Sample analysis system and sample analysis method, electronic device and storage medium

Abstract

The present application discloses a sample analysis system and a sample analysis method, an electronic device and a storage medium, wherein the sample analysis method comprises: an electronic device acquires at least two images of a sample container; the at least two images are processed to obtain a sample analysis result of the sample container; wherein the sample analysis result characterizes a sample classification corresponding to the blood sample in the sample container; the sample classification comprises a normal sample, or comprises at least one of a hemolytic sample, a icteric sample and a lipemia sample; when the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample, the sample container is dispatched to a biochemical analysis device for serum index detection and / or biochemical item detection; the detection of biochemical items is performed when the serum index of the blood sample in the sample container is normal.

Description

Technical Field

[0001] The present application relates to the technical field of medical equipment, and in particular to a sample analysis system and a sample analysis method, an electronic device and a storage medium. Background Art

[0002] Abnormal serum quality such as hemolysis, lipemia, and jaundice will affect the accuracy of blood sample test results. For example, chylomicrons may cause falsely high hemoglobin measurement results, and blood clots may cause abnormal sample aspiration. Therefore, serum quality testing is an important part of clinical laboratory blood sample testing. In order to control serum quality, the conventional practice is that after the sample test line obtains the test results, the clinician or laboratory technician will observe the test results manually by naked eye when the test results are found to be abnormal, to confirm whether there is abnormality in the serum quality of the sample, for example, by naked eye to judge whether the serum sample contains chylomicrons or hemolysis of red blood cells or high jaundice. However, the number of blood samples tested in hospitals every day is usually more than 500. The use of the above method to control the serum quality of samples is not only inefficient, but also highly subjective. There are large differences in the judgment results of different personnel, and the confidence of the judgment results is low. Summary of the invention

[0003] In view of this, embodiments of the present application provide a sample analysis system and a sample analysis method, an electronic device, and a storage medium.

[0004] To achieve the above purpose, the technical solution of this application is implemented as follows:

[0005] The embodiment of the present application provides a sample analysis system, including an electronic device, and a first biochemical analysis device coupled to the electronic device, a camera, a sample seat, a rotating device, and a transmission track for transmitting the sample seat carrying a sample container; wherein the biochemical analysis device includes a sample component, a reagent component, and a measurement component;

[0006] The sample seat is used to carry the sample container so that the sample container remains in a vertical state;

[0007] The rotating device is used to drive the sample holder to rotate, so as to drive the sample container carried by the sample holder to rotate around the vertical central axis;

[0008] The camera is used to capture at least two images of the sample container during its rotation process;

[0009] The electronic device is used to process the at least two images to obtain a sample analysis result of the sample container; the sample analysis result represents a sample classification corresponding to the blood sample in the sample container; the sample classification includes a normal sample, or includes at least one of a hemolytic sample, a jaundice sample, and a lipemia sample; and is used to dispatch the sample container to the first biochemical analysis device for processing when the sample analysis result is at least one of a hemolytic sample, a jaundice sample, and a lipemia sample;

[0010] After the electronic device dispatches the sample container to the first biochemical analysis device, the sample component of the first biochemical analysis device draws the blood sample from the sample container and provides the drawn blood sample to the measuring component; the reagent component of the first biochemical analysis device draws the reagent and provides it to the measuring component; the measuring component of the first biochemical analysis device mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction liquid, incubates the reaction liquid, and performs a serum index test on the incubated reaction liquid to obtain the serum index of the blood sample in the sample container.

[0011] The present application also provides a sample analysis method, which is applied to an electronic device in a sample analysis system, wherein the sample analysis system further comprises a biochemical analysis device coupled to the electronic device, a camera, a sample holder, a rotating device for driving the sample holder to rotate, and a transport track for transporting the sample holder carrying a sample container, wherein the camera is used to capture at least two images of the sample container when the rotating device drives the sample container to rotate around a vertical central axis; the sample analysis method comprises:

[0012] acquiring at least two images of the sample container;

[0013] Processing the at least two images to obtain a sample analysis result of the sample container; wherein the sample analysis result represents a sample classification corresponding to the blood sample in the sample container; the sample classification includes a normal sample, or includes at least one of a hemolytic sample, a icteric sample, and a lipemia sample;

[0014] When the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample, the sample container is dispatched to a biochemical analysis device for serum index detection and / or biochemical item detection; the detection of biochemical items is performed when the serum index of the blood sample in the sample container is normal.

[0015] The present application also provides an electronic device, including: a processor and a memory for storing a computer program that can be run on the processor.

[0016] Wherein, the processor is used to execute the steps of any of the above methods when running the computer program.

[0017] An embodiment of the present application further provides a storage medium having a computer program stored thereon, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0018] The sample analysis system and sample analysis method, electronic device and storage medium provided by the embodiment of the present application are used by a camera to take at least two images of the same sample container when the rotating device drives the sample container to rotate around the vertical central axis, and the electronic device processes the at least two images to determine whether the blood sample in the sample container is a normal sample or an abnormal sample such as hemolysis, jaundice, lipemia, etc.; when the blood sample in the sample container is at least one of a hemolysis sample, a jaundice sample and a lipemia sample, the electronic device dispatches the sample container to a biochemical analysis device for serum index detection, and when the serum index of the blood sample in the sample container is normal, the biochemical analysis device performs a biochemical project detection. Compared with the scheme of judging whether the blood sample is abnormal by the naked eye in the related art, the above scheme can improve the efficiency and accuracy of blood sample quality control, and when the electronic device judges that the blood sample in the sample container is an abnormal sample, the blood sample in the sample container is tested for serum index by the biochemical analysis device to determine whether the serum index of the blood sample in the sample container is normal, which further improves the accuracy and confidence of the sample analysis result. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is an example diagram of a sample analysis system architecture according to an embodiment of the present application;

[0020] Figure 2 This is another example diagram of the sample analysis system architecture of the embodiment of the present application;

[0021] Figure 3 This is another example diagram of a sample analysis system architecture according to an embodiment of the present application;

[0022] Figure 4 This is an example diagram of rotating photography in an embodiment of the present application;

