Syphilis detection result interpretation method, interpretation device and electronic equipment

Abstract

The invention relates to the technical field of syphilis detection, and discloses a syphilis detection result interpretation method, an interpretation device and electronic equipment. The syphilis detection result interpretation method comprises the following steps: acquiring a diluted reaction card image; determining a reaction card interpretation result under the 2n-time titer based on the reaction card image under the 2n-time titer and the reaction card image under the previous titer; wherein n is a positive integer greater than 0; and under the condition that the reaction card interpretation result is positive, obtaining a reaction card image under the latter titer, and repeating the steps until the reaction card interpretation result under the latter titer is negative. Unnecessary dilution and detection steps can be avoided, and consumption of reagents, reaction cards and time is remarkably reduced. As manual interpretation is not needed, the problems of high subjectivity, limited accuracy and low efficiency of manual interpretation of the RPR detection result by inspection personnel in the prior art are solved, and the accuracy of interpretation of the detection result is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of syphilis detection, and in particular to a syphilis detection result interpretation method, an interpretation device and an electronic device. BACKGROUND

[0002] RPR (Rapid Plasma Reagin, rapid plasma reagin test) is a commonly used syphilis screening test, which belongs to a non-treponema test (non-specific antibody detection). It detects the presence of antibodies (reagin) produced in response to the release of cardiolipin antigen after infection with syphilis spirochetes in the patient's blood, indirectly determining whether there is syphilis infection. It can detect the presence of antibodies in the early stage of infection, quickly identify possible syphilis infection, and thus perform further diagnosis and treatment as soon as possible to reduce disease transmission. Through RPR detection, infected persons can be detected in a timely manner, reducing the spread of syphilis in the population. In addition, in terms of treatment monitoring, the antibody titer of RPR detection can reflect the activity of syphilis infection, and has important value for the evaluation of treatment effect. The antibody titer of RPR detection can also be used to judge disease recurrence. After treatment, if the RPR test result is positive again or the antibody titer value rises, it may indicate a recurrence of syphilis, and the treatment plan needs to be adjusted in a timely manner.

[0003] Therefore, it is particularly important to accurately interpret the RPR test results. The conventional result interpretation mainly relies on manual interpretation by the test personnel, which has strong subjectivity and different personnel may have different interpretation standards, which can easily lead to inconsistency of the results. Moreover, the accuracy is limited, as it is observed by the naked eye, which can be affected by factors such as the experience of the operator and visual fatigue, leading to the occurrence of false positive and false negative results. The efficiency is relatively low, and when a large number of samples are processed, the work efficiency of manual interpretation is relatively low, and the accuracy can be reduced due to factors such as fatigue. In addition, it requires a high operating environment, and needs to be performed in a suitable environment with sufficient light and no vibration, otherwise it can affect the accuracy of the results.

[0004] Therefore, how to accurately interpret the RPR test results is a problem that needs to be solved in the industry. SUMMARY

[0005] The present application provides a syphilis detection result interpretation method, an interpretation device and an electronic device to solve the problems of strong subjectivity, limited accuracy and low efficiency in the prior art of manually interpreting RPR test results by test personnel.

[0006] The present application provides a syphilis detection result interpretation method for interpreting the results of a rapid plasma reagin test, comprising: obtaining an image of a diluted reaction card; based on 2 nthe reaction card image under the current dilution and the reaction card image under the previous dilution, to determine the 2 n the reaction card image under the current dilution and the reaction card image under the previous dilution, to determine the 2 In the case that the reaction card interpretation result is positive, the reaction card image under the next dilution is obtained, and the above steps are repeated until the reaction card interpretation result under the next dilution is negative.

[0007] According to the syphilis detection result interpretation method provided by the application, the 2 n the reaction card image under the current dilution and the reaction card image under the previous dilution, to determine the 2 n the reaction card image under the current dilution and the reaction card image under the previous dilution, to determine the 2 extracting a region of interest of the reaction card image; extracting feature information based on the region of interest, and determining the 2 n the reaction card image under the current dilution and the reaction card image under the previous dilution, to determine the 2

[0008] According to the syphilis detection result interpretation method provided by the application, the feature information includes high-dimensional features, which refers to features extracted in a deep learning model.

