Artificial intelligence based quantitative analysis system for diagnosis kit and method thereof

Abstract

The present disclosure provides a quantitative analysis system for an artificial intelligence-based diagnostic kit and a method thereof. The quantitative analysis system for a diagnostic kit of the present disclosure may be configured to receive an image of a diagnostic kit, analyze the image to quantitatively detect at least one of an antibody possession rate or an antigen possession rate expressed in the diagnostic kit, and provide a result report related to at least one of the antibody possession rate or the antigen possession rate.

Description

Technology Field

[0001] The present disclosure relates to a quantitative analysis system and method for a machine learning-based diagnostic kit, and more specifically, to a system and method that, when a rapid immunodiagnostic kit qualitatively determines whether antibodies acquired due to vaccination or infection against a specific antigen are possessed, photographs the kit and uploads the image to a dedicated system to which a machine learning algorithm is applied, quantitatively analyzes whether antibodies have been formed, and notifies the user of the results and statistical information. Background Technology

[0002] With the COVID-19 pandemic, the utility and importance of rapid immunodiagnostic kits are increasingly expanding. When bacteria or viruses invade the body or vaccination is completed, antibodies against specific antigens are formed, producing effects such as cell phagocytosis, neutralization of toxins, and inactivation of viruses. Among the various antibodies, immunoglobulin (Ig) antibodies, which do not anchor to the cell surface and can move freely within the blood (serum), consist of two heavy chains and two light chains connected by SS bonds; depending on the type of heavy chain, they are classified into antibodies such as IgG, IgM, IgA, IgD, and IgE.

[0003] Among these, IgM antibodies increase rapidly in the early stages of the immune response and possess a strong ability to activate complement—a protein that sterilizes and lyses bacteria or cells to which the antibody binds—but they exhibit a characteristic of rapidly decreasing over time (~2 weeks), serving as an indicator that various infections have recently occurred. IgG antibodies are major antibodies that account for approximately 75% of immunoglobulins in the serum; they appear in large quantities after the expression of IgM antibodies and continuously provide the body's primary immune function against specific antigens over a long period. Therefore, the presence of only IgM antibodies suggests a recent infection; the simultaneous presence of IgM and IgG antibodies indicates that an infection is actively progressing; and the presence of only IgG antibodies suggests that primary immunity has been established through previous vaccination or infection.

[0004] Recently, rapid immunodiagnostic kits capable of qualitatively identifying IgM / IgG antibodies formed due to vaccination or infection are being developed one after another amidst the COVID-19 pandemic. These rapid kits typically utilize the Lateral Flow Assay (LFA) method, which involves binding IgM / IgG antibodies present in a patient's blood to a gold nanoparticle-non-pathogenic antigen polymer to cause them to flow in a specific direction; when IgM / IgG antibodies immobilized at specific locations within the kit capture these antibodies, the presence of IgM / IgG antibodies is qualitatively determined using the light scattering phenomenon of the gold nanoparticles.

[0005] Rapid immunoassay kits based on the LFA method can only qualitatively indicate the presence of antibodies, and thus cannot provide quantitative information such as the amount of various antibodies. To compensate for this, dedicated analysis systems that provide quantified antibody information by measuring the light scattering phenomenon of gold nanoparticles in rapid immunoassay kits are being developed one after another; however, these systems are subject to limitations, such as being able to measure results only for specific rapid immunoassay kit products or requiring separate equipment. Prior art literature

[65535] International Publication WO2022 / 076516(2022.04.14.) The problem to be solved

[0006] The present disclosure provides a system and a method for qualitatively determining whether antibodies acquired due to vaccination or infection with a specific antigen have been formed by photographing a rapid immunodiagnostic kit and uploading the image to a dedicated system, which then quantitatively analyzes whether antibodies have been formed and notifies the user of the results and statistical information. means of solving the problem

[0007] The present disclosure provides a quantitative analysis system and method for an artificial intelligence-based rapid immunodiagnostic kit.

[0008] A method of a quantitative analysis system for a diagnostic kit of the present disclosure may include the steps of receiving an image of said diagnostic kit, analyzing said image to quantitatively detect at least one of an antibody possession rate or an antigen possession rate expressed in said diagnostic kit, and providing a result report related to at least one of said antibody possession rate or antigen possession rate.

[0009] A quantitative analysis system for a diagnostic kit of the present disclosure may include a communication module configured to receive an image of the diagnostic kit, an image analysis module configured to analyze the image and quantitatively detect at least one of an antibody possession rate or an antigen possession rate expressed in the diagnostic kit, and a report generation module configured to provide a result report related to at least one of the antibody possession rate or the antigen possession rate.

