A method and system for detecting parasitic eggs

Abstract

The present invention discloses a method and system for detecting parasitic eggs, relating to the technical field of egg detection. The method includes the following steps: collecting a certain volume of test sample and putting it into a centrifuge tube, performing a centrifugation operation, and retaining the sediment part at the bottom of the tube; resuspending the centrifuged sediment part in physiological saline, injecting the mixed liquid into a microfluidic chip, where protruding electrodes are provided in the microfluidic chip, and the surfaces of the electrodes are coated with specific antibodies to capture eggs; calculating the current at different times, and simultaneously collecting microscope images of the electrodes; establishing a Yo lov5s model, training the Yo lov5s model with the contour of the parasitic eggs as labels; inputting the microscope images of the electrodes into the Yo lov5s model, identifying the contour of the parasitic eggs in the images, and extracting features from the contour image part; jointly judging whether there are parasitic eggs in the sample based on the change of the current at different times in combination with the characteristic parameters. If there are, calculating the concentration of the parasitic eggs based on the current change and the number of parasitic eggs.

Description

Technical Field

[0001] The present invention relates to the technical field of egg detection, and specifically to a method and system for detecting parasitic eggs. Background Art

[0002] Parasitic infections are common public health problems globally. The transmission of parasitic diseases is closely related to people's living conditions, hygiene habits, and environmental factors. The eggs of parasites are a crucial stage in their life cycle, capable of surviving in the environment for a long time, and their transmission methods are diverse, including water sources, soil, and food, posing a serious threat to human health. Therefore, quickly and accurately detecting the presence of parasitic eggs has become an important task in public health detection and disease control.

[0003] Traditional methods for detecting parasitic eggs mostly rely on manual identification and counting under a microscope. This method is not only cumbersome to operate but also greatly affected by the subjective experience of the operator, resulting in limitations in the accuracy and reliability of the detection results. In addition, traditional methods usually require a long time to process samples and analyze results, which is not ideal in the case of rapid-response public health emergencies. Therefore, there is an urgent need for a novel, fast, and automated parasitic egg detection technology to improve detection efficiency and accuracy.

[0004] In recent years, the development of microfluidic technology and machine learning has provided new solutions for parasitic egg detection. Microfluidic chips have the characteristics of high sensitivity and high throughput, and can effectively process and analyze samples. Deep learning models based on computer vision (such as Yolov5s) can efficiently extract features from microscope images for automated recognition. The combination of the two can greatly improve the efficiency and accuracy of parasitic egg detection and solve the deficiencies in traditional methods.

[0005] In the prior art, the publication number CN104700112B discloses a method for detecting parasitic eggs in feces based on morphological features. It mainly preprocesses the image by graying, binarizing, filling, and screening the area of connected regions; the detection part dilates, erodes the preprocessed binary image, calculates the area of connected regions, eccentricity, elliptical hardness, and circularity characteristic parameters, and detects parasitic eggs. However, in complex fecal samples, parasitic eggs may be mixed with other impurities and cells, and traditional image processing methods may be difficult to effectively separate and identify the target. Moreover, it highly depends on the quality and shooting conditions of the image. Changes in light, background impurities, and the mixing degree of the sample will directly affect the effects of graying and binarizing, resulting in inaccurate feature extraction and thus affecting the final detection result, which is prone to false positives or false negatives, reducing the accuracy and effectiveness of the detection.

[0006] The above information disclosed in the background art section is only used to enhance the understanding of the background of the present disclosure, and thus it may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The object of the present invention is to provide a method and system for detecting parasitic eggs to solve the problems raised in the above background art.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] A method for detecting parasitic eggs, the specific steps including:

[0010] Collect a certain volume of test sample from the uniformly mixed sample to be detected, put the collected test sample into a centrifuge tube, add physiological saline, and put it into a centrifuge for centrifugation. After centrifugation, remove the upper liquid and retain the sediment at the bottom of the tube;

[0011] Resuspend the centrifuged sediment in physiological saline, mix it evenly, set the flow rate of the mixed liquid injection, and inject the mixed liquid into the microfluidic chip based on this flow rate. There are fluid channels in the microfluidic chip, and protruding electrodes are arranged in the flow channels. The surfaces of the electrodes are coated with specific antibodies for adsorbing parasitic eggs;

[0012] Obtain the time series of the electrode potential change in the microfluidic chip during the whole injection process, calculate the current at different times based on the time series data of the potential change, and at the same time collect the microscope image of the electrode in the microfluidic chip after the mixed liquid is completely injected into the microfluidic chip;

[0013] Collect microscope pictures of different types of parasitic eggs, mark the outlines of the parasitic eggs in the collected pictures, establish a Yolov5s model, use the pictures with the outlines of the parasitic eggs marked as the input of the model, and use the outlines of the parasitic eggs as labels to train the Yolov5s model;

[0014] Input the microscope image of the electrode in the microfluidic chip into the trained Yolov5s model, identify the outlines of the parasitic eggs in the microscope image of the electrode in the microfluidic chip, extract the features of the image part identified as parasitic eggs, and obtain feature parameters, where the feature parameters include contour area, contour perimeter, and circularity;

[0015] Based on the change of the current at different times and the feature parameters, jointly judge whether there are parasitic eggs in the sample. If so, calculate the concentration of the parasitic eggs based on the current change and the number of parasitic eggs.

