Early coagulation monitoring system of arteriovenous pot based on image processing

Abstract

The invention relates to the technical field of image analysis, in particular to an early coagulation monitoring system of an arteriovenous pot based on image processing. The system obtains an arterial pot image and a venous pot image in real time; acquiring an early coagulation coefficient of the arteriovenous jug at the current moment according to the blood wall hanging condition in the arteriovenous jug image and the flocculus floating condition in the venous jug image in the current time period; according to the bubble distribution condition in the arterial jug image at the current moment and the liquid level height change condition in the arterial jug image and the venous jug image in the current time period, the abnormal degree of the dialysis pipeline at the current moment is obtained; correcting the early blood coagulation coefficient according to the abnormal degree of the dialysis pipeline, and obtaining the corrected early blood coagulation coefficient at the current moment to judge whether the early blood coagulation phenomenon exists at the current moment or not. According to the method, the early coagulation coefficient is accurately obtained and corrected in real time, so that the early coagulation phenomenon can be timely and accurately found and timely treated, and the stability of hemodialysis is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of image analysis, and particularly to an early coagulation monitoring system for arteriovenous pots based on image processing. Background Art

[0002] During hemodialysis, the arterial pot and the venous pot are two key components in the dialysis pipeline. The arterial pot and the venous pot prevent air from entering the patient's blood vessels through multiple bubble interceptions. At the same time, medical staff judge early coagulation by observing the blood wall adhesion situation in the arterial pot and the floc floating situation in the venous pot. However, in actual situations, the pressure changes caused by abnormal dialysis pipelines will affect the blood wall adhesion situation in the arterial pot and the floc floating situation in the venous pot, and thus it is impossible to accurately monitor early coagulation directly based on the blood wall adhesion situation in the arterial pot and the floc floating situation in the venous pot. Summary of the Invention

[0003] In order to solve the technical problem that it is impossible to accurately monitor early coagulation directly based on the blood wall adhesion situation in the arterial pot and the floc floating situation in the venous pot, the purpose of the present invention is to provide an early coagulation monitoring system for arteriovenous pots based on image processing, and the specific technical solution adopted is as follows: An embodiment of the present invention provides an early coagulation monitoring system for arteriovenous pots based on image processing. The system includes the following steps: An image acquisition module for real-time acquiring arterial pot images and venous pot images at each moment; An early coagulation coefficient acquisition module for acquiring the early coagulation coefficient of the arteriovenous pot at the current moment according to the blood wall adhesion situation in each arterial pot image and the floc floating situation in each venous pot image within the current time period; A dialysis pipeline abnormality degree acquisition module for acquiring the abnormality degree of the dialysis pipeline at the current moment according to the distribution of bubbles in the arterial pot image at the current moment and the change of the liquid level height in the arterial pot images and venous pot images within the current time period; An early coagulation monitoring module for correcting the early coagulation coefficient by the abnormality degree of the dialysis pipeline, acquiring the corrected early coagulation coefficient of the arteriovenous pot at the current moment, and judging whether there is an early coagulation phenomenon at the current moment.

[0004] Further, the method for acquiring the early coagulation coefficient is as follows: According to the liquid level height, the color distinctness of the blood wall adhesion area, and the change trend of the wall adhesion height in the arterial pot images at each moment within the current time period, the wall adhesion coefficient of each arterial pot image within the current time period is acquired; Obtain the floc coefficient of each intravenous drip chamber image in the current time period according to the color significance and size of the floc area in the intravenous drip chamber image at each moment in the current time period; Obtain the early coagulation coefficient of the arteriovenous drip chamber at the current moment according to the correlation between the wall adhesion coefficient and the floc coefficient in the current time period, as well as the wall adhesion coefficient and the floc coefficient at the current moment;

[0005] Further, the method for obtaining the wall adhesion coefficient is as follows: For the arterial drip chamber image at any moment in the current time period, obtain the blood area in the arterial drip chamber image as the first blood area through HSV color space segmentation and morphological optimization; Detect and obtain the straight line of the catheter-free side wall of the arterial drip chamber image as the reference line through the Hough transform. Extract all line segments parallel to the reference line in the first blood area as reference line segments, and take the average value of the lengths of all reference line segments as the liquid level height in the arterial drip chamber image; When the liquid level height is equal to the preset liquid level height, the wall adhesion coefficient of the arterial drip chamber image is defaulted to 0; When the liquid level height is less than the preset liquid level height, the connected domain with the variance of gray values within the preset variance range within a specified range above the first blood area is used as the blood wall adhesion area; Obtain the color distinctness of the blood wall adhesion area according to the difference in the R channel values between the blood wall adhesion area and the first blood area; Take the length corresponding to the longest line segment parallel to the reference line in the blood wall adhesion area as the wall adhesion height, and obtain the change degree of the wall adhesion height of the arterial drip chamber image according to the size of the wall adhesion height in the arterial drip chamber image and its preset neighboring arterial drip chamber images; Take the normalized result of the product of the color distinctness and the change degree of the wall adhesion height as the wall adhesion coefficient of the arterial drip chamber image.

[0006] Further, the method for obtaining the color distinctness is as follows: Obtain the average value of the R channel values of the pixel points in the blood wall adhesion area as the first value; Obtain the average value of the R channel values of the pixel points in the first blood area as the second value; Take the ratio of the first value to the second value as the color distinctness of the blood wall adhesion area.