[0010] A quantitative analysis system for a diagnostic kit of the present disclosure may include an electronic device configured to transmit an image of said diagnostic kit, and a server configured to receive said image from said electronic device, analyze said image to quantitatively detect at least one of an antibody possession rate or an antigen possession rate expressed in said diagnostic kit, and provide a result report related to at least one of said antibody possession rate or antigen possession rate. Effects of the invention

[0011] According to the present disclosure, a user of a diagnostic kit can not only quantitatively determine at least one of their antibody or antigen possession rate through simple imaging alone, without being limited by the kit manufacturer or a separate analysis system, but also conveniently determine at least one statistical information regarding the antibody or antigen possession rate based on gender, age, vaccination or infection status, vaccine type, and the elapsed time since vaccination or infection, thereby helping to determine the necessity of additional vaccination or to numerically determine an individual's immunity to a specific antigen, thus contributing to the promotion of public health. Brief explanation of the drawing

[0012] FIG. 1 is a diagram schematically illustrating a quantitative analysis system according to the present disclosure. Figure 2 is a diagram illustrating the configuration of the server of Figure 1. Figure 3 is a diagram illustrating the detailed configuration of the image analysis module of Figure 2. FIGS. 4, FIGS. 5, FIGS. 6, FIGS. 7, and FIGS. 8 are drawings for exemplarily explaining the operational features of the image analysis module of FIG. 2. FIG. 9 is a drawing illustrating a method of a quantitative analysis system according to the present disclosure. FIG. 10 is a graph showing the COVID-19 antibody prevalence (IgG / C) over time of various users (by type and stage of vaccination) measured using the quantitative analysis system and method according to the present disclosure. FIG. 11 is a graph showing the change in antibody possession rate of confirmed COVID-19 patients over time before and after diagnosis, measured using the quantitative analysis system and method according to the present disclosure. Specific details for implementing the invention

[0013] Hereinafter, various embodiments of the present disclosure are described with reference to the accompanying drawings.

[0015] FIG. 1 is a diagram for schematically illustrating a quantitative analysis system (100) according to the present disclosure.

[0016] Referring to FIG. 1, the quantitative analysis system (100) of the present disclosure may include an electronic device (110) and a server (120). In this case, the electronic device (110) and the server (120) can communicate wirelessly.

[0017] An electronic device (110) may be configured to transmit an image (I) of a diagnostic kit to a server (120). For example, the electronic device (110) may include at least one of a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. According to one embodiment, the electronic device (110) may transmit an image (I) captured directly through a camera module to the server (120). In this case, when a user injects blood into the diagnostic kit and a predetermined reaction time elapses, the electronic device (110) may capture an image (I) of the diagnostic kit through the camera module. According to another embodiment, the electronic device (110) may transmit an input image (I) to the server (120). In this case, when the user injects blood into the diagnostic kit and a predetermined time has elapsed, the user can take an image (I) of the diagnostic kit through a separate device having a camera module and input the image (I) into the electronic device (110).

[0018] Specifically, the diagnostic kit to be photographed can be prepared as follows. First, a predetermined amount of the user's whole blood, e.g., 5 to 20 μL, is collected and then introduced into the diagnostic kit. Then, a dedicated buffer solution provided with the diagnostic kit is additionally introduced into the diagnostic kit to bind specific antibodies contained in the blood with a recognition material (e.g., gold nanoparticle-nonpathogenic antigen polymer, etc.). Then, after a predetermined reaction time, e.g., approximately 10 to 15 minutes for the LFA reaction, lines (e.g., G, M, T, C) that can be recognized by the human eye or a camera module can be generated around the area where capture antibodies specific to the target substance (antibody) contained in the blood are immobilized, due to light scattering by gold nanoparticles, etc. Once such lines are generated, an image (I) of the diagnostic kit can be captured.

[0019] The server (120) may be configured to receive an image (I) of a diagnostic kit from an electronic device (110) and analyze it. At this time, the server (120) can rapidly analyze the image (I) through an artificial intelligence analysis algorithm. Through this, the server (120) can finally provide a result report (user report) (R) including the analysis results and statistical location to the user.

[0020] FIG. 2 is a diagram illustrating the configuration of the server (120) of FIG. 1.

[0021] Referring to FIG. 2, the server (120) of the present disclosure is provided to analyze an image (I) of a diagnostic kit and may include a web server (210) and an analysis server (220). According to one embodiment, the web server (210) and the analysis server (220) may be implemented as an integrated unit. According to another embodiment, the web server (210) and the analysis server (220) may be implemented separately.