[0016] Further, place the collected test samples into a centrifuge tube. Based on the volume of the collected test samples, add physiological saline to the centrifuge tube at a ratio of 1:2. Place the centrifuge tube containing the test samples into a centrifuge, set the centrifuge speed to 3000 RMP, and the centrifugation time to 10 minutes, where RMP represents revolutions per minute. After centrifugation, obtain the sediment part at the bottom of the tube. Take the same volume of physiological saline as the sediment part and resuspend the centrifuged sediment part in the physiological saline.

[0017] Further, set the injection flow rate of the mixed liquid. Based on this flow rate, inject the mixed liquid into the microfluidic chip, determine the volume of the mixed liquid, the cross-sectional area of the fluid channel of the microfluidic chip, and the injection time required. The formula for setting the injection flow rate of the mixed liquid based on the determined injection parameters is:

[0018]

[0019] In the formula, v represents the injection flow rate, V is the volume of the mixed liquid, t z represents the set injection time required, and A is the cross-sectional area of the fluid channel of the microfluidic chip;

[0020] Inject the mixed liquid into the microfluidic chip repeatedly for multiple times to allow the mixed liquid to fully react with the electrodes in the fluid channel of the microfluidic chip.

[0021] Further, there are protruding electrodes in the flow channel, and the surfaces of the electrodes are coated with specific antibodies for adsorbing parasite eggs. The specific antibody is a protein produced by B cells and has high specificity. It can recognize and bind to specific antigen molecules. The specific antigen molecules include glycoproteins and lipids on the surface of parasite eggs. Coating the specific antibody on the electrode surface increases its ability to capture parasite eggs. In the microfluidic chip, when the mixed liquid passes through the flow channel, the eggs will come into contact with the antibodies on the electrode surface and be captured.

[0022] Further, collect the time series sequence E(t) of the electrode potential changes in the microfluidic chip during the entire process of repeatedly injecting the mixed liquid into the microfluidic chip multiple times. The formula for calculating the current at different times based on the time series data of the potential changes is:

[0023]

[0024] In the formula, I(t) represents the current on the electrode surface at time t, and I 0 is the current on the electrode surface at the initial time, R is the gas constant, and T is the air temperature;

[0025] Based on the calculated current on the electrode surface at different times, calculate the maximum change amount of the current on the electrode surface during the entire test process. The formula for calculating the maximum change amount of the current on the electrode surface is:

[0026] ΔI max = max|I(t) - I 0 |

[0027] In the formula, ΔI max represents the maximum change in the current on the electrode surface;

[0028] After the experiment, place the position of the electrode in the microfluidic chip under the microscope to collect images, and input the collected microscope images into the trained Yolov5s model.

[0029] Further, the steps of training the Yolov5s model include: collecting pictures of different types of parasite eggs under the microscope, using the method of manual marking to mark the outlines of different parasite eggs in the microscope pictures of parasite eggs, inputting the marked microscope pictures into the Yolov5s model, and using the outlines of the parasite eggs as labels to train the Yolov5s model. Finally, obtain a model with input as microscope pictures and output as pictures with the outlines of parasite eggs marked in the images.

[0030] Further, input the collected images of the electrode in the microfluidic chip under the microscope into the trained Yolov5s model. The model identifies and marks the parasite eggs captured on the electrode, extracts the marked contour images, and performs feature extraction to obtain feature parameters;

[0031] The formula for calculating the contour area using the pixel counting method is:

[0032] M i = E i * α

[0033] In the formula, M i represents the area of the i-th marked contour, E i represents the number of pixel points in the i-th marked contour image, and α represents the actual area of each pixel. Here, i is the index of the marked contour, i = 1, 2,..., n, where n represents the total number of marked contours;

[0034] The formula for calculating the contour perimeter is:

[0035]

[0036] In the formula, L i represents the contour perimeter of the i-th marked contour, P i,j represents the j-th boundary pixel point in the i-th marked contour, P i,j+1 represents the (j + 1)-th boundary pixel point in the i-th marked contour, that is, the adjacent pixel point of the j-th boundary pixel point, d(P i,j,P i,j+1 ) represents the distance between adjacent points P i,j and P i,j+1 in the contour, j is the index of the boundary pixel points, j = 1, 2, …, m, and m is the total number of boundary pixel points in the contour;

[0037] Calculate the circularity of the contour based on the contour area and the contour perimeter. The specific formula is as follows:

[0038]

[0039] In the formula, C i is the circularity of the contour;

[0040] Generate a parasite egg judgment coefficient based on the characteristic parameters. The specific formula is as follows:

[0041] xs i = ω 1 *C i + ω 2 *M i + ω 3 *L i

[0042] In the formula, xs i represents the judgment coefficient of the i-th marked contour, ω 1 , ω 2 and ω 3 are the weight coefficients of the contour circularity, the contour area, and the contour perimeter respectively. Among them, ω 1 > ω 2 ≥ ω 3 and ω 1 , ω 2 and ω 3 are all greater than 0.