[0009] According to the syphilis detection result interpretation method provided by the application, the feature information includes statistical characteristics of image pixels, and the statistical characteristics include at least one of a gray value variance, a contrast ratio, an energy, an entropy, a homogeneity, and an area ratio of a condensation region, and / or the statistical characteristics include at least one of a ratio of the gray value variance, a contrast ratio, an energy, an entropy, a homogeneity, and an area ratio of a condensation region of image pixels under the current dilution and under the previous dilution. n the reaction card image under the current dilution and the reaction card image under the previous dilution, to determine the 2

[0010] According to the syphilis detection result interpretation method provided by the application, the extraction of the region of interest of the reaction card image includes: the region of interest of the reaction card image is extracted by using a deep learning semantic segmentation algorithm; According to the feature that the reagent reaction region is circular, the region of interest of the reaction card image is extracted by using a circular detection algorithm, and the region of interest is the reagent reaction region.

[0011] According to the syphilis detection result interpretation method provided by the application, in the case that n is greater than a threshold value N, the interpretation is ended, and the interpretation result is output.

[0012] According to the syphilis detection result interpretation method provided by the application, the method further includes: In the case that the interpretation result is negative, the interpretation is ended, and the interpretation result is output.

[0013] The second aspect of the present application provides a syphilis detection result judging device, comprising: An acquisition module configured to acquire an image of a diluted reaction card; A determination module configured to determine a reaction card reading result at a 2 n n-fold dilution based on the image of the reaction card at the 2 n n-fold dilution and an image of a reaction card at a previous dilution, wherein n is a positive integer greater than 0. In a case where the reading result is positive, the acquisition module acquires an image of a reaction card at a next dilution, and the determination module is configured to repeat the above steps until the reading result of the reaction card at the next dilution is negative.

[0014] The third aspect of the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the syphilis detection result reading method according to any one of the above aspects when executing the computer program.

[0015] The fourth aspect of the present application provides a non-transitory computer readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the syphilis detection result reading method according to any one of the above aspects.

[0016] The syphilis detection result reading method provided by the present application determines a reading result of a reaction card at a 2 n n-fold dilution based on an image at the 2 n-1 n-fold dilution and an image of a reaction card at a previous dilution (i.e., at a 2 n n-fold dilution), which can avoid misjudgment of positive and negative results caused by image blurring due to external environmental influences when capturing images from the aspect of image acquisition, eliminate individual differences from the aspect of samples, identify weak positive or critical samples, and reduce the risk of misjudgment. In a case where the reading result is positive, an image of a reaction card at a next dilution is acquired, and the above steps are repeated until the reading result of the reaction card at the next dilution is negative, which can avoid unnecessary dilution and detection steps, significantly reduce reagent, reaction card, and time consumption, and is suitable for large-scale screening scenarios. In addition, because human reading is not required, the problems of strong subjectivity, limited accuracy, and low efficiency in the prior art of manually reading RPR detection results by inspectors are solved, and the accuracy of reading detection results is improved. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0018] Figure 1 is one of the flowcharts of the syphilis test result interpretation method provided by the present application.

[0019] Figure 2 is the second flowchart of the syphilis test result interpretation method provided by the present application.

[0020] Figure 3 is the third flowchart of the syphilis test result interpretation method provided by the present application.

[0021] Figure 4 is the image of the diluted reaction card in the syphilis test result interpretation method provided by the present application.

[0022] Figure 5 is the region of interest of the image of the diluted reaction card in the syphilis test result interpretation method provided by the present application.

[0023] Figure 6 is one of the structural diagrams of the deep learning model provided by the present application.

[0024] Figure 7 is the second structural diagram of the deep learning model provided by the present application.

[0025] Figure 8 is the structural diagram of the syphilis test result interpretation device provided by the present application.

[0026] Figure 9 is the structural diagram of the electronic device provided by the present application. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the present application clearer, the following will combine the drawings in the present application to clearly and completely describe the technical solutions in the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0028] In the embodiments of the present application, "at least one" refers to one or more, and "more" refers to two or more. The association relationship between the associated objects is described, which means that there can be three relationships, for example, A and / or B, which can represent the following three cases: A exists alone, A and B exist together, and B exists alone.