[0022] A web server (210) may be configured to receive images of diagnostic kits for which the response time has elapsed. At this time, the web server (210) may receive personal information about the user along with the images. Specifically, the web server (210) may include a communication module (211), a database (213), a report management module (215), an authentication module (217), and a report rendering module (219). The communication module (211) may communicate with an external device. Here, the external device may include other electronic devices in addition to the electronic device (110). The communication module (211) may communicate with the external device via a network. For example, the network may include at least one of a cellular network, the Internet, or a computer network such as a LAN (local area network) or a WAN (wide area network). The database (213) may store images (I) of diagnostic kits and personal information received through the communication module (211) together. The report management module (215) can manage result reports corresponding to images (I) and personal information regarding the diagnostic kit. The authentication module (217) can perform authentication for requests received through the communication module (211). At this time, the authentication module (217) can perform authentication by comparing the request with personal information stored in the database (213). The report rendering module (219) can provide the result report (R) to the user. At this time, if authentication is successful by the authentication module (217), the report rendering module (219) can transmit the result report (R) through the communication module (211).

[0023] The analysis server (220) may be configured to analyze an image (I) of a diagnostic kit. Specifically, the analysis server (220) may include a database verification module (221), an image analysis module (223), and a report generation module (225). The database verification module (221) may detect an image (I) to be analyzed from the database (213) of the web server (210). The image analysis module (223) may analyze the image (I). At this time, the image analysis module (223) may rapidly analyze the image (I) through an artificial intelligence analysis algorithm. The report generation module (225) may generate a result report (R) including the analysis results and statistical location. At this time, the report generation module (225) may provide the result report (R) to the report management module (215) of the web server (210).

[0024] FIG. 3 is a drawing illustrating the detailed configuration of the image analysis module (223) of FIG. 2. FIG. 4, FIG. 5, FIG. 6, FIG. 7, and FIG. 8 are drawings for exemplarily explaining the operational features of the image analysis module (223) of FIG. 2.

[0025] Referring to FIG. 3, the image analysis module (223) of the present disclosure is provided to analyze an image (I) of a diagnostic kit through an artificial intelligence analysis algorithm and may include a kit detection module (310), a region detection module (320), and a pixel intensity detection module (330).

[0026] The kit detection module (310) may be pre-trained. To this end, a training data set for the kit detection module (310) may be prepared, which includes raw images (I) of multiple diagnostic kits. T ) and raw images(I T Reference areas (annotated area) (AA) in ) T It may include coordinate information for ). For example, a raw image (I) as shown in FIG. 4(a).T ) and reference area (AA) as shown in FIG. 4(b). T Coordinate information for ) can be prepared as a training dataset. Reference region (AA T ) may refer to information areas within the diagnostic kit where the reaction results to the blood appear. For example, the reference area of ​​a rapid immunodiagnostic kit refers to a rectangular area extending from the left side of the membrane area, where three purple lines representing IgM antibody, IgG antibody, and control are displayed, to the right side of the blood injection port. Through this, the kit detection module (310) based on the training data set, the raw image (I T In ) reference regions (AA T It can be trained to detect ) . At this time, the kit detection module (310) can be trained by performing machine learning.

[0027] For example, the kit detection module (310) uses the FastR-CNN algorithm to detect a raw image (I T The bounding box region of each diagnostic kit is learned from the ), and the MaskR-CNN algorithm is used to analyze the raw images (I T ) learns the mask region within each diagnostic kit from ). In this way, the kit detection module (310) learns each raw image (I T Mask regions can be detected in the ), and among them, mask regions having a region of interest (RoI) score exceeding a threshold can be selected and the process repeated so that only mask regions with high RoI scores remain. Through this, the kit detection module (310) can detect the remaining mask regions as reference regions (AA T ) is detected by. The learning of the kit detection module (310) is performed on a reference area (AA T It proceeds by reducing the actual and predicted values ​​of the coordinate positions for ).

[0028] The region detection module (320) may be pre-trained. To this end, a training data set for the region detection module (320) may be prepared, which includes raw images (I) of multiple diagnostic kits. T )'s reference regions (AA T Partial images (PI) for ) P ) and partial images (PI T Membrane regions (MA) in ) T It may include coordinate information for ). For example, a partial image (PI) as shown in FIG. 5(a). T ) and membrane regions (MA) as shown in FIG. 5(b) T Coordinate information for ) can be prepared as a training dataset. Here, partial images (PI P The ratio of ) to raw images (I T It is maintained identically to the ratio in ), but partial images (PI P The size of ) can be adjusted to a predetermined size through standardization. For example, partial images (PI P The size of the ) can be adjusted so that the horizontal length becomes 600 pixels. Through this, the region detection module (320) based on the training data set, partial images (PI T In the membrane regions (MA) T It can be trained to detect ) areas. At this time, the area detection module (320) can be trained by performing machine learning.

