A method for analyzing and managing detection data of aquatic bacteria drug sensitivity test kit

Abstract

The present invention belongs to the technical field of microbial drug sensitivity detection, and relates to a method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit. The method analyzes the images of the test kit where various drug sensitivity reagents are located for each disease sample, quickly and accurately evaluates the effective antibacterial degree of various drug sensitivity reagents for each disease sample, fully considers the severity of the symptoms and the physiological metabolism degree of each disease sample, eliminates the individual differences of each disease sample, and thoroughly understands the sensitivity coefficients of the current disease bacteria in the target aquaculture farm to various drug sensitivity reagents, thereby screening the best antimicrobial drug type that is compatible with the current disease in the target aquaculture farm, and combines the actual situation of the target aquaculture farm to analyze and feedback the actual drug dosage of the best antimicrobial drug type per unit aquatic acre of the target aquaculture farm, which not only improves the efficiency and accuracy of drug sensitivity analysis, but also provides a scientific and intelligent disease prevention and control solution for the aquaculture farm.

Description

Technical Field

[0001] The invention belongs to the technical field of microbial drug sensitivity detection, and relates to a method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit. Background Art

[0002] In recent years, the aquaculture industry has developed rapidly, but the increase in breeding scale and density has increased the incidence of bacterial diseases in aquatic animals, causing serious harm. Drug sensitivity testing is an important means to scientifically select drugs and avoid drug abuse. It can improve the accuracy of medication, the effect of disease treatment, reduce costs and improve the quality of farmed animals. It is widely used in the prevention and control of aquaculture diseases. However, the actual application is complicated and lengthy, and it is easy to make mistakes due to personnel or instrument problems. In addition, if the drug sensitivity results are not fed back in time, the reporting error rate is high, and the drug selection is unreasonable, the application effect will also be affected. Therefore, it is very important to develop efficient, accurate and practical data analysis and management methods for aquatic bacterial drug sensitivity test kits.

[0003] In the prior art, there are also some solutions related to drug sensitivity test management, for example, a drug sensitivity test result recognition method and system based on a decision tree is disclosed in China Patent Publication No. CN111310792B, which collects drug sensitivity test result data, converts the drug sensitivity test result data into a training data set for a decision tree classifier, uses the trained decision tree classifier to determine the positive and negative classification results of the micropores of the drug sensitivity plate, calculates the MIC in combination with the drug layout information of the micropores, and determines the drug resistance results based on the MIC results and the breakpoint value standard. Compared with the traditional method of determining the positive and negative results of drug sensitivity tests by OD value, it is not affected by the size of the OD value of the positive control well, can flexibly mine the rules in the data, and has a higher compliance rate with the visual inspection method, thereby improving the accuracy of determining the positive and negative results.

[0004] Another Chinese patent publication number CN116150675A is a drug sensitivity classification method, system and device based on multi-omics data integration. It uses joint non-negative matrix decomposition to decompose multiple omics matrices of all multi-omics data samples. The obtained shared matrix represents the linear integration features of all samples, and the nonlinear integration features of all samples are obtained by using variational autoencoders. The spliced ​​feature vector obtained by splicing linear integration features, nonlinear integration features and drug features is used for drug sensitivity classification. The complementarity of linear integration features and nonlinear integration features is used to mine the potential information between multi-omics data, thereby greatly improving the accuracy of drug sensitivity classification.

[0005] However, the existing technology still has certain limitations, specifically: 1. The existing technology for drug sensitivity analysis is too complicated and time-consuming, requiring high-performance computing equipment and a lot of computing time. It is not suitable for small or medium-sized aquaculture sites, and fails to effectively grasp the changing characteristics of the impact of drug sensitivity on the color of the drug sensitivity test solution, and cannot be carried out in the most intuitive and convenient image analysis method.

[0006] 2. Existing technologies for drug sensitivity analysis ignore individual differences in disease samples. The collected pathogens may be affected by the severity of their host disease or metabolic level, which may lead to different drug sensitivity responses of the same pathogens in different disease samples, making the drug sensitivity analysis results unreliable and inaccurate.

[0007] 3. After conducting drug sensitivity testing, existing technologies often fail to provide customized guidance and suggestions based on the specific conditions and needs of aquaculture farms, resulting in aquaculture farms being unable to take the most effective measures when dealing with diseases, thus affecting breeding results and economic benefits. Summary of the invention

[0008] In view of this, in order to solve the problems raised in the above background technology, a method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit is now proposed.

[0009] The purpose of the present invention can be achieved through the following technical solutions: The present invention provides a method for analyzing and managing detection data of an aquatic bacterial drug sensitivity test kit, including: S1. Randomly extracting a preset number of disease samples of the same species and the same symptoms in a target aquaculture farm, and preparing bacterial drug sensitivity test solutions containing various types of antibacterial drugs at preset concentrations for each disease sample in the target aquaculture farm according to a preset operating procedure, which are recorded as various types of drug sensitivity reagents for each disease sample.

[0010] S2. Inject various drug sensitivity reagents of various disease samples into the preset row wells of their corresponding test kits, place them in a standard incubator and culture them for a fixed period of time, then collect images of the test kits where various drug sensitivity reagents of various disease samples are located.

[0011] S3. Analyze the images of the test kits containing various drug-sensitive reagents for each disease sample, and evaluate the effective antibacterial degree of various drug-sensitive reagents for each disease sample.