[0029] The following will be described in detail Figures 1 to 9 The syphilis test result interpretation method, interpretation device and electronic equipment of the present application will be described in detail. It should be noted that the execution subject of the syphilis test result interpretation method of the present application can be a controller or a syphilis test result interpretation device. The electronic equipment includes a computer or a server. The following will be described taking the execution subject of the syphilis test result interpretation method as a controller as an example.

[0030] The experimental process of RPR (rapid plasma reagin test) includes: dropping patient serum on a reaction card, and then serially diluting the patient serum to quantitatively detect syphilis.

[0031] It should be noted that the reaction card is a specially designed glass or paper card with a circle.

[0032] As Figure 1 shown, the present application provides a syphilis test result interpretation method. The syphilis test result interpretation method is used for the interpretation of the result of rapid plasma reagin (RPR) test. The syphilis test result interpretation method includes: S100, obtaining an image of the diluted reaction card.

[0033] Optionally, a camera device (such as a camera) can be used to take a picture of the diluted reaction card; the controller obtains the image of the reaction card from the camera device, as Figure 4 shown.

[0034] S200, based on the image of the reaction card at 2 n times dilution and the image of the reaction card at the previous dilution, determining the interpretation result of the reaction card at 2 n times dilution; wherein n is a positive integer greater than 0; In the case that the interpretation result of the reaction card is positive, the image of the reaction card at the next dilution is obtained, and the above steps are repeated until the interpretation result of the reaction card at the next dilution is negative.

[0035] In this embodiment, by using the image at 2 n times dilution and the image of the reaction card at the previous dilution (i.e. at 2 n-1 times dilution), the interpretation result of the reaction card at 2 nThe interpretation results of the reaction card at the times titer can avoid the error of positive and negative judgment caused by the blurred image caused by the influence of the external environment when taking the image from the aspect of image acquisition; from the aspect of samples, individual differences can be eliminated, weak positive or critical samples can be identified, and the risk of misjudgment in interpretation can be reduced. In the case of a positive interpretation result, an image of the reaction card at the next titer is obtained, and the above steps are repeated until the interpretation result of the reaction card at the next titer is negative. This can avoid unnecessary dilution and detection steps, significantly reduce the consumption of reagents, reaction cards and time, and dilute the reaction cards with positive interpretation results again instead of covering the entire range, which is suitable for large-scale screening scenarios. In addition, because no manual interpretation is required, the problems of strong subjectivity, limited accuracy and low efficiency in the manual interpretation of RPR test results by inspectors in the prior art are solved, and the accuracy of the interpretation of test results is improved.

[0036] In one embodiment, at 2 n If the result of the reaction card is positive at the times titer, the controller can obtain the result of the next titer, i.e. n+1 Images of reaction cards at multiple titers; and based on 2 n+1 The image of the reaction card at the titer is the same as 2 n Image of the reaction card at the titer, determine 2 n+1 Interpretation results of reaction cards at multiple titers; In 2 n+1 If the result of the reaction card is negative at the times titer, the controller can directly output the result, i.e. n+1 fold titer negative; In 2 n+1 If the result of the reaction card is positive at the multiple titer, the controller can continue to obtain 2 n+2 Images of reaction cards at multiple titers; and based on 2 n+1 The image of the reaction card at the titer is the same as 2 n+2 Image of the reaction card at the titer, determine 2 n+2 Interpretation results of reaction cards at multiple titers; In 2 n+2 If the result of the reaction card is negative at the times titer, the controller can directly output the result, i.e. n+2 fold titer negative; In 2 n+2 If the result of the reaction card is positive at the multiple titer, the controller can continue to obtain 2 n+3 Repeat the above reading process until the result of the reaction card at the next titer is negative.

[0037] like Figure 2 As shown, in some embodiments, based on 2n the reaction card image under the 2 n times dilution and the reaction card image under the previous dilution, determining the 2 S210, extracting a region of interest of the reaction card image, as Figure 5 shown.

[0038] S220, extracting feature information based on the region of interest, and determining the reaction card interpretation result under the 2 n times dilution.

[0039] In this embodiment, by extracting the region of interest, background interference can be excluded, key reaction areas can be concentrated for analysis, and interpretation accuracy can be improved. By processing the region of interest instead of the entire image, the computational complexity can be reduced, which is suitable for high-throughput detection scenarios.

