Gene Chip Microbead Detection Method, Device, Electronic Device and Readable Storage Medium

Abstract

The present application relates to a method, device, electronic device and readable storage medium for detecting microbeads on a gene chip, including: obtaining an image of a target microbead rectangular region, where the image of the target microbead rectangular region is formed by splicing a plurality of sub-images; processing the image of the target microbead rectangular region using a target detection model to obtain microbead-related parameters; constructing a target matrix based on the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result, where the target matrix stores the microbead-related parameters according to the arrangement of the microbeads in the target microbead rectangular region. The present application uses a target detection model trained by deep learning to identify the image of the target microbead rectangular region, obtain corresponding microbead-related parameters, and construct a target matrix in combination with the microbead-related parameters and the target microbead rectangular region, which can quickly and accurately complete microbead positioning and bright-dark recognition while outputting a clear and complete detection result.

Description

Technical Field

[0001] The present invention relates to the technical field of biochips, and particularly to a method, device, electronic device and readable storage medium for detecting gene chip microbeads. Background Art

[0002] Microbeads are distributed within a long rectangular area Rect (the length W of the long side is more than twice the length H of the short side) of the chip, and the distribution positions of the microbeads are distributed at the grid points of a rectangular grid or in a regular hexagonal honeycomb pattern.

[0003] The existing solution is to use a line-scan camera. A laser light source emits light within a specific wavelength range to excite the fluorescence of the microbeads. The line-scan camera captures images. The laser light source and the camera move synchronously along the long side of the rectangle, and a fluorescence signal in one frequency band is captured during one movement.

[0004] When performing microbead positioning on the captured images, there are usually two methods: 1. Using an iterative search algorithm based on the adjacent relationship to traverse the microbead positions; 2. The projection method.

[0005] When using a line-scan camera, the image is scanned line by line. The fluorescence excitation time is short, which requires a relatively high power of the laser light source, resulting in high costs and short service life. Due to the small diameter of the microbeads, the magnification of the lens is high and the depth of field is small. Since the area scanned by the line-scan camera is large, it is required that the straightness of the camera movement is highly perpendicular to the chip surface. Otherwise, the object distance changes greatly, exceeding the depth of field range, and some areas of the captured image are blurred. In addition, a high flatness requirement for the chip surface itself leads to high hardware costs and great difficulty in equipment debugging.

[0006] The iterative algorithm is time-consuming and prone to repeated calculations. The projection method requires the microbead distribution to be horizontal and vertical, that is, the microbead matrix must be rotated correctly, otherwise the positioning deviation of the projection method is large. Summary of the Invention

[0007] To solve the above technical problems, the embodiments of the present application provide a method, device, electronic device and readable storage medium for detecting gene chip microbeads that can accurately and quickly complete microbead positioning and bright-dark classification recognition. The specific solutions are as follows:

[0008] In a first aspect, the embodiments of the present application provide a method for detecting gene chip microbeads, including:

[0009] Obtaining an image of a target microbead rectangular area, where the image of the target microbead rectangular area is formed by splicing a plurality of sub-images, and the sub-images cover partial areas of the target microbead rectangular area;

[0010] Process the image of the target microbead rectangular region using a target detection model to obtain microbead-related parameters, where the target detection model is a model trained based on deep learning, and the microbead-related parameters include the microbead position, the microbead light and dark classification result, and the average gray value of the microbead region;

[0011] Construct a target matrix based on the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result, where the target matrix stores the microbead-related parameters according to the arrangement of the microbeads in the target microbead rectangular region.

[0012] According to a specific implementation manner of an embodiment of the present application, the obtaining of the image of the target microbead rectangular region includes:

[0013] Divide the target microbead rectangular region into multiple sub-regions to be photographed, where adjacent sub-regions to be photographed include a preset overlapping region, the target microbead rectangular region includes a first side and a second side, and the length of the first side is greater than the length of the second side;

[0014] Obtain the images of the sub-regions to be photographed to obtain multiple sub-images;

[0015] Perform a preset splicing process on the multiple sub-images to obtain the image of the target microbead rectangular region.

