Blood card interpretation method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention provides a blood card interpretation method and device, electronic equipment and a storage medium. The method comprises the steps that a blood card image corresponding to a to-be-interpreted blood card is obtained, the to-be-interpreted blood card is a blood card obtained through blood card detection reaction based on a microcolumn gel method, and the blood card comprises a plurality of microcolumn gel tubes; performing image detection on the reaction image based on a first image processing model to obtain a first detection result of each micro-column gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on a second image processing model to obtain a second detection result of each micro-column gel tube in the blood card to be interpreted, the first image processing model is different from the second image processing model; and determining a target interpretation result of each micro-column gel tube in the blood card to be interpreted according to the first detection result and the second detection result. The method can improve the accuracy of blood card interpretation.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a blood card reading method, device, electronic device and storage medium. Background Technology

[0002] Blood cards are primarily based on the principle of antigen-antibody reactions. Taking microcolumn gel cards as an example, known antibodies, such as anti-A, anti-B, and anti-D monoclonal antibodies, are added to the microcolumn gel tube. The blood to be tested is then added to the microcolumn gel tube, and the results can be interpreted based on the reaction.

[0003] Blood cell interpretation involves analyzing the morphology, distribution, or location of red blood cells in a gel through image processing, converting this data into agglutination intensity scores or positive / negative results, and thus determining the interpretation outcome, thereby improving the efficiency of the judgment.

[0004] However, current blood card interpretation methods are easily affected by image quality (such as image brightness, background, bubbles, etc., which have a significant impact on the interpretation results), have difficulty dealing with complex image shapes, have fixed interpretation rules, and have poor generalization ability, resulting in low accuracy of interpretation results. Summary of the Invention

[0005] The main purpose of this application is to provide a blood card reading method, device, electronic device and storage medium to improve the accuracy of blood card reading.

[0006] To achieve the above objectives, this application proposes a blood card interpretation method, including: Acquire the reaction image corresponding to the blood card to be judged. The blood card to be judged is a blood card obtained by blood card detection reaction based on microcolumn gel method. The blood card includes multiple microcolumn gel tubes. The reaction image is detected based on the first image processing model to obtain the first detection result of each micropillar gel tube in the blood card to be read, and the reaction image is detected based on the second image processing model to obtain the second detection result of each micropillar gel tube in the blood card to be read. The first image processing model and the second image processing model are different. The interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined based on the first and second test results.

[0007] Another aspect of this application proposes a blood card reading device, comprising: The acquisition unit is used to acquire the reaction image corresponding to the blood card to be judged. The blood card to be judged is a blood card obtained by blood card detection reaction based on microcolumn gel method. The blood card includes multiple microcolumn gel tubes. The detection unit is used to perform image detection on the reaction image based on the first image processing model to obtain the first detection result of each micropillar gel tube in the blood card to be read, and to perform image detection on the reaction image based on the second image processing model to obtain the second detection result of each micropillar gel tube in the blood card to be read. The first image processing model and the second image processing model are different. The determination unit is used to determine the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result.

[0008] Optionally, in one embodiment, the first image processing model is an image segmentation model, the second image processing model is an object detection model, and the detection unit includes: The first segmentation subunit is used to segment the reaction image based on the image segmentation model to obtain the first detection result and the corresponding first confidence level of each microcolumn gel tube in the blood card to be judged. The first detection subunit is used to perform target detection on the reaction image based on the target detection model, and obtain the second detection result and the corresponding second confidence level of each microcolumn gel tube in the blood card to be judged. The defined unit includes: The first determining subunit is used to determine the consistency between the first detection result and the second detection result corresponding to each micropillar gel tube; The second determining subunit is used to determine the interpretation result of the target micropillar gel tube in the blood card to be interpreted based on the first confidence level and the second confidence level when the consistency indicator target micropillar gel tube is different from the first detection result and the second detection result; when only one image processing model outputs the detection result in the image segmentation model and the target detection model, and a third detection result is obtained, the interpretation result of each micropillar gel tube in the blood card to be interpreted is determined based on the third detection result.

[0009] Optionally, in one embodiment, the detection unit is specifically used for: Based on the first image processing model, image detection is performed on the reaction image to obtain the first coordinate position and first detection result of each microcolumn gel tube in the blood card to be read; and based on the second image processing model, image detection is performed on the reaction image to obtain the second coordinate position and second detection result of each microcolumn gel tube in the blood card to be read. The defined unit includes: The third determining subunit is used to obtain the number of microcolumn gel tubes in the blood card to be interpreted, and to determine the spacing between adjacent microcolumn gel tubes in the reaction image based on the number of microcolumn gel tubes and the width of the reaction image. The fourth determining subunit is used to determine the fourth detection result and the third coordinate position of each microcolumn gel tube in the blood card to be interpreted based on the first coordinate position, the first detection result, the second coordinate position, and the second detection result. The fifth determining subunit is used to determine the category label corresponding to the fourth detection result based on the spacing and the third coordinate position; The sixth determining subunit is used to determine the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the fourth detection result and category label of each microcolumn gel tube.

[0010] Optionally, in one embodiment, the detection unit further includes: An adjustment subunit is used to resize the reaction image; A conversion subunit is used to convert the adjusted reaction image into a multidimensional array format.