[0007] Further, the method for obtaining the change degree of the wall adhesion height is as follows: Take the preset number of arterial drip chamber images closest to the arterial drip chamber image in time sequence as the preset neighboring arterial drip chamber images of the arterial drip chamber image; Arrange the wall attachment heights of the arterial kettle images and their preset neighborhood arterial kettle images according to the time sequence of the corresponding arterial kettle images to obtain a wall attachment height sequence; Obtain the slope of the straight line fitted by the wall attachment heights in the wall attachment height sequence as the degree of change in the wall attachment height of the arterial kettle image.

[0008] Furthermore, the method for obtaining the flocculation coefficient is as follows: For any venous kettle image at any moment within the current time period, extract the blood region in the venous kettle image as the second blood region through HSV color space segmentation, segment the second blood region through the Otsu threshold segmentation algorithm, and take the high gray level region as the flocculation region; Take the region in the second blood region except the flocculation region as the reference blood region; Obtain the difference between the average gray value of the pixel points in the flocculation region and the average gray value of the pixel points in the reference blood region as the color significance degree of the flocculation region; Take the normalized result of the product of the color significance degree and the area of the flocculation region as the flocculation coefficient of the venous kettle image.

[0009] Furthermore, the method for obtaining the early coagulation coefficient is as follows: Arrange the wall attachment coefficients within the current time period according to the time sequence of the corresponding arterial kettle images to obtain a wall attachment coefficient sequence; Arrange the flocculation coefficients within the current time period according to the time sequence of the corresponding venous kettle images to obtain a flocculation coefficient sequence; Take the Pearson correlation coefficient of the wall attachment coefficient sequence and the flocculation coefficient sequence as the first eigenvalue; Take the average value of the wall attachment coefficient and the flocculation coefficient at the current moment as the coagulation analysis value at the current moment; Take the normalized result of the product of the coagulation analysis value and the first eigenvalue as the early coagulation coefficient of the arterial and venous kettles at the current moment.

[0010] Furthermore, the method for obtaining the degree of abnormality of the dialysis pipeline is as follows: Regard the connected regions in the first blood region of the arterial kettle image at the current moment as bubbles, and obtain the area of each bubble through the Hough circle detection algorithm as the first area; Take the sum result of all the first areas as the first abnormal value of the dialysis pipeline; Obtain the difference in the liquid level height between each moment and the next adjacent moment in the arterial kettle image within the current time period as the height analysis change value; Take the variance of the height analysis change value as the second abnormal value of the dialysis pipeline; For the venous chamber image at any moment within the current time period, the straight line of the catheter-free side wall of the venous chamber in the venous chamber image is detected and obtained through the Hough transform as the target straight line. All line segments parallel to the target straight line in the second blood region of the venous chamber image are extracted as target line segments, and the average value of the lengths of all target line segments is used as the liquid level height in the venous chamber image; Obtain the variance of the liquid level heights in all venous chamber images within the current time period as the third outlier of the dialysis pipeline; The result of normalizing the product of the first outlier of the dialysis pipeline, the second outlier of the dialysis pipeline, and the third outlier of the dialysis pipeline is used as the degree of abnormality of the dialysis pipeline at the current moment.

[0011] Further, the method for obtaining the corrected early coagulation coefficient is as follows: The result of taking the negative correlation of the degree of abnormality of the dialysis pipeline is used as the correction weight; The product of the correction weight and the early coagulation coefficient is used as the corrected early coagulation coefficient of the arteriovenous chamber at the current moment.

[0012] Further, the method for determining whether there is an early coagulation phenomenon at the current moment is as follows: When the corrected early coagulation coefficient is greater than the preset early coagulation coefficient threshold, it is determined that there is an early coagulation phenomenon at the current moment; When the corrected early coagulation coefficient is less than or equal to the preset early coagulation coefficient threshold, it is determined that there is no early coagulation phenomenon at the current moment.

[0013] The present invention has the following beneficial effects: The present invention first obtains the early coagulation coefficient of the arteriovenous chamber at the current moment according to the blood wall attachment situation in each arterial chamber image and the floc floating situation in each venous chamber image within the current time period, initially reflecting the possibility of early coagulation at the current moment; in order to reduce the interference of dialysis pipeline abnormalities on the analysis of early coagulation, and then according to the bubble distribution situation in the arterial chamber image at the current moment and the liquid level height change situation in the arterial chamber images and venous chamber images within the current time period, the degree of abnormality of the dialysis pipeline at the current moment is obtained, accurately reflecting the abnormal situation of the dialysis pipeline at the current moment, which is beneficial to accurately correcting the early coagulation coefficient subsequently and improving the accuracy of early coagulation monitoring; therefore, the early coagulation coefficient is corrected by the degree of abnormality of the dialysis pipeline to accurately obtain the corrected early coagulation coefficient of the arteriovenous chamber at the current moment, accurately reflecting the possibility of early coagulation at the current moment; and then based on the corrected early coagulation coefficient, it is accurately determined whether there is an early coagulation phenomenon at the current moment, effectively improving the accuracy of early coagulation monitoring, which is beneficial to timely and accurately discovering the early coagulation phenomenon and dealing with it in a timely manner, and improving the stability of hemodialysis. Description of the Drawings

[0014] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0015] Figure 1 A structural block diagram of an early coagulation monitoring system for an arteriovenous chamber based on image processing provided by an embodiment of the present invention; Figure 2 A flowchart of a method for obtaining an early coagulation coefficient provided by an embodiment of the present invention; Figure 3 A schematic diagram of a computer device provided by an embodiment of the present invention. Detailed implementation manners

[0016] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features and effects of an early coagulation monitoring system for an arteriovenous chamber based on image processing proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0017] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which the present invention belongs.

[0018] The following specifically describes the specific solution of an early coagulation monitoring system for an arteriovenous chamber based on image processing provided by the present invention with reference to the accompanying drawings.