[0012] S4. Eliminate the individual differences of each disease sample and screen the best type of antimicrobial drug that is compatible with the current disease in the target aquaculture farm.

[0013] S5. Analyze the actual dosage of the best type of antimicrobial drug per unit area of ​​aquatic products in the target aquaculture farms and provide feedback.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) The present invention analyzes the images of the test kits containing various drug-sensitive reagents for various disease samples, converts the image color space, identifies the effective inhibition zones, and analyzes their area characteristic inhibition index, boundary characteristic inhibition index, and texture characteristic inhibition index, so as to accurately analyze the effective inhibition degree of various drug-sensitive reagents for various disease samples. The analysis process is highly automated, simplified, and scientific, providing a scientific, efficient, and intelligent disease prevention and control solution for aquaculture farms.

[0015] (2) The present invention eliminates the individual differences of various disease samples and has a detailed understanding of the sensitivity coefficients of the current disease bacteria in the target aquaculture farm to various drug sensitivity reagents, thereby screening the best type of antimicrobial drugs that are compatible with the current diseases in the target aquaculture farm. This provides a scientific, efficient and personalized antimicrobial drug screening program for aquaculture farms, significantly improves the accuracy and effectiveness of disease prevention and control, and promotes the healthy development of the aquaculture industry.

[0016] (3) The present invention combines the actual situation of the target aquaculture farms to analyze and feedback the actual dosage of the best antimicrobial drug type per unit area of ​​aquatic products in the target aquaculture farms, thereby significantly improving the accuracy and efficiency of drug use, promoting targeted disease prevention and control, and promoting the sustainable development of the aquaculture industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0018] Figure 1 The present invention is a flowchart of the steps for implementing the method.

[0019] Figure 2 It is a schematic diagram of the image of the test kit in which each drug-sensitive reagent for each disease sample of the present invention is located.

[0020] Figure 3 A logical schematic diagram of the present invention for screening the best type of antimicrobial drug compatible with the current disease of the target aquaculture farm. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] See also Figure 1 As shown, the present invention provides a method for analyzing and managing detection data of an aquatic bacterial drug sensitivity test kit, including: S1. randomly extracting a preset number of disease samples of the same species and the same disease in a target aquaculture farm, and preparing a bacterial drug sensitivity test solution containing various types of antibacterial drugs at preset concentrations for each disease sample in the target aquaculture farm according to a preset operating procedure, which is recorded as various types of drug sensitivity reagents for each disease sample.

[0023] See also Figure 2 As shown, S2. Each disease sample and each drug sensitivity reagent are injected into each preset row plate of the corresponding test kit, placed in a standard incubator for a fixed period of time, and then the image of the test kit where each disease sample and each drug sensitivity reagent are located is collected.

[0024] S3. Analyze the images of the test kits containing various drug-sensitive reagents for each disease sample, and evaluate the effective antibacterial degree of various drug-sensitive reagents for each disease sample.

[0025] Specifically, the evaluation of the effective antibacterial degree of each type of drug sensitivity reagent for each disease sample includes: S31. Identifying and cutting each liquid filling hole in the drug sensitivity box image where each type of drug sensitivity reagent for each disease sample is located, and converting the image into Color space, recording the pixel in each filling hole The color intensity value.

[0026] Fill each liquid hole Color intensity values ​​are in preset Each pixel within the red component intensity value range of the color space is regarded as a red pixel, and the proportion of red pixels in each filling hole is counted. , is the number of each filling hole, , through the formula The first-order inhibition degree of each liquid-filled well was analyzed.

[0027] S32. According to the effective antibacterial pixel stored in the WEB cloud The preset standard intensity interval of each color channel in the color space is set to Each pixel whose color channel intensity value is within its preset standard intensity range is taken as each effective antibacterial pixel, and each effective antibacterial circle stored in each liquid filling hole is identified and cut.

[0028] The area characteristic antibacterial index, boundary characteristic antibacterial index and texture characteristic antibacterial index of each effective antibacterial circle in each liquid-filled hole were analyzed, and then the second-order antibacterial degree of each liquid-filled hole was analyzed.

[0029] S33. The first-order antibacterial degree and the second-order antibacterial degree of the filling hole are respectively accumulated with the product of their corresponding preset weights, and the accumulated value is used as the comprehensive antibacterial degree of the filling hole. If the comprehensive antibacterial degree of a certain filling hole is greater than or equal to the preset comprehensive antibacterial degree reaching the standard threshold, it means that the built-in antibacterial drug in the filling hole achieves effective antibacterial effect, and the filling hole is recorded as an antibacterial filling hole. In this way, the antibacterial filling holes in the drug sensitivity box where various drug sensitivity reagents of various disease samples are located are screened, and the proportion of the number of antibacterial filling holes in the drug sensitivity box where various drug sensitivity reagents of various disease samples are located and the average antibacterial degree of the antibacterial filling holes exceeding the standard are sorted out. The proportion of the number of antibacterial filling holes and the average antibacterial degree of the antibacterial filling holes exceeding the standard are multiplied to obtain the effective antibacterial degree of various drug sensitivity reagents of various disease samples.

[0030] Specifically, the identifying and cutting of each effective antibacterial circle stored in each liquid-filling hole includes: performing a connected domain search with any effective antibacterial pixel point in each liquid-filling hole as a starting point, and identifying each connected domain composed of effective antibacterial pixel points in each liquid-filling hole based on the condition that the area of ​​the searched connected domain is greater than or equal to a preset reference forming area.