[0011] Another aspect of this application provides a training apparatus for an image segmentation model, comprising: The acquisition unit is used to acquire the first sample image and the segmentation mask label obtained after the first sample image is labeled with a mask. The segmentation unit is used to perform image segmentation on the first sample image based on the image segmentation model to obtain the first classification result; The update unit is used to update the parameters of the image segmentation model based on the difference between the first classification result and the segmentation mask label.

[0012] Optionally, in one embodiment, the segmentation unit includes: The data augmentation subunit is used to perform data augmentation on the first sample image to obtain multiple augmented sample images; The segmentation subunit is used to perform image segmentation on each enhanced sample image based on the image segmentation model to obtain the first classification result.

[0013] Another aspect of this application provides a training apparatus for an object detection model, comprising: The acquisition unit is used to acquire the second sample image and the bounding box label obtained after the second sample image is selected and annotated. The detection unit is used to perform target detection on the second sample image based on the target detection model to obtain the second classification result; The update unit is used to update the parameters of the object detection model based on the difference between the second classification result and the bounding box label.

[0014] Another aspect of this application provides an electronic device, comprising: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is used to execute programs in memory, including methods for performing the aspects mentioned above; Bus systems are used to connect memory and processor to enable communication between them.

[0015] Another aspect of this application provides a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described above.

[0016] As can be seen from the above technical solutions, the embodiments of this application have the following advantages: This method classifies the reaction images of the blood card to be interpreted using image processing models based on different classification methods. Then, based on the detection results of each microcolumn gel tube in the blood card to be interpreted obtained from different image processing models, the interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined. This method can combine the classification results of image processing models with different classification methods to improve the accuracy of blood card interpretation. Attached Figure Description

[0017] Figure 1 This is a system architecture diagram of the blood card interpretation method provided in the embodiments of this application; Figure 2 This is a flowchart illustrating the blood card interpretation method provided in the embodiments of this application; Figure 3 This is a schematic diagram of the bounding box label provided in an embodiment of this application; Figure 4 This is a flowchart illustrating another blood card interpretation method provided in an embodiment of this application; Figure 5 This is a schematic diagram of the blood card reading device provided in the embodiments of this application; Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0019] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0020] The term “exemplary” as used herein means “serving as an example, embodiment, or illustration.” Any embodiment illustrated herein as “exemplary” is not necessarily to be construed as superior to or better than other embodiments.

[0021] In the embodiments of this application, the terms "module" or "unit" refer to a computer program or part of a computer program that has a predetermined function and works with other related parts to achieve a predetermined goal, and can be implemented wholly or partially using software, hardware (such as processing circuitry or memory), or a combination thereof. Similarly, a processor (or multiple processors or memory) can be used to implement one or more modules or units. Furthermore, each module or unit can be part of an overall module or unit that includes the functionality of that module or unit.

[0022] Furthermore, to better illustrate this application, numerous specific details are provided in the following detailed embodiments. Those skilled in the art should understand that this application can be implemented without certain specific details. In some instances, methods, means, components, and circuits well-known to those skilled in the art have not been described in detail in order to highlight the main points of this application.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0024] System architecture and scenario description used in the embodiments of this application: Figure 1 This is a system architecture diagram of the blood card interpretation method according to an embodiment of this application. It includes a terminal 140, an Internet 130, a gateway 120, a server 110, etc.

[0025] Terminal 140 includes various device forms with display screens, such as desktop computers, laptops, PDAs (personal digital assistants), mobile phones, dedicated terminals, and intelligent voice interaction devices. Furthermore, it can be a single device or a collection of multiple devices. Terminal 140 can communicate with the Internet 130 and exchange data via wired or wireless means.

[0026] Server 110 refers to a computer system that can provide certain services to terminal 140. Compared to ordinary terminal 140, server 110 has higher requirements in terms of stability, security, and performance. Server 110 can be a single high-performance computer in a network platform, a cluster of multiple high-performance computers, a portion of a single high-performance computer (e.g., a virtual machine), or a combination of portions of multiple high-performance computers (e.g., virtual machines).

[0027] Gateway 120, also known as an internetwork connector or protocol converter, is a computer system or device that acts as a translator, enabling network interconnection at the transport layer. It bridges the gap between two systems using different communication protocols, data formats, languages, or even completely different architectures. Gateways can also provide filtering and security functions. Messages sent from terminal 140 to server 110 are forwarded to the corresponding server 110 via gateway 120. Messages sent from server 110 to terminal 140 are also forwarded to the corresponding terminal 140 via gateway 120.

[0028] The blood card interpretation method provided in this application embodiment can be implemented separately in terminal 140, separately in server 110, or partially in terminal 140 and partially in server 110.

[0029] When the blood card interpretation method provided in this application embodiment is implemented alone in the terminal 140, the terminal 140 acquires the reaction image corresponding to the blood card to be interpreted. The blood card to be interpreted is a blood card obtained by blood card detection reaction based on the microcolumn gel method, and the blood card includes multiple microcolumn gel tubes. The terminal 140 performs image detection on the reaction image based on a first image processing model to obtain a first detection result for each microcolumn gel tube in the blood card to be interpreted, and performs image detection on the reaction image based on a second image processing model to obtain a second detection result for each microcolumn gel tube in the blood card to be interpreted. The first image processing model and the second image processing model are different. The terminal 140 determines the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result.