[0029] The kit detection module (310) can detect a reference region (AA) in an image (I) of a diagnostic kit received from an electronic device (110). Since the kit detection module (310) is pre-trained, it can detect the reference region (AA) in the image (I) based on this. For example, the kit detection module (310) can receive an image (I) as shown in FIG. 6 (a) and detect the reference region (AA) in the image (I) as shown in FIG. 6 (b). Through this, the kit detection module (310) can extract a partial image (PI) of the reference region (AA) from the image (I). In some embodiments, the kit detection module (310) can convert the partial image (PI) to black and white. At this time, the kit detection module (310) can adjust the size of the partial image (PI). Here, the ratio of the partial image (PI) is maintained to be the same as the ratio in the image (I), but the size of the partial images (PI) can be adjusted to a predetermined size through a standardization process. For example, the size of the partial image (PI) can be adjusted so that the horizontal length is 600 pixels. For example, the kit detection module (310) can extract the partial image (PI) as shown in (c) of FIG. 6.

[0030] The region detection module (320) can detect membrane regions (MA) in partial images (PI) extracted from image (I). Since the region detection module (320) is pre-trained, it can detect membrane regions (MA) in partial images (PI) based on this. For example, the region detection module (320) can detect membrane regions (MA) in partial images (PI) as shown in FIG. 7.

[0031] The pixel intensity detection module (330) can detect the pixel intensity of each pixel in the membrane region (MA) of the partial image (PI). At this time, the pixel intensity detection module (330) can perform a graph flattening operation on the detected pixel intensity of each pixel. The graph flattening operation is performed by, when representing the pixel intensity of each pixel as a graph, the point of the first pixel (X0, Y0) and the point of the last pixel (X n , Y n It is a process of correcting pixel intensity using line segments connecting ). For example, this is performed as follows: (i) the last pixel value (Y n Subtract the first pixel value (Y0) from ), and (ii) with the number of pixel values ​​(X n The result of (i) is divided to derive the slope value, (iii) the individual pixel values ​​are multiplied by the value of (ii), (iv) the Y-intercept value is added to the values ​​of (iii), (v) the Y-values ​​of the line segment generated in the raw pixel value are subtracted, and (vi) negative values ​​can be returned as 0. Through this, a pixel spectrum for the pixel intensity of each pixel in the membrane region (MA) of the image (PI) can be derived. Thus, the pixel intensity detection module (330) can visualize the pixel spectrum. For example, the pixel intensity detection module (330) can visualize the pixel spectrum as illustrated in FIG. 8.

[0032] Thus, the report generation module (225) can generate a result report (R) based on the pixel spectrum. That is, the report generation module (225) can identify maximum values ​​for each antibody and control group from the pixel spectrum and use them to generate a result report (R). For example, the report generation module (225) can identify the respective maximum values ​​for IgM antibodies, IgG antibodies, and control groups from the pixel spectrum. In this result report (R), at least one of the specific antibody possession rate (IgG / C or IgM / C) or the specific antigen possession rate compared to the control group, and statistical information such as the relative position relative to the same gender, relative position relative to the same age, and relative position relative to the same vaccination, may be provided together. Therefore, the user can identify at least one of their antibody possession rate or antigen possession rate from the result report (R).

[0033] FIG. 9 is a drawing illustrating a method of a quantitative analysis system (100) according to the present disclosure.

[0034] Referring to FIG. 9, the quantitative analysis system (100) can receive an image (I) of a diagnostic kit in step 910. Specifically, the electronic device (110) can transmit an image (I) of a diagnostic kit to a server (120) after the user's blood has been injected and a predetermined reaction time has elapsed. According to one embodiment, the electronic device (110) can transmit an image (I) that is directly captured through a camera module to the server (120). According to another embodiment, the electronic device (110) can transmit an input image (I) to the server (120). Through this, the server (120) can receive an image (I) of a diagnostic kit from the electronic device (110).

[0035] Next, the quantitative analysis system (100) can analyze the image (I) in steps 920 through 950. At this time, the server (120) can analyze the image (I) through an artificial intelligence analysis algorithm. To this end, the kit detection module (310) and the region detection module (320) of the analysis server (220) may be pre-trained.