[0023] Figure 5 This is another example diagram of a sample analysis system architecture according to an embodiment of the present application;

[0024] Figure 6 This is a schematic diagram of the sample analysis method implementation flow of the present application embodiment;

[0025] Figure 7 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0027] The present application embodiment provides a sample analysis system, referring to Figure 1 The sample analysis system at least includes: an electronic device 101, and a first biochemical analysis device 102, a camera 103, a sample holder 104, a rotating device 105, and a transmission track 106 for transmitting the sample holder carrying the sample container coupled to the electronic device 101; wherein the biochemical analysis device includes a sample component, a reagent component, and a determination component. The electronic device 101 can be directly coupled with the first biochemical analysis device 102, the camera 103, the rotating device 105, and the transmission track 106, for example, the electronic device 101 and the first biochemical analysis device 102, the camera 103, etc. are communicated and connected through a universal serial bus (USB), a high-definition multimedia interface (HDMI), etc. The electronic device 101 can also be indirectly coupled with the first biochemical analysis device 102, the camera 103, the rotating device 105, and the transmission track 106, for example, the electronic device 101 communicates and connects with the first biochemical analysis device 102, the camera 103, the rotating device 105, and the transmission track 106 through an intermediate device or other devices. in,

[0028] The sample holder 104 is used to carry the sample container so as to keep the sample container in a vertical state;

[0029] The rotating device 105 is used to drive the sample holder to rotate, so as to drive the sample container carried by the sample holder to rotate around the vertical central axis;

[0030] A camera 103, used to capture at least two images of the sample container during its rotation;

[0031] The electronic device 101 is used to process the at least two images to obtain a sample analysis result of the sample container; the sample analysis result represents a sample classification corresponding to the blood sample in the sample container; the sample classification includes a normal sample, or includes at least one of a hemolytic sample, a icteric sample, and a lipemia sample; and is used to dispatch the sample container to the first biochemical analysis device 102 for processing when the sample analysis result is at least one of a hemolytic sample, a icteric sample, and a lipemia sample;

[0032] After the electronic device 101 dispatches the sample container to the first biochemical analysis device 102, the sample component of the first biochemical analysis device 102 draws the blood sample from the sample container and provides the drawn blood sample to the measuring component; the reagent component of the first biochemical analysis device 102 draws the reagent and provides it to the measuring component; the measuring component of the first biochemical analysis device 102 mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction liquid, incubates the reaction liquid, and performs a serum index test on the incubated reaction liquid to obtain the serum index of the blood sample in the sample container.

[0033] Here, the electronic device 101 can be a terminal device, a control device, a server or other device with computing capabilities. The sample holder 104 is connected to the rotating device 105, and the sample holder 104 can clamp the bottom of the sample container to keep the sample container in a vertical state; the rotating device 105 can drive the sample container carried by the sample holder 104 to rotate around the vertical center axis, for example, 360 degrees. The camera 103 can take at least two images of the sample container during the rotation of the sample container around the vertical center axis, that is, perform rotation scanning or rotation photography on the same sample container; the at least two images taken by the camera 103 for the sample container have images with different shooting perspectives or different shooting angles. The camera 103 can directly transmit all images of the sample container to the electronic device 101, or transmit all images of the sample container to other devices for storage, and the electronic device 101 can obtain the image of the sample container from other devices. Further, the camera 103 saves the image of the sample container taken to the set storage path of the camera 103 or other electronic devices, and the electronic device 101 obtains and saves the image of the sample container from the set storage path. In actual application, a corresponding folder can be created for each sample container, and the images of the sample containers can be stored in the corresponding folders respectively, so as to realize the distinction between the images of different sample containers. In addition, the camera 103 stores all the images of a sample container captured into the set storage path each time. After the electronic device 101 obtains all the images of the sample container from the set storage path, the electronic device 101 can clear all the images under the set storage path. Thereafter, the camera 103 stores all the images of another sample container captured into the set storage path, so as to realize the image reading of the sample container one by one.

[0034] In practical applications, the sample container can be understood as a transparent or translucent container for loading blood samples, which can be a blood collection tube, a test tube, a sample tube, a sampling tube, a test tube, a bottle, a sample cup, etc. The sample container is loaded with a blood sample, which can be a serum sample or a plasma sample, and a reagent for detection can be added to the blood sample. A label is pasted or attached to the surface of the sample container, which is used to mark or record relevant information of the blood sample. The label may include identification information of the blood sample in the sample container, such as a barcode, or a serial code composed of letters and / or numbers.

[0035] In actual application, the duration of the camera 103 taking pictures of the sample container needs to be greater than or equal to the duration required for the sample container to rotate one circle or 360 degrees, so as to ensure that the camera 103 can obtain images of the sample container from different shooting angles or shooting perspectives during the sample container's rotation. Considering that the camera 103 is prone to motion artifacts when photographing a moving object, in the scene of rotating photography, in order to ensure that the camera 103 can obtain clear images of the sample container at different shooting angles during the sample container's rotation, further, the exposure duration and / or shooting frequency of the camera have a set corresponding relationship or mapping relationship with the rotation speed of the rotating mechanism. Here, different rotation speeds of the rotating device 105 correspond to different exposure durations, and / or different rotation speeds of the rotating device 105 correspond to different shooting frequencies. The rotation speed of the rotating device 105 can be determined according to the recognition speed of the label on the sample container; of course, the rotation speed of the rotating device 105 can also be a set rotation speed. The exposure duration can also be understood as the exposure time. In order to ensure that the camera 103 can capture a clear image, the exposure time of the camera 103 is less than or equal to the quotient of the accuracy of the camera 103 and the rotation speed of the rotating mechanism. The accuracy of the camera 103 can also be called pixel accuracy, which is equal to the quotient of the unidirectional field of view of the camera and the unidirectional resolution. In practical applications, the shooting frequency can be replaced by the frame rate; the frame rate can be understood as the number of frames of the image captured per second, for example, the frame rate is 20 frames per second.