[0040] In one embodiment, the region of interest of the reaction card image is extracted by using a deep learning semantic segmentation algorithm. It has strong robustness to deformation caused by card tilt or uneven illumination.

[0041] In another embodiment, the region of interest of the reaction card image is extracted by using a circular detection algorithm according to the characteristics of the reagent reaction area being circular. The region of interest is the reagent reaction area. The computational complexity is much lower than that of the deep learning semantic segmentation algorithm, and the real-time processing speed is high. By using prior knowledge such as the radius range and circularity parameters of the reaction area, non-circular artifacts and weak edge reactions can be effectively excluded.

[0042] In one embodiment, high-dimensional features are extracted based on the region of interest, and the reaction card interpretation result under the 2 n times dilution is determined; wherein the high-dimensional features refer to features extracted in a deep learning model.

[0043] As Figure 6 and Figure 7 shown, optionally, the deep learning model is trained based on the following steps: obtaining and inputting historical reaction card images under the 2 n times dilution into the feature extraction structure of an initial deep learning model to obtain first high-dimensional features output by the initial deep learning model; obtaining and inputting reaction card images under the previous dilution into the feature extraction structure of the initial deep learning model to obtain second high-dimensional features output by the initial deep learning model. The first high-dimensional features and the second high-dimensional features are input into the classification structure of the initial deep learning model to obtain the reaction card interpretation result under the 2 n times dilution output by the classification structure of the initial deep learning model.

[0044] According to 2 n The true label of the reaction card interpretation result under the 2-fold dilution updates the model parameters of the initial deep learning model, and a trained deep learning model is obtained.

[0045] The current 2 n Fold dilution reaction card image and the reaction card image under the previous dilution are input into the trained deep learning model, and the 2 n Fold dilution reaction card interpretation result output by the trained deep learning model is obtained.

[0046] Optionally, the network structure of the deep learning model includes a network structure based on a convolutional neural network (Convolutional Neural Network, CNN) or a network structure based on a Transformer. The Transformer is a deep learning model based on an attention mechanism.

[0047] Optionally, the 2 n Fold dilution reaction card interpretation result output by the trained deep learning model includes 0 and 1. Wherein, 0 represents negative, and 1 represents positive.

[0048] In another embodiment, statistical features of image pixels in the region of interest are extracted, and the 2 n Fold dilution reaction card interpretation result is determined; the statistical features include at least one of the gray value variance, contrast, energy, entropy, homogeneity, and area ratio of the condensed region, and / or the statistical features include at least one of the ratio of the gray value variance, the contrast ratio, the energy ratio, the entropy ratio, the homogeneity ratio, and the area ratio of the condensed region of the image pixels under the 2 n Fold dilution and the previous dilution, as shown in Table 1.

[0049] Optionally, the statistical feature refers to a feature obtained by statistical numerical calculation on the pixel value of the region of interest, and the statistical feature includes at least one of the gray value variance, contrast, energy, entropy, homogeneity, and area ratio of the condensed region.

[0050] These statistical features are input into a classification structure, which can be a support vector machine model or a random forest model.

[0051] Optionally, the classification structure can be trained based on the following steps: inputting the calculated first statistical feature and second statistical feature into an initial classification structure model to obtain the 2 n Fold dilution reaction card interpretation result output by the initial classification structure model. Wherein, the first statistical feature is the 2 nThe first statistical feature is a feature obtained by performing statistical numerical calculation on the pixel values ​​of the region of interest of the reaction card at a times titer; the second statistical feature is a feature obtained by performing statistical numerical calculation on the pixel values ​​of the region of interest of the reaction card at a previous titer; According to 2 n The actual labels of the reaction card interpretation results at the times titer are used to update the model parameters of the initial classification structure model to obtain a trained classification structure model.

[0052] Set the current 2 n The statistical features corresponding to the reaction card image at the times titer and the reaction card image at the previous titer are input into the trained classification structure model to obtain the 2 output of the trained classification structure model. n The results were interpreted using reaction cards at multiple titers.