[0019] Embodiment 1: The present invention proposes an early coagulation monitoring system for an arteriovenous chamber based on image processing. Please refer to Figure 1 , which shows a structural block diagram of an early coagulation monitoring system for an arteriovenous chamber based on image processing provided by an embodiment of the present invention. The system includes: an image acquisition module 10, an early coagulation coefficient acquisition module 20, a dialysis pipeline abnormality degree acquisition module 30, and an early coagulation monitoring module 40.

[0020] The image acquisition module 10 is used to acquire the arterial chamber image and the venous chamber image at each moment in real time.

[0021] Specifically, the process of hemodialysis is as follows: First, the blood pump draws the patient's blood out of the body and then passes it through the arterial chamber into the dialyzer. After that, the blood undergoes toxin clearance treatment in the dialyzer and then enters the venous chamber. Finally, it is transfused back into the patient's body from the venous chamber. The functions of the arterial and venous chambers are to capture air bubbles in the blood to prevent air from entering the patient's body and to monitor pressure at the same time, ensuring smooth blood flow without obstruction and avoiding severe coagulation.

[0022] In order to timely and accurately detect the early coagulation phenomenon in the arterial and venous chambers, enabling medical staff to intervene and handle it in a timely manner and effectively avoid the impact of coagulation, in this embodiment, a medical camera is used to obtain the arterial chamber image and venous chamber image at each moment in real time. It should be noted that during the process of obtaining the arterial chamber image and venous chamber image, the medical camera is installed on a fixed anti-shake bracket to prevent the obtained arterial chamber image and venous chamber image from being blurred. At the same time, a small supplementary light is installed, the surfaces of the arterial and venous chambers are wiped with alcohol for disinfection, the positions of the arterial and venous chambers and the shooting angles are adjusted to ensure that the arterial and venous chambers are in a position with clear vision, no occlusion, and no reflection, so that the obtained arterial chamber image and venous chamber image have no reflection interference and surface contamination interference. At the same time, this embodiment takes a complete hemodialysis process as an example for analysis. Among them, the time interval between two adjacent moments is set to 1 second in this embodiment. The implementer can set the time interval between two adjacent moments according to the actual situation, and no limitation is made here.

[0023] It is known that this embodiment analyzes the arterial and venous chambers in real time to timely detect the early coagulation phenomenon. Therefore, in order to improve the analysis efficiency, this embodiment uses a semantic segmentation network to obtain the arterial chamber image containing only the arterial chamber area and the venous chamber image containing only the venous chamber area. Among them, the semantic segmentation network in this embodiment uses the U-net neural network, with the input being the denoised arterial chamber image and venous chamber image; the output being the arterial chamber image containing only the arterial chamber area and the venous chamber image containing only the venous chamber area; the way of training and labeling the U-net neural network is: marking the areas to be detected, that is, the arterial chamber area and the venous chamber area, as 1, and other areas as 0; the loss function of the U-net neural network is the cross-entropy loss function. Among them, the U-net neural network is a well-known technology and will not be elaborated here.

[0024] It should be noted that the subsequent arterial chamber images are all images containing only the arterial chamber and the venous chamber images are all images containing only the venous chamber.

[0025] The early coagulation coefficient acquisition module 20 is used to obtain the early coagulation coefficient of the arterial and venous chambers at the current moment according to the blood wall adhesion situation in each arterial chamber image and the flocculation situation in each venous chamber image within the current time period.

[0026] Specifically, during hemodialysis, when coagulation occurs, it will cause the blood dialysis pipeline to become blocked, resulting in a slight increase in the pressure in the arteriovenous chamber. Due to the different positions of the arterial chamber and the venous chamber, the performance of the arterial chamber and the venous chamber is different under coagulation conditions; when there is pressure caused by early coagulation in the arterial chamber, the blood liquid level in the arterial chamber will drop slightly, and at the same time, due to poor blood anticoagulation, blood wall adhesion will occur during the process of the blood liquid level dropping in the arterial chamber; when there is pressure caused by early coagulation in the venous chamber, protein precipitation will occur in the blood in the venous chamber, and thus floc floating phenomenon will occur in the venous chamber. Under coagulation conditions, the blood wall adhesion in the arterial chamber and the floc floating phenomenon in the venous chamber should occur synchronously, that is, the more serious the blood wall adhesion phenomenon in the arterial chamber, the more serious the floc floating phenomenon in the venous chamber; on the other hand, it is known that the coagulation situation is a continuous process, and the coagulation situation will not disappear without human intervention. Therefore, in this embodiment, according to the blood wall adhesion situation in each arterial chamber image and the floc floating situation in each venous chamber image within the current time period, the early coagulation coefficient of the arteriovenous chamber at the current moment is obtained. The larger the early coagulation coefficient, the more likely there is an early coagulation phenomenon at the current moment. Among them, in this embodiment, the current time period is set to 20 seconds, and the implementer can set the size of the current time period according to the actual situation, which is not limited here. It should be noted that the end moment of the current time period must be the current moment, and hemodialysis has at least started for 20 seconds.

[0027] Preferably, in an implementable manner of this embodiment, for the method of obtaining the early coagulation coefficient, please refer to Figure 2 , which shows a flowchart of a method for obtaining an early coagulation coefficient provided in this embodiment. The method includes the following steps: Step S201: According to the liquid level height, the color obviousness of the blood wall adhesion area, and the change trend of the wall adhesion height in the arterial chamber image at each moment within the current time period, obtain the wall adhesion coefficient of each arterial chamber image within the current time period.