[0031] The grayscale gradient value of each boundary pixel point in each connected domain composed of the effective antibacterial pixel points in each liquid-filled hole is calculated, and the boundary pixel points whose grayscale gradient value is less than the preset reference edge grayscale gradient value are eliminated, and the boundaries of each connected domain are re-outlined to generate each effective antibacterial circle in the memory of each liquid-filled hole.

[0032] It should be noted that the specific calculation process of the grayscale gradient value of each boundary pixel point in each connected domain composed of the effective antibacterial pixel points in each liquid-filled hole is as follows: construct the grayscale gradient value of each boundary pixel point in each connected domain composed of the effective antibacterial pixel points in each liquid-filled hole. The gray value matrix of the neighborhood pixels is convolved with the horizontal convolution kernel and the vertical convolution kernel preset in the Sobel operator to obtain the horizontal gradient and vertical gradient of each boundary pixel point in each connected domain composed of the effective antibacterial pixel points in each liquid-filled hole. The horizontal gradient and the vertical gradient are vector-synthesized, that is, the squares of the two directional gradients are added and the square root is taken to obtain the gray gradient value of each boundary pixel point in each connected domain composed of the effective antibacterial pixel points in each liquid-filled hole.

[0033] Specifically, the analysis of the second-order antibacterial degree of each filling hole includes: counting the number of pixels contained in each effective antibacterial circle in each filling hole, converting the area of ​​each effective antibacterial circle in each filling hole with a preset ratio, and taking the ratio of the area of ​​each effective antibacterial circle in each filling hole to the preset standard area of ​​the filling hole of the drug sensitive box as the area characteristic antibacterial index of each effective antibacterial circle in each filling hole , is the number of each effective inhibition zone, .

[0034] The grayscale gradient values ​​of each boundary pixel point of each effective inhibition zone in each liquid-filled hole were sorted out. According to the grayscale gradient average value and grayscale gradient standard deviation of the boundary pixels of each effective inhibition zone in each liquid-filled hole, the grayscale gradient average value was used as the numerator and the grayscale gradient standard deviation was used as the denominator for ratio analysis. The ratio analysis result was used as the boundary clarity, so as to obtain the boundary clarity of each effective inhibition zone in each liquid-filled hole.

[0035] The minimum fitting circle of each effective inhibition circle in each liquid-filled hole is constructed, and the deviation distance of each boundary pixel point of each effective inhibition circle in each liquid-filled hole with respect to its minimum fitting circle is obtained. According to the root mean square of the deviation distance of each boundary pixel point of each effective inhibition circle in each liquid-filled hole with respect to its minimum fitting circle, the inverse of the root mean square is taken as the boundary regularity, thereby obtaining the boundary regularity of each effective inhibition circle in each liquid-filled hole.

[0036] It should be noted that the process of obtaining the deviation distance of each boundary pixel point of each effective inhibition circle in each liquid-filling hole with respect to its minimum fitting circle is as follows: constructing an image coordinate system, obtaining the position coordinates of each boundary pixel point of each effective inhibition circle in each liquid-filling hole, obtaining the center coordinates and radius of the minimum fitting circle of each effective inhibition circle in each liquid-filling hole, substituting the position coordinates of a boundary pixel point of a certain effective inhibition circle in a certain liquid-filling hole and the center coordinates of the minimum fitting circle of the effective inhibition circle in the liquid-filling hole into the Euclidean distance formula, further subtracting the calculated result from the radius of the minimum fitting circle of the effective inhibition circle in the liquid-filling hole, converting the difference into an absolute value to obtain the deviation distance of the boundary pixel point of the effective inhibition circle in the liquid-filling hole with respect to its minimum fitting circle, thereby obtaining the deviation distance of each boundary pixel point of each effective inhibition circle in each liquid-filling hole with respect to its minimum fitting circle.

[0037] It should be noted that when the grayscale gradient standard deviation and root mean square are used as denominators, a preset constant needs to be added to prevent the denominator from being zero.

[0038] The cumulative value of boundary clarity and boundary regularity is used as the boundary characteristic antibacterial index, thereby obtaining the boundary characteristic antibacterial index of each effective antibacterial circle in each filling hole .

[0039] The image is converted into a grayscale image to construct a grayscale symbiosis matrix in each effective inhibition zone in each liquid-filled hole. According to the energy, contrast and entropy fed back by the grayscale symbiosis matrix, the energy is used as the numerator and the sum of contrast and entropy is used as the denominator to carry out ratio analysis. The ratio analysis result is used as the texture feature antibacterial index, thereby obtaining the texture feature antibacterial index of each effective inhibition zone in each liquid-filled hole. .

[0040] It should be noted that the analysis basis of the antibacterial index of the texture characteristics of each effective antibacterial circle in each of the above-mentioned liquid-filled holes is as follows: under normal conditions, bacteria that are not affected by the antibacterial effect are randomly distributed on the culture medium and continue to proliferate, forming colonies of different sizes and shapes that are intertwined with each other, causing the surface texture of the culture medium to appear messy.

[0041] When conducting a bacterial sensitivity test, if the antibacterial drugs in the test solution are effective, the growth of bacteria in the inhibition zone will be inhibited. If the antibacterial effect is good, the growth and reproduction of bacteria will be significantly hindered, and there will be no complex texture changes in the inhibition zone due to bacterial growth, thus presenting a uniform texture state.