[0036] Specifically, the kit detection module (310) can detect a reference region (AA) in the image (I) at step 920. For example, the kit detection module (310) receives the image (I) as shown in FIG. 6 (a) and can detect the reference region (AA) in the image (I) as shown in FIG. 6 (b). Then, the kit detection module (310) can extract a partial image (PI) for the reference region (AA) in the image (I) at step 930. In some embodiments, the kit detection module (310) can convert the partial image (PI) to black and white. At this time, the kit detection module (310) can adjust the size of the partial image (PI). Here, the ratio of the partial image (PI) is maintained the same as the ratio in the image (I), but the size of the partial images (PI) can be adjusted to a predetermined size through a standardization process. For example, the size of the partial image (PI) can be adjusted so that the horizontal length becomes 600 pixels. For example, the kit detection module (310) can extract a partial image (PI) as shown in (c) of FIG. 6.

[0037] Next, the region detection module (320) can detect the membrane region (MA) in the partial image (PI) at step 940. Since the region detection module (320) is pre-trained, it can detect the membrane region (MA) in the partial image (PI) based on this. For example, the region detection module (320) can detect the membrane region (MA) in the partial image (PI) as shown in FIG. 7.

[0038] Furthermore, the pixel intensity detection module (330) can detect the pixel intensity of each pixel in the membrane region (MA) at step 950. Then, the pixel intensity detection module (330) can perform a graph flattening operation on the pixel intensity of each detected pixel. Through this, a pixel spectrum for the pixel intensity of each pixel in the membrane region (MA) of the image (PI) can be derived. Thus, the pixel intensity detection module (330) can visualize the pixel spectrum. For example, the pixel intensity detection module (330) can visualize the pixel spectrum as shown in FIG. 8.

[0039] Finally, the quantitative analysis system (100) can provide a result report (R) at step 960. At this time, the server (120) can identify the maximum values ​​for each antibody and control group from the pixel spectrum and use them to generate the result report (R). For example, the report generation module (225) can identify the respective maximum values ​​for IgM antibodies, IgG antibodies, and control groups from the pixel spectrum. In this result report (R), at least one of the specific antibody possession rate (IgG / C or IgM / C) or the specific antigen possession rate compared to the control group, and statistical information such as the relative position relative to the same gender, relative position relative to the same age, and relative position relative to the same vaccination, may be provided together. Therefore, the user can identify at least one of their antibody possession rate or antigen possession rate from the result report (R).

[0040] FIG. 10 is a graph showing the COVID-19 antibody possession rate (IgG / C) over time of various users (by type and stage of vaccination) measured using the quantitative analysis system (100) and the method according to the present disclosure.

[0041] Referring to FIG. 10, while a rapid immunodiagnostic kit typically allows for only qualitative evaluation or requires separate kit analysis equipment, the quantitative analysis system (100) and method according to the present disclosure can be used to conveniently check the user's immune status by simply taking an image of the rapid immunodiagnostic kit and uploading the image to a server (120), which immediately analyzes and quantifies the user's antibody possession rate using a dedicated algorithm, and provides relative position and statistical information compared to conditions similar to the user (type of vaccination, dose, confirmed status, elapsed time, gender, age, etc.). Based on the same elapsed time (76 days), it can be confirmed that the specific antibody possession rate (IgG / C) of the third dose recipient of the first vaccine is 64%, which is about 22% lower than the same antibody possession rate of 86% of the third dose recipient of the second vaccine, and in the case of confirmed patients, the antibody possession rate is very high at 102% based on an average elapsed time of 34 days. In addition, it can be seen that those who received the second dose of the first or second vaccine (average 153 days and 136 days elapsed) showed antibody retention rates 24% and 42% lower, respectively, compared to those who received the third dose (average 76 days elapsed).

[0042] FIG. 11 is a graph showing the change in antibody possession rate of confirmed COVID-19 patients over time before and after diagnosis, measured using the quantitative analysis system (100) and the method according to the present disclosure.

[0043] Referring to Figure 11, the specific antibody (IgG / C) level formed prior to the date of diagnosis due to reasons such as vaccination showed a significant increase based on the date of diagnosis, and then naturally decreased gradually over time. This can be interpreted as an experimental result that supports the established theory in academia that antibodies generated by an immune response naturally decrease over time.

[0044] According to the present disclosure, a user of a diagnostic kit can not only quantitatively determine at least one of their antibody or antigen possession rate through simple imaging alone, without being limited by the kit manufacturer or a separate analysis system, but also conveniently determine at least one statistical information regarding the antibody or antigen possession rate based on gender, age, vaccination or infection status, vaccine type, and the elapsed time since vaccination or infection, thereby helping to determine the necessity of additional vaccination or to numerically determine an individual's immunity to a specific antigen, thus contributing to the promotion of public health.

[0046] In summary, the present disclosure may provide a quantitative analysis system (100) for an artificial intelligence-based diagnostic kit and a method thereof.