[0016] According to a specific implementation manner of an embodiment of the present application, the performing a preset splicing process on the multiple sub-images to obtain the image of the target microbead rectangular region includes:

[0017] For two adjacent sub-images, determine a first adjacent region of one sub-image as a template region, and determine a second adjacent region of the other sub-image as a region to be matched;

[0018] Search for a position in the region to be matched that matches the template region until a target matching position is obtained, where the target matching position is the position with the highest similarity between the region to be matched and the template region;

[0019] Move the other sub-image according to the target matching position and discard redundant partial images until the pixel points of the template region and the region to be matched are the same;

[0020] When any two adjacent sub-images are spliced, determine the spliced image as the image of the target microbead rectangular region.

[0021] According to a specific implementation manner of an embodiment of the present application, before processing the image of the target microbead rectangular region using the target detection model to obtain microbead-related parameters, the method further includes:

[0022] Obtain different gene chip images, where the gene chip images include microbeads;

[0023] Perform annotation of microbead-related parameters on the gene chip images;

[0024] According to the annotated gene chip images, use an object detection network or a segmentation network for model training to obtain the object detection model.

[0025] According to a specific implementation manner of an embodiment of the present application, the constructing a target matrix based on the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result includes:

[0026] Obtain a target affine matrix according to the position coordinates of the target microbead rectangular region, where the distribution state of the target affine matrix is a horizontal and vertical state;

[0027] Construct a virtual matrix according to the microbead distribution in the target microbead rectangular region, where the number of rows and columns of the virtual matrix corresponds to the number of microbeads in the row direction and the column direction in the microbead distribution;

[0028] Combine the target affine matrix and the virtual matrix, and map the microbead-related parameters to each element of the virtual matrix to obtain the microbead detection result, where one element corresponds to one microbead.

[0029] According to a specific implementation manner of an embodiment of the present application, the obtaining a target affine matrix according to the position coordinates of the target microbead rectangular region includes:

[0030] Extract four boundary lines of the target microbead rectangular region according to a preset iterative fitting algorithm;

[0031] Connect the four boundary lines to obtain an edge matrix;

[0032] Perform an affine transformation on the edge matrix to obtain the target affine matrix.

[0033] According to a specific implementation manner of an embodiment of the present application, the mapping the microbead-related parameters to each element of the virtual matrix to obtain the microbead detection result includes:

[0034] Initialize the virtual matrix and fill a preset content in the target element, where the target element is the element in the virtual matrix corresponding to the microbead position in the target affine matrix;

[0035] Traverse the unupdated elements in the virtual matrix, and map and fill the corresponding microbead-related parameters for each unupdated element, where the preset content is filled in the unupdated elements.

[0036] In a second aspect, an embodiment of the present application provides a gene chip bead detection device, including:

[0037] An acquisition module, configured to acquire an image of a target bead rectangular region, where the image of the target bead rectangular region is formed by stitching a plurality of sub-images, and the sub-images cover partial regions of the target bead rectangular region;

[0038] A detection module, configured to process the image of the target bead rectangular region by using a target detection model to obtain bead-related parameters, where the target detection model is a model trained based on deep learning, and the bead-related parameters include bead position, bead brightness and darkness classification result, and the average gray value of the bead region;

[0039] An output module, configured to construct a target matrix according to the bead-related parameters and the target bead rectangular region to obtain a bead detection result, where the target matrix stores the bead-related parameters according to the arrangement of the beads in the target bead rectangular region.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, which includes:

[0041] At least one processor; and,

[0042] A memory communicatively connected to the at least one processor; where

[0043] The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the gene chip bead detection method described in the first aspect.

[0044] In a fourth aspect, an embodiment of the present application further provides a non-transitory computer-readable storage medium, which stores computer instructions for causing the computer to execute the gene chip bead detection method described in the first aspect.

[0045] In summary, this embodiment provides a method, device, electronic device, and readable storage medium for detecting microbeads on a gene chip, including: obtaining an image of a target microbead rectangular region, where the image of the target microbead rectangular region is formed by stitching multiple sub-images; processing the image of the target microbead rectangular region using a target detection model to obtain microbead-related parameters; constructing a target matrix based on the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result, where the target matrix stores the microbead-related parameters according to the arrangement of the microbeads in the target microbead rectangular region. This application uses a target detection model trained through deep learning to recognize the image of the target microbead rectangular region, obtain the corresponding microbead-related parameters, and construct a target matrix in combination with the microbead-related parameters and the target microbead rectangular region, which can quickly and accurately complete microbead positioning and bright-dark recognition while outputting a clear and complete detection result. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] To more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for the embodiments. Obviously, the drawings in the following description are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a schematic flowchart of a method for detecting microbeads on a gene chip provided by an embodiment of the present application;