[0042] From the perspective of the parameters for feedback texture uniformity, energy is the sum of the squares of the grayscale co-occurrence matrix element values. When the energy value is high, it indicates that the probability of a certain grayscale combination in the image is high, which means that the texture has high regularity and uniformity. Contrast is used to measure the degree of local change in the image. For areas with uniform texture, the difference in grayscale values ​​between adjacent pixels is small, and the elements of its grayscale co-occurrence matrix are concentrated near the diagonal, and the contrast is low. Entropy is a measure of the richness of image texture information. For images with uniform texture, the distribution of grayscale co-occurrence matrix elements is relatively concentrated, and only a few grayscale combinations have a high probability of occurrence, so the entropy value is low. In summary, when evaluating the antibacterial index of texture features, energy is positively correlated with the antibacterial effect, and entropy and contrast are negatively correlated with the antibacterial effect.

[0043] Then by the formula The second-order inhibition degree of each filling hole was analyzed. The preset weights are the area feature antibacterial index, boundary feature antibacterial index, and texture feature antibacterial index. Indicates The maximum value of the comprehensive antibacterial index of the liquid-filled holes combined with the area characteristics, boundary characteristics, and texture characteristics.

[0044] For example, the above The specific value can be The value is based on the following: the size of the inhibition zone is directly related to the diffusion range and antibacterial ability of the antibacterial agent. A larger inhibition zone area generally means that the antibacterial agent can inhibit bacterial growth in a larger range, which intuitively reflects the effective range of the antibacterial agent. Clear and regular boundaries often mean that the diffusion of the antibacterial agent in the medium is relatively stable and uniform, and the boundaries of the area where bacterial growth is inhibited are clear, which indirectly reflects the stability of the antibacterial process and the effective effect of the antibacterial agent. Uniform texture usually means that bacterial growth in the inhibition zone is well inhibited, and there is no complex texture change caused by bacterial growth. However, texture characteristics may be affected by some external factors, such as the texture of the culture medium, slight differences in the experimental operation process, etc. Compared with area characteristics and boundary characteristics, its direct reflection of the degree of inhibition is slightly weaker.

[0045] Specifically, the average antibacterial degree exceeding the standard of the antibacterial filling holes in the drug sensitivity box where each type of drug sensitivity reagent is located for each disease sample is the calculated average of the difference between the comprehensive antibacterial degree of each antibacterial filling hole in the drug sensitivity box where each type of drug sensitivity reagent is located for each disease sample and the preset comprehensive antibacterial degree reaching the standard threshold.

[0046] The embodiment of the present invention analyzes the images of the test kits where various drug-sensitive reagents for various disease samples are located, converts the image color space, identifies the effective inhibition zones and analyzes their area characteristic inhibition indexes, boundary characteristic inhibition indexes and texture characteristic inhibition indexes, accurately analyzes the effective inhibition degree of various drug-sensitive reagents for various disease samples, and the analysis process is highly automated, simplified and scientific, providing a scientific, efficient and intelligent disease prevention and control solution for aquaculture farms.

[0047] S4. Eliminate the individual differences of each disease sample and screen the best type of antimicrobial drug that is compatible with the current disease in the target aquaculture farm.

[0048] See also Figure 3 Specifically, the screening of the best antimicrobial drug type suitable for the current disease in the target aquaculture farm includes: obtaining the symptom status data and growth status data of each disease sample in the target aquaculture farm, analyzing the standardized symptom severity of each disease sample in the target aquaculture farm and physiological metabolism , is the number of each disease sample in the target aquaculture farm, , extract the effective antibacterial degree of various drug sensitivity reagents from various disease samples , is the serial number of each drug sensitivity reagent. Calculate the sensitivity coefficient of the current pathogenic bacteria in the target aquaculture farm relative to various drug sensitivity reagents ,in They are the preset impact weights corresponding to the severity of the disease and the degree of physiological metabolism. , is the number of disease samples in the target aquaculture farm, The preset constant is used to screen the antimicrobial drug type in the drug sensitivity reagent corresponding to the maximum sensitivity coefficient as the best antimicrobial drug type suitable for the current disease in the target aquaculture farm.

[0049] It should be noted that the analysis basis of the calculation formula for the sensitivity coefficient of the current diseased bacteria in the above-mentioned target aquaculture farms to various drug sensitivity reagents is that the severity of the symptoms and the degree of physiological metabolism of the diseased specimens are important factors affecting the reaction of drug sensitivity reagents.

[0050] In terms of the severity of the symptoms, when the symptoms of the disease-like body are more serious, the reproduction and destruction of the pathogen in the body are higher, such as large areas of ulceration on the fish body and a large number of black spots on the shrimp body. The disease-like body's own defense mechanism is greatly damaged, making it easier for the drugs in the drug sensitivity reagent to interact with the pathogen, resulting in a greater reaction of the drug sensitivity reagent.

[0051] In terms of physiological metabolism, when the physiological metabolism level of the disease sample is high, the material exchange and energy metabolism in the body are active, which is conducive to the absorption of drug components in the drug sensitivity reagent and will also lead to a greater reaction of the drug sensitivity reagent.