[0036] When the electronic device 101 obtains at least two images of the same sample container, it processes all images of the sample container to obtain the sample analysis result of the sample container, thereby obtaining the sample classification corresponding to the blood sample in the sample container. Among them, the sample classification of the blood sample can be divided into the following four types: hemolysis (H, Hemolysis) sample, icterus (I, Icterus) sample, lipemia (L, Lipemia) sample and normal (Normal) sample. Hemolysis, icterus and lipemia are collectively referred to as HIL in this application, and lipemia is also called chyle blood. Normal samples can be understood as serum or plasma with an acceptable small amount of hemolysis, icterus and lipemia, and the color presented by normal samples is transparent yellow or light yellow. Lipemia samples can be understood as blood samples with abnormally high concentrations of emulsified fat, and the color presented by lipemia samples is dark yellow, gray, white or milky white; the color presented by blood samples is different due to different lipemia indexes. For example, when the lipemia index is low, the blood sample presents dark yellow, and when the lipemia index is high, the blood sample presents gray, white or milky white. Hemolysis samples can be understood as blood samples in which red blood cells are ruptured and hemoglobin escapes from the red blood cells. The color of hemolysis samples is light red, dark red, or light red to dark red. The higher the hemolysis index, the darker the color of the blood sample. Jaundice samples can be understood as blood samples that are yellowed due to increased bilirubin. The color of jaundice samples. It is precisely because abnormal blood samples will show corresponding color and other characteristics that the sample quality can be judged based on image features to determine whether the sample quality is abnormal.

[0037] In the case where the sample analysis result of the blood sample in the sample container is at least one of a hemolysis sample, a icteric sample, and a lipemia sample, the electronic device 101 dispatches the sample container to the first biochemical analysis device 102 for processing through the transmission track 106. After the electronic device 101 dispatches the sample container to the first biochemical analysis device 102, the sample component of the first biochemical analysis device 102 absorbs the blood sample from the sample container and provides the absorbed blood sample to the determination component of the first biochemical analysis device 102; the reagent component of the first biochemical analysis device 102 absorbs the reagent and provides it to the determination component of the first biochemical analysis device 102; the determination component of the first biochemical analysis device 102 mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction solution, incubates the reaction solution, and performs a serum index test on the incubated reaction solution to obtain the serum index of the blood sample in the sample container. The serum index (HIL) refers to the determination of the degree of hemolysis, icterus, and lipid turbidity of the blood sample, and obtains the hemolysis index, icterus index, and lipid turbidity index.

[0038] Wherein, the sample component may include a sample carrying component and a sample dispensing mechanism. The sample carrying component is used to carry a sample container. In some examples, the sample carrying component may include a sample delivery module (SDM) and a front track. In other examples, the sample carrying component may also be a sample tray, which includes a plurality of sample positions such as sample containers. The sample tray can dispatch the sample container to a corresponding position by rotating its disk structure, such as a position for the sample dispensing mechanism to absorb a blood sample. The sample dispensing mechanism is used to absorb a blood sample and discharge it into a reaction cup to be loaded with a sample. For example, the sample dispensing mechanism may include a sample needle, which performs a two-dimensional or three-dimensional movement in space through a two-dimensional or three-dimensional driving mechanism, so that the sample needle can move to absorb the blood sample in the sample container carried by the sample carrying component, and move to the reaction cup to be loaded with a sample, and discharge the blood sample into the reaction cup.

[0039] Wherein, the reagent component may include a reagent carrying component and a reagent dispensing mechanism. The reagent carrying component is used to carry reagents. In one embodiment, the reagent carrying component may be a reagent disk, which is provided in a disc-shaped structure and has a plurality of positions for carrying reagent containers. The reagent carrying component can rotate and drive the reagent container it carries to rotate, and is used to rotate the reagent container to a specific position, such as a position where the reagent is sucked by the reagent dispensing mechanism. The number of reagent carrying components may be one or more. The reagent dispensing mechanism is used to absorb the reagent and discharge it into a reaction cup to be added with the reagent. In one embodiment, the reagent dispensing mechanism may include a reagent needle, which performs two-dimensional or three-dimensional motion in space through a two-dimensional or three-dimensional driving mechanism, so that the reagent needle can move to absorb the reagent carried by the reagent carrying component, and move to the reaction cup to be added with the reagent, and discharge the reagent to the reaction cup.

[0040] Among them, in some embodiments, the measuring component may include a reaction component and a light measuring component. The reaction component has at least one placement position, and the placement position is used to place a reaction cup and incubate the reaction liquid in the reaction cup. For example, the reaction component can be a reaction disk, which is arranged in a disc-shaped structure and has one or more placement positions for placing reaction cups. The reaction disk can rotate and drive the reaction cups in its placement positions to rotate, and is used to schedule reaction cups in the reaction disk and incubate the reaction liquid in the reaction cups. The light measuring component is used to perform light measurement on the reaction liquid after incubation to obtain the serum index of the blood sample in the sample container, the test results of biochemical items, or the test of immune items. The light measuring component can be separately arranged outside the reaction component.

[0041] In one embodiment, when the serum index of the blood sample in the sample container is normal, the first biochemical analysis device 102 uses the remaining blood sample in the sample container to detect biochemical items.

[0042] Here, when the serum index of the blood sample in the sample container is normal, if the first biochemical analysis device 102 supports the detection of biochemical items, the sample component of the first biochemical analysis device 102 continues to draw blood samples from the remaining blood samples in the sample container, and provides the drawn blood samples to the determination component of the first biochemical analysis device 102; the reagent component of the first biochemical analysis device 102 draws the reagent and provides it to the determination component of the first biochemical analysis device 102; the determination component of the first biochemical analysis device 102 mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction liquid, incubates the reaction liquid, and performs biochemical item detection on the reaction liquid after the incubation, to obtain the detection results of the biochemical items of the blood sample in the sample container. Among them, the normal serum index can be understood as normal HIL, that is, the hemolysis index, icterus index and lipid turbidity index are all normal.

[0043] In this embodiment, when the serum index of the blood sample in the sample container is normal, the first biochemical analysis device 102 uses the remaining blood sample in the sample container to detect the biochemical items, which can improve the reliability of the detection results of the biochemical items.

