method and device. Background Art

[0002] Ascites drainage refers to abdominal drainage, which is a common surgical operation technique. If the operation is not standardized, it may cause bleeding, drainage material slipping into the abdominal cavity, secondary infection, drainage tube breakage, nerve damage and other adverse effects.

[0003] In the prior art, the monitoring process of ascites drainage often relies on on-site manual methods for monitoring, requiring specialized medical staff to continuously monitor the patient's drainage status. The human resource cost is high, and the experience and judgment standards of different medical staff may vary, resulting in increased ascites drainage monitoring costs and low consistency and accuracy of monitoring results. Summary of the invention

[0004] The embodiments of the present application provide a method and device for monitoring ascites drainage, which can solve the problem of relying on on-site manual monitoring during the monitoring of ascites drainage, resulting in increased ascites drainage monitoring costs and low consistency and accuracy of monitoring results.

[0005] In a first aspect, an embodiment of the present application provides a method for monitoring ascites drainage, comprising: Acquire ascites drainage data and drainage image data of the target monitored object; wherein the drainage image data is used to reflect the real-time drainage status of the target monitored object; Determining first monitoring information of the target monitoring object based on the ascites drainage data of the target monitoring object; Based on the drainage image data of the target monitoring object, obtaining second monitoring information of the target monitoring object; wherein the first monitoring information and the second monitoring information are different; The ascites drainage process of the target monitoring object is evaluated according to the first monitoring information and the second monitoring information of the target monitoring object, and the safety status of the target monitoring object is determined.

[0006] The above technical solutions in the embodiments of the present application have at least the following technical effects: The ascites drainage monitoring method provided in the embodiment of the present application provides an accurate basis for subsequent safety assessments by obtaining the ascites drainage data and drainage image data of the target monitoring object. Based on the ascites drainage data of the target monitoring object, the first monitoring information of the target monitoring object is determined to identify potential drainage problems. Based on the drainage image data of the target monitoring object, the second monitoring information of the target monitoring object is obtained, and the potential risks in the drainage process are monitored and identified through visual features. Based on the first monitoring information and the second monitoring information of the target monitoring object, the ascites drainage process of the target monitoring object is evaluated to determine the safety status of the target monitoring object, reduce the ascites drainage monitoring cost, and improve the consistency and accuracy of the monitoring results.

[0007] In a second aspect, an embodiment of the present application provides an ascites drainage monitoring system, comprising: An acquisition unit, used to acquire ascites drainage data and drainage image data of a target monitoring object; wherein the drainage image data is used to reflect the real-time drainage status of the target monitoring object; A first monitoring unit, configured to determine first monitoring information of the target monitoring object based on the ascites drainage data of the target monitoring object; A second monitoring unit, configured to obtain second monitoring information of the target monitoring object based on the drainage image data of the target monitoring object; wherein the first monitoring information and the second monitoring information are different; An evaluation unit is used to evaluate the ascites drainage process of the target monitoring object based on the first monitoring information and the second monitoring information of the target monitoring object, and determine the safety status of the target monitoring object.

[0008] In a third aspect, an embodiment of the present application provides an ascites drainage monitoring device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method as described in any one of the above aspects when executing the computer program.

[0009] In a fourth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an ascites drainage monitoring device, the ascites drainage monitoring device is enabled to perform the method of any one of the above aspects.

[0010] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the above aspects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0012] Figure 1 It is a flow chart of a method for monitoring ascites drainage provided in one embodiment of the present application; Figure 2 It is a schematic diagram of the operation of the ascites drainage monitoring method provided in one embodiment of the present application; Figure 3 is a flow chart of step S300 in the ascites drainage monitoring method provided in one embodiment of the present application; Figure 4 is a flow chart of step S400 in the ascites drainage monitoring method provided in one embodiment of the present application; Figure 5 is a structural schematic diagram of an ascites drainage monitoring system provided in an embodiment of the present application; Figure 6 It is a structural schematic diagram of an ascites drainage monitoring device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0013] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0014] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0015] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0016] As used in the specification of this application and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if the described condition or event is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce the described condition or event is detected" or "in response to detecting the described condition or event" depending on the context.

[0017] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0018] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0019] In the prior art, the monitoring process of ascites drainage often relies on on-site manual methods for monitoring, requiring specialized medical staff to continuously monitor the patient's drainage status. The human resource cost is high, and the experience and judgment standards of different medical staff may vary, resulting in increased ascites drainage monitoring costs and low consistency and accuracy of monitoring results.

[0020] To solve the above problems, an embodiment of the present application provides a method and device for monitoring ascites drainage. In this method, by obtaining the ascites drainage data and drainage image data of the target monitoring object, an accurate basis is provided for subsequent safety assessment. Based on the ascites drainage data of the target monitoring object, the first monitoring information of the target monitoring object is determined to identify potential drainage problems. Based on the drainage image data of the target monitoring object, the second monitoring information of the target monitoring object is obtained, and the potential risks in the drainage process are monitored and identified through visual features. Based on the first monitoring information and the second monitoring information of the target monitoring object, the ascites drainage process of the target monitoring object is evaluated, the safety status of the target monitoring object is determined, the ascites drainage monitoring cost is reduced, and the consistency and accuracy of the monitoring results are improved.