[0053] Optionally, the classification structure can also be obtained by training based on the following steps: inputting the calculated first statistical feature, the second statistical feature and the third statistical feature into the initial classification structure model to obtain the output of the initial classification structure model. n The first statistical feature is the interpretation of the reaction card under the titer of 2 times. n The first statistical feature is a feature obtained by performing statistical numerical calculation on the pixel values ​​of the region of interest of the reaction card at the first titer; the second statistical feature is a feature obtained by performing statistical numerical calculation on the pixel values ​​of the region of interest of the reaction card at the previous titer; the third statistical feature is the ratio of the first statistical feature to the second statistical feature, as shown in Table 1.

[0054] According to 2 n The actual labels of the reaction card interpretation results at the times titer are used to update the model parameters of the initial classification structure model to obtain a trained classification structure model.

[0055] Set the current 2 n The statistical features and ratios of the reaction card image at the times titer and the reaction card image at the previous titer are input into the trained classification structure model to obtain the 2 output of the trained classification structure model. n The results were interpreted using reaction cards at multiple titers.

[0056] It should be noted that the first statistical feature includes 2 n At least one of the grayscale value variance, contrast, energy, entropy, homogeneity and area ratio of agglutinated regions of image pixels at a multiple of titer.

[0057] The second statistical feature includes at least one of grayscale value variance, contrast, energy, entropy, homogeneity, and area ratio of agglutinated regions of image pixels at a previous titer.

[0058] The third statistical feature includes 2n at least one of a ratio of a variance of gray scale values of pixels in the current drop and a variance of gray scale values of pixels in the previous drop, a contrast ratio, an energy ratio, an entropy ratio, a homogeneity ratio, and a ratio of an area of the agglutination area.

[0059] The specific extraction process of the statistical characteristics is described below.

[0060] The controller first converts the image into a gray scale image and determines the gray scale value of each pixel.

[0061] The controller can determine the gray scale value of each pixel by using a standard weighted average method in combination with formula (1). .

[0062] Formula (1).

[0063] In formula (1), R represents the pixel value in the red channel, G represents the pixel value in the green channel, and B represents the pixel value in the blue channel.

[0064] The controller can determine the variance of the gray scale values of the region of interest by using formula (2). .

[0065] Formula (2).

[0066] In formula (2), N is the number of pixels, R is the region of interest, and G is the gray scale value of the pixel point.

[0067] The controller determines the contrast based on the gray scale co-occurrence matrix of the region of interest. The contrast can be used to measure the degree of local gray scale change, and the larger the value, the clearer the black precipitate on the reaction card.

[0068] The controller can also determine the energy based on the gray scale co-occurrence matrix of the region of interest. The energy can reflect the uniformity of the gray scale distribution of the image, and the larger the value, the more uniform the texture, i.e., the reaction card is almost a flat background without black precipitate.

[0069] The controller can also determine the entropy based on the gray scale co-occurrence matrix of the region of interest. The entropy is used to describe the randomness of the texture, and the larger the value, the more complex the texture, i.e., the black precipitate is randomly distributed on the slide.

[0070] ​​​​​​​​​​The controller can also determine homogeneity based on the gray level co-occurrence matrix of the region of interest. Homogeneity reflects local gray level similarity, and a large value indicates that the texture is smoother, and the color of the local region is consistent, which is a color consistent background.

[0071] Considering that the distribution of precipitates in the wave plate (i.e., the reaction card) is independent of direction, a symmetric gray level co-occurrence matrix is constructed using equation (3) .

[0072] Equation (3).

[0073] Equation (4).

[0074] In equation (3), d represents the probability of two pixels with a distance of d appearing simultaneously in the image, where one pixel has a gray level value of i and the other pixel has a gray level value of j; In equation (4), and are determined by the distance d and the direction ; M represents the width of the image, N represents the height of the image, and d is usually taken as 1.

[0075] When d = 1, When d = 2, When d = 3, When d = 4, Specifically, the controller can calculate the contrast based on the gray level co-occurrence matrix of equation (3) .

[0076] Specifically, the controller can calculate the energy based on the gray level co-occurrence matrix of equation (3) .

[0077] Specifically, the controller can calculate the homogeneity based on the gray level co-occurrence matrix of equation (3) .

[0078] Optionally, the controller can binarize the grayscale image of the region of interest to determine the area ratio of the aggregation region.

[0079] Specifically, the controller binarizes the grayscale image of the region of interest to distinguish the foreground and the background, where the foreground is the black precipitate of the antigen-antibody reaction, and extracts features of the binarized image.