[0044] like Figure 2 As shown, in one embodiment, the sample analysis system may further include a second biochemical analysis device 107; the electronic device 101 is further used to dispatch the sample container to the second biochemical analysis device 107 for biochemical item detection when the serum index of the blood sample in the sample container is normal.

[0045] Here, when the serum index of the blood sample in the sample container is normal, if the first biochemical analysis device 102 only supports the detection of some biochemical items, or does not support the detection of biochemical items, then the electronic device 101 dispatches the sample container to the second biochemical analysis device 107 through the transmission track 106, and the remaining blood sample in the sample container of the second biochemical analysis device 107 is used to detect the biochemical items. The second biochemical analysis device 107 includes a sample component, a reagent component, and a measurement component. The biochemical items detected by the second biochemical analysis device 107 may be different from the biochemical items detected by the first biochemical analysis device 102.

[0046] Specifically, when the serum index of the blood sample in the sample container is normal, the electronic device 101 dispatches the sample container to the second biochemical analysis device 107 through the transmission track 106. After the electronic device 101 dispatches the sample container to the second biochemical analysis device 107, the sample component of the second biochemical analysis device 107 absorbs the blood sample from the remaining blood sample in the sample container, and provides the absorbed blood sample to the determination component of the second biochemical analysis device 107; the reagent component of the second biochemical analysis device 107 absorbs the reagent and provides it to the determination component of the second biochemical analysis device 107; the determination component of the second biochemical analysis device 107 mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction liquid, incubates the reaction liquid, and performs biochemical project detection on the incubated reaction liquid to obtain the detection result of the biochemical project of the blood sample in the sample container. In this way, the credibility of the detection result of the biochemical project can be improved.

[0047] like Figure 3 As shown, in one embodiment, the sample analysis system also includes an immunoassay device 108; the electronic device 101 is also used to dispatch the sample container to the immunoassay device 108 for immunoassay testing when the blood sample in the sample container completes the biochemical test.

[0048] Here, when the serum index of the blood sample in the sample container is normal and the blood sample in the sample container completes the detection of biochemical items, the electronic device 101 dispatches the sample container to the immunoassay device 108 through the transmission track 106; the immunoassay device 108 includes a sample component, a reagent component and a measurement component.

[0049] After the electronic device 101 dispatches the sample container to the immunoanalyzer 108, the sample component of the immunoanalyzer 108 draws the blood sample from the remaining blood sample in the sample container and provides the drawn blood sample to the measuring component of the immunoanalyzer 108; the reagent component of the immunoanalyzer 108 draws the reagent and provides it to the measuring component of the immunoanalyzer 108; the measuring component of the immunoanalyzer 108 mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction liquid, incubates the reaction liquid, and performs an immune test on the incubated reaction liquid to obtain the test result of the immune test of the blood sample in the sample container. This can improve the credibility of the test result of the immune test.

[0050] In one embodiment, the electronic device 101 is used to call an AI (Artificial Intelligence) model to process the at least two images to obtain at least one first image, and to process the at least one first image to obtain a sample analysis result of the sample container; wherein the first image represents an image of the at least two images that meets the set sample analysis conditions.

[0051] Here, the electronic device 101 processes all images of the same sample container by calling the AI ​​model to obtain at least one first image, and the first image represents the image that meets the set sample analysis conditions among all images of the same sample container, that is, the electronic device 101 screens the images that meet the set sample analysis conditions through the AI ​​model, and processes at least one screened first image to obtain the sample analysis result of the sample container, thereby obtaining the sample classification corresponding to the blood sample in the sample container. Among them, the AI ​​model is trained based on the image samples of the sample container; the AI ​​model is used to process the input image to obtain the image for sample analysis, and process the image for sample analysis to obtain the sample analysis result of the sample container. The AI ​​model takes the image of the sample container as input and the sample analysis result of the sample container as output.

[0052] In this embodiment, the electronic device 101 calls the AI ​​model to screen out at least one first image from at least two images of the same sample container, and then processes the first image to obtain the sample analysis result of the sample container, rather than directly performing sample analysis on all images of the same sample container to determine the sample analysis result. This reduces the data processing amount of the sample analysis, can improve the sample analysis efficiency, and the first image meets the set sample analysis conditions, which can improve the accuracy and confidence of the sample analysis result.

[0053] In one embodiment, the electronic device 101 is used to call the first AI model to process the at least two images to obtain at least one first image, and call the second AI model to process the at least one first image to obtain the sample analysis result of the sample container.

[0054] Here, the electronic device 101 processes all images of the same sample container by calling the first AI model to obtain at least one first image, and the first image represents the image that meets the set sample analysis conditions among all images of the same sample container. Here, the images that meet the set sample analysis conditions are screened by the first AI model, and then the second AI model is called to process the screened at least one first image to obtain the sample analysis result of the sample container, thereby obtaining the sample classification corresponding to the blood sample in the sample container. Among them, the at least one first image can be an image directly output by the first AI model, or it can be based on the at least one second image output by the first AI model, and the electronic device 101 verifies each second image according to the set sample analysis conditions, and selects at least one first image from the second images output by the first AI model according to the verification results.

[0055] Here, the first AI model is trained based on the image sample of the sample container; the first AI model is used to process the input image to obtain an image for sample analysis, that is, an image that meets the set sample analysis conditions. Specifically, the first AI model extracts at least one type of image features of the input image, so as to determine the image for sample analysis in the input image according to the extracted image features. At least one type of image features includes at least one of the following: edge features, grayscale distribution features, color features, texture features, shape features, and spatial relationship features. Edge features are used to characterize the existence of step changes (slope-type edges) or roof-like changes (roof-type edges) in the pixel grayscale, pixel brightness, or pixel color of the image; grayscale distribution features characterize the distribution of grayscale values ​​of the image. Both color features and texture features are global features that describe the surface properties of the blood sample corresponding to the image or image area. Shape features include contour features, which mainly describe the contour or boundary of the label and / or sample container. Spatial relationship features refer to the spatial position or relative direction relationship between multiple targets segmented from the image. These relationships can be divided into connection relationships or adjacency relationships, overlapping relationships or overlapping relationships, inclusion relationships or independent relationships, etc.