[0030] The blood card interpretation method provided in the embodiments of this application will be described below with reference to the accompanying drawings. The execution subject of the blood card interpretation method described below is a terminal device, which can be implemented by the terminal device by running the various computer programs mentioned above. Of course, based on the understanding of the following text, it is not difficult to see that the blood card interpretation method provided in the embodiments of this application can also be implemented by the terminal device and the server in collaboration.

[0031] First, let's analyze some of the terms used in this application: Microcolumn gel chromatography is a detection method that combines antigen-antibody specific reactions, gel molecular sieve filtration, and centrifugation techniques, primarily used for erythrocyte antigen-antibody detection. A microcolumn gel card typically consists of a plastic casing and multiple internal microcolumn gel tubes. Each microcolumn gel tube is divided into a sample application chamber at the top and a gel separation column at the bottom. The gel separation column is composed of porous gel particles (such as dextran gel) and antibodies. When the antigen on the surface of erythrocytes binds to the corresponding antibody in the gel, the erythrocytes agglutinate; if there is no corresponding antigen on the surface of the erythrocytes, the antibody will not bind, and the erythrocytes remain in a free state. The principle utilizes the molecular sieve properties of the gel medium. Under centrifugal force, free erythrocytes can freely pass through the gel gaps, while agglutinated erythrocytes, due to their increased size, cannot pass through the gel gaps and are thus retained in the upper layer of the gel or dispersed within the gel. By observing the distribution of erythrocytes in the gel, it is possible to determine whether an antigen-antibody reaction has occurred.

[0032] The procedure includes sample preparation, sample loading, incubation, centrifugation, and result observation. First, red blood cells are washed and prepared into a suspension of appropriate concentration. Then, the red blood cell suspension and antibody suspension are added to a microcolumn gel tube. Next, the microcolumn gel tube is placed in an incubator and incubated at a suitable temperature and time to promote antigen-antibody reaction. After incubation, low-speed centrifugation is performed. Finally, the distribution of red blood cells in the gel is observed after centrifugation. If red blood cells agglutinate, they will be distributed in the upper or middle layer of the gel, indicating a positive result; if red blood cells do not agglutinate, they will be deposited at the bottom of the gel, indicating a negative result.

[0033] Existing image-based blood type recognition algorithms can crop the image of a blood card into small images of individual micropillar gel tubes, and then use traditional image processing methods to process the micropillar gel tube images to obtain blood type classification results. However, current image processing methods have fixed interpretation rules and poor generalization, which can easily affect the interpretation results, leading to low accuracy in blood card identification.

[0034] In response, this application provides a blood card interpretation method that can solve the above-mentioned problems.

[0035] Please see Figure 2 ,like Figure 2 The diagram shown is a flowchart of a blood card interpretation method provided in this embodiment. The method includes: Step 201: Obtain the reaction image corresponding to the blood card to be interpreted.

[0036] The blood card to be interpreted can be a blood card detection reaction based on the microcolumn gel method. Red blood cells have various antigens on their surface, such as A and B antigens in the ABO blood group system, and D, C, c, E, and e antigens in the Rh blood group system. Blood card detection reactions can be based on antigen-antibody specific reactions. By reacting red blood cells with known antibodies and observing whether agglutination occurs, the type of antigen on the surface of the red blood cells can be determined.

[0037] A blood test can include multiple microcolumn gel tubes, each corresponding to a detection indicator (such as A antigen, B antigen, RhD antigen, etc.). The reaction state inside the microcolumn gel tube directly reflects the test result.

[0038] The reaction image can be image data acquired by imaging equipment, showing the overall appearance of the blood card and the state of each microcolumn gel tube after the microcolumn gel method test. The image can cover all microcolumn gel tubes of the microcolumn gel method blood card that has completed the blood card test reaction, including the physical outline of the blood card, the spatial distribution of the microcolumn gel tubes, and can also show the gel medium, morphology and distribution characteristics of red blood cells in each microcolumn gel tube, such as specific details such as agglutination area, clear area, and interface state.

[0039] Step 202: Perform image detection on the reaction image based on the first image processing model to obtain the first detection result of each microcolumn gel tube in the blood card to be read, and perform image detection on the reaction image based on the second image processing model to obtain the second detection result of each microcolumn gel tube in the blood card to be read.

[0040] Image processing models refer to algorithmic systems built upon technologies such as computer vision and pattern recognition. These models acquire, preprocess, extract, analyze, and interpret pixel data from images to automatically identify, detect, segment, or classify information such as the shape, attributes, and state of target objects within the image. The first and second image processing models differ in their choice of training data or network architecture. The first image processing model can automatically detect reaction images and output the detection results for each individual micropillar gel tube; this detection result can be called the first detection result. Similarly, the second image processing model can automatically detect the same reaction image and output the detection results for each individual micropillar gel tube within the reaction image; this detection result can be called the second detection result.