[0080] The grayscale image is converted to a binarized image, where values greater than a threshold T are 1 and values less than the threshold T are 0.

[0081] First, the grayscale value distribution of all pixels in the region of interest is counted to obtain a histogram H(k).

[0082] Equation (4).

[0083] In equation (4), is the Dirac function. If , then ; else, 。

[0084] The peak value of the histogram is . The peak value refers to the grayscale value with the highest frequency in the histogram.

[0085] The grayscale value with the highest frequency in the grayscale image is that of the background. However, due to uneven lighting during shooting, the grayscale of the background is distributed within a certain range. Therefore, the threshold T can be a function of .

[0086] Considering that the color of the reaction precipitate is generally quite dark, close to black 0, the calculation function of the threshold T can be v on the basis of . Optionally, v can be 20.

[0087] The area ratio of the aggregation region (i.e., the black region) is .

[0088] wherein is the Dirac function. If , then ; else, 。

[0089] Table 1 Statistical characteristics

[0090] like Figure 3 As shown, in some embodiments, if n is greater than a threshold value N, the reading is terminated and the reading result is output. A maximum dilution factor (determined by N) is set to avoid infinite testing due to system errors or anomalies. N can be adjusted according to experimental requirements to balance the detection range and resource consumption.

[0091] Optionally, N can be 8 or 10.

[0092] Optionally, when n is greater than N, the output judgment result is 2 n-1 Positive at a titer of 1.

[0093] like Figure 3 As shown, in some embodiments, when n is 0, the reaction card interpretation result at 1x titer is determined based on the reaction card image at 1x titer and the reaction card image of the negative control sample. By setting n equal to 0, the detection of the original sample is ensured, avoiding missed detections. Using a negative control eliminates systematic errors and improves reliability.

[0094] Optionally, when the result of the reaction card at 1x titer is negative, a negative result at 1x titer is output.

[0095] Optionally, if the result of the reaction card at 1x titer is positive, obtain 2 1 Then, based on the reaction card image of 2 times the titer 1 The reaction card image at the times titer and the reaction card image at the previous titer (i.e. 1 times titer) are used to determine the 2 1 Interpretation results of reaction cards at multiple titers.

[0096] like Figure 3 As shown, in some embodiments, in 2 n If the reaction card is negative at the titer, the reading is terminated and the result is output. If the titer is 1:16 (n=4) and the result is negative, there is no need to test higher dilutions such as 1:32 (n=5) and 1:64 (n=6). 1:8 (n=3) is directly output as the last positive titer.

[0097] Optional, in 2 n If the result of the reaction card under the titer is negative, the output result is 2 n-1 Positive at a titer of 1.

[0098] like Figure 3 As shown, in some embodiments, when the reading result of the reaction card is negative at the latter titer, the output reading result is 2 n Positive at a titer of 1.

[0099] As Figure 8 shown, the second aspect of the present application provides a syphilis test result interpretation device. The interpretation device includes an acquisition module and a determination module; the acquisition module is used to acquire the image of the diluted reaction card; the determination module is used to determine the reaction card interpretation result under the 2 n fold dilution based on the reaction card image under the 2 n fold dilution and the reaction card image under the previous dilution; wherein n is a positive integer greater than 0; in the case of a positive interpretation result, the acquisition module acquires the reaction card image under the next dilution, and the determination module is used to repeat the above steps until the reaction card interpretation result under the next dilution is negative.

[0100] Figure 9 An example of a schematic diagram of the physical structure of an electronic device is shown in Figure 9 , which can include a processor 810, a communications interface 820, a memory 830, and a communications bus 840, wherein the processor 810, the communications interface 820, and the memory 830 communicate with each other through the communications bus 840. The processor 810 can invoke the logical instructions in the memory 830 to execute a syphilis test result interpretation method, which includes: acquiring the image of the diluted reaction card; determining the reaction card interpretation result under the 2 n fold dilution based on the reaction card image under the 2 n fold dilution and the reaction card image under the previous dilution; wherein n is a positive integer greater than 0; in the case of a positive interpretation result, the acquisition module acquires the reaction card image under the next dilution, and the determination module is used to repeat the above steps until the reaction card interpretation result under the next dilution is negative.