[0021] The ascites drainage monitoring method provided in the embodiment of the present application can be applied to an ascites drainage monitoring device. In this case, the ascites drainage monitoring device is the executor of the ascites drainage monitoring method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the ascites drainage monitoring device.

[0022] For example, the ascites drainage monitoring device may be an ultra-mobile personal computer (UMPC), a netbook, a desktop computer, a computer, a laptop computer, a communication device, a computing device, a satellite wireless device, or the like.

[0023] In order to better understand the ascites drainage monitoring method provided in the embodiment of the present application, the specific implementation process of the ascites drainage monitoring method provided in the embodiment of the present application is exemplarily introduced below.

[0024] Figure 1 A schematic flow chart of a method for monitoring ascites drainage provided in an embodiment of the present application is shown. Figure 2 The schematic diagram of the operation of the ascites drainage monitoring method provided in the embodiment of the present application is shown, and the ascites drainage monitoring method includes: S100, obtaining ascites drainage data and drainage image data of the target monitored object; wherein the drainage image data is used to reflect the real-time drainage status of the target monitored object.

[0025] It can be understood that the ascites drainage data of the target monitoring object mainly refers to the digital information related to ascites drainage recorded during the monitoring process, including the drainage speed and drainage time, which can be obtained by recording and uploading data through electronic monitoring equipment or sensors. The target monitoring object refers to the target object or patient who needs to be closely monitored. The drainage speed represents the speed at which the ascites flows out, and the drainage time records the duration of the drainage process. The drainage image data is the visual information of the ascites drainage process recorded in real time by an image acquisition device (such as a camera or an infrared camera). Through the image data, the working status of the drainage device and the ascites collection device can be observed, reflecting the actual drainage situation, including whether the equipment is normal and whether the drainage is smooth.

[0026] S200: Determine first monitoring information of the target monitoring object based on the ascites drainage data of the target monitoring object.

[0027] It is understandable that, based on the collected ascites drainage data, such as drainage speed and drainage time, the drainage process of the target monitoring object can be preliminarily analyzed through a preset algorithm or model, and the first monitoring information can be obtained. The first monitoring information reflects the basic state of the drainage process, such as the stability and continuity of the drainage. The first monitoring information may involve content such as whether the drainage is normal, whether it exceeds the preset safety range, etc.

[0028] In a possible implementation, the ascites drainage data includes an ascites drainage speed and an ascites drainage time; S200, based on the ascites drainage data of the target monitoring object, determining first monitoring information of the target monitoring object, including: S210, determining a real-time drainage volume of the target monitoring object based on the ascites drainage speed and ascites drainage time of the target monitoring object.

[0029] It is understood that the real-time drainage volume of the target monitored object can be obtained by multiplying the drainage speed (such as the volume of fluid flowing out per minute or per hour) by the drainage time (such as the time elapsed during the monitoring process) in real time. The real-time drainage volume reflects the total amount of ascites flowing out and is used to evaluate whether the real-time drainage volume is within the desired drainage target.

[0030] S220, comparing the ascites drainage speed and the real-time drainage volume with the preset threshold ranges respectively to determine the risk point information of the target monitored object; wherein the risk point information is used to reflect the real-time risk situation of the ascites drainage speed and the real-time drainage volume.

[0031] It can be understood that risk point information refers to a detailed description of potential dangers or abnormal conditions identified after analyzing various types of ascites drainage data during drainage monitoring. A safe drainage speed and drainage volume range can be set according to medical standards or historical data, such as a single drainage volume not exceeding 350ml. If the real-time drainage speed or drainage volume is not within the preset threshold range, there is a risk, such as drainage too quickly may cause patient discomfort or abdominal cavity injury. By comparing the drainage data with these thresholds, potential risk points can be automatically identified and risk point information can be generated to provide a basis for further analysis.

[0032] S230, determining first monitoring information of the target monitoring object based on the risk point information of the target monitoring object; wherein the first monitoring information is used to reflect the quantity of the risk point information.

[0033] It can be understood that the first monitoring information is a summary of the ascites drainage data monitoring. It not only contains a single data, but also contains all risk point information and the number of risk point information. For example, if multiple risk points are detected during the drainage process in different time periods or different areas, the summary of the first monitoring information will provide important data support for subsequent safety assessments and interventions. The identified risk point information can be classified and counted, the number of risk points in each category can be calculated, and the overall summary can be performed. The first monitoring information is generated based on statistical data, and the risk level in the drainage process can be judged through the first monitoring information.

[0034] For example, assume that after analysis, the following risk point information is identified: Risk points: 2 Drainage speed is too fast: 1 time Excessive drainage: 1 time Before determining the first monitoring information of the target monitoring object, the method further includes: S240, generating a risk warning signal based on the risk point information of the target monitoring object.

[0035] With this setting, a corresponding risk warning signal can be generated based on the risk point information identified from the drainage data and drainage monitoring, which is used to monitor the health status of the target monitoring object in real time and warn of potential risks in a timely manner. The risk warning signal is used to reflect the risk status during the ascites drainage process. The risk warning signal can be triggered in multiple ways, such as: Real-time alerts: displayed on the control panel or terminal to indicate possible risks.

[0036] Sound and light signal instructions: The corresponding sound and light signals are controlled by sound and light signal instructions.