[0041] In one embodiment, the first image processing model is an image segmentation model, and the second image processing model is a target detection model. The steps of performing image detection on the reaction image based on the first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on the second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be interpreted, include: Based on the image segmentation model, the reaction image is segmented to obtain the first detection result and the corresponding first confidence level of each microcolumn gel tube in the blood card to be judged; Based on the target detection model, target detection is performed on the reaction image to obtain the second detection result and the corresponding second confidence level of each microcolumn gel tube in the blood card to be interpreted. Based on the first and second test results, the interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined, including: Determine the consistency between the first and second detection results for each micropillar gel tube; When the consistency indicator for the target microcolumn gel tube is different from the first and second detection results, the interpretation result of the target microcolumn gel tube in the blood card to be interpreted is determined based on the first confidence level and the second confidence level. When only one image processing model outputs a detection result in the image segmentation model and the object detection model, and a third detection result is obtained, the interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined based on the third detection result.

[0042] In this implementation, the image segmentation model can classify each pixel of the input image, grouping pixels with the same semantic meaning into the same region based on features such as grayscale, texture, and color, thereby achieving structured image segmentation. For reaction images, the segmentation objects include the overall area of ​​the blood card and the background area, the areas of each individual micropillar gel tube, and the gel medium area and red blood cell distribution area within each micropillar gel tube, among other semantically different parts. The final output is the segmentation result labeled with the category and boundary of each region, along with the corresponding confidence level. This segmentation result can be referred to as the first detection result.

[0043] Object detection models can extract deep features from images to identify objects that match a predefined target definition. They can determine the target's category and output its location information within the image. They can focus on key targets of interest, directly capturing the target's core features and spatial location. The final output includes the target category, bounding box coordinates, and confidence score; this result can be called the secondary detection result. Object detection models, along with image segmentation models, can provide both category and region location information. These models can focus on key areas where reactions occur, are more sensitive to subtle color variations and inconspicuous reactions, and can visually display each agglomeration region and interpretation result, facilitating source identification and reducing missed and false positives.

[0044] Confidence score can be considered a quantitative score of the model's confidence in its own output detection results, ranging from 0 to 1. It measures the reliability of the model's judgment. Here, it represents the model's certainty regarding whether the detection result is negative or positive. Specifically, the confidence score of the first detection result corresponding to each micropillar gel tube output by the image segmentation model can be called the first confidence score, and the confidence score of the second detection result corresponding to each micropillar gel tube output by the object detection model can be called the second confidence score. The closer the score is to 1, the higher the certainty of the model regarding the detection result; the closer it is to 0, the lower the certainty.

[0045] Since the first and second test results are not necessarily the same, the interpretation result corresponding to the microcolumn gel tube can be determined by combining the first and second confidence levels. That is, the test result with higher confidence level is selected as the interpretation result.

[0046] Consistency measures the degree of agreement between the first and second test results (both positive / negative) from the same microcolumn gel tube in terms of conclusion. Only when consistency indicates a difference between the first and second test results is confidence level considered when determining the interpretation. For example, first determine if the two sets of test results are consistent, and simultaneously check if both confidence levels are higher than a preset confidence threshold (e.g., 0.5). If the results are consistent and both confidence levels meet the threshold, the consistent conclusion is directly used as the interpretation. If the two sets of test results conflict (one positive and one negative), the values ​​of the first and second confidence levels are compared, and the test result with the higher confidence level is taken as the corresponding interpretation. For example, if the first confidence level is 0.83 (positive result) and the second confidence level is 0.47 (negative result), then the positive result is adopted. It is understandable that if either confidence level is lower than the preset confidence threshold, regardless of whether the results are consistent, it can be determined that manual review is required.

[0047] Consistency can categorize results into "consistent" and "conflicting" scenarios, and confidence comparison is only enabled when there is a conflict. This eliminates the need for complex confidence weighting or analysis on all microcolumn gel tubes, reducing redundant computations.

[0048] Understandably, in a conventional dual-model collaborative interpretation process, the outputs of two models need to be cross-validated and mutually verified to confirm the position and aggregation state of the micropillar gel tubes. While this approach improves interpretation accuracy, if one model fails to output a valid result due to poor image quality, weakened target features, or model issues, directly discarding the valid data from the other model would lead to the omission of interpretation information for the corresponding micropillar gel tubes, resulting in missed detections. Therefore, the detection result corresponding to the model providing valid output (referred to here as the third detection result) can be used as the final detection result to parse and obtain the interpretation result. Furthermore, based on the confidence level of the detection result, results with a confidence level higher than a preset threshold can be directly used as the final interpretation basis, while results with a confidence level lower than the threshold are marked for manual review.

[0049] In one embodiment, the steps of performing image detection on the reaction image based on a first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on a second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be interpreted, include: Based on the first image processing model, image detection is performed on the reaction image to obtain the first coordinate position and first detection result of each microcolumn gel tube in the blood card to be read; and based on the second image processing model, image detection is performed on the reaction image to obtain the second coordinate position and second detection result of each microcolumn gel tube in the blood card to be read. The steps for determining the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first and second test results include: The number of microcolumn gel tubes in the blood card to be interpreted is obtained, and the spacing between adjacent microcolumn gel tubes in the reaction image is determined based on the number of microcolumn gel tubes and the width of the reaction image. Based on the first coordinate position, the first detection result, the second coordinate position, and the second detection result, determine the fourth detection result and the third coordinate position of each microcolumn gel tube in the blood card to be interpreted; The category label corresponding to the fourth detection result is determined based on the spacing and the third coordinate position. The interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined based on the fourth test result and category label of each microcolumn gel tube.