[0056] The set sample analysis conditions can be understood as the prerequisites that need to be met when the blood sample in the sample container can be analyzed. The set sample analysis conditions can be set according to actual conditions.

[0057] In actual application, the set sample analysis conditions may include at least one of the following:

[0058] The images contain blood samples;

[0059] There is a window or area on the surface of the sample container in the image that is not covered by the label;

[0060] The image of the blood sample in the sample container is clear;

[0061] The first parameter value of the image is greater than a set threshold value; wherein the first parameter value represents a ratio of the first area to the second area; the first area represents an area occupied by the blood sample in the image; and the second area represents an area occupied by the sample container in the image;

[0062] The brightness of the image meets the set brightness requirements;

[0063] The clarity of the image meets the set clarity requirements;

[0064] The contrast of the image meets the set contrast requirement.

[0065] That is, the first parameter value of the first image is greater than the set threshold value, and further, the first image can represent an image with the highest first parameter value among the at least two images. At least one type of image parameter of the first image meets the set parameter requirements; the at least one type of image parameter includes at least one of the following:

[0066] brightness;

[0067] Clarity;

[0068] Contrast.

[0069] Figure 4 An example of rotating photography is shown. The first image described above may include Figure 4 Figures (c) and (d) in the figure can also include only Figure 4 Figure (d) in the figure. Figure 4 In the figure (d), the window of the sample container not covered by the label is the largest, and the area occupied by the blood sample in the image is also the largest. Therefore, under the condition that the image parameters (such as brightness, clarity, contrast, etc.) of all images taken by the image acquisition device 102 are the same, the electronic device 101 adopts Figure 4 It is easier to obtain accurate sample analysis results by performing sample analysis according to Figure (d) in the figure.

[0070] The second AI model is trained based on the image sample of the sample container, and the image sample includes the image of the blood sample; the second AI model is used to process the input image to obtain the corresponding sample analysis result. Specifically, the second AI model at least recognizes the feature information of the image of the blood sample contained in the input image, such as the color feature and / or texture feature of the blood sample, and determines the sample analysis result corresponding to the input image based on the feature information of the image of the blood sample; the second AI model can also recognize the area on the surface of the sample container in the input image that is not obscured by the label, and recognize the image of the blood sample in the area on the surface of the sample container that is not obscured by the label.

[0071] It should be noted that in the embodiment of the present application, the structure of the first AI model and the structure of the second AI model may be different or the same, and the structure of the first AI model and the structure of the second AI model are not limited here. For example, the first AI model and the second AI model are both neural network models, and the first neural network and the second neural network may be composed of convolutional neural networks (CNN). For example, the second neural network model may include a cascaded convolution layer, a pooling layer, a fully connected layer and a softmax layer; the convolution layer is used to extract the feature information of the input image, and the feature information can be represented by a vector, and the feature information at least includes the color features of the blood sample contained in the input image; the pooling layer is used to downsample the feature information extracted by the convolution layer (downsampling is also called downsampling) to obtain a downsampling result to select or extract feature information; the fully connected layer is used to process the downsampling result input by the pooling layer to obtain each sample classification of the blood sample; the softmax layer is used to output the probability of each sample classification of the blood sample.

[0072] Based on the above embodiments, the electronic device 101 first selects at least one first image from at least two images of the same sample container through the first AI model, and then processes the first image through the second AI model to obtain the sample analysis result of the sample container, instead of directly performing sample analysis on all images of the same sample container to determine the sample analysis result. This reduces the data processing amount of the sample analysis, can improve the sample analysis efficiency, and the first image meets the set sample analysis conditions, which can improve the accuracy and confidence of the sample analysis result.

[0073] In one embodiment, the electronic device 101 is further configured to:

[0074] When the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample, the at least one first image is output and displayed, and / or an alarm signal is issued.

[0075] Here, when the sample analysis results characterize an abnormal blood sample, for example, the blood sample is at least one of a hemolytic sample, a icteric sample, and a lipemia sample, the electronic device 101 outputs a first image of the corresponding sample container, and / or issues an alarm signal so that relevant personnel can review the sample analysis results, handle the abnormal blood sample, etc. based on the first image and / or the alarm signal. For example, the relevant personnel transfer the corresponding sample container to the abnormal sample area for further processing.

[0076] In one embodiment, the sample analysis system further includes:

[0077] A light source is used to provide a shooting light source for the camera.

[0078] Here, the light source can improve the brightness of the shooting environment, thereby improving the brightness of the image captured by the camera 103 to obtain a clear image.

[0079] like Figure 5 As shown, in one embodiment, the sample analysis system further includes: a scheduling device 109 coupled to the electronic device 101;

[0080] The electronic device 101 is further used to: send a first instruction to the scheduling device 109 when the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample; the first instruction is used to instruct to transfer the sample container to an abnormal sample area;

[0081] The scheduling device 109 is used to receive the first instruction and transfer the sample container to the abnormal sample area through the transmission track 106.

[0082] Here, when the sample analysis result of the sample container is at least one of a hemolytic sample, a jaundice sample, and a lipemia sample, it indicates that the blood sample in the sample container is abnormal. At this time, the electronic device 101 can send a first instruction to the scheduling device 109, or directly display the first instruction, so that the relevant personnel can transfer the corresponding sample container to the abnormal sample area for further processing. The first instruction can carry relevant information of the label on the sample container, so that the scheduling device 109 or the relevant personnel can accurately take out the corresponding sample container according to the information carried by the first instruction.

[0083] When receiving the first instruction, the scheduling device 109 transfers the sample container with abnormal blood sample from the set area to the abnormal sample area through the transmission track 106. The set area can be an area for storing sample containers after photographing. The scheduling device 109 is used to schedule the sample container through the transmission track 106. The scheduling device can also be called a scheduling component or a scheduling mechanism.

[0084] It should be noted that the various components in the sample analysis system (electronic device 101, first biochemical analysis device 102, camera 103, sample holder 104, rotating device 105, second biochemical analysis device 107, immunoassay device 108 and scheduling device 109) are coupled together through a bus system. It can be understood that the bus system is used to achieve connection and communication between these components. In addition to the data bus, the bus system also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, various buses are referred to as bus systems.