[0037] Email or SMS notification: Alert relevant medical staff or monitoring personnel for quick response.

[0038] S300, obtaining second monitoring information of the target monitoring object based on the drainage image data of the target monitoring object; wherein the first monitoring information and the second monitoring information are different.

[0039] It can be understood that the drainage image data reflects the visual drainage process, which may include the equipment status, changes in the patient's body shape, the working condition of the ascites collection device, etc. The second monitoring information is different from the first monitoring information. The second monitoring information mainly focuses on the results extracted from the image data. Please refer to Figure 3 , such as whether the device is operating normally, whether the ascites has abnormal color or level changes, the relative relationship between the device and the patient's body position, etc. Through the analysis of image data, detailed visual feedback on ascites drainage can be provided.

[0040] In a possible implementation, S300, obtaining second monitoring information of the target monitoring object based on the drainage image data of the target monitoring object includes: S310, dividing the drainage image data of the target monitoring object into blocks to obtain a plurality of block image data of the drainage image data.

[0041] It can be understood that drainage image data contains a lot of visual information. In order to analyze the image efficiently, the image data can be segmented into multiple blocks, each of which focuses on a specific area. For example, the image can be divided into three main parts: the target monitoring object, the drainage tube, and the ascites collection device. The analysis of each area helps to evaluate its operating status separately without confusing the information in other areas.

[0042] Optionally, S310, dividing the drainage image data of the target monitoring object into blocks to obtain a plurality of block image data of the drainage image data, including: S311, performing image preprocessing on the drainage image data of the target monitoring object to determine image features of the drainage image data.

[0043] It can be understood that image preprocessing is a key step to ensure the accuracy of subsequent image analysis results. Preprocessing operations can include image denoising, brightness adjustment, contrast enhancement, etc. to enhance important features in the image and reduce the interference of environmental noise on the analysis. Image preprocessing can be performed by Gaussian filtering or median filtering. Image features can include object edges, morphological changes, color distribution, etc., which are helpful for subsequent identification and analysis. Gray level co-occurrence matrix (GLCM) or local binary pattern (LBP) can be applied to extract image features of drainage image data.

[0044] S312, identifying the drainage image data according to the image features of the drainage image data, and determining a plurality of target blocks corresponding to the drainage image data.

[0045] It can be understood that according to the image features, key objects and areas in the image are identified, such as the patient's body, drainage tube, ascites collection device, etc. Multiple target blocks can be accurately separated from the image through object recognition algorithms, image processing technology, etc., providing a basis for subsequent abnormal point detection and monitoring evaluation.

[0046] Exemplarily, S312, identifying the drainage image data according to the image features of the drainage image data, and determining a plurality of target blocks corresponding to the drainage image data, includes: S3121, identifying the drainage image data according to image features of the drainage image data, and identifying the target monitoring object, drainage tube, and ascites collection device in the drainage image data.

[0047] It can be understood that image processing algorithms such as edge detection and morphological analysis can be used. The input drainage image data is grayed, the color image is converted into a grayscale image, the complexity of the data is reduced, and an edge detection algorithm (such as Canny edge detection) is used to identify the boundary features in the image. The results of edge detection reflect the contour information of the target object in the image and provide a basis for subsequent steps. After obtaining the edge features, the integrity of the contour can be further optimized through morphological operations (such as dilation and erosion) to reduce noise interference. For target monitoring objects, drainage tubes, and ascites collection devices, preliminary classification and labeling can be performed by geometric features (such as shape, area, and proportion) to determine the existence and location of these key targets.

[0048] S3122, according to the target monitoring object, drainage tube, and ascites collecting device in the drainage image data, respectively determine the circumscribed rectangle of the target monitoring object, the circumscribed rectangle of the drainage tube, and the circumscribed rectangle of the ascites collecting device in the drainage image data.

[0049] It can be understood that the generation of the circumscribed rectangle can be achieved by finding the minimum circumscribed rectangle of each target area. This can be done by calculating the coordinates of the boundary pixel points of the target area, and by extracting the minimum and maximum x, y coordinate values ​​of the area, thereby determining the coordinates of the upper left corner and the lower right corner of the rectangle. The circumscribed rectangle can be optimized according to the specific shape characteristics of the target area, such as applying a rotated circumscribed rectangle to the inclined area to better fit the target shape, so that the circumscribed rectangles of the target monitoring object, drainage tube and ascites collection device are clearly marked in the drainage image, providing a clear range for subsequent area extraction.

[0050] S3123, based on the circumscribed rectangle of the target monitoring object, the circumscribed rectangle of the drainage tube, and the circumscribed rectangle of the ascites collecting device in the drainage image data, a plurality of target blocks corresponding to the drainage image data are obtained.

[0051] It can be understood that the image sub-region corresponding to each circumscribed rectangle can be directly determined as an independent block image, i.e., a target block, based on the coordinate information of the circumscribed rectangle, and the precise boundary of each target block can be determined. For example, for a drainage tube, its upper and lower connecting parts can be included in the block to maintain the integrity of the region, and these block images can be organized into a structured data set, each block corresponding to a specific target area.

[0052] S313, obtaining a plurality of block image data of the drainage image data based on a plurality of target blocks corresponding to the drainage image data.