[0050] In this embodiment, the image processing model can automatically detect the reaction image and output the coordinate position of each independent micropillar gel tube and the detection result. The first image processing model outputs the first coordinate position and the first detection result, and the second image processing model outputs the second coordinate position and the second detection result.

[0051] For the two sets of detection results, they can be paired one by one based on the coordinate position. Then, the consistency of the paired results is checked. That is, the first detection result and the second detection result are paired based on the first coordinate position and the second coordinate position. Then, through the consistency check, the final detection result of each microcolumn gel tube is obtained. Here, the detection result is called the fourth detection result, and the coordinate position corresponding to the fourth detection result can be called the third coordinate position.

[0052] The number of micropillar gel tubes can refer to the total number of independent slots on the blood sac used to carry the blood sac's detection reaction. Based on the width of the reaction image and the number of micropillar gel tubes, the spacing between adjacent micropillar gel tubes in the blood sac can be determined. For example, dividing the total pixel width of the reaction image (denoted as W) by the number of micropillar gel tubes (denoted as N) yields the spacing between the center positions of adjacent micropillar gel tubes (denoted as N). The microcolumn gel tubes in the blood card are ordered, with different serial numbers corresponding to different category labels. Each category label corresponds to a pre-set test item. The test items on the same blood card can be different or the same. When the test items are the same, different samples are added to different microcolumn gel tubes. For example, in the ABO blood typing and Rh blood typing test card, the 8 microcolumn gel tubes correspond to different test items, and the category labels are A, B, Ctl, D, N (self), Ac, Bc, and N (oc). In the anti-human globulin antigen test card (8 microcolumn gel tube blood card), the 8 microcolumn gel tubes correspond to the same test item. During the experiment, different samples are added, and the category labels can be recorded as anti-human 1, anti-human 2, anti-human 3, anti-human 4, anti-human 5, anti-human 6, anti-human 7, and anti-human 8. Based on the relationship between the coordinate position and the spacing output by the image processing model, the index corresponding to that coordinate position can be calculated, and then the corresponding category label can be determined based on the index. For example, if the coordinate position is X and the spacing is w, then the index corresponding to that coordinate position is the rounded-up index. Using this method, the serial numbers of the microcolumns corresponding to all third coordinate positions are obtained, thus yielding the category label corresponding to the fourth detection result. Based on the category label, the detection item corresponding to each fourth detection result can be determined; that is, based on the detection results corresponding to different detection items, the interpretation result of the blood card to be interpreted can be determined. The algorithm quickly identifies and divides each slot, eliminating the need for manual selection of micropillar gel tubes in each image. This enables continuous and uninterrupted image segmentation, shortening the overall detection process time.

[0053] In one embodiment, before performing image detection on the reaction image based on a first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be interpreted, and before performing image detection on the reaction image based on a second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be interpreted, the method further includes: Resize the reaction image; Convert the adjusted reaction image into a multidimensional array format.

[0054] In this embodiment, size adjustment can refer to scaling, cropping, or stretching the original reaction image based on the input specifications of the first and second image processing models, so that the resolution, aspect ratio, and other parameters of the adjusted image match the input dimensions of the model, thereby eliminating the problem of inconsistent input sizes caused by differences in image acquisition devices.

[0055] Multidimensional array format conversion refers to converting a resized image into a computer-computable multidimensional array (tensor) format. The dimensions of the array correspond to the number of channels in the image (e.g., an RGB image is a 3-dimensional array: height × width × number of channels), pixel coordinates, and other characteristics.

[0056] Size adjustment ensures that the image size perfectly matches the input specifications of the first and second image processing models by unifying parameters such as resolution and aspect ratio of the reaction image. This avoids model errors caused by incompatible input sizes. Multidimensional array format conversion directly provides the model with computable numerical data without requiring additional format parsing, thus improving the model's detection efficiency.

[0057] In one implementation, the training process of the image segmentation model includes the following steps: Obtain the first sample image and the segmentation mask label obtained after mask annotation of the first sample image; The first sample image is segmented based on the image segmentation model to obtain the first classification result; The parameters of the image segmentation model are updated based on the difference between the first classification result and the segmentation mask label.

[0058] In this embodiment, the first sample image can be an image captured of a micropillar gel tube in different detection states. The segmentation mask label can be obtained through pixel-level annotation, where each pixel in the label corresponds to a specific category. The first sample image can be divided into multiple regions, with each pixel in each region labeled as a category. Each category can be manually annotated or obtained through manual review of the annotated images.

[0059] The prepared first sample image is input into the image segmentation model to be trained. The model uses its built-in feature extraction network to extract pixel features (such as grayscale, texture, and boundary information) from the image, and classifies each pixel based on these features, finally outputting the first classification result. The difference between the first classification result and the segmentation mask label is calculated. The difference can be quantified using a loss function, and then the loss value is fed back to each layer of the model network through the backpropagation algorithm to adjust the model's weights, biases, and other parameters according to the gradient descent direction.

[0060] The parameters of the image segmentation model can be adjusted by defining a certain gap. By continuously inputting samples, calculating the gap, and adjusting the parameters, the model's guesses can get closer and closer to the true answer, thus gradually improving the accuracy of the model's predictions.