[0047] The method of the quantitative analysis system (100) of the diagnostic kit of the present disclosure may include the steps of receiving an image (I) of the diagnostic kit, analyzing the image (I) to quantitatively detect at least one of the antibody possession rate or antigen possession rate expressed in the diagnostic kit, and providing a result report related to at least one of the antibody possession rate or antigen possession rate.

[0048] According to the present disclosure, the step of quantitatively detecting at least one of an antibody possession rate or an antigen possession rate may include the step of detecting a membrane region (MA) in which a reaction result of a diagnostic kit appears from an image (I), the step of detecting the pixel intensity of each pixel in the membrane region (MA), and the step of quantitatively detecting at least one of an antibody possession rate or an antigen possession rate based on the pixel intensity of each pixel.

[0049] According to the present disclosure, the step of detecting a membrane region (MA) may include the step of detecting a reference region (AA) containing the membrane region (MA) from an image (I), the step of extracting a partial image (PI) for the reference region (AA) from the image (I), the step of adjusting the size of the partial image (PI) to a predetermined size while maintaining the ratio of the partial image (PI), and the step of detecting the membrane region (MA) from the partial image (PI).

[0050] According to the present disclosure, the step of adjusting the size of a partial image (PI) to a predetermined size may include the step of adjusting the width of the partial image (PI) to correspond to a predetermined number of pixels.

[0051] According to the present disclosure, the step of detecting a membrane region (MA) may further include the step of converting a partial image (PI) into black and white.

[0052] According to the present disclosure, the step of quantitatively detecting at least one of an antibody possession rate or an antigen possession rate based on the pixel intensity of each pixel may include the step of visualizing a pixel spectrum by representing the pixel intensity of each pixel as a graph.

[0053] According to the present disclosure, the step of providing a result report may include confirming at least one of an antibody possession rate or an antigen possession rate based on a pixel spectrum, generating a result report with an analysis result indicating at least one of the antibody possession rate or an antigen possession rate and statistical information regarding at least one of the antibody possession rate or an antigen possession rate, and providing the result report to a user.

[0054] The quantitative analysis system (100) of the diagnostic kit of the present disclosure may include a communication module (211) configured to receive an image (I) of the diagnostic kit, an image analysis module (223) configured to analyze the image (I) and quantitatively detect at least one of the antibody possession rate or antigen possession rate expressed in the diagnostic kit, and a report generation module (225) configured to provide a result report related to at least one of the antibody possession rate or antigen possession rate.

[0055] According to the present disclosure, an image analysis module (223) may be configured to detect a membrane region (MA) in which a reaction result of a diagnostic kit appears from an image (I), detect the pixel intensity of each pixel in the membrane region (MA), and quantitatively detect at least one of an antibody retention rate or an antigen retention rate based on the pixel intensity of each pixel.

[0056] According to the present disclosure, the image analysis module (223) may include a kit detection module (310) configured to detect a reference region (AA) including a membrane region (MA) from an image (I), extract a partial image (PI) for the reference region (AA) from the image (I), and adjust the size of the partial image (PI) to a predetermined size while maintaining the ratio of the partial image (PI), and a region detection module (320) configured to detect a membrane region (MA) from the partial image (PI).

[0057] According to the present disclosure, the kit detection module (310) may be configured to adjust the horizontal length of a partial image (PI) to correspond to a predetermined number of pixels.

[0058] According to the present disclosure, the kit detection module (310) may be configured to convert a partial image (PI) into black and white.

[0059] According to the present disclosure, the image analysis module (223) may further include a pixel intensity detection module configured to visualize a pixel spectrum by representing the pixel intensity of each pixel as a graph.

[0060] According to the present disclosure, a report generation module (225) may be configured to identify at least one of an antibody possession rate or an antigen possession rate based on a pixel spectrum, generate a result report with an analysis result indicating at least one of the antibody possession rate or an antigen possession rate and statistical information regarding at least one of the antibody possession rate or an antigen possession rate, and provide the result report to a user.

[0061] The quantitative analysis system (100) of the diagnostic kit of the present disclosure may include an electronic device (110) configured to transmit an image (I) of the diagnostic kit, and a server (120) configured to receive the image (I) from the electronic device (110), analyze the image (I) to quantitatively detect at least one of the antibody possession rate or antigen possession rate expressed in the diagnostic kit, and provide a result report related to at least one of the antibody possession rate or antigen possession rate.