[0048] Figure 2 It is a schematic flowchart of the steps for obtaining an image of a target microbead rectangular region in an embodiment of the present application;

[0049] Figure 3 It is a schematic flowchart of the steps for performing a preset stitching process on multiple sub-images in an embodiment of the present application;

[0050] Figure 4 It is a schematic flowchart of the steps for training a target detection model in an embodiment of the present application;

[0051] Figure 5 It is a schematic flowchart of the steps for obtaining a microbead detection result in an embodiment of the present application;

[0052] Figure 6 It is a schematic flowchart of the steps for obtaining a target affine matrix in an embodiment of the present application;

[0053] Figure 7 It is a schematic flowchart of the steps for mapping microbead-related parameters in a virtual matrix in an embodiment of the present application;

[0054] Figure 8 It is a schematic diagram of a target microbead rectangular region provided by an embodiment of the present application;

[0055] Figure 9 Schematic diagram of multiple sub-images collected by the area array camera in the embodiment of the present application;

[0056] Figure 10 Application schematic diagram of preset stitching processing on multiple sub-images in the embodiment of the present application

[0057] Figure 11 Application schematic diagram of labeling microbeads in the microbead rectangular area in the embodiment of the present application;

[0058] Figure 12 Application schematic diagram of calculating the target affine matrix in the embodiment of the present application;

[0059] Figure 13 Device module schematic diagram of a gene chip microbead detection device provided in the embodiment of the present application. Detailed implementation manners

[0060] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0061] The following uses specific specific examples to illustrate the implementation manners of the present disclosure. Those skilled in the art can easily understand other advantages and effects of the present disclosure from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present disclosure, rather than all the embodiments. The present disclosure can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present disclosure. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present disclosure without creative efforts fall within the protection scope of the present disclosure.

[0062] It should be noted that the following describes various aspects of the embodiments within the scope of the appended claims. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is illustrative only. Based on the present disclosure, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number of aspects described herein can be used to implement the device and / or practice the method. In addition, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0063] It should also be noted that the illustrations provided in the following embodiments only schematically illustrate the basic concept of the present disclosure. The diagrams only show the components related to the present disclosure, rather than being drawn according to the number, shape, and size of the components in actual implementation. The types, quantities, and proportions of the components in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0064] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0065] In the related art, the microbeads on the gene chip generally refer to the small spherical bodies used in gene chip technology and coupled with specific sequence DNA fragments on the surface. These microbeads play a key role in the gene chip. As the carrier of the probe, they can hybridize with the DNA or RNA sample to be detected, thereby realizing the detection of information such as gene expression and gene mutation.

[0066] In the actual application process, the microbeads are arranged in a long strip form on the gene chip, which can make full use of the chip area, improve the detection throughput, and facilitate the addition of the sample and the operation of the hybridization reaction. The long strip distribution of the microbeads makes the signal detection more concentrated. In the related art, devices such as laser scanners are often used to detect the positioning and bright-dark classification of the microbeads on the gene chip.

[0067] In the related art, the steps for detecting the position of the microbeads on the gene chip include: extracting the DNA or RNA sample to be detected and performing a labeling process. Then, hybridize the labeled sample with the microbeads on the gene chip. Control the laser light source of the line scan camera to emit light within a specific wavelength range to excite the fluorescence of the microspheres, and then collect images through the line scan camera. The laser light source and the camera move synchronously along the long side of the long rectangular shape of the gene chip, and a band of fluorescence signals is collected during one movement.

[0068] However, when using a line scan camera, the image is scanned line by line, the fluorescence excitation time is short, which requires a relatively large power of the laser light source, high cost, and short service life. Also, due to the small diameter of the microbeads, the high magnification of the lens, and the small depth of field, and the large scanning area of the line scan camera, it is required that the straightness of the camera movement with respect to the chip surface is high. Otherwise, there will be a large change in the object distance, exceeding the depth of field range, and regional blurring will occur in the collected image. In addition, a high flatness requirement for the chip surface itself makes the hardware cost high and the equipment debugging difficult.

[0069] To solve the above problems, an embodiment of the present application provides a method for detecting microbeads on a gene chip. By replacing the line scanner with an area scan camera, the method acquires images of microbeads distributed in a strip on the gene chip through the area scan camera, and quickly completes microbead positioning and bright-dark classification through a deep learning neural network model, which can improve the detection efficiency of microbeads on the gene chip while reducing equipment costs.