[0061] In one example, the first sample image can cover various types of red blood cell surface antigens and include samples with different agglutination intensities. Multiple imaging devices and lighting conditions can be used during the acquisition process to enhance data diversity and model generalization ability. Each image should clearly label the location of the antigen reaction area and the corresponding agglutination reaction status, and establish corresponding flocculation result labels to obtain segmentation mask labels. For example, flocculation result labels can be labeled as "-", "+ / -", "1+", "2+", "3+", "4+", "H (hemolysis)", "? (unrecognizable)", "Dp", and "BLK (empty)", with each category represented by 0-9. The first sample image and segmentation mask labels can be divided into training and validation sets. The parameters of the image segmentation model are updated based on the training set, and the image segmentation model is validated based on the validation set.

[0062] In one implementation, the step of performing image segmentation on a first sample image based on an image segmentation model to obtain a first classification result includes: Data augmentation is performed on the first sample image to obtain multiple augmented sample images; The image segmentation model is used to segment each enhanced sample image to obtain the first classification result.

[0063] In this implementation, data augmentation refers to expanding and perturbing the original training samples through a series of random or deterministic spatial, color, and geometric transformations without altering the semantic information of the image, thereby generating diverse and high-fidelity new samples. The first sample image for data augmentation can be called the augmented sample image. For each data-augmented sample image, it can be independently input into a trained image segmentation model. The model performs forward inference on the augmented image based on the learned pixel-level discrimination rules and outputs the corresponding classification result.

[0064] Data augmentation can simulate various imaging differences and deformations that may exist in real-world scenarios, improving the model's robustness and generalization ability to unseen data.

[0065] In one implementation, the training process of the object detection model includes the following steps: Obtain the second sample image and the bounding box labels obtained after selecting and annotating the second sample image; The second sample image is used to perform object detection based on the object detection model to obtain the second classification result; The parameters of the object detection model are updated based on the difference between the second classification result and the bounding box label.

[0066] In this embodiment, the second sample image can be an image captured from a micropillar gel tube in different detection states. The bounding box label can be a category label assigned to each bounding box by selecting each target (such as each agglutinated particle or red blood cell cluster) in the image with a rectangular bounding box, ensuring the bounding box completely encloses the target. This can be obtained through manual selection and labeling, or through manual review of already labeled images.

[0067] The second sample image is input into the target detection model to be trained. The model's built-in backbone network extracts target features from the image (such as the size, shape, grayscale texture, and spatial distribution of aggregated particles). Based on the extracted features, the model first predicts candidate regions in the image where targets may exist, then classifies each candidate region and corrects its bounding box coordinates, finally outputting the second classification result. A loss function is used to measure the deviation between the model's predicted target category and the true category in the label. Through the backpropagation algorithm, the total loss value is fed back to each layer of the model network, adjusting the model's weights, biases, and other parameters according to the gradient descent direction.

[0068] The parameters of the target detection model can be adjusted by defining the gap. By continuously inputting samples, calculating the gap, and adjusting the parameters, the model's guesses can get closer and closer to the true answer, thus gradually improving the accuracy of the model's predictions.

[0069] In one example, a diagram of the bounding box label can be found here. Figure 3 As shown, firstly, the rectangular boxes corresponding to the eight micropillar gel tubes A, B, D, Ctl, N (self), Ac, Bc, and N (oc) are precisely marked on the entire card image. Then, each box is assigned a specific flocculation result label such as "-", "+ / -", "1+", "2+", "3+", "4+", "H (hemolysis)", "? (unrecognizable)", "Dp", and "BLK (empty)". A positive result indicates that agglutination occurs in the micropillar gel tube and red blood cells are retained in the upper layer of the gel, while a negative result indicates that there is no agglutination and red blood cells settle to the bottom of the tube. In this way, each training image ultimately corresponds to eight groups of micropillar gel tubes and eight classification segments. During the inference stage, only the confidence score of the local image within the box needs to be calculated to directly output the interpretation result.

[0070] Step 203: Determine the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first and second test results.

[0071] Taking a single microcolumn gel tube as an example, the first and second test results indicate the interpretation result of the microcolumn gel tube, such as a positive or negative result. The consistency of the first and second test results can be verified. If the two conclusions overlap, the consistent conclusion can be directly adopted as the interpretation result. If a conflict is found during verification, such as one test result being positive and the other negative, a predetermined rule can be used to select one of the first and second test results as the interpretation result.

[0072] In one example, a flowchart illustrating another blood card interpretation method according to an embodiment of this application can be referred to. Figure 4 As shown.

[0073] Step 401: Obtain the reaction image, which can be a photograph of the entire blood card taken by a camera.

[0074] Step 402: Preprocess the reaction image. This can include size normalization, illumination correction, or converting the reaction image to a fixed size, such as resizing the image to 640*480 pixels.

[0075] Step 403: Input the preprocessed reaction image into the image segmentation model and the target detection model to obtain the first detection result and first confidence level of each micropillar gel tube output by the image segmentation model, and the second detection result and second confidence level of each micropillar gel tube output by the target detection model.

[0076] Step 404: Determine whether the first and second detection results of each microcolumn gel tube are consistent. If yes, proceed to step 405; otherwise, proceed to step 406.

[0077] Step 405: Output the detection results corresponding to the microcolumn gel tubes with consistent output results.

[0078] Step 406: Output the detection results corresponding to the microcolumn gel tubes with high confidence.