[0053] It can be understood that based on the precise boundaries of the target blocks corresponding to each bounding rectangle information that has been generated, the original drainage image data can be processed by using the regional cropping technology to extract the pixel values ​​corresponding to each target area to form a new independent image block. For example, the block image data generation process can be achieved by directly cropping the regional data of the bounding rectangle, and the matrix index can be used to locate the specific position of the target monitoring object in each frame of the image.

[0054] Exemplarily, S313, based on the multiple target blocks corresponding to the drainage image data, obtaining multiple block image data of the drainage image data includes: S3131, based on the multiple target blocks corresponding to the drainage image data, the drainage image data is edited to obtain the first block image data corresponding to the target monitoring object in the drainage image data, the second block image data corresponding to the drainage tube, and the third block image data corresponding to the ascites collection device; wherein the first block image data, the second block image data, and the third block image data are continuous frame images used to reflect the conditions of the corresponding areas.

[0055] It can be understood that based on the precise boundaries of each target block that has been generated, the original drainage image is processed by using the regional cropping technology, and the pixel values ​​corresponding to each target area are extracted to form a new independent image block. For example, the generation process of the first block can be achieved by directly cropping the regional data of the circumscribed rectangle, which uses the matrix index to locate the specific position of the target monitoring object in each frame of the image. Similarly, the generation method of the second block and the third block is the same. The same cropping and editing operations can be performed on each frame of the image. It can be completed in batches using automated scripts, and the core process includes frame reading, cropping, and frame sequence saving. For frame reading, an image processing library (such as OpenCV or Pillow) can be used to extract images frame by frame from the video data and sort the frames according to the time axis. For the cropping operation, the image area of ​​each frame is segmented one by one using the known circumscribed rectangle coordinates to generate a block image sequence of continuous frames. The data format of the block image must be consistent during the saving stage to facilitate subsequent loading and analysis. Each block image sequence can be stored as a set of files arranged by frame number or directly encoded as a video stream file to reduce storage space. Motion tracking algorithms (such as optical flow or correlation tracking algorithms) can be used to dynamically adjust the boundaries of the circumscribed rectangle to ensure that the cropped area always accurately covers the target. For the results of image editing, in order to further improve the analysis efficiency, each block image sequence can be standardized, including steps such as uniform size adjustment, color space correction, and noise removal. The generated first block image data, second block image data, and third block image data correspond to the continuous frame images of the target monitoring object, drainage tube, and ascites collection device, respectively. By cropping by region and processing continuous frames, the independence and integrity of key visual information are ensured, which lays an important prerequisite for efficient image analysis.

[0056] S320, performing an outlier analysis on each block image data of the drainage image data to determine outlier point information of each block image data; wherein the outlier point information is used to reflect an abnormal situation corresponding to the block image data.

[0057] It can be understood that the outlier analysis aims to identify possible problems in each block of drainage image data. It can reveal potential abnormalities by detecting the features of each block image data. Each block image can be used as an analysis object, and the information of the time dimension and the space dimension can be combined to accurately locate and describe the outlier information. Each block image data is subjected to denoising and standardization, such as applying bilateral filtering to retain edge features while eliminating noise; secondly, segmentation and feature extraction are performed, such as using a watershed algorithm or a region growing algorithm to extract the boundary information of key areas in each block. In the outlier analysis, each block image data needs to be combined with a feature extraction method for a specific scene, such as morphological feature detection, dynamic texture analysis, etc. For dynamic changes within the block, the pixel changes of consecutive frames can be calculated by the inter-frame difference method. The generation of outlier information is a summary of each block image based on the analysis results, including location, time and type information. For example, outliers may include "abnormal drainage tube morphology, location: (x, y)" or "joint range of motion exceeds expectations, time frame: t", providing accurate data support for subsequent comprehensive evaluation.

[0058] Optionally, S320, performing an outlier analysis on each block of image data of the drainage image data to determine outlier information of each block of image data includes: S321, performing key point recognition on the first block image data of the drainage image data to determine the human body joint positions of the target monitoring object in the first block image data.

[0059] It is understood that the boundary information in the first block image data can be extracted by edge detection algorithm, for example, using Canny edge detection method to extract contour lines in the image. A recognition algorithm based on geometric features (such as Hough transform) can search for shape features (such as circle or ellipse) that conform to the characteristics of human joints in a specific area, and by determining the distribution of these geometric features, the human joint position of the target monitoring object is determined and output in the form of pixel coordinates.

[0060] S322, performing continuous frame image processing on the first block image data according to the human body joint position of the target monitoring object in the first block image data to determine the pixel displacement of the human body joint position of the target monitoring object in the first block image data.

[0061] It can be understood that after determining the human joint position of the target monitoring object, the continuous frames of the first block image data are processed, the changes of the human joints in the continuous frames are analyzed, and the pixel displacement is determined. First, the joint positions in the continuous frames are matched with the reference frames, and the displacement vector of the joint is obtained by calculating the coordinate change of each joint point (for example, from (x1, y1) to (x2, y2)). Template matching or optical flow method can be used to track the motion trajectory of the joint to achieve high-precision pixel displacement calculation. Sparse optical flow (such as Lucas-Kanade method) or dense optical flow (such as Farneback method) can be used. By performing displacement analysis on the joint positions in continuous frames, dynamic change information can be extracted to provide support for the calculation of subsequent motion amplitudes.