[0101] In addition, the logical instructions in the memory 830 described above can be implemented in the form of a software functional unit and sold or used as a standalone product, which can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0102] In another aspect, the present application also provides a computer program product comprising a computer program, which can be stored on a non-transitory computer-readable storage medium, and the computer program, when executed by a processor, enables a computer to perform the syphilis test result interpretation method provided by the above-mentioned methods, which comprises: obtaining the image of the diluted reaction card; determining the reaction card interpretation result at the 2 n fold dilution based on the image of the reaction card at the 2 n fold dilution and the image of the reaction card at the previous dilution; wherein n is a positive integer greater than 0; in the case that the reaction card interpretation result is positive, obtaining the image of the reaction card at the next dilution, and repeating the above steps until the reaction card interpretation result at the next dilution is negative.

[0103] In another aspect, the present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and the computer program, when executed by a processor, enables a computer to perform the syphilis test result interpretation method provided by the above-mentioned methods, which comprises: obtaining the image of the diluted reaction card; determining the reaction card interpretation result at the 2 n fold dilution based on the image of the reaction card at the 2 n fold dilution and the image of the reaction card at the previous dilution; wherein n is a positive integer greater than 0; in the case that the reaction card interpretation result is positive, obtaining the image of the reaction card at the next dilution, and repeating the above steps until the reaction card interpretation result at the next dilution is negative.

[0104] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0105] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary general hardware platforms, and of course can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in terms of the contribution to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0106] Finally, it should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same; although the present application has been described in detail with reference to the foregoing examples, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing examples, or make equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for interpreting syphilis test results, characterized in that: Used for interpretation of rapid plasma reagin test results, including: Acquire the diluted reaction card image; Based on 2 n The reaction card image under the times titer and the reaction card image under the previous titer are used to determine the 2 n The result of the reaction card interpretation under the titer is n; wherein n is a positive integer greater than 0; In the case where the result of the reaction card reading is positive, an image of the reaction card at the next titer is obtained, and the above steps are repeated until the result of the reaction card reading at the next titer is negative.

2. The method for interpreting syphilis test results according to claim 1, wherein: Based on 2 n The reaction card image under the times titer and the reaction card image under the previous titer are used to determine the 2 n The results of the reaction card interpretation under the titer include: Extracting a region of interest from the reaction card image; Extract feature information based on the region of interest and determine the 2 n The results were interpreted using reaction cards at multiple titers.

3. The method for interpreting syphilis test results according to claim 2, wherein: The feature information includes high-dimensional features; the high-dimensional features refer to features extracted from a deep learning model.

4. The method for interpreting syphilis test results according to claim 2, wherein: The feature information includes statistical features of image pixels; the statistical features include at least one of gray value variance, contrast, energy, entropy, homogeneity and area ratio of agglomerated regions, and / or the statistical features include 2 n At least one of the ratio of the gray value variance of the image pixels at the times titer and the previous titer, the contrast ratio, the energy ratio, the entropy ratio, the homogeneity ratio and the ratio of the area proportion of the agglutination region.

5. The method for interpreting syphilis test results according to claim 2, wherein: The extracting the region of interest of the reaction card image includes: Using a deep learning semantic segmentation algorithm to extract the region of interest of the reaction card image; or; According to the characteristic that the reagent reaction area is circular, a circle detection algorithm is used to extract the region of interest of the reaction card image, where the region of interest is the reagent reaction area.

6. The method for interpreting syphilis test results according to claim 1, wherein: When n is greater than the threshold value N, the determination is terminated and the determination result is output.

7. The method for interpreting syphilis test results according to any one of claims 1 to 6, characterized in that: Also includes: When the determination result is negative, the determination is terminated and the determination result is output.

8. A syphilis test result judgment device, characterized in that: include: An acquisition module, used for acquiring a diluted reaction card image; Determine the module for 2-based n The reaction card image under the times titer and the reaction card image under the previous titer are used to determine the 2 n The result of the reaction card interpretation under the titer is n; wherein n is a positive integer greater than 0; When the result of the determination is positive, the acquisition module acquires the image of the reaction card at the next titer, and the determination module is used to repeat the above steps until the result of the determination of the reaction card at the next titer is negative.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for interpreting syphilis test results according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for interpreting syphilis test results according to any one of claims 1 to 7 is implemented.

Images