[0043] Furthermore, the logic for jointly judging whether there are parasite eggs in the sample based on the change of current at different times combined with the characteristic parameters is as follows:

[0044] Generate an egg presence judgment coefficient based on the maximum change in the current on the electrode surface and the number of eggs determined by the image. The specific formula is as follows:

[0045] pd = ΔI max + G

[0046] In the formula, pd is the egg presence judgment coefficient, and G is the number of eggs determined by the image;

[0047] When pd > yu, it is judged that the test sample contains parasite eggs, where yu is the egg presence judgment threshold;

[0048] The logic for determining the number of parasite eggs G is as follows: The initial value of the number of parasite eggs G is set to 0. By comparing the preset parasite egg judgment threshold with the parasite egg judgment coefficient, if 0.4*yz ≤ xs i ≤ 0.6*yz, then the contour of the marked object is determined to be a parasite egg, and the number of eggs G determined by the image is incremented by 1.

[0049] Further, when it is determined that the test sample contains parasite eggs, the concentration of parasite eggs is calculated based on the current change and the number of parasite eggs. The formula for calculating the concentration of parasite eggs is as follows:

[0050]

[0051] In the formula, ND represents the concentration of parasite eggs, k is the sensitivity coefficient, ω 4 and ω 5 are respectively the maximum change in the current on the electrode surface and the weight coefficient of the number of eggs determined by the image. W α is the total volume of the sample to be tested, and W β is the volume of the test sample. Among them, ω 5 > ω 4 and ω 4 and ω 5 are both greater than 0.

[0052] The present invention also provides a detection system for parasite eggs. The detection system for parasite eggs is used to execute the above-mentioned detection method for parasite eggs, and includes:

[0053] A sample pretreatment module, which is used to collect a certain volume of test sample from the uniformly mixed sample to be tested, put the collected test sample into a centrifuge tube, add physiological saline, and perform a centrifugation operation in a centrifuge. After centrifugation, the upper liquid is removed, and the precipitate at the bottom of the tube is retained;

[0054] A parasite egg capture module, which is used to resuspend the centrifuged precipitate in physiological saline, mix it evenly, set the injection flow rate of the mixed liquid, and inject the mixed liquid into the microfluidic chip based on this flow rate. The microfluidic chip is provided with a fluid channel, and the flow channel is provided with protruding electrodes, and the electrode surface is coated with a specific antibody for adsorbing parasite eggs;

[0055] A test information acquisition module, which is used to obtain the time series of the electrode potential change in the microfluidic chip during the entire injection process, calculate the current at different times based on the time series data of the potential change, and simultaneously collect the microscopic image of the electrode in the microfluidic chip after the mixed liquid is completely injected into the microfluidic chip;

[0056] The recognition model training module is used to collect microscopic images of different types of parasite eggs, mark the outlines of the parasite eggs in the collected images, establish a Yolov5s model, use the images with the marked outlines of the parasite eggs as the input of the model, and use the outlines of the parasite eggs as labels to train the Yolov5s model;

[0057] The image feature extraction module is used to input the microscopic image of the electrode in the microfluidic chip into the trained Yolov5s model, identify the outlines of the parasite eggs in the microscopic image of the electrode in the microfluidic chip, extract features from the image part identified as a parasite egg, and obtain feature parameters, where the feature parameters include the outline area, the outline perimeter, and the circularity;

[0058] The egg concentration acquisition module is used to jointly judge whether there are parasite eggs in the sample based on the change of current at different times combined with the feature parameters. If there are, calculate the concentration of the parasite eggs based on the current change and the number of parasite eggs.

[0059] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0060] By combining microfluidic technology with a deep learning model, first, by utilizing the efficient centrifugation and precipitation separation capabilities of the microfluidic chip and combining with electrodes coated with specific antibodies, parasite eggs can be quickly and effectively extracted from complex samples, significantly shortening the detection time required. In addition, the design of the microfluidic chip can achieve high-throughput processing of samples, making the detection process more automated and improving work efficiency. Second, by training the Yolov5s model and performing deep learning with the outlines of parasite eggs under the microscope as labels, accurate egg recognition and counting can be achieved. This automated recognition not only reduces the errors of manual operations but also maintains consistency and reliability in large-scale detections. Finally, by combining the analysis of current changes and feature parameters, the concentration of parasite eggs in the sample can be quantitatively evaluated, realizing the automation, rapidity, and high precision of parasite egg detection. Description of the Drawings

[0061] Figure 1 It is a schematic diagram of the overall method flow of the present invention;

[0062] Figure 2 It is a schematic diagram of the overall system structure of the present invention. Detailed Embodiments

[0063] To make the objectives, technical solutions, and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below in conjunction with specific embodiments.