[0052] In the calculation formula for the sensitivity coefficient of the current disease bacteria in the target aquaculture farm to various drug sensitivity reagents, the severity of the disease and the degree of physiological metabolism after standardized treatment are multiplied by their respective preset weights and added up. The accumulated value represents the degree of influence of the individual differences of the disease samples on the comprehensive reaction of the drug sensitivity reagents. The effective antibacterial degree of each drug sensitivity reagent for each disease sample is used as the numerator, and the above accumulated value and the preset constant that prevents the denominator from being 0 are further accumulated as the denominator to remove the calculation deviation caused by the individual differences of the disease samples on the reaction of the drug sensitivity reagent, so that the calculation result more reasonably reflects the actual effect of the drug sensitivity reagent.

[0053] For example, the above The specific value can be .

[0054] Specifically, the The specific analysis process includes: according to the symptom status data of each disease sample in the target aquaculture farm, the symptom record content and symptom duration The symptom record content includes the appearance lesion area ratio, appearance lesion location, abnormal behavior frequency, abnormal behavior corresponding to each descriptive keyword and each physiological index monitoring value. According to the appearance lesion area ratio and appearance lesion location, the appearance symptom severity index of the disease sample is analyzed. According to the abnormal behavior frequency and each descriptive keyword corresponding to the abnormal behavior, the abnormal behavior severity index of the disease sample is analyzed. According to the monitoring value of each physiological index, the physiological state severity index of the disease sample is analyzed. The appearance symptom severity index, abnormal behavior severity index and physiological state severity index of the disease sample are respectively accumulated with the product of their corresponding preset weights to obtain the symptom severity index of the disease sample, thereby obtaining the symptom severity index of each disease sample in the target aquaculture farm. , according to the formula Obtain the severity of each disease sample in the target aquaculture farm, and calculate the average severity of the disease samples in the target aquaculture farm and standard deviation , further by the formula Obtain standardized symptom severity of each disease specimen in the target aquaculture farm.

[0055] It should be noted that the specific analysis processes of the above-mentioned disease-sample appearance symptom severity index, abnormal behavior severity index, and physiological state severity index are as follows: setting the important influence weights of each appearance part of the disease-sample to obtain the important influence weights of the appearance lesion parts of the disease-sample, and multiplying them by the proportion of the appearance lesion area of ​​the disease-sample to obtain the appearance symptom severity index of the disease-sample.

[0056] The abnormal behavior frequency of the disease sample is compared with the preset reference abnormal behavior frequency to obtain the abnormal behavior frequency ratio of the disease sample, and the symptom content corresponding to each abnormal behavior level of the disease sample species stored in the WEB cloud is extracted and compared with each description keyword corresponding to the abnormal behavior of the disease sample to obtain the highest abnormal behavior level involved in the description keyword of the abnormal behavior of the disease sample, and the abnormal degree value corresponding to each abnormal behavior level of the aquaculture species is set to obtain the abnormal degree value corresponding to the highest abnormal behavior level involved in the description keyword of the abnormal behavior of the disease sample, which is multiplied by the abnormal behavior frequency ratio of the disease sample to obtain the abnormal behavior severity index of the disease sample.

[0057] The reasonable monitoring intervals of various physiological indicators preset for the disease sample species stored in the WEB cloud are extracted and compared with the monitoring values ​​of various physiological indicators of the disease sample. If the monitoring value of a physiological indicator of the disease sample is within its reasonable monitoring interval, the abnormal ratio of the physiological indicator of the disease sample is set to 0. If the monitoring value of a physiological indicator of the disease sample is outside its reasonable monitoring interval and is greater than the upper limit of the interval, the absolute difference between the monitoring value of the physiological indicator of the disease sample and the upper limit of its reasonable monitoring interval is calculated, and the absolute difference is analyzed with the upper limit of its reasonable monitoring interval to obtain the abnormal ratio of the physiological indicator of the disease sample. If the monitoring value of a physiological indicator of the disease sample is outside its reasonable monitoring interval and is less than the lower limit of the interval, the absolute difference between the monitoring value of the physiological indicator of the disease sample and the lower limit of its reasonable monitoring interval is calculated, and the absolute difference is analyzed with the lower limit of its reasonable monitoring interval to obtain the abnormal ratio of the physiological indicator of the disease sample. In this way, the abnormal ratios of various physiological indicators of the disease sample are obtained, and the accumulation is used to obtain the severity index of the physiological state of the disease sample.

[0058] Specifically, the The specific analysis process includes: the growth status data of each diseased sample in the target aquaculture farm include weight, body length and test oxygen consumption, the fatness of the diseased sample is calculated based on weight and body length, and the preset material metabolism level index corresponding to the fatness interval of each material metabolism level stored in the WEB cloud is combined to obtain the preset material metabolism level index corresponding to the material metabolism level of the fatness interval of each diseased sample in the target aquaculture farm. .

[0059] It should be noted that the specific calculation process of the fatness of the above diseased sample is as follows: ,in are the weight and length of the diseased specimen, is a preset constant, which can be 100 or 1000. It should be noted that the fatness formula is for fish or aquatic organisms. The general calculation formula for fatness involves analysis and calculation between two different dimensions. In the actual calculation process, the units of the weight value and the body length value must be consistent. For example, if the weight unit is kilograms, the body length unit must be meters, or if the weight unit is grams, the body length unit must be centimeters. Substitute the weight value and body length value with consistent units into the formula, and do not substitute the dimension units, so that the fatness of the diseased sample is a dimensionless unit value, that is, fatness is only a relative value, which is used for comparison between the same species or similar species, and does not rely on specific physical units to reflect its meaning.