[0063] The device described above may be implemented as a hardware component, a software component, and / or a combination of a hardware component and a software component. For example, the device and components described in the embodiments may be implemented using one or more general-purpose or special-purpose computers, such as a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions. The processing unit may execute an operating system (OS) and one or more software applications executed on said operating system. Additionally, the processing unit may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing unit may be described as being used as a single unit, but those skilled in the art will understand that the processing unit may include multiple processing elements and / or multiple types of processing elements. For example, the processing unit may include multiple processors or one processor and one controller. In addition, other processing configurations, such as parallel processors, are also possible.

[0064] Software may include computer programs, code, instructions, or a combination of one or more of these, and may configure a processing unit to operate as desired or instruct the processing unit independently or collectively. Software and / or data may be embodied in any type of machine, component, physical device, computer storage medium, or device so as to be interpreted by the processing unit or to provide instructions or data to the processing unit. Software may be distributed over networked computer systems and may be stored or executed in a distributed manner. Software and data may be stored on one or more computer-readable recording media.

[0065] Methods according to various embodiments may be implemented in the form of program instructions that can be executed through various computer means and may be recorded on a computer-readable medium. In this case, the medium may continuously store a program executable by a computer, or temporarily store it for execution or download. Furthermore, the medium may be various recording or storage means in the form of a single or several combined hardware, and may not be limited to a medium directly connected to a computer system but may exist distributed over a network. Examples of media may include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and media configured to store program instructions, including ROM, RAM, and flash memory. Additionally, other examples of media may include recording or storage media managed by app stores that distribute applications or sites and servers that supply or distribute various other software.

[0066] The various embodiments of the present disclosure and the terms used therein are not intended to limit the technology described in this document to specific embodiments and should be understood to include various modifications, equivalents, and / or substitutions of such embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar components. A singular expression may include a plural expression unless the context clearly indicates otherwise. In this document, expressions such as "A or B," "at least one of A and / or B," "A, B or C," or "at least one of A, B and / or C" may include all possible combinations of items listed together. Expressions such as "first," "second," "first," or "second" may modify the components, regardless of order or importance, and are used only to distinguish one component from another and do not limit the components. When it is mentioned that a certain (e.g., first) component is "(functionally or telecommunicationally) connected" or "connected" to another (e.g., second) component, said certain component may be directly connected to said other component or connected through another component (e.g., third component).

[0067] As used in this document, the term "module" includes a unit composed of hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be a component formed as a whole, or a minimum unit or part thereof that performs one or more functions. For example, a module may be composed of an application-specific integrated circuit (ASIC).

[0068] According to various embodiments, each component (e.g., module or program) of the described components may include a singular or multiple entities. According to various embodiments, one or more of the aforementioned components or steps may be omitted, or one or more other components or steps may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as they were performed by the corresponding component among the multiple components prior to integration. According to various embodiments, steps performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically; one or more of the steps may be executed in a different order; omitted; or one or more other steps may be added.