[0062] S323, determining the movement amplitude of the target monitoring object based on the pixel displacement of the human body joint position of the target monitoring object in the first block image data.

[0063] It can be understood that the motion amplitude of the target monitoring object can be further calculated based on the pixel displacement of the human joint position of the target monitoring object in the first block image number. The motion amplitude can be obtained by calculating the displacement vector modulus of the joint point, which are the coordinates of the joint in the reference frame and the target frame respectively. If the movement of the joint involves changes in multiple directions, the motion amplitudes of all frames can be compared to determine the maximum vector modulus in continuous time as the motion amplitude of the target monitoring object. The motion amplitude calculation method based on pixel displacement can intuitively reflect the movement of the target monitoring object and provide a basis for the analysis of abnormal points.

[0064] S324, determining abnormal point information of the first block image data based on the motion amplitude of the target monitoring object.

[0065] It is understandable that the normal range of motion amplitude can be predefined, for example, by setting a threshold value based on historical data or statistical methods. If the motion amplitude exceeds this range, it is considered that an abnormal point has occurred. For example, when the motion amplitude is too large, it may indicate a violent movement. By comparing the motion amplitude with the threshold, a series of abnormal point information is generated. The abnormal point information may include a timestamp, a motion amplitude value, and an abnormal category. Finally, the abnormal point information will be summarized and stored to provide key input data for the safety status assessment of the target monitoring object.

[0066] Optionally, S320, performing an outlier analysis on each block of the drainage image data to determine outlier information of each block of the image data includes: S325, performing edge detection on the second block image data of the drainage image data to determine the morphological information of the drainage tube in the second block image data.

[0067] It is understandable that an edge detection algorithm (such as Sobel, Canny, Prewitt, etc.) may be used to extract edge features in the image to obtain the morphological information of the drainage tube in the second block image data.

[0068] Exemplarily, the Canny algorithm can obtain the morphological information of the drainage tube in the second block image data by calculating the gradient, detecting the area with significant grayscale changes in the image, and retaining the true edge points through non-maximum suppression. Double thresholds can be applied to separate strong edges and weak edges, and the separated edge points can be assembled into a complete boundary morphology through edge connection. The final output is a binary image containing the drainage tube boundary information. Based on the extracted edge information, the shape, position and size of the drainage tube can be further analyzed. These morphological information provides an important basis for subsequent abnormality analysis.

[0069] S326, determining abnormal point information of the second block image data based on the morphological information of the drainage tube in the second block image data.

[0070] It is understood that the geometric features of the drainage tube, such as length, width, curvature and shape consistency, can be determined by the extracted morphological information. It can be described by mathematical methods, such as using polygonal approximation to calculate the morphological parameters of the drainage tube, and comparing these morphological parameters with the preset normal range. The definition of the normal range can be based on historical data, representing the morphological features of the drainage tube under normal conditions. For each geometric feature, if its value deviates from the preset range, it can be marked as an abnormal point. For example, excessive curvature may indicate a blocked pipe, the geometric feature shows an abnormal intersection, and an abnormal reduction in width may mean that the tube wall is compressed and deformed.

[0071] Optionally, S320, performing an outlier analysis on each block of image data of the drainage image data to determine outlier information of each block of image data includes: S327, performing image feature extraction on the third block image data of the drainage image data, and determining the ascites color information and ascites level information collected by the ascites collection device in the third block image data.

[0072] It can be understood that the image can be converted from RGB to a color space more suitable for analysis (such as HSV or Lab) through color space conversion, so that color features are easier to separate. Based on the converted image, a segmentation algorithm is used to extract the ascites area, such as using a threshold segmentation method to separate the pixels of the ascites area. When extracting color information, the color distribution of the ascites area can be calculated, for example, by statistically analyzing the hue distribution in its HSV space to obtain the dominant component of the color. At the same time, the saturation and brightness distribution of the color can also be used as auxiliary features to describe the transparency or turbidity of the ascites. For the extraction of liquid level information, the edge of the ascites can be analyzed by morphological methods or histogram projection. The horizontal line of the liquid level can be determined by edge detection, and the interfering features (such as reflections) can be eliminated by morphological operations, and the liquid level height can be mapped to the actual physical height range to obtain the ascites level information.

[0073] S328, performing a change rate analysis on the ascites level information collected by the ascites collecting device in the third block image data within a preset time period, and determining the ascites level change information corresponding to the ascites collecting device in the third block image data.

[0074] It can be understood that the liquid level height data within the preset time period is sorted by timestamp to generate a time series. Then, the height change rate between each two consecutive time points is calculated, and the formula is: ΔH / Δt=(H(t2)−H(t1)) / t2−t1, where ΔH / Δt represents the liquid level change rate, H(t1) and H(t2) are the liquid level heights at two time points, and t1 and t2 are the corresponding times. If the liquid level change rate deviates significantly from the normal value range (for example, a too fast drop may indicate a leak, and a too slow drop may indicate a blockage), it can be recorded as abnormal change information. In this way, the dynamic changes in the liquid level of the ascites collection device can be fully monitored and analyzed.