[0060] According to the oxygen consumption intervals corresponding to each energy metabolism level and the preset energy metabolism level indicators stored in the WEB cloud, the preset energy metabolism level indicators corresponding to the energy metabolism level of the test oxygen consumption interval of each disease sample in the target aquaculture farm are obtained. .

[0061] By formula The physiological metabolic degree of each disease sample in the target aquaculture farm is obtained, which is consistent with the calculation method of the standardized symptom severity of each disease sample in the target aquaculture farm, and the standardized physiological metabolic degree of each disease sample in the target aquaculture farm is obtained.

[0062] The embodiment of the present invention eliminates the individual differences of various disease samples and carefully understands the sensitivity coefficients of the current disease bacteria in the target aquaculture farm to various drug sensitivity reagents, thereby screening the best type of antimicrobial drugs suitable for the current diseases in the target aquaculture farm, providing a scientific, efficient and personalized antimicrobial drug screening program for aquaculture farms, significantly improving the accuracy and effectiveness of disease prevention and control, and promoting the healthy development of the aquaculture industry.

[0063] S5. Analyze the actual dosage of the best type of antimicrobial drug per unit area of ​​aquatic products in the target aquaculture farms and provide feedback.

[0064] Specifically, the analysis of the actual dosage of the best antimicrobial drug type per unit aquatic land in the target aquaculture farm includes: detecting the minimum inhibitory concentration of the best antimicrobial drug type for the current disease in the target aquaculture farm through a drug sensitivity concentration experiment , obtain the water volume corresponding to the total aquatic land per mu of the target aquaculture farm , effective drug diffusion coefficient and drug loss rate , according to the formula Analyze the actual dosage of the best antimicrobial drug type per unit area of ​​aquaculture in the target aquaculture farms, including The actual drug dosage of the best antibiotic type per unit aquatic acre is converted to the total aquatic land area of ​​the target aquaculture farm, and compared with the preset safe release concentration threshold of the best antibiotic type for the current disease in the target aquaculture farm. If the comparison relationship is less than or equal to, the actual drug dosage of the best antibiotic type per unit aquatic acre is judged to meet the benchmark safety conditions for drug use. If the comparison relationship is greater than, the preset safe release concentration of the best antibiotic type for the current disease in the target aquaculture farm is used as the release standard for release.

[0065] It should be noted that the specific process of obtaining the water volume corresponding to the total aquatic land per mu of the above-mentioned target aquaculture farms, the effective diffusion coefficient of the drug and the drug loss rate is as follows: the managers of the target aquaculture farms measure the average water depth in the farms, convert the mu unit into square meters, and multiply it by the average water depth to obtain the water volume corresponding to the total aquatic land per mu of the target aquaculture farms.

[0066] Release the preset quality to the preset area of ​​the target aquaculture farm A preset number of detection points are set at the delivery point, and the change of tracer concentration over time is monitored by a fluorescence spectrophotometer. The distribution formula of the tracer concentration change over time at the delivery point under the one-dimensional diffusion state is deduced based on Fick's law. , is the location variable of the placement point, is the time variable, is the preset constant, The diffusion coefficient of the tracer concentration is substituted into the tracer concentration at each unit time point in the preset time period to obtain the diffusion coefficient of the tracer concentration and use it as the effective diffusion coefficient of the drug corresponding to the total aquatic land per mu of the target aquaculture farm.

[0067] For the target aquaculture farm, a closed aquaculture water unit of preset volume is selected and a fixed mass of medicine is released into it. After a preset period of time, the management personnel use chemical technology to detect the remaining mass of the medicine, subtract the remaining mass of the medicine from the fixed mass of the medicine, and calculate the difference, which is further analyzed with the ratio of the fixed mass of the medicine released to obtain the drug loss rate corresponding to the total aquatic land per mu of the target aquaculture farm.

[0068] It should also be noted that the actual drug dosage unit of the best antimicrobial drug type per unit of aquatic land is specifically converted into Convert to When the preset safe release concentration of the best antimicrobial drug type for the current disease in the target aquaculture farm is used as the release standard, it is actually necessary to change the preset safe release concentration unit of the best antimicrobial drug type for the current disease in the target aquaculture farm from Convert to .

[0069] For example, the target aquaculture farm has an area of ​​5 mu and an average water depth of 1.5 meters. The total aquatic land area corresponds to a water volume of 5000.25 cubic meters. The minimum inhibitory concentration of the best antimicrobial drug type for the current disease in the target aquaculture farm is 0.5 The total aquatic area of ​​the target aquaculture farm corresponds to an effective drug diffusion coefficient of 0.7 and a drug loss rate of 0.2. The formula Obtain the actual dosage of the best type of antimicrobial drug per unit acre of aquatic land in the target aquaculture farm.

[0070] Specifically, the preset safe release concentration threshold of the best antibiotic type for the current disease of the target aquaculture farm is a preset multiple of the minimum inhibitory concentration of the best antibiotic type for the current disease of the target aquaculture farm.

[0071] The embodiment of the present invention analyzes and feeds back the actual dosage of the best antimicrobial drug type per unit acre of aquatic land in the target aquaculture farm in combination with the actual situation of the target aquaculture farm, thereby significantly improving the accuracy and efficiency of drug use, promoting targeted disease prevention and control, and promoting the sustainable development of the aquaculture industry.