[0085] Based on the above embodiments, it is not necessary to manually judge whether the quality of the blood sample is abnormal by naked eyes, which can improve the efficiency of analyzing the quality of the sample. In addition, the electronic device in the sample analysis system selects at least one first image for sample analysis from at least two images of the same sample container through the first neural network model, and then processes the at least one first image through the second neural network model to obtain the sample analysis result; instead of directly determining the sample analysis result based on all images of the same sample container, the data processing amount of the sample analysis is reduced, and the sample analysis efficiency can be further improved. Since the first image is an image used for sample analysis, the first image meets the image requirements of the sample analysis, which can improve the accuracy and confidence of the sample analysis result.

[0086] Based on the relevant description of the above embodiments, correspondingly, the embodiment of the present application also provides a sample analysis method, which is applied to Figures 1 to 3 , Figure 5 The electronic device 101 in the sample analysis system. Figure 6 , the method comprising:

[0087] Step 601: Acquire at least two images of a sample container.

[0088] Here, at least two images are taken by the camera 103 of the same sample container when the rotating device 105 drives the sample container to rotate around the vertical central axis. The at least two images taken by the camera 103 of the same sample container have different shooting perspectives or different shooting angles.

[0089] Step 602: Process the at least two images to obtain a sample analysis result of the sample container.

[0090] The sample analysis result represents a sample classification corresponding to the blood sample in the sample container; the sample classification includes a normal sample, or at least one of a hemolytic sample, a icteric sample and a lipemia sample.

[0091] Here, the implementation process of step 602 please refer to the relevant description above, which will not be repeated here.

[0092] Step 603: When the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample, the sample container is dispatched to a biochemical analysis device for serum index detection and / or biochemical item detection; the detection of biochemical items is performed when the serum index of the blood sample in the sample container is normal.

[0093] Here, the implementation process of step 603 please refer to the relevant description above, which will not be repeated here.

[0094] In order to reduce the amount of data processing for sample analysis, improve sample analysis efficiency, and improve the accuracy and confidence of sample analysis results, in one embodiment, the processing of the at least two images to obtain the sample analysis results of the sample container includes:

[0095] Calling the AI ​​model to process the at least two images to obtain at least one first image, and processing the at least one first image to obtain a sample analysis result of the sample container; wherein the first image represents an image of the at least two images that meets the set sample analysis conditions.

[0096] Here, the AI ​​model is called to process at least two images to obtain the sample analysis results of the sample container. For the specific implementation process, please refer to the relevant description above, which will not be repeated here.

[0097] In one embodiment, the first parameter value of the first image is greater than a set threshold; wherein,

[0098] The first parameter value represents a ratio of a first area to a second area; the first area represents an area occupied by a blood sample in an image; and the second area represents an area occupied by a sample container in an image.

[0099] Here, considering that if the value of the first parameter of the first image is too small, or the first image does not contain an image of sample blood, the sample analysis result obtained by the electronic device based on the first image may be inaccurate or even impossible to obtain the sample analysis result, therefore, in order to improve the accuracy of the sample analysis result, the first parameter value of the first image is greater than the set threshold.

[0100] The first area may also be understood as the area of ​​a window or region on the surface of the sample container in the acquired image that is not blocked by the label.

[0101] In one embodiment, the first image represents an image having the highest first parameter value among the at least two images.

[0102] For example, the first image can be Figure 4 Middle figure (d).

[0103] Considering that the image quality of the sample container may be poor, for example, it may be blurry and the blood sample cannot be distinguished in the image, therefore, in order to ensure that the image of the blood sample contained in the first image is clear and visible, the first image that meets the set image quality parameter requirements can be screened out by setting image parameters to ensure the image quality of the first image, thereby improving the accuracy of the sample analysis result. Based on this, in one embodiment, at least one type of image parameter of the first image meets the set parameter requirements; the at least one type of image parameter includes at least one of the following:

[0104] brightness;

[0105] Clarity;

[0106] Contrast.

[0107] Here, the brightness of the first image may meet a set brightness requirement, and / or the clarity of the first image may meet a set clarity requirement, and / or the contrast of the first image may meet a set contrast requirement.

[0108] In one embodiment, the calling of the AI ​​model to process the at least two images to obtain at least one first image, and the processing of the at least one first image to obtain the sample analysis result of the sample container include:

[0109] The first AI model is called to process the at least two images to obtain at least one first image, and the second AI model is called to process the at least one first image to obtain a sample analysis result of the sample container.

[0110] In order to avoid inaccurate recognition by the first AI model, or the first AI model only selects an optimal image but this optimal image may not meet the set sample analysis conditions, thereby affecting the sample analysis results, it is necessary to verify the image output by the first AI model so as to perform sample analysis based on the verified image. In one embodiment, calling the first AI model to process the at least two images to obtain at least one first image includes:

[0111] Calling the first AI model to process the at least two images to obtain at least one second image output by the first AI model;

[0112] Each of the at least one second image is verified according to the set sample analysis condition, and the at least one first image is selected from the at least one second image according to the verification result.

[0113] Here, in the case of obtaining at least two images of the same sample container, the first AI model is called to process the at least two images to obtain at least one second image output by the first AI model, and each second image is verified to determine whether it meets the set sample analysis conditions to obtain the verification result of the second image; in the case where the verification result indicates that the corresponding second image meets the set sample analysis conditions, the corresponding second image is determined as the first image; in the case where the verification result indicates that the corresponding second image does not meet the set sample analysis conditions, the corresponding second image is discarded. In this way, it can be ensured that the first image input into the second AI model meets the set sample analysis conditions, thereby reducing the impact of the first image on the sample analysis results. On the other hand, discarding the second image that does not meet the set sample analysis conditions can also reduce the data processing amount of the electronic device, save data processing resources, and reduce the total time consumed by sample analysis, thereby improving sample analysis efficiency.