[0075] S329, determining abnormal point information of the third block image data according to the ascites level change information corresponding to the ascites collecting device in the third block image data, the ascites color information and the ascites level information collected by the ascites collecting device.

[0076] It can be understood that the abnormal points of the third block image data can be determined by analyzing the ascites color information, liquid level information and liquid level change rate respectively. Pattern matching is performed on the liquid level information and the change rate to identify abnormal situations that do not match the historical data. For example, if the liquid level changes rapidly in a short period of time, the color is abnormal (such as red indicates blood mixing), etc., there may be serious problems. The abnormal features are integrated into abnormal point information, which includes the time, location and type of the abnormal point. The abnormal point information finally generated can be used for the alarm system or further analysis steps, providing an important basis for the evaluation of the operating status of the ascites collection device.

[0077] S330, obtaining second monitoring information of the target monitoring object according to the abnormal point information of all block image data.

[0078] It can be understood that the abnormal point information of all block image data can be aggregated to generate the second monitoring information of the target monitoring object. The second monitoring information reflects whether the overall state of the target monitoring object is abnormal by aggregating the time series data and spatial distribution data of the abnormal points. The second monitoring information provides a different dimension from the first monitoring information through image data analysis.

[0079] Before obtaining the second monitoring information of the target monitoring object, the method further includes: S340, generating an abnormal warning signal based on the abnormal point information of all block image data.

[0080] With this configuration, a corresponding risk warning signal can be generated based on the abnormal point information identified from all block image data, which is used to monitor the health status of the target monitoring object in real time and warn of potential risks in a timely manner. The abnormal warning signal is used to warn of the risk status during the ascites drainage process. The abnormal warning signal can be triggered in multiple ways, such as: Real-time alerts: displayed on the control panel or terminal to indicate possible risks.

[0081] Sound and light signal instructions: The corresponding sound and light signals are controlled by sound and light signal instructions.

[0082] Email or SMS notification: Alert relevant medical staff or monitoring personnel for quick response.

[0083] S400, evaluating the ascites drainage process of the target monitoring object according to the first monitoring information and the second monitoring information of the target monitoring object, and determining the safety status of the target monitoring object.

[0084] It can be understood that the two types of monitoring information (first monitoring information and second monitoring information) extracted from the drainage image data can be used. Figure 4 , evaluate the ascites drainage process of the target monitored object to determine its safety status. By comprehensively analyzing various types of data from the two monitoring information, it is evaluated whether there are potential safety hazards, and then it is determined whether there are abnormalities in the ascites drainage process of the target monitored object, which helps to fully reflect the ascites drainage process. The evaluation process can adopt certain evaluation models or rules, such as threshold-based judgment rules, statistical analysis based on empirical data, or machine learning algorithms to determine the safety status of the target monitored object, reduce the cost of ascites drainage monitoring, and improve the consistency and accuracy of monitoring results.

[0085] In a possible implementation, S400, based on the first monitoring information and the second monitoring information of the target monitoring object, evaluating the ascites drainage process of the target monitoring object to determine the safety status of the target monitoring object includes: S410: Determine drainage monitoring abnormality information of the target monitoring object according to the first monitoring information and the second monitoring information of the target monitoring object.

[0086] It can be understood that drainage monitoring abnormal information is determined based on the first monitoring information and the second monitoring information of the target monitoring object. The drainage monitoring abnormal information is an evaluation data that integrates the first monitoring information and the second monitoring information, which can enhance the accuracy of monitoring.

[0087] Optionally, S410, determining drainage monitoring abnormality information of the target monitoring object according to the first monitoring information and the second monitoring information of the target monitoring object, includes: S411, constructing a hierarchical path analysis map of the target monitoring object according to the first monitoring information and the second monitoring information of the target monitoring object; wherein the hierarchical path analysis map is used to reflect the security risk distribution of the target monitoring object; It can be understood that a graph structure, namely a hierarchical path analysis graph, can be constructed based on the two types of monitoring information (first monitoring information and second monitoring information) of the target monitoring object. The hierarchical path analysis graph is similar to a network, which represents the hierarchical relationship between various types of monitoring information. Each level represents a different dimension of monitoring information. By combining the first monitoring information and the second monitoring information (such as image data, joint position, etc.), a dynamic multi-level analysis graph can be obtained, that is, only the risk points or abnormal points identified in the first monitoring information and the second monitoring information will become a level, and the level will be continuously updated to reflect the real-time change distribution during the monitoring process.

[0088] For example, when constructing a graph, the concepts of "nodes" and "edges" in graph theory can be used, where a node represents each monitoring data point or area, and an edge represents the relationship or influence between different monitoring data. Different algorithms, such as hierarchical clustering and path algorithms, can be introduced to construct complex hierarchical paths.

[0089] S412, determining the occurrence intensity of each level in the hierarchical path analysis map based on the hierarchical path analysis map of the target monitoring object; It is understood that each level in the map can be analyzed to determine its "occurrence intensity". That is, the frequency of occurrence of each identified risk point or abnormal point throughout the monitoring process will be quantified by the intensity value. The occurrence intensity helps to judge the urgency of the impact of the level.

[0090] S413, based on the occurrence intensity of each level in the hierarchical path analysis map, determine the drainage monitoring abnormality information of the target monitoring object.