[0028] For the arterial kettle image at any moment within the current time period, when there is no liquid level drop in the blood in the arterial kettle image, it indicates that there is no blood wall adhesion in the arterial kettle image; when there is a liquid level drop in the blood in the arterial kettle image, it indicates that there is blood wall adhesion in the arterial kettle image. It is known that as the coagulation condition worsens, the color of the blood wall adhesion area will become more and more obvious, that is, it will be more and more consistent with the color of the blood. At the same time, the degree of adhesion of the blood wall adhesion area will become larger and larger. Among them, the degree of adhesion of the blood wall adhesion area can be analyzed through the change trend of the wall adhesion height of the blood wall adhesion area. That is, when the change trend of the wall adhesion height is getting larger and larger, it indicates that the blood wall adhesion is getting more and more serious, indirectly reflecting that the coagulation condition is more serious. Therefore, in this embodiment, according to the liquid level height, the color obviousness of the blood wall adhesion area, and the change trend of the wall adhesion height in the arterial kettle image at each moment within the current time period, the wall adhesion coefficient of each arterial kettle image within the current time period is obtained. The larger the wall adhesion coefficient, the more serious the coagulation condition corresponding to the moment of the arterial kettle image.

[0029] In a feasible implementation manner of this embodiment, the method for obtaining the wall adhesion coefficient is as follows: for the arterial kettle image at any moment within the current time period, first, the blood area in the arterial kettle image is obtained through HSV color space segmentation. In order to avoid the interference of air bubbles and the blood wall adhesion area, morphological optimization is then performed to accurately obtain the blood area in the arterial kettle image as the first blood area; among them, both HSV color space segmentation and morphology are well-known technologies and will not be elaborated here. In order to accurately analyze whether there is a liquid level drop in the arterial kettle image, in this embodiment, the straight line of the catheter-free side kettle wall in the arterial kettle image is obtained through Hough transform detection as the reference straight line, and then all line segments parallel to the reference straight line in the first blood area are extracted as reference line segments; among them, the endpoints of the reference line segments are the edge pixel points on the outermost edge line of the first blood area; finally, the average value of the lengths of all reference line segments is used as the liquid level height in the arterial kettle image; among them, Hough transform detection is a well-known technology and will not be elaborated here. When the liquid level height is equal to the preset liquid level height, it indicates that there is no liquid level drop in the arterial kettle image; when the liquid level height is less than the preset liquid level height, it indicates that there is a liquid level drop in the arterial kettle image. Among them, the preset liquid level height is the liquid level height in the arterial kettle set artificially during hemodialysis, and the implementer can set it according to the actual situation and will not be limited here; When the liquid level height is equal to the preset liquid level height, the wall adhesion coefficient of the arterial kettle image is defaulted to 0 at this time; when the liquid level height is less than the preset liquid level height, the connected domain within the specified range above the first blood region with the variance of gray values within the preset variance range is used as the blood wall adhesion region; since the blood wall adhesion region is next to the liquid level and the color distribution in the blood wall adhesion region is consistent, in this embodiment, the specified range is set to 2px to 30px and the preset variance range is set to 0 to 0.3. The implementer can set the specified range and the preset variance range according to the actual situation and is not limited here. Thus, the blood wall adhesion region in the arterial kettle image is accurately determined; In order to analyze the blood wall adhesion situation in the arterial kettle image, and then according to the R-channel value difference between the blood wall adhesion region and the first blood region, the color distinctness of the blood wall adhesion region is obtained; the greater the color distinctness, the more serious the blood wall adhesion situation in the arterial kettle image. Among them, the way to obtain the color distinctness is as follows: First, obtain the mean value of the R-channel values of the pixel points in the blood wall adhesion region as the first value; then obtain the mean value of the R-channel values of the pixel points in the first blood region as the second value; when the first value and the second value are more equal, it indicates that the color of the blood wall adhesion region is more distinct, and then the ratio of the first value to the second value is used as the color distinctness of the blood wall adhesion region; In order to more accurately analyze the blood wall adhesion situation in the arterial kettle image, further take the length of the longest line segment parallel to the reference line in the blood wall adhesion region as the wall adhesion height, and then according to the size of the wall adhesion height in this arterial kettle image and its preset neighboring arterial kettle images, obtain the change degree of the wall adhesion height of this arterial kettle image; the greater the change degree of the wall adhesion height, the greater the increasing trend of the wall adhesion height in this arterial kettle image, indirectly reflecting that the blood wall adhesion situation in this arterial kettle image is more serious. Among them, the method to obtain the change degree of the wall adhesion height is as follows: Take the preset number of arterial kettle images closest to this arterial kettle image in time sequence as the preset neighboring arterial kettle images of this arterial kettle image; in this embodiment, the preset number is set to 10, and the implementer can set the size of the preset number according to the actual situation and is not limited here. Arrange the wall adhesion heights of this arterial kettle image and its preset neighboring arterial kettle images in the order of the time sequence of the corresponding arterial kettle images from front to back to obtain a wall adhesion height sequence; then obtain the slope of the fitted line of the wall adhesion heights in the wall adhesion height sequence as the change degree of the wall adhesion height of this arterial kettle image. Among them, the method of fitting the line is a well-known technology and will not be elaborated here; It is known that the greater the color distinctness and the greater the change degree of the wall adhesion height both indicate that the blood wall adhesion situation in the arterial kettle image is more serious. Therefore, in this embodiment, the result of normalizing the product of the color distinctness and the change degree of the wall adhesion height is used as the wall adhesion coefficient of this arterial kettle image. Among them, the calculation formula of the wall adhesion coefficient is: ; where, is the wall adhesion coefficient of the arterial kettle image at the a-th moment within the current time period; is the first value corresponding to the blood wall adhesion area in the arterial kettle image at the a-th moment within the current time period; is the second value corresponding to the first blood area in the arterial kettle image at the a-th moment within the current time period; is the color distinctness of the blood wall adhesion area in the arterial kettle image at the a-th moment within the current time period; is the degree of change in the wall adhesion height of the arterial kettle image at the a-th moment within the current time period; norm is the normalization function.