[0064] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the ordinary meanings understood by those with ordinary skills in the field to which the present invention pertains. The "first", "second" and similar terms used in the present invention do not denote any order, quantity or importance, but are only used to distinguish different components. The terms such as "comprising" or "including" mean that the elements or objects appearing before this word cover the elements or objects listed after this word and their equivalents, without excluding other elements or objects. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left" and "right" are only used to represent relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0065] Embodiment:

[0066] Please refer to Figure 1 , the present invention provides a technical solution:

[0067] A method for detecting parasite eggs, the specific steps include:

[0068] Step 1: Collect a certain volume of test sample from the uniformly mixed sample to be detected, put the collected test sample into a centrifuge tube, add physiological saline, and place it in a centrifuge for centrifugation. After centrifugation, remove the upper liquid and retain the sediment at the bottom of the tube;

[0069] Put the collected test sample into a centrifuge tube. Based on the volume of the collected test sample, add physiological saline to the centrifuge tube at a ratio of 1:2. Place the centrifuge tube containing the test sample in the centrifuge, set the centrifuge speed to 3000 RMP, and the centrifugation time to 10 minutes, where RMP represents revolutions per minute. After centrifugation, obtain the sediment at the bottom of the tube. Take the same volume of physiological saline as the sediment part and resuspend the centrifuged sediment part in physiological saline.

[0070] During centrifugation, solid particles (such as parasite eggs) in the sample will settle to the bottom of the tube due to the action of centrifugal force. This is because the centrifugal force will cause the denser solid particles to overcome the buoyancy of the liquid and form a precipitate. After centrifugation, all heavier particles (including parasite eggs) will accumulate at the bottom of the tube, while the upper liquid is mainly composed of lighter liquid components. Therefore, after removing the upper liquid, the sediment part at the bottom of the tube will retain the eggs.

[0071] Step 2: Resuspend the centrifuged precipitate portion in physiological saline. After mixing it evenly, set the flow rate of the mixed liquid injection. Based on this flow rate, inject the mixed liquid into the microfluidic chip. The microfluidic chip is provided with a fluid channel, and the flow channel is provided with protruding electrodes. The surface of the electrodes is coated with specific antibodies for adsorbing parasite eggs;

[0072] Set the flow rate of the mixed liquid injection. Based on this flow rate, inject the mixed liquid into the microfluidic chip. Determine the volume of the mixed liquid, the cross-sectional area of the fluid channel of the microfluidic chip, and the injection required time. The formula for setting the flow rate of the mixed liquid injection based on the determined injection parameters is as follows:

[0073]

[0074] In the formula, v represents the injection flow rate, V is the volume of the mixed liquid, t z represents the set injection required time, A is the cross-sectional area of the fluid channel of the microfluidic chip, and the set injection required time is set and modified according to the actual situation;

[0075] Inject the mixed liquid into the microfluidic chip repeatedly for multiple times to allow the mixed liquid to fully react with the electrodes in the fluid channel of the microfluidic chip.

[0076] The flow channel is provided with several protruding electrodes. The surface of the electrodes is coated with specific antibodies for adsorbing parasite eggs. The specific antibody is a protein produced by B cells and has high specificity. It can recognize and bind to specific antigen molecules. The specific antigen molecules include glycoproteins and lipids on the surface of parasite eggs. Coating the specific antibody on the surface of the electrodes increases its ability to capture parasite eggs. In the microfluidic chip, when the mixed liquid passes through the flow channel, the eggs will come into contact with the antibodies on the surface of the electrodes and be captured.

[0077] For different types of parasite eggs, the commonly used specific antibodies are usually antibodies against the surface characteristics of these eggs, such as specific antigens (such as eggshell proteins) against liver fluke eggs. Antibodies extracted from infected animals or synthesized monoclonal antibodies can be used. For specific antigens on the surface of whipworm eggs, they are usually the outer shell components of the eggs, and for antibodies against the surface characteristics of Ascaris eggs, such as specific glycoprotein antibodies against the eggshell. Therefore, different types of parasite eggs can be captured by coating different specific antibodies on the protruding electrodes.