[0079] Step 407: Integrate the detection results output from each microcolumn gel tube, and output the interpretation result corresponding to the blood card to be interpreted based on the detection results corresponding to all microcolumn gel tubes.

[0080] The blood card interpretation method of this application includes acquiring a reaction image corresponding to a blood card to be interpreted, wherein the blood card to be interpreted is a blood card obtained by blood card detection reaction based on the microcolumn gel method, and the blood card includes multiple microcolumn gel tubes; performing image detection on the reaction image based on a first image processing model to obtain a first detection result for each microcolumn gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on a second image processing model to obtain a second detection result for each microcolumn gel tube in the blood card to be interpreted; determining the result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result, and then combining the results of each microcolumn gel tube to obtain a comprehensive interpretation result of the blood card to be interpreted.

[0081] This method classifies the reaction images of the blood card to be interpreted using image processing models based on different classification methods. Then, based on the detection results of each microcolumn gel tube in the blood card to be interpreted obtained from different image processing models, the interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined. This method can combine the classification results of image processing models with different classification methods to improve the accuracy of blood card interpretation.

[0082] The above describes the blood card interpretation method. The following describes the device used to execute this method. Please refer to [link / reference]. Figure 5 The diagram shows a blood card reading device 500, which includes: The acquisition unit 501 is used to acquire the reaction image corresponding to the blood card to be judged. The blood card to be judged is a blood card obtained by blood card detection reaction based on microcolumn gel method. The blood card includes multiple microcolumn gel tubes. The detection unit 502 is used to perform image detection on the reaction image based on the first image processing model to obtain the first detection result of each micropillar gel tube in the blood card to be read, and to perform image detection on the reaction image based on the second image processing model to obtain the second detection result of each micropillar gel tube in the blood card to be read. The first image processing model and the second image processing model are different. The determination unit 503 is used to determine the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result.

[0083] Optionally, in one embodiment, the first image processing model is an image segmentation model, the second image processing model is an object detection model, and the detection unit 502 includes: The first segmentation subunit is used to segment the reaction image based on the image segmentation model to obtain the first detection result and the corresponding first confidence level of each microcolumn gel tube in the blood card to be judged. The first detection subunit is used to perform target detection on the reaction image based on the target detection model, and obtain the second detection result and the corresponding second confidence level of each microcolumn gel tube in the blood card to be judged. The determining unit 503 includes: The first determining subunit is used to determine the consistency between the first detection result and the second detection result corresponding to each micropillar gel tube; The second determining subunit is used to determine the interpretation result of the target micropillar gel tube in the blood card to be interpreted based on the first confidence level and the second confidence level when the consistency indicator target micropillar gel tube is different from the first detection result and the second detection result; when only one image processing model outputs the detection result in the image segmentation model and the target detection model, and a third detection result is obtained, the interpretation result of each micropillar gel tube in the blood card to be interpreted is determined based on the third detection result.

[0084] Optionally, in one embodiment, the detection unit 502 is specifically used for: Based on the first image processing model, image detection is performed on the reaction image to obtain the first coordinate position and first detection result of each microcolumn gel tube in the blood card to be read; and based on the second image processing model, image detection is performed on the reaction image to obtain the second coordinate position and second detection result of each microcolumn gel tube in the blood card to be read. The defined unit includes: The third determining subunit is used to obtain the number of microcolumn gel tubes in the blood card to be interpreted, and to determine the spacing between adjacent microcolumn gel tubes in the reaction image based on the number of microcolumn gel tubes and the width of the reaction image. The fourth determining subunit is used to determine the fourth detection result and the third coordinate position of each microcolumn gel tube in the blood card to be interpreted based on the first coordinate position, the first detection result, the second coordinate position, and the second detection result. The fifth determining subunit is used to determine the category label corresponding to the fourth detection result based on the spacing and the third coordinate position; The sixth determining subunit is used to determine the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the fourth detection result and category label of each microcolumn gel tube.

[0085] Optionally, in one embodiment, the detection unit 502 further includes: An adjustment subunit is used to resize the reaction image; A conversion subunit is used to convert the adjusted reaction image into a multidimensional array format.

[0086] Another aspect of this application provides a training apparatus for an image segmentation model, comprising: The acquisition unit is used to acquire the first sample image and the segmentation mask label obtained after the first sample image is labeled with a mask. The segmentation unit is used to perform image segmentation on the first sample image based on the image segmentation model to obtain the first classification result; The update unit is used to update the parameters of the image segmentation model based on the difference between the first classification result and the segmentation mask label.

[0087] Optionally, in one embodiment, the segmentation unit includes: The data augmentation subunit is used to perform data augmentation on the first sample image to obtain multiple augmented sample images; The segmentation subunit is used to perform image segmentation on each enhanced sample image based on the image segmentation model to obtain the first classification result.

[0088] Another aspect of this application provides a training apparatus for an object detection model, comprising: The acquisition unit is used to acquire the second sample image and the bounding box label obtained after the second sample image is selected and annotated. The detection unit is used to perform target detection on the second sample image based on the target detection model to obtain the second classification result; The update unit is used to update the parameters of the object detection model based on the difference between the second classification result and the bounding box label.