[0091] It can be understood that the probability of occurrence of each level is calculated. Assuming that there are n levels in the spectrum, the occurrence intensity P of each level i is i Its strength H i The sum of all levels of strength H t The ratio is calculated as: P i =P i / H t , where H t is the sum of the intensities of all levels in the spectrum: , based on the occurrence intensity P of each level i , we can calculate an entropy-like value S to quantify the complexity or uncertainty of the graph, i.e., drainage monitoring abnormal information. The calculation formula of drainage monitoring abnormal information S is similar to the Shannon entropy formula: ,in, Is a logarithmic function, usually taking the natural logarithm (log e ). This formula represents the uncertainty degree of the occurrence intensity at different levels in the spectrum, and the safety status of the target monitoring object can be judged based on the drainage monitoring abnormal information S.

[0092] S420, determining a safety status of the target monitoring object based on the drainage monitoring abnormality information of the target monitoring object.

[0093] It can be understood that the safety status of the target monitoring object can be further judged based on the determined drainage monitoring abnormal information, and the safety status of the target monitoring object can be judged based on the calculated drainage monitoring abnormal information S. For example: when the S value is large, it means that the monitoring data has a high uncertainty, there are many abnormal situations, and the drainage status of the target monitoring object is unstable. When the S value is small, it means that the monitoring data is relatively stable, there are fewer abnormal points, and the drainage status of the target monitoring object is relatively normal. By evaluating the safety status through drainage monitoring abnormal information, real-time evaluation of the drainage process is achieved, reducing the cost of ascites drainage monitoring and improving the consistency and accuracy of monitoring results.

[0094] Corresponding to the ascites drainage monitoring method of the above embodiment, the embodiment of the present application also provides an ascites drainage monitoring system, and each unit of the system can implement each step of the ascites drainage monitoring method. Figure 5 A structural block diagram of an ascites drainage monitoring system provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0095] Reference Figure 5 , the ascites drainage monitoring system includes: An acquisition unit, used to acquire ascites drainage data and drainage image data of a target monitoring object; wherein the drainage image data is used to reflect the real-time drainage status of the target monitoring object; A first monitoring unit, configured to determine first monitoring information of the target monitoring object based on the ascites drainage data of the target monitoring object; A second monitoring unit, configured to obtain second monitoring information of the target monitoring object based on the drainage image data of the target monitoring object; wherein the first monitoring information and the second monitoring information are different; An evaluation unit is used to evaluate the ascites drainage process of the target monitoring object based on the first monitoring information and the second monitoring information of the target monitoring object, and determine the safety status of the target monitoring object.

[0096] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0097] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0098] The present application also provides an ascites drainage monitoring device, Figure 6 This is a schematic diagram of the structure of an ascites drainage monitoring device provided in one embodiment of the present application. Figure 6 As shown, the ascites drainage monitoring device 6 of this embodiment includes: at least one processor 60 ( Figure 6 Only one is shown), at least one memory 61 ( Figure 6Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the ascites drainage monitoring device 6 implements the steps in any of the above-mentioned ascites drainage monitoring method embodiments, or implements the functions of each unit in the above-mentioned system embodiments.

[0099] Exemplarily, the computer program 62 may be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the ascites drainage monitoring 6.

[0100] The ascites drainage monitoring device 6 can be a computing device or terminal device such as a desktop computer, a notebook, a PDA, and a cloud server. The ascites drainage monitoring device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Figure 6 It is only an example of the ascites drainage monitoring device 6 and does not constitute a limitation of the ascites drainage monitoring device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, buses, etc.

[0101] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0102] In some embodiments, the memory 61 may be an internal storage unit of the ascites drainage monitoring device 6, such as a hard disk or memory of the ascites drainage monitoring device 6. In other embodiments, the memory 61 may also be an external storage device of the ascites drainage monitoring device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the ascites drainage monitoring device 6. Further, the memory 61 may also include both an internal storage unit and an external storage device of the ascites drainage monitoring device 6. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0103] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0104] An embodiment of the present application provides a computer program product. When the computer program product is run on an ascites drainage monitoring device, the ascites drainage monitoring device is enabled to implement the steps in any of the above-mentioned method embodiments.

[0105] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the ascites drainage monitoring device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0106] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0107] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0108] In the embodiments provided in the present application, it should be understood that the disclosed ascites drainage monitoring system / ascites drainage monitoring equipment and method can be implemented in other ways. For example, the ascites drainage monitoring system / ascites drainage monitoring equipment embodiment described above is only schematic, for example, the division of the units is only a kind of logical function division, and there can be other division modes during actual implementation, for example, multiple units or components can be combined or can be integrated into another system, or some features can be ignored, or not executed. Another point, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for monitoring ascites drainage, characterized in that: include: Acquire ascites drainage data and drainage image data of the target monitored object; wherein the drainage image data is used to reflect the real-time drainage status of the target monitored object; Determining first monitoring information of the target monitoring object based on the ascites drainage data of the target monitoring object; Based on the drainage image data of the target monitoring object, obtaining second monitoring information of the target monitoring object; wherein the first monitoring information and the second monitoring information are different; The ascites drainage process of the target monitoring object is evaluated according to the first monitoring information and the second monitoring information of the target monitoring object, and the safety status of the target monitoring object is determined.