Claims

Claim 1 A quantitative analysis method performed by a quantitative analysis system for a diagnostic kit comprises: a communication module receiving an image of the diagnostic kit; an image analysis module analyzing the image to quantitatively detect at least one of an antibody possession rate or an antigen possession rate expressed in the diagnostic kit; and a report generation module providing a result report related to at least one of the antibody possession rate or the antigen possession rate, wherein the step of quantitatively detecting comprises: detecting a membrane region in which a reaction result of the diagnostic kit appears from the image; and detecting the pixel intensity of each pixel in the membrane region.The method comprises the step of quantitatively detecting at least one of the antibody possession rate or antigen possession rate based on the pixel intensity of each pixel, wherein the step of detecting the pixel intensity of each pixel comprises: first performing an image standardization operation in which a partial image of the membrane region extracted from the image is converted to grayscale and the size is adjusted so that the horizontal length becomes a predetermined number of pixels while maintaining the aspect ratio of the partial image, and then detecting the pixel intensity of each pixel in the standardized partial image; wherein the step of quantitatively detecting comprises the step of visualizing the pixel spectrum by representing the pixel intensity of each pixel as a graph; wherein the step of visualizing the pixel spectrum comprises the step of performing a graph flattening operation in which a line segment connecting the point of the first pixel and the point of the last pixel in the graph is generated as a reference line, and the pixel intensity value of each pixel is corrected by subtracting the value corresponding to the reference line from the pixel intensity value of each pixel, and correcting the subtracted value to 0 if it is negative; and wherein the step of quantitatively detecting the antibody possession rate or antigen possession rate is measured from the pixel spectrum corrected by the graph flattening operation with the maximum value of the control group A quantitative analysis method comprising extracting a maximum value for a target antibody or a target antigen for measurement, respectively, and calculating a specific antibody possession rate or a specific antigen possession rate relative to a control group based on the result of comparing the maximum value of the control group with the maximum value for the target antibody or the target antigen for measurement. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete Claim 6 delete Claim 7 A quantitative analysis method according to claim 1, wherein the step of providing the result report comprises: confirming at least one of the antibody possession rate or antigen possession rate based on the pixel spectrum; generating the result report with an analysis result indicating at least one of the antibody possession rate or antigen possession rate and statistical information regarding at least one of the antibody possession rate or antigen possession rate; and providing the result report to a user. Claim 8 A quantitative analysis system for a diagnostic kit, comprising: a communication module configured to receive an image of the diagnostic kit; and an image analysis module configured to analyze the image and quantitatively detect at least one of an antibody possession rate or an antigen possession rate expressed in the diagnostic kit.The system includes a report generation module configured to provide a result report related to at least one of the antibody possession rate or antigen possession rate, wherein the image analysis module is configured to detect a membrane region in which the reaction result of the diagnostic kit appears from the image, detect the pixel intensity of each pixel in the membrane region, and quantitatively detect at least one of the antibody possession rate or antigen possession rate based on the pixel intensity of each pixel, wherein in detecting the pixel intensity of each pixel, the image analysis module performs an image standardization operation prior to converting a partial image of the membrane region extracted from the image into grayscale and adjusting the size so that the horizontal length becomes a predetermined number of pixels while maintaining the aspect ratio of the partial image, and then detects the pixel intensity of each pixel in the standardized partial image, wherein the image analysis module is configured to visualize a pixel spectrum by expressing the pixel intensity of each pixel as a graph, wherein in visualizing the pixel spectrum, a line segment connecting the point of the first pixel and the point of the last pixel in the graph is created as a baseline, and the corresponding baseline corresponding to the pixel intensity value of each pixel A quantitative analysis system configured to perform a graph flattening operation to correct the pixel intensity value of each pixel by subtracting a value, wherein if the subtracted value is negative, it is corrected to 0; and to calculate the antibody possession rate or antigen possession rate as a specific antibody possession rate or a specific antigen possession rate relative to a control group based on the result of comparing the maximum value of the control group and the maximum value of the target antibody or target antigen, respectively, extracted from the pixel spectrum corrected by the graph flattening operation. Claim 9 delete Claim 10 delete Claim 11 delete Claim 12 delete Claim 13 delete Claim 14 A quantitative analysis system according to claim 8, wherein the report generation module is configured to identify at least one of the antibody possession rate or antigen possession rate based on the pixel spectrum, generate the result report with an analysis result indicating at least one of the antibody possession rate or antigen possession rate and statistical information regarding at least one of the antibody possession rate or antigen possession rate, and provide the result report to a user. Claim 15 In a quantitative analysis system for a diagnostic kit, an electronic device configured to transmit an image of the diagnostic kit; The system includes a server configured to receive the image from the electronic device, analyze the image to quantitatively detect at least one of the antibody possession rate or antigen possession rate expressed in the diagnostic kit, and provide a result report related to at least one of the antibody possession rate or antigen possession rate; the server includes an image analysis module; the image analysis module is configured to detect a membrane region in which the reaction result of the diagnostic kit appears from the image, detect the pixel intensity of each pixel in the membrane region, and quantitatively detect at least one of the antibody possession rate or antigen possession rate based on the pixel intensity of each pixel; in detecting the pixel intensity of each pixel, the image analysis module is configured to perform an image standardization operation prior to converting a partial image of the membrane region extracted from the image into grayscale and adjusting the size so that the horizontal length becomes a predetermined number of pixels while maintaining the aspect ratio of the partial image, and then detect the pixel intensity of each pixel in the standardized partial image; and the image analysis module is configured to visualize a pixel spectrum by expressing the pixel intensity of each pixel as a graph, wherein the pixel spectrum In visualization, the graph is configured to generate a line segment connecting the point of the first pixel and the point of the last pixel in the graph as a reference line, and to perform a graph flattening operation in which the pixel intensity value of each pixel is corrected by subtracting the value corresponding to the reference line from the pixel intensity value of each pixel, wherein if the subtracted value is negative, it is corrected to 0, and the antibody possession rate or antigen possession rate,A quantitative analysis system comprising: a pixel spectrum corrected by the graph flattening operation described above, wherein the maximum value of the control group and the maximum value for the target antibody or target antigen are respectively extracted from the control group and the maximum value for the target antibody or target antigen are respectively extracted, and the result of comparing the maximum value of the control group and the maximum value for the target antibody or target antigen is calculated as the possession rate of a specific antibody or the possession rate of a specific antigen relative to the control group.

Images