[0089] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described blood card reading method. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0090] Please see Figure 6 , Figure 6 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 601 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 602 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 602 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 602 and is called and executed by the processor 601 using the blood card reading method of the embodiments of this application. The input / output interface 603 is used to implement information input and output; The communication interface 604 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 605 transmits information between various components of the device (e.g., processor 601, memory 602, input / output interface 603, and communication interface 604); The processor 601, memory 602, input / output interface 603, and communication interface 604 are connected to each other within the device via bus 605.

[0091] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described blood card reading method.

[0092] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0093] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0094] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0095] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0096] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0097] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0098] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0100] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0101] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0102] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0103] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for interpreting blood cards, characterized in that, include: Acquire the reaction image corresponding to the blood card to be interpreted, wherein the blood card to be interpreted is a blood card obtained by blood card detection reaction based on microcolumn gel method, and the blood card includes multiple microcolumn gel tubes; The reaction image is detected based on a first image processing model to obtain a first detection result for each microcolumn gel tube in the blood card to be read, and the reaction image is detected based on a second image processing model to obtain a second detection result for each microcolumn gel tube in the blood card to be read. The first image processing model and the second image processing model are different. The interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined based on the first detection result and the second detection result.

2. The method according to claim 1, characterized in that, The first image processing model is an image segmentation model, and the second image processing model is a target detection model. The step of performing image detection on the reaction image based on the first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on the second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be interpreted, includes: Based on the image segmentation model, the reaction image is segmented to obtain the first detection result and the corresponding first confidence level of each microcolumn gel tube in the blood card to be judged. Based on the target detection model, target detection is performed on the reaction image to obtain the second detection result and the corresponding second confidence level for each microcolumn gel tube in the blood card to be interpreted. The step of determining the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result includes: Determine the consistency between the first detection result and the second detection result corresponding to each micropillar gel tube; When the consistency indicator target microcolumn gel tube corresponds to the first detection result and the second detection result, the interpretation result of the target microcolumn gel tube in the blood card to be interpreted is determined based on the first confidence level and the second confidence level. When only one image processing model outputs a detection result in the image segmentation model and the target detection model, and a third detection result is obtained, the interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined based on the third detection result.

3. The method according to claim 1, characterized in that, The process of performing image detection on the reaction image based on a first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on a second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be interpreted, includes: Based on the first image processing model, image detection is performed on the reaction image to obtain the first coordinate position and first detection result of each microcolumn gel tube in the blood card to be read; and based on the second image processing model, image detection is performed on the reaction image to obtain the second coordinate position and second detection result of each microcolumn gel tube in the blood card to be read. The step of determining the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result includes: The number of microcolumn gel tubes in the blood card to be interpreted is obtained, and the spacing between adjacent microcolumn gel tubes in the reaction image is determined based on the number of microcolumn gel tubes and the width of the reaction image. Based on the first coordinate position, the first detection result, the second coordinate position, and the second detection result, determine the fourth detection result and the third coordinate position of each microcolumn gel tube in the blood card to be interpreted; The category label corresponding to the fourth detection result is determined based on the spacing and the third coordinate position; The interpretation result of each microcolumn gel tube in the blood card to be interpreted is determined based on the fourth detection result of each microcolumn gel tube and the category label.

4. The method according to claim 1, characterized in that, Before performing image detection on the reaction image based on the first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be interpreted, and performing image detection on the reaction image based on the second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be interpreted, the method further includes: The size of the reaction image is adjusted; The adjusted reaction image is converted into a multidimensional array format.

5. The method according to claim 2, characterized in that, The training process of the image segmentation model includes: Obtain the first sample image and the segmentation mask label obtained after mask annotation of the first sample image; Based on the image segmentation model, the first sample image is segmented to obtain a first classification result; The parameters of the image segmentation model are updated based on the difference between the first classification result and the segmentation mask label.

6. The method according to claim 5, characterized in that, The step of segmenting the first sample image based on the image segmentation model to obtain a first classification result includes: Data augmentation is performed on the first sample image to obtain multiple augmented sample images; Based on the image segmentation model, each enhanced sample image is segmented to obtain the first classification result.

7. The method according to claim 2, characterized in that, The training process of the target detection model includes: Obtain the second sample image and the bounding box label obtained after selecting and annotating the second sample image; Based on the target detection model, target detection is performed on the second sample image to obtain a second classification result; The parameters of the object detection model are updated based on the difference between the second classification result and the bounding box label.

8. A blood card reading device, characterized in that, include: The acquisition unit is used to acquire the reaction image corresponding to the blood card to be judged, wherein the blood card to be judged is a blood card obtained by blood card detection reaction based on microcolumn gel method, and the blood card includes multiple microcolumn gel tubes; The detection unit is used to perform image detection on the reaction image based on a first image processing model to obtain a first detection result for each micropillar gel tube in the blood card to be read, and to perform image detection on the reaction image based on a second image processing model to obtain a second detection result for each micropillar gel tube in the blood card to be read, wherein the first image processing model and the second image processing model are different; A determining unit is used to determine the interpretation result of each microcolumn gel tube in the blood card to be interpreted based on the first detection result and the second detection result.

9. An electronic device, characterized in that, include: Memory, transceiver, processor, and bus system; The memory is used to store programs; The processor is configured to execute a program in the memory, including performing the method as described in any one of claims 1 to 7; The bus system is used to connect the memory and the processor to enable communication between the memory and the processor.

10. A computer-readable storage medium, characterized in that, Includes instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 7.

Images