[0114] In order to facilitate relevant personnel to review sample analysis results, handle abnormal blood samples, etc., in one embodiment, the method further includes:

[0115] When the sample analysis result is at least one of a hemolytic sample, an icteric sample, and a lipemia sample, at least one of the following is performed:

[0116] Outputting and displaying the at least one first image;

[0117] Send out an alarm signal;

[0118] A first instruction is issued; the first instruction is used to instruct to transfer the sample container to an abnormal sample area.

[0119] Here, when the sample analysis result is at least one of a hemolytic sample, a jaundice sample, and a lipemia sample, any of the above-mentioned methods can be used to remind or indicate that the blood sample in the sample container is abnormal.

[0120] The relevant personnel may review the sample analysis results of the blood samples in the corresponding sample containers by viewing the first image, and may also transfer the sample containers with abnormal blood samples to the abnormal sample area according to the alarm signal and / or the first instruction.

[0121] The present application also provides an electronic device, such as Figure 7 As shown, the electronic device 700 includes:

[0122] Communication interface 701, capable of exchanging information with other nodes;

[0123] The processor 702 is connected to the communication interface 701 to implement information exchange with other nodes, and is used to execute the method provided by one or more technical solutions of the electronic device side when running the computer program. The computer program is stored in the memory 703.

[0124] Specifically, the processor 702 is used to acquire at least two images of the sample container; process the at least two images to obtain the sample analysis result of the sample container; wherein the at least two images represent images captured during the rotation of the sample container around the vertical center axis; the sample analysis result represents the sample classification corresponding to the blood sample in the sample container; the sample classification includes normal samples, or includes at least one of hemolytic samples, icteric samples and lipemia samples; when the sample analysis result is at least one of hemolytic samples, icteric samples and lipemia samples, the sample container is dispatched to a biochemical analysis device for serum index detection and / or biochemical item detection; the detection of biochemical items is performed when the serum index of the blood sample in the sample container is normal.

[0125] In one embodiment, the processor 702 is specifically used to call the AI ​​model to process the at least two images to obtain at least one first image, and to process the at least one first image to obtain the sample analysis result of the sample container; wherein the first image represents the image of the at least two images that meets the set sample analysis conditions.

[0126] In one embodiment, the first parameter value of the first image is greater than a set threshold; wherein,

[0127] The first parameter value represents a ratio of a first area to a second area; the first area represents an area occupied by a blood sample in an image; and the second area represents an area occupied by a sample container in an image.

[0128] In one embodiment, the first image represents an image having the highest first parameter value among the at least two images.

[0129] In one embodiment, at least one type of image parameter of the first image meets a set parameter requirement; the at least one type of image parameter includes at least one of the following:

[0130] brightness;

[0131] Clarity;

[0132] Contrast.

[0133] In one embodiment, the processor 702 is specifically used to call the first AI model to process the at least two images to obtain at least one first image, and call the second AI model to process the at least one first image to obtain the sample analysis result of the sample container.

[0134] In one embodiment, the processor 702 is specifically used to call the first AI model to process the at least two images to obtain at least one second image output by the first AI model; verify each of the at least one second image according to the set sample analysis conditions, and select the at least one first image from the at least one second image according to the verification result.

[0135] In one embodiment, the processor 702 is further configured to, when the sample analysis result is at least one of a hemolytic sample, a icteric sample, and a lipemia sample, perform at least one of the following:

[0136] Outputting and displaying the at least one first image;

[0137] Send out an alarm signal;

[0138] A first instruction is issued; the first instruction is used to instruct to transfer the sample container to an abnormal sample area.

[0139] It should be noted that the specific processing process of the processor 702 and the communication interface 701 can be understood by referring to the above method.

[0140] Of course, in actual application, the various components in the electronic device 700 are coupled together through the bus system 704. It can be understood that the bus system 704 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 704 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, Figure 7 Various buses are labeled as bus system 704 .

[0141] The memory 703 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device 700. Examples of such data include: any computer program used to operate on the electronic device 700.

[0142] The method disclosed in the above embodiment of the present application can be applied to the processor 702, or implemented by the processor 702. The processor 702 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor 702 or an instruction in the form of software. The above-mentioned processor 702 may be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 702 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. A general-purpose processor may be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a storage medium, which is located in the memory 703, and the processor 702 reads the information in the memory 703 and completes the steps of the above method in combination with its hardware.

[0143] In an exemplary embodiment, the electronic device 700 can be implemented by one or more application specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field programmable gate arrays (FPGAs), general-purpose processors, controllers, microcontrollers (MCUs), microprocessors, or other electronic components to execute the aforementioned method.

[0144] It can be understood that the memory (memory 703) of the embodiment of the present application can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a ferromagnetic random access memory, a flash memory, a magnetic surface memory, an optical disc, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAMbus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0145] In an exemplary embodiment, the present application embodiment further provides a storage medium, namely a computer storage medium, specifically a computer-readable storage medium, for example, including a memory 703 storing a computer program, and the computer program can be executed by a processor 702 of an electronic device 700 to complete the steps of the aforementioned first electronic device side method. The computer-readable storage medium can be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, Flash Memory, magnetic surface storage, optical disk, or CD-ROM.

[0146] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0147] The term "and / or" herein is only a description of the association relationship of the associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent including any one or more elements selected from the set consisting of A, B, and C.

[0148] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0149] The above description is only a preferred embodiment of the present application and is not intended to limit the protection scope of the present application.

Claims

1. A sample analysis system, characterized in that: The invention comprises an electronic device, and a first biochemical analysis device coupled to the electronic device, a camera, a sample holder, a rotating device and a transport track for transporting the sample holder carrying a sample container; wherein the biochemical analysis device comprises a sample component, a reagent component and a measurement component; The sample seat is used to carry the sample container so that the sample container remains in a vertical state; The rotating device is used to drive the sample holder to rotate, so as to drive the sample container carried by the sample holder to rotate around the vertical central axis; The camera is used to capture at least two images of the sample container during its rotation process; The electronic device is used to process the at least two images to obtain a sample analysis result of the sample container; the sample analysis result represents a sample classification corresponding to the blood sample in the sample container; the sample classification includes a normal sample, or includes at least one of a hemolytic sample, a jaundice sample, and a lipemia sample; and is used to dispatch the sample container to the first biochemical analysis device for processing when the sample analysis result is at least one of a hemolytic sample, a jaundice sample, and a lipemia sample; After the electronic device dispatches the sample container to the first biochemical analysis device, the sample component of the first biochemical analysis device draws the blood sample from the sample container and provides the drawn blood sample to the measuring component; the reagent component of the first biochemical analysis device draws the reagent and provides it to the measuring component; the measuring component of the first biochemical analysis device mixes the blood sample provided by the sample component and the reagent provided by the reagent component into a reaction liquid, incubates the reaction liquid, and performs a serum index test on the incubated reaction liquid to obtain the serum index of the blood sample in the sample container.