2. The ascites drainage monitoring method according to claim 1, characterized in that: The ascites drainage data include ascites drainage speed and ascites drainage time; The determining the first monitoring information of the target monitoring object based on the ascites drainage data of the target monitoring object includes: Determining a real-time drainage volume of the target monitoring object based on the ascites drainage speed and the ascites drainage time of the target monitoring object; Comparing the ascites drainage speed and the real-time drainage volume with preset threshold intervals respectively to determine the risk point information of the target monitoring object; wherein the risk point information is used to reflect the real-time risk situation of the ascites drainage speed and the real-time drainage volume; Based on the risk point information of the target monitoring object, first monitoring information of the target monitoring object is determined; wherein the first monitoring information is used to reflect the quantity of the risk point information.

3. The ascites drainage monitoring method according to claim 1, characterized in that: The obtaining second monitoring information of the target monitoring object based on the drainage image data of the target monitoring object includes: Dividing the drainage image data of the target monitoring object into blocks to obtain a plurality of block image data of the drainage image data; Performing an outlier analysis on each of the block image data of the drainage image data to determine outlier point information of each of the block image data; wherein the outlier point information is used to reflect the abnormal situation corresponding to the block image data; The second monitoring information of the target monitoring object is obtained according to the abnormal point information of all the block image data.

4. The ascites drainage monitoring method according to claim 3, characterized in that: The dividing the drainage image data of the target monitoring object into blocks to obtain a plurality of block image data of the drainage image data includes: performing image preprocessing on the drainage image data of the target monitoring object to determine image features of the drainage image data; According to the image features of the drainage image data, the drainage image data is identified to determine a plurality of target blocks corresponding to the drainage image data; Based on the multiple target blocks corresponding to the drainage image data, multiple block image data of the drainage image data are obtained.

5. The ascites drainage monitoring method according to claim 4, characterized in that: The step of identifying the drainage image data according to the image features of the drainage image data and determining a plurality of target blocks corresponding to the drainage image data includes: According to the image features of the drainage image data, the drainage image data is identified to identify the target monitoring object, the drainage tube, and the ascites collection device in the drainage image data; According to the target monitoring object, the drainage tube, and the ascites collecting device in the drainage image data, respectively determine the circumscribed rectangle of the target monitoring object, the circumscribed rectangle of the drainage tube, and the circumscribed rectangle of the ascites collecting device in the drainage image data; Based on the circumscribed rectangle of the target monitoring object, the circumscribed rectangle of the drainage tube, and the circumscribed rectangle of the ascites collecting device in the drainage image data, a plurality of target blocks corresponding to the drainage image data are obtained.

6. The ascites drainage monitoring method according to claim 5, characterized in that: The obtaining a plurality of block image data of the drainage image data based on the plurality of target blocks corresponding to the drainage image data comprises: Based on the multiple target blocks corresponding to the drainage image data, the drainage image data is edited to obtain first block image data corresponding to the target monitoring object in the drainage image data, second block image data corresponding to the drainage tube, and third block image data corresponding to the ascites collection device; wherein the first block image data, the second block image data, and the third block image data are continuous frame images used to reflect the conditions of the corresponding areas.

7. The ascites drainage monitoring method according to claim 6, characterized in that: The performing an outlier analysis on each block of the drainage image data to determine outlier information of each block of the image data includes: Performing key point recognition on the first block image data of the drainage image data to determine the human body joint position of the target monitoring object in the first block image data; Performing continuous frame image processing on the first block image data according to the human body joint position of the target monitoring object in the first block image data to determine the pixel displacement of the human body joint position of the target monitoring object in the first block image data; Determining a movement amplitude of the target monitoring object based on the pixel displacement of the human body joint position of the target monitoring object in the first block image data; Based on the movement amplitude of the target monitoring object, abnormal point information of the first block image data is determined.

8. The ascites drainage monitoring method according to claim 6, characterized in that: The performing an outlier analysis on each block of the drainage image data to determine outlier information of each block of the image data includes: Performing edge detection on the second block image data of the drainage image data to determine the morphological information of the drainage tube in the second block image data; Based on the morphological information of the drainage tube in the second block image data, determining abnormal point information of the second block image data; And / or, performing an outlier analysis on each block of the drainage image data to determine outlier information of each block of the image data includes: Performing image feature extraction on the third block image data of the drainage image data to determine ascites color information and ascites level information collected by the ascites collection device in the third block image data; Performing a change rate analysis on the ascites level information collected by the ascites collecting device in the third block image data within a preset time period to determine the ascites level change information corresponding to the ascites collecting device in the third block image data; The abnormal point information of the third block image data is determined based on the ascites level change information corresponding to the ascites collecting device in the third block image data, the ascites color information and the ascites level information collected by the ascites collecting device.

9. The ascites drainage monitoring method according to claim 1, characterized in that: The step of evaluating the ascites drainage process of the target monitoring object according to the first monitoring information and the second monitoring information of the target monitoring object to determine the safety status of the target monitoring object includes: Determining drainage monitoring abnormality information of the target monitoring object according to the first monitoring information and the second monitoring information of the target monitoring object; Based on the drainage monitoring abnormality information of the target monitoring object, the safety status of the target monitoring object is determined.

10. An ascites drainage monitoring device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 9 is implemented.

Images