[0030] Thus, the wall adhesion coefficient of each arterial kettle image within the current time period is obtained.

[0031] Step S202: According to the color distinctness and size of the floc region in the venous kettle image at each moment within the current time period, obtain the floc coefficient of each venous kettle image within the current time period.

[0032] For the venous kettle image at any moment within the current time period, when the floc region in the venous kettle image is more obvious and larger, it indicates that the blood coagulation condition at the corresponding moment of the venous kettle image is more serious. Furthermore, in this embodiment, according to the color distinctness and size of the floc region in the venous kettle image at each moment within the current time period, the floc coefficient of each venous kettle image within the current time period is obtained. The larger the floc coefficient, the more serious the blood coagulation condition at the corresponding moment of the corresponding venous kettle image.

[0033] In a feasible implementation manner of this embodiment, the method for obtaining the flocculation coefficient is as follows: for the venous kettle image at any moment within the current time period, the blood area in the venous kettle image is extracted through HSV color space segmentation as the second blood area. Since it is known that the flocs are significantly brighter than the blood in the blood, the Otsu threshold segmentation algorithm is then used to segment the second blood area, and the high gray-level area is taken as the floc area; among them, the Otsu threshold segmentation algorithm is a well-known technology and will not be elaborated here. The area in the second blood area except the floc area is taken as the reference blood area; the absolute value of the difference between the average gray value of the pixel points in the floc area and the average gray value of the pixel points in the reference blood area is obtained as the color significance degree of the floc area; the greater the color significance degree, the more obvious the floc area, and the more serious the floc phenomenon in the venous kettle image; at the same time, when the area of the floc area is larger, it also indicates that the floc phenomenon in the venous kettle image is more serious. Among them, the method for obtaining the area of the floc area is a well-known technology and will not be elaborated here. In order to accurately represent the floc situation in the venous kettle image, the normalized result of the product of the color significance degree and the area of the floc area is used as the flocculation coefficient of the venous kettle image. In this embodiment, the norm normalization function is used to normalize the product of the color significance degree and the area of the floc area.

[0034] Thus, the flocculation coefficients of each venous kettle image within the current time period are obtained.

[0035] Step S203: According to the relevant situation of the wall adhesion coefficient and the flocculation coefficient within the current time period, as well as the wall adhesion coefficient and the flocculation coefficient at the current moment, obtain the early coagulation coefficient of the arteriovenous kettle at the current moment.

[0036] Since it is known that the situations caused by the coagulation condition to the arteriovenous kettle occur synchronously, in this embodiment, the reliability of early coagulation of the arteriovenous kettle at the current moment is analyzed according to the relevant situation of the wall adhesion coefficient and the flocculation coefficient within the current time period. When both the wall adhesion coefficient and the flocculation coefficient at the current moment are larger, it indicates that there is a greater possibility of coagulation at the current moment. Then, in this embodiment, according to the relevant situation of the wall adhesion coefficient and the flocculation coefficient within the current time period, as well as the wall adhesion coefficient and the flocculation coefficient at the current moment, the early coagulation coefficient of the arteriovenous kettle at the current moment is obtained.

[0037] In an implementable manner of this embodiment, the method for obtaining the early coagulation coefficient is as follows: Arrange the wall adhesion coefficients within the current time period in the chronological order from the front to the back according to the corresponding arterial kettle images to obtain a wall adhesion coefficient sequence; Arrange the flocculation coefficients within the current time period in the chronological order from the front to the back according to the corresponding venous kettle images to obtain a flocculation coefficient sequence; Use the Pearson correlation coefficient between the wall adhesion coefficient sequence and the flocculation coefficient sequence as the first eigenvalue. The larger the first eigenvalue, the more accurate the analysis of the early coagulation situation at the current moment; Among them, the method for obtaining the Pearson correlation coefficient is a well-known technology and will not be elaborated here. When both the wall adhesion coefficient and the flocculation coefficient at the current moment are larger, it indicates that there is a greater possibility of early coagulation at the current moment; Furthermore, in this embodiment, the average value of the wall adhesion coefficient and the flocculation coefficient at the current moment is used as the coagulation analysis value at the current moment; In order to improve the accuracy of the analysis of the coagulation situation at the current moment, the coagulation analysis value is then corrected by the first eigenvalue. Therefore, the result of normalizing the product of the coagulation analysis value and the first eigenvalue is used as the early coagulation coefficient of the arteriovenous kettle at the current moment. In this embodiment, the norm normalization function is used to normalize the product of the coagulation analysis value and the first eigenvalue.

[0038] The dialysis pipeline abnormality degree acquisition module 30 is configured to obtain the abnormality degree of the dialysis pipeline at the current moment according to the distribution of bubbles in the arterial kettle image at the current moment and the change in the liquid level height in the arterial kettle image and the venous kettle image within the current time period.