2. The sample analysis system according to claim 1, characterized in that: When the serum index of the blood sample in the sample container is normal, the first biochemical analysis device uses the remaining blood sample in the sample container to detect biochemical items.

3. The sample analysis system according to claim 1, characterized in that: The electronic device is also used for dispatching the sample container to a second biochemical analysis device for biochemical item detection when the serum index of the blood sample in the sample container is normal.

4. The sample analysis system according to claim 2 or 3, characterized in that: The sample analysis system also includes an immunoanalysis device; the electronic device is further used to dispatch the sample container to the immunoanalysis device for immunological testing when the blood sample in the sample container has completed the testing of biochemical items.

5. The sample analysis system according to claim 1, characterized in that: The electronic device is used to call the AI ​​model to process the at least two images to obtain at least one first image, and to process the at least one first image to obtain the sample analysis result of the sample container; wherein, The first image represents an image among the at least two images that meets the set sample analysis conditions.

6. The sample analysis system according to claim 5, characterized in that: The electronic device is used to call the first AI model to process the at least two images to obtain at least one first image, and call the second AI model to process the at least one first image to obtain the sample analysis result of the sample container.

7. The sample analysis system according to claim 5 or 6, characterized in that: The first parameter value of the first image is greater than a set threshold; wherein, The first parameter value represents a ratio of a first area to a second area; the first area represents an area occupied by a blood sample in an image; and the second area represents an area occupied by a sample container in an image.

8. The sample analysis system according to claim 7, characterized in that: The first image represents an image having the highest first parameter value among the at least two images.

9. The sample analysis system according to claim 7, characterized in that: At least one type of image parameter of the first image meets the set parameter requirements; the at least one type of image parameter includes at least one of the following: brightness; Clarity; Contrast.

10. The sample analysis system according to claim 1, characterized in that: The sample analysis system further comprises: A light source is used to provide a shooting light source for the camera.

11. The sample analysis system according to claim 1, characterized in that: The electronic device is also used for: When the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample, the at least one first image is output and displayed, and / or an alarm signal is issued.

12. The sample analysis system according to claim 1, characterized in that: The sample analysis system further includes: a scheduling device coupled to the electronic device; The electronic device is further used to send a first instruction to the scheduling device when the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample; the first instruction is used to instruct the sample container to be transferred to an abnormal sample area; In response to receiving the first instruction, the scheduling device transfers the sample container to the abnormal sample area via the track.

13. A sample analysis method, characterized in that: An electronic device used in a sample analysis system, the sample analysis system further comprising a biochemical analysis device coupled to the electronic device, a camera, a sample holder, a rotating device for driving the sample holder to rotate, and a transport track for transporting the sample holder carrying a sample container, the camera being used to capture at least two images of the sample container when the rotating device drives the sample container to rotate around a vertical central axis; The sample analysis method comprises: acquiring at least two images of the sample container; Processing the at least two images to obtain a sample analysis result of the sample container; wherein the sample analysis result represents a sample classification corresponding to the blood sample in the sample container; the sample classification includes a normal sample, or includes at least one of a hemolytic sample, a icteric sample, and a lipemia sample; When the sample analysis result is at least one of a hemolytic sample, a icteric sample and a lipemia sample, the sample container is dispatched to a biochemical analysis device for serum index detection and / or biochemical item detection; the detection of biochemical items is performed when the serum index of the blood sample in the sample container is normal.

14. The method according to claim 13, characterized in that The processing of the at least two images to obtain the sample analysis result of the sample container includes: Calling the AI ​​model to process the at least two images to obtain at least one first image, and processing the at least one first image to obtain a sample analysis result of the sample container; wherein the first image represents an image of the at least two images that meets the set sample analysis conditions.

15. The method according to claim 14, characterized in that The first parameter value of the first image is greater than a set threshold; wherein, The first parameter value represents a ratio of a first area to a second area; the first area represents an area occupied by a blood sample in an image; and the second area represents an area occupied by a sample container in an image.

16. The method according to claim 15, characterized in that The first image represents an image having the highest first parameter value among the at least two images.

17. The method according to claim 15, characterized in that At least one type of image parameter of the first image meets the set parameter requirements; the at least one type of image parameter includes at least one of the following: brightness; Clarity; Contrast.

18. The method according to claim 14, characterized in that The calling of the AI ​​model to process the at least two images to obtain at least one first image, and the processing of the at least one first image to obtain the sample analysis result of the sample container include: The first AI model is called to process the at least two images to obtain at least one first image, and the second AI model is called to process the at least one first image to obtain a sample analysis result of the sample container.

19. The method according to claim 18, characterized in that The calling the first AI model to process the at least two images to obtain at least one first image includes: Calling the first AI model to process the at least two images to obtain at least one second image output by the first AI model; Each of the at least one second image is verified according to the set sample analysis condition, and the at least one first image is selected from the at least one second image according to the verification result.

20. The method according to any one of claims 13 to 19, characterized in that The method further comprises: When the sample analysis result is at least one of a hemolytic sample, an icteric sample, and a lipemia sample, at least one of the following is performed: Outputting and displaying the at least one first image; Send out an alarm signal; A first instruction is issued; the first instruction is used to instruct to transfer the sample container to an abnormal sample area.

21. An electronic device, characterized in that: include: a processor and a memory for storing a computer program capable of being executed on the processor, Wherein, when the processor is used to run the computer program, it executes the steps of the method described in any one of claims 13 to 20.

22. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 13 to 20 are implemented.

Images