[0078] Step 3: Obtain the time series sequence of the electrode potential change in the microfluidic chip during the entire injection process. Calculate the current at different moments based on the time series sequence data of the potential change. At the same time, collect the microscope images of the electrodes in the microfluidic chip after the mixed liquid is completely injected into the microfluidic chip;

[0079] During the process of repeatedly injecting the mixed liquid into the microfluidic chip for multiple times, collect the time series sequence E(t) of the electrode potential change in the microfluidic chip. The formula for calculating the current at different times based on the time series data of the potential change is as follows:

[0080]

[0081] In the formula, I(t) represents the current on the electrode surface at time t, and I 0 is the current on the electrode surface at the initial time. R is the gas constant, usually 8.314 J / (mol·K), and T is the air temperature.

[0082] Based on the calculated current on the electrode surface at different times, calculate the maximum change in the current on the electrode surface during the entire test process. The formula for calculating the maximum change in the current on the electrode surface is as follows:

[0083] ΔI max =max|I(t)-I 0 |

[0084] In the formula, ΔI max represents the maximum change in the current on the electrode surface.

[0085] After the test, place the position of the electrode in the microfluidic chip under the microscope to collect images, and input the collected microscope images into the trained Yolov5s model.

[0086] The presence of eggs may adsorb on the electrode, reducing the availability of reactants and thus reducing the current. For example, the molecular structure on the surface of the eggs may compete for adsorption with the electrode surface, hindering the reactants from participating in the reaction.

[0087] Step 4: Collect microscope images of different types of parasite eggs, mark the outlines of the parasite eggs in the collected images, establish a Yolov5s model, use the images with the marked outlines of the parasite eggs as the input of the model, and use the outlines of the parasite eggs as labels to train the Yolov5s model.

[0088] The steps for training the Yolov5s model include: collecting microscope images of different types of parasite eggs, using the manual marking method to mark the outlines of different parasite eggs in the microscope images of the parasite eggs, inputting the microscope images with markings into the Yolov5s model, and using the outlines of the parasite eggs as labels to train the Yolov5s model. Finally, obtain a model with microscope images as the input and images with the marked outlines of the parasite eggs in the images as the output.

[0089] Step 5: Input the microscopic image of the electrodes in the microfluidic chip into the trained Yolov5s model, identify the outlines of parasite eggs in the microscopic image of the electrodes in the microfluidic chip, extract the features of the image parts identified as parasite eggs, and obtain feature parameters, where the feature parameters include contour area, contour perimeter, and circularity;

[0090] Input the collected microscopic image of the electrodes in the microfluidic chip into the trained Yolov5s model. The model identifies and marks the parasite eggs captured on the electrodes, extracts the marked contour images, and performs feature extraction to obtain feature parameters;

[0091] The formula for calculating the contour area using the pixel counting method is as follows:

[0092] M i = E i * α

[0093] In the formula, M i represents the area of the i-th marked contour, E i represents the number of pixel points in the i-th marked contour image, and α represents the actual area of each pixel. Here, i is the index of the marked contour, i = 1, 2, …, n, where n represents the total number of marked contours;

[0094] The formula for calculating the contour perimeter is as follows:

[0095]

[0096] In the formula, L i represents the contour perimeter of the i-th marked contour, P i,j represents the j-th boundary pixel point in the i-th marked contour, P i,j+1 represents the (j + 1)-th boundary pixel point in the i-th marked contour, that is, the adjacent pixel point of the j-th boundary pixel point. d(P i,j , P i,j+1 ) represents the distance between adjacent points P i,j and P i,j+1 in the contour. j is the index of the boundary pixel point, j = 1, 2, …, m, and m is the total number of boundary pixel points in the contour;

[0097] Based on the contour area and contour perimeter, calculate the contour circularity. The specific formula is as follows:

[0098]

[0099] In the formula, C i is the contour circularity;

[0100] Based on the feature parameters, generate a parasite egg judgment coefficient. The specific formula is as follows:

[0101] xs i = ω 1 * C i + ω 2 * M i + ω 3 * L i

[0102] In the formula, xs i represents the judgment coefficient of the i-th marker contour, ω 1 , ω 2 and ω 3 are the weight coefficients of the contour circularity, contour area, and contour perimeter respectively. Among them, since the contour circularity of the parasite eggs has the greatest impact on judging whether they are parasite eggs, and the contour area and contour perimeter have less impact on the judgment compared to the contour circularity, so ω 1 > ω 2 ≥ ω 3 and ω 1 , ω 2 and ω 3 are all greater than 0.

[0103] Step 6: Based on the change of current at different times combined with characteristic parameters, jointly judge whether there are parasite eggs in the sample. If there are, calculate the concentration of parasite eggs based on the current change and the number of parasite eggs.