[0039] Specifically, in actual situations, when the dialysis pipeline is abnormal, it will also cause abnormal pressure, which in turn affects the blood wall adhesion and flocculation in the arteriovenous kettle. Therefore, the early coagulation coefficient obtained by the early coagulation coefficient acquisition module 20 cannot accurately analyze whether there is an early coagulation phenomenon at the current moment. It is known that the pressure change caused by the abnormality of the dialysis pipeline will cause bubbles to appear in the blood in the arterial kettle and the liquid level to drop suddenly, while the decrease in the liquid level of the arterial kettle caused by early coagulation is slight and stable; On the other hand, the pressure change caused by the abnormality of the dialysis pipeline will cause obvious fluctuations in the liquid level of the venous kettle. Therefore, in this embodiment, the abnormality degree of the dialysis pipeline at the current moment is obtained according to the distribution of bubbles in the arterial kettle image at the current moment and the change in the liquid level height in the arterial kettle image and the venous kettle image within the current time period. The greater the abnormality degree of the dialysis pipeline, the greater the possibility of abnormality of the dialysis pipeline at the current moment, the less accurate the early coagulation coefficient of the arteriovenous kettle at the current moment, and the greater the degree of correction required.

[0040] Preferably, in an implementable manner of this embodiment, the method for obtaining the degree of abnormality of the dialysis pipeline is as follows: all connected domains in the first blood region in the arterial kettle image at the current moment are regarded as bubbles, and the area of each bubble is obtained through the Hough circle detection algorithm and taken as the first area; the Hough circle detection algorithm is a well-known technology and will not be elaborated here. When the first areas are all larger, it indicates that there are more bubbles in the arterial kettle image at the current moment, indirectly indicating a greater possibility of abnormality of the dialysis pipeline at the current moment. Furthermore, the sum of all the first areas is taken as the first abnormality value of the dialysis pipeline; the larger the first abnormality value of the dialysis pipeline, the greater the possibility of abnormality of the dialysis pipeline at the current moment; In order to accurately analyze the abnormality of the dialysis pipeline at the current moment, and then obtain the difference in the liquid level height in the arterial kettle images at each moment and its adjacent next moment within the current time period, all of which are taken as the height analysis change values; when there are obvious differences in the height analysis change values, it is more likely that there is an abnormality in the dialysis pipeline, indicating a greater possibility of abnormality of the dialysis pipeline at the current moment; furthermore, the variance of the height analysis change values is taken as the second abnormality value of the dialysis pipeline; the larger the second abnormality value of the dialysis pipeline, the greater the possibility of abnormality of the dialysis pipeline at the current moment; Furthermore, for the venous kettle image at any moment within the current time period, the straight line of the catheter-free side kettle wall in the venous kettle image is obtained through Hough transform detection as the target straight line, and all line segments parallel to the target straight line are extracted in the second blood region in the venous kettle image as the target line segments, where the endpoints of the target line segments are the edge pixel points on the outermost edge line of the second blood region; the average value of the lengths of all the target line segments is taken as the liquid level height in the venous kettle image; the variance of the liquid level heights in all the venous kettle images within the current time period is obtained as the third abnormality value of the dialysis pipeline; the larger the third abnormality value of the dialysis pipeline, it indicates that the liquid level fluctuation of the venous kettle within the current time period is greater, and the greater the possibility of abnormality of the dialysis pipeline at the current moment; In order to accurately represent the abnormality of the dialysis pipeline at the current moment and enable accurate correction of the early coagulation coefficient in the subsequent process, in this embodiment, the normalized result of the product of the first abnormality value of the dialysis pipeline, the second abnormality value of the dialysis pipeline, and the third abnormality value of the dialysis pipeline is taken as the degree of abnormality of the dialysis pipeline at the current moment. In this embodiment, the product of the first abnormality value of the dialysis pipeline, the second abnormality value of the dialysis pipeline, and the third abnormality value of the dialysis pipeline is normalized through the norm normalization function.

[0041] Thus, the degree of abnormality of the dialysis pipeline at the current moment is obtained.

[0042] The early coagulation monitoring module 40 is used to correct the early coagulation coefficient through the degree of abnormality of the dialysis pipeline, obtain the corrected early coagulation coefficient of the arteriovenous kettle at the current moment, and judge whether there is an early coagulation phenomenon at the current moment.

[0043] Specifically, it is known that the greater the degree of abnormality of the dialysis pipeline, the more inaccurate the early coagulation coefficient at the corresponding moment. Therefore, in this embodiment, the early coagulation coefficient at the current moment is corrected by the degree of abnormality of the dialysis pipeline at the current moment to obtain the corrected early coagulation coefficient of the arteriovenous chamber at the current moment. When the corrected early coagulation coefficient is larger, it indicates that there is a higher possibility of early coagulation phenomenon at the current moment. Therefore, in this embodiment, based on the corrected early coagulation coefficient, it is accurately judged whether there is an early coagulation phenomenon at the current moment.

[0044] Preferably, in a realizable manner of this embodiment, the method for obtaining the corrected early coagulation coefficient is as follows: the result of negatively correlating the degree of abnormality of the dialysis pipeline at the current moment is used as the correction weight; the product of the correction weight and the early coagulation coefficient at the current moment is used as the corrected early coagulation coefficient of the arteriovenous chamber at the current moment. Among them, the calculation formula for the corrected early coagulation coefficient is: ; In the formula, is the corrected early coagulation coefficient of the arteriovenous chamber at the current moment; is the early coagulation coefficient of the arteriovenous chamber at the current moment; is the degree of abnormality of the dialysis pipeline at the current moment; is the correction weight.