[0072] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A method for analyzing and managing detection data of aquatic bacteria drug sensitivity test kit, characterized in that: include: S1. Randomly select a preset number of disease samples of the same species and the same disease in the target aquaculture farm, and prepare bacterial drug sensitivity test solutions containing various antimicrobial drugs of preset concentrations for each disease sample in the target aquaculture farm according to the preset operation process, which are recorded as various drug sensitivity reagents for each disease sample; S2. Inject each disease sample and each drug sensitivity reagent into each preset row well plate of its corresponding test kit, place it in a standard incubator and culture it for a fixed period of time, and then collect images of the test kit where each drug sensitivity reagent of each disease sample is located; S3. Analyze the images of the test kits of various drug-sensitive reagents for each disease sample, and evaluate the effective antibacterial degree of various drug-sensitive reagents for each disease sample, including: S31. Identify and cut each liquid-filled hole in the drug sensitivity box image where each drug sensitivity reagent of each disease sample is located, and convert the image into Color space, recording the pixel in each filling hole Color intensity value; Fill each liquid hole Color intensity values ​​are in preset Each pixel within the red component intensity value range of the color space is regarded as a red pixel, and the proportion of red pixels in each filling hole is counted. , is the number of each filling hole, , through the formula Analyze the first-order inhibition degree of each liquid-filled well; S32. According to the effective antibacterial pixel stored in the WEB cloud The preset standard intensity interval of each color channel in the color space is set to Each pixel whose color channel intensity value is within its preset standard intensity range is regarded as each effective antibacterial pixel, and each effective antibacterial circle stored in each liquid filling hole is identified and cut; The area characteristic antibacterial index, boundary characteristic antibacterial index and texture characteristic antibacterial index of each effective antibacterial circle in each liquid-filled hole are analyzed, and then the second-order antibacterial degree of each liquid-filled hole is analyzed; S33. The first-order antibacterial degree and the second-order antibacterial degree of the filling well are respectively accumulated with the product of their corresponding preset weights, and the accumulated value is used as the comprehensive antibacterial degree of the filling well. If the comprehensive antibacterial degree of a filling well is greater than or equal to the preset comprehensive antibacterial degree reaching the standard threshold, it means that the antibacterial drug built into the filling well achieves effective antibacterial effect, and the filling well is recorded as an antibacterial filling well, thereby screening the antibacterial filling wells in the drug sensitivity box where various drug sensitivity reagents of various disease samples are located, sorting out the proportion of the number of antibacterial filling wells in the drug sensitivity box where various drug sensitivity reagents of various disease samples are located and the average antibacterial degree of the antibacterial filling wells exceeding the standard, and multiplying the two to obtain the effective antibacterial degree of various drug sensitivity reagents of various disease samples; S4. Eliminate the individual differences of each disease sample and select the best type of antimicrobial drug that is compatible with the current disease in the target aquaculture farm; S5. Analyze the actual dosage of the best type of antimicrobial drug per unit area of ​​aquatic products in the target aquaculture farms and provide feedback.

2. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 1, characterized in that: The identifying and cutting of each effective antibacterial circle stored in each liquid-filling hole comprises: starting from any effective antibacterial pixel point in each liquid-filling hole, searching for a connected domain, and identifying each connected domain composed of effective antibacterial pixel points in each liquid-filling hole according to a condition that the area of ​​the searched connected domain is greater than or equal to a preset reference forming area; The grayscale gradient value of each boundary pixel point in each connected domain composed of the effective antibacterial pixel points in each liquid-filled hole is calculated, and the boundary pixel points whose grayscale gradient value is less than the preset reference edge grayscale gradient value are eliminated, and the boundaries of each connected domain are re-outlined to generate each effective antibacterial circle in the memory of each liquid-filled hole.

3. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 2, characterized in that: The analysis of the second-order antibacterial degree of each liquid-filling hole includes: counting the number of pixels contained in each effective antibacterial circle in each liquid-filling hole, converting the area of ​​each effective antibacterial circle in each liquid-filling hole according to a preset ratio, and taking the ratio of the area of ​​each effective antibacterial circle in each liquid-filling hole to the preset standard area of ​​the filling hole of the drug sensitive box as the area characteristic antibacterial index of each effective antibacterial circle in each liquid-filling hole , is the number of each effective inhibition zone, ; The grayscale gradient values ​​of the boundary pixels of each effective inhibition zone in each liquid-filling hole are sorted, and the grayscale gradient average value of the boundary pixels of each effective inhibition zone in each liquid-filling hole is compared with the grayscale gradient standard deviation to obtain the boundary clarity of each effective inhibition zone in each liquid-filling hole; Construct the minimum fitting circle of each effective inhibition circle in each liquid-filling hole, obtain the deviation distance of each boundary pixel point of each effective inhibition circle in each liquid-filling hole with respect to its minimum fitting circle, and calculate the boundary regularity of each effective inhibition circle in each liquid-filling hole according to the root mean square of the deviation distance of each boundary pixel point of each effective inhibition circle in each liquid-filling hole with respect to its minimum fitting circle, and take the inverse of the root mean square as the boundary regularity; The cumulative value of boundary clarity and boundary regularity is used as the boundary characteristic antibacterial index, thereby obtaining the boundary characteristic antibacterial index of each effective antibacterial circle in each filling hole ; The image is converted into a grayscale image to construct a grayscale co-occurrence matrix of each effective inhibition zone in each liquid-filled well. According to the energy, contrast and entropy feedback of the grayscale co-occurrence matrix, the texture characteristics and antibacterial index of each effective inhibition zone in each liquid-filled well are analyzed. ; Then by the formula The second-order inhibition degree of each filling hole was analyzed. The preset weights are the area feature antibacterial index, boundary feature antibacterial index, and texture feature antibacterial index. Indicates The maximum value of the comprehensive antibacterial index of the liquid-filled holes combined with the area characteristics, boundary characteristics, and texture characteristics.

4. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 2, characterized in that: The average antibacterial degree exceeding the standard of the antibacterial filling holes in the drug sensitivity box where each type of drug sensitivity reagent is located for each disease sample is the calculated average of the difference between the comprehensive antibacterial degree of each antibacterial filling hole in the drug sensitivity box where each type of drug sensitivity reagent is located for each disease sample and the preset comprehensive antibacterial degree reaching the standard threshold.

5. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 2, characterized in that: The screening of the best antimicrobial drug type suitable for the current disease in the target aquaculture farm includes: obtaining the symptom status data and growth status data of each disease sample in the target aquaculture farm, analyzing the standardized symptom severity of each disease sample in the target aquaculture farm and physiological metabolism , is the number of each disease sample in the target aquaculture farm, , extract the effective antibacterial degree of various drug sensitivity reagents from various disease samples , is the serial number of each drug sensitivity reagent. Calculate the sensitivity coefficient of the current pathogenic bacteria in the target aquaculture farm relative to various drug sensitivity reagents ,in They are the preset impact weights corresponding to the severity of the disease and the degree of physiological metabolism. , is the number of disease samples in the target aquaculture farm, The preset constant is used to screen the antimicrobial drug type in the drug sensitivity reagent corresponding to the maximum sensitivity coefficient as the best antimicrobial drug type suitable for the current disease in the target aquaculture farm.

6. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 5, characterized in that: Said The specific analysis process includes: according to the symptom status data of each disease sample in the target aquaculture farm, the symptom record content and symptom duration The symptom record content includes the appearance lesion area ratio, appearance lesion location, abnormal behavior frequency, abnormal behavior corresponding to each descriptive keyword and each physiological index monitoring value. According to the appearance lesion area ratio and appearance lesion location, the appearance symptom severity index of the disease sample is analyzed. According to the abnormal behavior frequency and each descriptive keyword corresponding to the abnormal behavior, the abnormal behavior severity index of the disease sample is analyzed. According to the monitoring value of each physiological index, the physiological state severity index of the disease sample is analyzed. The appearance symptom severity index, abnormal behavior severity index and physiological state severity index of the disease sample are respectively accumulated with the product of their corresponding preset weights to obtain the symptom severity index of the disease sample, thereby obtaining the symptom severity index of each disease sample in the target aquaculture farm. , according to the formula Obtain the severity of each disease sample in the target aquaculture farm, and calculate the average severity of the disease samples in the target aquaculture farm and standard deviation , further by the formula Obtain standardized symptom severity of each disease specimen in the target aquaculture farm.

7. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 5, characterized in that: Said The specific analysis process includes: the growth status data of each diseased sample in the target aquaculture farm include weight, body length and test oxygen consumption, the fatness of the diseased sample is calculated based on weight and body length, and the preset material metabolism level index corresponding to the fatness interval of each material metabolism level stored in the WEB cloud is combined to obtain the preset material metabolism level index corresponding to the material metabolism level of the fatness interval of each diseased sample in the target aquaculture farm. ; According to the oxygen consumption intervals corresponding to each energy metabolism level and the preset energy metabolism level indicators stored in the WEB cloud, the preset energy metabolism level indicators corresponding to the energy metabolism level of the test oxygen consumption interval of each disease sample in the target aquaculture farm are obtained. ; By formula The physiological metabolic degree of each disease sample in the target aquaculture farm is obtained, and then the standardized physiological metabolic degree of each disease sample in the target aquaculture farm is obtained.

8. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 2, characterized in that: The analysis of the actual dosage of the best antimicrobial drug type per unit aquatic area of ​​the target aquaculture farm includes: detecting the minimum inhibitory concentration of the best antimicrobial drug type for the current disease in the target aquaculture farm through a drug sensitivity concentration experiment , obtain the water volume corresponding to the total aquatic land per mu of the target aquaculture farm , drug effective diffusion coefficient and drug loss rate , according to the formula Analyze the actual dosage of the best antimicrobial drug type per unit area of ​​aquaculture in the target aquaculture farms, including The actual drug dosage of the best antibiotic type per unit aquatic acre is converted to the total aquatic acre area of ​​the target aquaculture farm, and compared with the preset safe release concentration threshold of the best antibiotic type for the current disease in the target aquaculture farm. If the comparison relationship is less than or equal to, it is judged that the actual drug dosage of the best antibiotic type per unit aquatic acre meets the benchmark safety conditions for drug use. If the comparison relationship is greater than, the preset safe release concentration of the best antibiotic type for the current disease in the target aquaculture farm is used as the release standard for release.

9. The method for analyzing and managing detection data of an aquatic bacteria drug sensitivity test kit according to claim 8, characterized in that: The preset safe release concentration threshold of the best antimicrobial drug type for the current disease of the target aquaculture farm is a preset multiple of the minimum inhibitory concentration of the best antimicrobial drug type for the current disease of the target aquaculture farm.

Images