[0104] The logic for jointly judging whether there are parasite eggs in the sample based on the change of current at different times combined with characteristic parameters is as follows:

[0105] Based on the maximum change amount of the current on the electrode surface and the number of eggs determined by the image, jointly generate an egg presence judgment coefficient. The specific formula is:

[0106] pd = ΔI max + G

[0107] In the formula, pd is the egg presence judgment coefficient, and G is the number of eggs determined by the image;

[0108] When pd > yu, it is judged that the test sample contains parasite eggs, where yu is the egg presence judgment threshold;

[0109] Among them, the logic for determining the number of eggs G is: Set the initial value of the number of eggs G to 0. By comparing the preset parasite egg judgment threshold yz with the parasite egg judgment coefficient, if 0.4 * yz ≤ xs i ≤ 0.6 * yz, then it is judged that the contour of this marker is a parasite egg, and the number of eggs G determined by the image is incremented by 1;

[0110] Among them, the egg presence judgment threshold yu and the preset parasite egg judgment threshold yz can be set according to expert experience and the types of eggs to be detected actually;

[0111] By jointly judging whether there are parasite eggs in the sample based on current change and image recognition, most missed judgments and misjudgments can be avoided. That is, when the electrode is interfered by impurities such as non-parasite eggs, resulting in changes in potential and current, but in image recognition, no eggs are detected, causing errors. At the same time, the microscope images of the electrodes in the microfluidic chip are collected, rather than directly collecting the images of the mixed liquid, excluding the computational amount of image processing and recognition, reducing the interference of impurities in the image, reducing the computational resources while increasing the effectiveness of recognition;

[0112] When it is judged that the test sample contains parasite eggs, the concentration of parasite eggs is calculated based on the current change and the number of parasite eggs. The formula for calculating the concentration of parasite eggs is as follows:

[0113]

[0114] In the formula, ND represents the concentration of parasite eggs, k is the sensitivity coefficient, ω 4 and ω 5 are the weight coefficients of the maximum change in the current on the electrode surface and the number of eggs determined by the image respectively, W α is the total volume of the sample to be tested, W β is the volume of the test sample. Among them, since the change in current may be affected by the environment, the weight coefficient of the number of eggs determined by the image is set to be greater than the maximum change in the current on the electrode surface, that is, ω 5 > ω 4 and ω 4 and ω 5 are both greater than 0.

[0115] Please refer to Figure 2 , the present invention also provides a detection system for parasite eggs. The detection system for parasite eggs is used to execute the above-mentioned detection method for parasite eggs, including:

[0116] A sample pretreatment module, which is used to collect a certain volume of test sample from the uniformly mixed sample to be tested, put the collected test sample into a centrifuge tube, add physiological saline, and perform centrifugation in a centrifuge. After centrifugation, the upper layer of liquid is removed, and the sediment at the bottom of the tube is retained;

[0117] A parasite egg capture module, which is used to resuspend the precipitated part after centrifugation in physiological saline, mix it evenly, set the injection flow rate of the mixed liquid, and inject the mixed liquid into a microfluidic chip based on this flow rate. The microfluidic chip is provided with a fluid channel, and the flow channel is provided with a protruding electrode, and the surface of the electrode is coated with a specific antibody for adsorbing parasite eggs;

[0118] A test information acquisition module, which is used to obtain the time series sequence of the electrode potential change in the microfluidic chip during the entire injection process, calculate the current at different times based on the time series sequence data of the potential change, and simultaneously collect the microscope image of the electrode in the microfluidic chip after the mixed liquid is completely injected into the microfluidic chip;

[0119] An identification model training module, which is used to collect microscope pictures of different types of parasite eggs, mark the outlines of the parasite eggs in the collected pictures, establish a Yolov5s model, use the pictures marked with the outlines of the parasite eggs as the input of the model, and use the outlines of the parasite eggs as labels to train the Yolov5s model;

[0120] An image feature extraction module, which is used to input the microscope image of the electrode in the microfluidic chip into the trained Yolov5s model, identify the outlines of the parasite eggs in the microscope image of the electrode in the microfluidic chip, extract the features of the image part identified as the parasite eggs, and obtain feature parameters, and the feature parameters include contour area, contour perimeter and circularity;

[0121] An egg concentration acquisition module, which is used to jointly judge whether there are parasite eggs in the sample based on the change of the current at different times and the feature parameters. If so, calculate the concentration of the parasite eggs based on the current change and the number of parasite eggs.

[0122] The above formulas are all dimensionless and take their numerical values for calculation. The formula is obtained by collecting a large amount of data for software simulation to get a formula closest to the actual situation. The preset parameters in the formula are set by those skilled in the art according to the actual situation.

[0123] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by the combination of computer software and electronic hardware. Whether these functions are executed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0124] The unit described as the separation component may or may not be physically separated. The component displayed as a unit may or may not be a physical unit, and it may be located in one place or distributed across multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0125] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present application can easily think of changes or substitutions, which should all be covered within the protection scope of the present application.