[0045] Preferably, in a realizable manner of this embodiment, the method for judging whether there is an early coagulation phenomenon at the current moment is as follows: In this embodiment, the preset early coagulation coefficient threshold is set to 0.5. The implementer can set the size of the preset early coagulation coefficient threshold according to the actual situation, which is not limited here. When the corrected early coagulation coefficient is greater than the preset early coagulation coefficient threshold, it is judged that there is an early coagulation phenomenon at the current moment. Then, an early coagulation alarm is issued at the current moment to remind the medical staff to conduct a further manual review of the coagulation situation in the arteriovenous chamber, so as to timely and accurately control the coagulation risk and ensure the stable progress of hemodialysis; When the corrected early coagulation coefficient is less than or equal to the preset early coagulation coefficient threshold, it is judged that there is no early coagulation phenomenon at the current moment. However, if the early coagulation coefficient is greater than the preset early coagulation coefficient threshold at this time, the medical staff is reminded to check the dialysis pipeline to accurately analyze whether there is an abnormality in the dialysis pipeline at the current moment and avoid the influence of the dialysis pipeline abnormality on hemodialysis; if the early coagulation coefficient is less than or equal to the preset early coagulation coefficient threshold at this time, it indicates that hemodialysis is stable at the current moment.

[0046] In summary, this embodiment obtains the arterial pot image and the venous pot image in real time; obtains the early coagulation coefficient of the arteriovenous pot at the current moment according to the blood hanging on the wall in the arterial pot image and the floating floccules in the venous pot image in the current time period; obtains the abnormality of the dialysis pipeline at the current moment according to the bubble distribution in the arterial pot image at the current moment and the change of the liquid level in the arterial pot image and the venous pot image in the current time period; corrects the early coagulation coefficient according to the abnormality of the dialysis pipeline, obtains the corrected early coagulation coefficient at the current moment to determine whether there is an early coagulation phenomenon at the current moment. The present invention accurately obtains the corrected early coagulation coefficient in real time, which is conducive to timely and accurate discovery of early coagulation phenomenon and timely treatment, and effectively improves the stability of hemodialysis.

[0047] Embodiment 2: The present invention also proposes an early coagulation monitoring device for an arteriovenous kettle based on image processing, the device includes a memory and a processor, wherein the memory stores an executable program code, and the processor is used to call and execute the executable program code to execute an early coagulation monitoring system for an arteriovenous kettle based on image processing provided in an embodiment of the present application. The device can be specifically a chip, a component or a module, and the chip may include a connected processor and a memory; wherein the memory is used to store instructions, and when the processor calls and executes the instructions, the chip can execute an early coagulation monitoring system for an arteriovenous kettle based on image processing provided in the above embodiment.

[0048] In addition, the present application embodiment also protects a computer device, see Figure 3 The computer device includes a memory 401, a processor 402, and a computer program 403 stored in the memory 401 and running on the processor 402, wherein when the processor 402 executes the computer program 403, the computer device can execute any one of the image processing-based early coagulation monitoring systems for arteriovenous vessels described above.

[0049] Embodiment 3: The present invention also provides a computer-readable storage medium, which stores computer program code. When the computer program code runs on a computer, the computer executes the above-mentioned related method steps to implement an early coagulation monitoring system for an arteriovenous cannula based on image processing provided in the above-mentioned embodiment.

[0050] Embodiment 4: The present invention also provides a computer program product. When the computer program product is run on a computer, the computer is enabled to execute the above-mentioned related steps to implement an early coagulation monitoring system for an arteriovenous chamber based on image processing provided in the above-mentioned embodiment.

[0051] Among them, the device, computer-readable storage medium, computer program product or chip provided in this embodiment are all used to execute the corresponding method provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method provided above, and will not be elaborated here.

[0052] It should be noted that the above sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0053] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An early coagulation monitoring system for arteriovenous fistula based on image processing, characterized in that, The system includes the following steps: An image acquisition module for real-time acquisition of arterial pot images and venous pot images at each moment; An early coagulation coefficient acquisition module for obtaining the early coagulation coefficient of the arterial and venous pots at the current moment according to the blood wall adhesion condition in each arterial pot image and the flocculation condition in each venous pot image within the current time period; A dialysis pipeline abnormality degree acquisition module for obtaining the abnormality degree of the dialysis pipeline at the current moment according to the distribution of bubbles in the arterial pot image at the current moment and the liquid level height change conditions in the arterial pot images and venous pot images within the current time period; An early coagulation monitoring module for correcting the early coagulation coefficient through the abnormality degree of the dialysis pipeline, obtaining the corrected early coagulation coefficient of the arterial and venous pots at the current moment, and determining whether there is an early coagulation phenomenon at the current moment.

2. The early blood coagulation monitoring system for arteriovenous ampoule based on image processing according to claim 1, characterized in that The method for obtaining the early coagulation coefficient is as follows: According to the liquid level height, the color distinctness of the blood wall adhesion area, and the change trend of the wall adhesion height in the arterial pot images at each moment within the current time period, obtain the wall adhesion coefficient of each arterial pot image within the current time period; According to the color distinctness and size of the flocculation area in the venous pot images at each moment within the current time period, obtain the flocculation coefficient of each venous pot image within the current time period; According to the correlation between the wall adhesion coefficient and the flocculation coefficient within the current time period, and the wall adhesion coefficient and the flocculation coefficient at the current moment, obtain the early coagulation coefficient of the arterial and venous pots at the current moment.