Claims

1. A method for detecting parasite eggs, characterized in that: The specific steps include: A certain volume of test sample is collected from the uniformly mixed sample to be tested, the collected test sample is placed in a centrifuge tube, physiological saline is added, and the tube is placed in a centrifuge for centrifugation. After the centrifugation is completed, the upper layer of liquid is removed and the sediment at the bottom of the tube is retained; The precipitate after centrifugation is resuspended in physiological saline, mixed evenly, and the flow rate of the mixed liquid injection is set. Based on the flow rate, the mixed liquid is injected into a microfluidic chip, wherein a fluid channel is provided in the microfluidic chip, and a protruding electrode is provided in the flow channel. The electrode surface is coated with a specific antibody for adsorbing parasite eggs; Obtain the time series of the potential changes of the electrodes in the microfluidic chip during the entire injection process, calculate the current at different times based on the time series data of the potential changes, and collect the microscope image of the electrodes in the microfluidic chip after the mixed liquid is completely injected into the microfluidic chip; Collect microscope pictures of parasite eggs of different types, mark the outlines of the parasite eggs in the collected pictures, establish a Yolov5s model, use the pictures with the marked outlines of the parasite eggs as input to the model, and use the outlines of the parasite eggs as labels to train the Yolov5s model; Inputting the microscope image of the electrode in the microfluidic chip into the trained Yolov5s model, identifying the contour of the parasite egg in the microscope image of the electrode in the microfluidic chip, performing feature extraction on the image portion identified as the parasite egg, and obtaining feature parameters, wherein the feature parameters include contour area, contour perimeter and circularity; Based on the changes in current at different times combined with characteristic parameters, it is determined whether there are parasite eggs in the sample. If there are, the concentration of the parasite eggs is calculated based on the current changes and the number of parasite eggs.

2. A method for detecting parasite eggs according to claim 1, characterized in that: Put the collected test sample into a centrifuge tube, add physiological saline to the centrifuge tube at a ratio of 1:2 based on the volume of the collected test sample, put the centrifuge tube with the test sample into a centrifuge, set the centrifuge speed to 3000RMP, and the centrifugation time to 10 minutes, where RMP represents revolutions per minute. After centrifugation, obtain the precipitate at the bottom of the tube, take the same volume of physiological saline as the precipitate, and resuspend the precipitate after centrifugation in physiological saline.

3. A method for detecting parasite eggs according to claim 2, characterized in that: The flow rate of the mixed liquid injection is set, and the mixed liquid is injected into the microfluidic chip based on the flow rate. The volume of the mixed liquid, the cross-sectional area of ​​the fluid channel of the microfluidic chip and the time required for injection are determined. The formula for setting the mixed liquid injection flow rate based on the determined injection parameters is: In the formula, v represents the injection flow rate, V is the volume of the mixed liquid, and t z represents the required time for the set injection, and A is the cross-sectional area of ​​the fluid channel of the microfluidic chip; The mixed liquid is repeatedly injected into the microfluidic chip to allow the mixed liquid to fully react with the electrodes in the fluid channel of the microfluidic chip.

4. The method for detecting parasite eggs according to claim 1, characterized in that: Several protruding electrodes are provided in the flow channel, and the electrode surfaces are coated with specific antibodies for adsorbing parasite eggs. The specific antibodies are proteins produced by B cells, which are highly specific and can recognize and bind to specific antigen molecules. The specific antigen molecules include glycoproteins and lipids on the surface of parasite eggs. Coating specific antibodies on the electrode surface increases its ability to capture parasite eggs. In the microfluidic chip, when the mixed liquid passes through the flow channel, the eggs will contact the antibodies on the electrode surface and be captured.

5. The method for detecting parasite eggs according to claim 1, characterized in that: During the whole process of repeatedly injecting the mixed liquid into the microfluidic chip, the time series E(t) of the electrode potential change in the microfluidic chip is collected. The formula for calculating the current at different times based on the time series data of the potential change is: In the formula, I(t) represents the current on the electrode surface at time t, I0 is the current on the electrode surface at the initial time, R is the gas constant, and T is the air temperature; Based on the calculated electrode surface current at different times, the maximum change of the electrode surface current during the entire test process is calculated, where the formula for calculating the maximum change of the electrode surface current is: ΔI max =max|I(t)-I0| In the formula, ΔI max Indicates the maximum change in current on the electrode surface; After the experiment, the location of the electrodes in the microfluidic chip was placed under a microscope to collect images, and the images collected under the microscope were input into the trained Yolov5s model.

6. A method for detecting parasite eggs according to claim 5, characterized in that: The steps of training the Yolov5s model include: collecting microscope images of different types of parasite eggs, marking the outlines of different parasite eggs in the microscope images of parasite eggs by manual labeling, inputting the marked microscope images into the Yolov5s model, and using the outlines of the parasite eggs as labels to train the Yolov5s model, and finally obtaining an image with the image under the microscope as input and the outlines of the parasite eggs in the image marked as output.

7. A method for detecting parasite eggs according to claim 6, characterized in that: The collected images of the electrodes in the microfluidic chip under a microscope are input into the trained Yolov5s model. The model identifies and marks the parasite eggs captured on the electrodes, extracts the marked contour images, performs feature extraction, and obtains feature parameters. The formula for calculating the contour area using the pixel counting method is: M i =E i *a Where M i represents the area of ​​the i-th marker contour, E i represents the number of pixels in the i-th marker contour image, α represents the actual area of ​​each pixel, where i is the index of the marker contour, i = 1, 2, …, n, where n represents the total number of marker contours; The formula for calculating the contour perimeter is: Where, L i represents the contour perimeter of the i-th marked contour, P i,j represents the jth boundary pixel in the i-th marker contour, P i,j+1 represents the j+1th boundary pixel in the i-th marker contour, that is, the neighboring pixel of the j-th boundary pixel, d(P i,j ,P i,j+1 ) represents the adjacent points P in the contour i,j and P i,j+1 The distance between them, j is the index of the boundary pixel, j = 1, 2, ..., m, m is the total number of boundary pixels in the contour; The circularity of the contour is calculated based on the contour area and contour perimeter, and the specific formula is: In the formula, C i is the contour circularity; The parasite egg determination coefficient is generated based on the characteristic parameters, and the specific formula is as follows: xs i =ω1*C i +ω2*M i +ω3*L i In the formula, xs i represents the judgment coefficient of the i-th marked contour, ω1, ω2 and ω3 are the weight coefficients of contour circularity, contour area and contour perimeter, respectively, where ω1>ω2≥ω3 and ω1, ω2 and ω3 are all greater than 0.

8. A method for detecting parasite eggs according to claim 7, characterized in that: The logic for judging whether there are parasite eggs in the sample based on the changes in current at different times combined with characteristic parameters is as follows: The egg presence judgment coefficient is generated based on the maximum change in the electrode surface current and the number of eggs determined by the image. The specific formula is: pd=ΔI max +G In the formula, pd is the judgment coefficient of the presence of eggs, and G is the number of eggs determined by the image; When pd>yu, the sample is judged to contain parasite eggs, where yu is the judgment threshold for the presence of parasite eggs; The logic for determining the number of eggs G is as follows: the initial value of the number of eggs G is limited to 0, and the preset parasite egg judgment threshold yz is compared with the parasite egg judgment coefficient. If 0.4*yz≤xs is satisfied i When ≤0.6*yz, the outline of the mark is judged to be a parasite egg, and the number of eggs G determined by the image is increased by 1.

9. A method for detecting parasite eggs according to claim 8, characterized in that: When it is determined that the test sample contains parasite eggs, the concentration of the parasite eggs is calculated based on the current change and the number of parasite eggs, wherein the formula for calculating the concentration of the parasite eggs is: Where ND represents the concentration of parasite eggs, k is the sensitivity coefficient, ω4 and ω5 are the weight coefficients of the maximum change of the electrode surface current and the number of eggs determined by the image, respectively, and W α is the total volume of the sample to be tested, W β is the volume of the test sample, where ω5>ω4 and ω4 and ω5 are both greater than 0.

10. A parasite egg detection system, characterized in that: The parasite egg detection system is used to implement the parasite egg detection system method according to any one of claims 1 to 9, comprising: The sample pretreatment module is used to collect a certain volume of test samples from the evenly mixed samples to be tested, put the collected test samples into a centrifuge tube, add physiological saline, put it into a centrifuge for centrifugation, and after the centrifugation, remove the upper layer of liquid and retain the sediment at the bottom of the tube; The parasite egg capture module is used to resuspend the precipitate after centrifugation in physiological saline, mix it evenly, set the flow rate of the mixed liquid injection, and inject the mixed liquid into the microfluidic chip based on the flow rate. The microfluidic chip is provided with a fluid channel, and the flow channel is provided with a protruding electrode. The surface of the electrode is coated with a specific antibody for adsorbing parasite eggs; The test information acquisition module is used to obtain the time series of the potential changes of the electrodes in the microfluidic chip during the entire injection process, calculate the current at different times based on the time series data of the potential changes, and collect the microscope image of the electrodes in the microfluidic chip after the mixed liquid is completely injected into the microfluidic chip; The recognition model training module is used to collect microscope pictures of different types of parasite eggs, mark the outlines of the parasite eggs in the collected pictures, establish a Yolov5s model, use the pictures with the marked outlines of the parasite eggs as input to the model, and use the outlines of the parasite eggs as labels to train the Yolov5s model; An image feature extraction module is used to input the microscope image of the electrode in the microfluidic chip into the trained Yolov5s model, identify the contour of the parasite egg in the microscope image of the electrode in the microfluidic chip, extract features of the image portion identified as the parasite egg, and obtain feature parameters, wherein the feature parameters include contour area, contour perimeter and circularity; The worm egg concentration acquisition module is used to determine whether there are parasite eggs in the sample based on the changes in current at different times combined with characteristic parameters. If so, the concentration of the parasite eggs is calculated based on the current changes and the number of parasite eggs.

Images