3. The early coagulation monitoring system for arteriovenous ampoules based on image processing according to claim 2, wherein The method for obtaining the wall adhesion coefficient is as follows: For the arterial pot image at any moment within the current time period, through HSV color space segmentation and morphological optimization, obtain the blood area in the arterial pot image as the first blood area; Detect and obtain the straight line of the catheter-free side pot wall in the arterial pot image through the Hough transform, extract all line segments parallel to the reference line in the first blood area as reference line segments, and take the mean value of the lengths of all reference line segments as the liquid level height in the arterial pot image; When the liquid level height is equal to the preset liquid level height, the wall adhesion coefficient of the arterial pot image is defaulted to 0; When the liquid level height is less than the preset liquid level height, the connected domain with the gray value variance within the preset variance range above the first blood area is used as the blood wall adhesion area; According to the R channel value difference between the blood wall adhesion area and the first blood area, obtain the color distinctness of the blood wall adhesion area; Take the length corresponding to the longest line segment parallel to the reference line in the blood wall adhesion area as the wall adhesion height, and according to the size of the wall adhesion height in the arterial pot image and its preset neighboring arterial pot images, obtain the change degree of the wall adhesion height of the arterial pot image; The result of normalizing the product of the color distinctness and the wall adhesion height change degree is used as the wall adhesion coefficient of the arterial pot image.

4. The early coagulation monitoring system for arteriovenous chamber based on image processing according to claim 3, wherein The method for obtaining the color distinctness is as follows: Obtain the mean value of the R channel values of the pixel points in the blood wall adhesion area as the first value; Obtain the mean value of the R channel values of the pixel points in the first blood area as the second value; Take the ratio of the first value to the second value as the color distinctness of the blood wall adhesion area.

5. The early coagulation monitoring system for an arteriovenous chamber based on image processing according to claim 3, wherein The method for obtaining the degree of change in the wall attachment height is as follows: Take the preset number of arterial pot images that are the closest in time sequence and before the arterial pot image as the preset neighborhood arterial pot images of the arterial pot image; Arrange the wall attachment heights of the arterial pot image and its preset neighborhood arterial pot images according to the time sequence of the corresponding arterial pot images to obtain a wall attachment height sequence; Obtain the slope of the straight line fitted by the wall attachment heights in the wall attachment height sequence as the degree of change in the wall attachment height of the arterial pot image.

6. The early coagulation monitoring system for arteriovenous ampoules based on image processing according to claim 3, wherein The method for obtaining the flocculation coefficient is as follows: For the venous pot image at any moment within the current time period, extract the blood region in the venous pot image as the second blood region through HSV color space segmentation, segment the second blood region through the Otsu threshold segmentation algorithm, and take the high gray level region as the flocculation region; Take the region in the second blood region except the flocculation region as the reference blood region; Obtain the difference between the average gray value of the pixel points in the flocculation region and the average gray value of the pixel points in the reference blood region as the color significance degree of the flocculation region; Take the normalized result of the product of the color significance degree and the area of the flocculation region as the flocculation coefficient of the venous pot image.

7. The early coagulation monitoring system of an arteriovenous chamber based on image processing according to claim 2, wherein The method for obtaining the early coagulation coefficient is as follows: Arrange the wall attachment coefficients within the current time period according to the time sequence of the corresponding arterial pot images to obtain a wall attachment coefficient sequence; Arrange the flocculation coefficients within the current time period according to the time sequence of the corresponding venous pot images to obtain a flocculation coefficient sequence; Take the Pearson correlation coefficient between the wall attachment coefficient sequence and the flocculation coefficient sequence as the first eigenvalue; Take the average value of the wall attachment coefficient and the flocculation coefficient at the current moment as the coagulation analysis value at the current moment; Take the normalized result of the product of the coagulation analysis value and the first eigenvalue as the early coagulation coefficient of the arterial and venous pots at the current moment.

8. The early coagulation monitoring system for arteriovenous ampulla based on image processing according to claim 6, characterized in that, The method for obtaining the degree of abnormality of the dialysis pipeline is as follows: Regard all the connected regions in the first blood region of the arterial pot image at the current moment as bubbles, and obtain the area of each bubble through the Hough circle detection algorithm as the first area; Take the sum result of all the first areas as the first abnormal value of the dialysis pipeline; Obtain the difference in the liquid level height between the arterial pot images at each moment and the next adjacent moment within the current time period as the height analysis change value; Take the variance of the height analysis change value as the second abnormal value of the dialysis pipeline; For the venous pot image at any moment within the current time period, detect and obtain the straight line of the catheter-free side wall of the venous pot image through the Hough transform as the target straight line, extract all the line segments parallel to the target straight line in the second blood region of the venous pot image as the target line segments, and take the average value of the lengths of all the target line segments as the liquid level height in the venous pot image; Obtain the variance of the liquid level heights in all the venous pot images within the current time period as the third abnormal value of the dialysis pipeline; Take the normalized result of the product of the first abnormal value of the dialysis pipeline, the second abnormal value of the dialysis pipeline, and the third abnormal value of the dialysis pipeline as the degree of abnormality of the dialysis pipeline at the current moment.

9. The early coagulation monitoring system for arteriovenous ampoules based on image processing according to claim 1, characterized in that, The method for obtaining the corrected early coagulation coefficient is as follows: Take the result with a negative correlation to the degree of abnormality of the dialysis pipeline as the correction weight; Take the product of the correction weight and the early coagulation coefficient as the corrected early coagulation coefficient of the arteriovenous chamber at the current moment.

10. An early coagulation monitoring system for an arteriovenous chamber based on image processing according to claim 1, characterized in that, The method for determining whether there is an early coagulation phenomenon at the current moment is as follows: When the corrected early coagulation coefficient is greater than the preset early coagulation coefficient threshold, it is determined that there is an early coagulation phenomenon at the current moment; When the corrected early coagulation coefficient is less than or equal to the preset early coagulation coefficient threshold, it is determined that there is no early coagulation phenomenon at the current moment.

Images