[0070] Referring to Figure 1 , an embodiment of the present application provides a method for detecting microbeads on a gene chip, including the following steps:

[0071] S101, obtaining an image of a target microbead rectangular area, where the image of the target microbead rectangular area is formed by stitching multiple sub-images, and the sub-images cover partial areas of the target microbead rectangular area.

[0072] In this embodiment, the target microbead rectangular area refers to a rectangular area on the gene chip that includes microbeads arranged in a strip form. As Figure 8 shown, the microbeads are distributed within the chip rectangular area, and the length of the long side W of this chip rectangular area can be 2 times or more than 2 times the length of the short side H. It should be noted that the length of the long side W is greater than the length of the short side H, and the specific length difference can be determined according to the microbead distribution in the actual application scenario.

[0073] In the actual application process, the distribution positions of the microbeads can be distributed at the grid points of a rectangular grid, for example Figure 8 as shown in part (B). The distribution positions of the microbeads can also be distributed in a regular hexagonal honeycomb pattern, for example Figure 8 as shown in part (A). The length of the long side of the rectangular area is , and the length of the short side is .

[0074] In this embodiment, based on the area scan camera, multiple sub-images within the target microbead rectangular area are acquired, and then the target microbead rectangular area image is obtained by stitching the multiple sub-images. In the actual application process, the target microbead rectangular area is divided into multiple sub-regions according to a grid. By taking pictures of each sub-region one by one with the area scan camera and performing focusing and shooting in sequence, clearer images can be obtained, providing a guarantee for subsequent microbead position detection and bright-dark classification detection.

[0075] It should be noted that both the grid division method of the sub-regions and the specific shooting method of the area scan camera can be custom-set according to the needs of the actual application scenario. For example, the target microbead rectangular area can be divided into a multi-grid area with two rows and multiple columns. Each grid covers partial areas of the target microbead rectangular area, and there is also an overlapping area between adjacent grids. The area scan camera can obtain images of all sub-regions at once, or can obtain images of each sub-region in sequence according to the arrangement order of the sub-regions.

[0076] S102, using the target detection model to process the target microbead rectangular area image to obtain microbead related parameters, wherein the target detection model is a model obtained based on deep learning training, and the microbead related parameters include the microbead position, the microbead light and dark classification results, and the grayscale mean of the microbead area.

[0077] In this embodiment, the target detection model is used to make predictions based on the input microbead rectangular area image, and output the microbead position (center point coordinates) in the image, the microbead brightness and darkness classification results, and the grayscale mean of the microbead area.

[0078] Deep learning (DL) is a branch of machine learning (ML). DL builds and trains deep neural network models to learn and extract features from data to achieve automated processing and decision-making of complex tasks. In this embodiment, deep learning training can be performed based on a large number of gene chip images containing microbeads to obtain a target detection model.

[0079] In a specific embodiment, the training target detection model can be trained based on the object detection (Object Detection) or segmentation network method. The steps of training the target detection model include: 1. Collecting sample data, the sample data includes a gene chip image with microbeads, and adding annotation information to the gene chip image with microbeads, and the annotation information includes microbead related parameters. 2. Selecting a suitable pre-trained model according to the needs of the actual application scenario, the pre-trained model includes YOLOv5, Faster R-CNN, Mask R-CNN and other models, among which YOLOv5 and Faster R-CNN are pre-trained models corresponding to target detection, and Mask R-CNN is a pre-trained model corresponding to the segmentation network. 3. Configure the environment for model training and install the deep learning framework required for the actual application scenario. 4. Load and pre-process the data. 5. Define training parameters such as loss function, optimizer, hyperparameters, and perform model training based on the training parameters and pre-trained model. 6. Perform performance verification on the trained target detection model to verify the effectiveness of the target detection model. Based on the above steps, a target detection model can be trained that can quickly detect and accurately output microbead-related parameter detection results.

[0080] This embodiment completes the detection of microbead related parameters through the target detection model, has accurate positioning and can simultaneously determine the light and dark classification results, has high parallel efficiency and fast speed, and does not need to consider the requirement of the projection method that the rectangular area image of the microbead must be straightened, which can greatly improve the efficiency of positioning detection and light and dark classification detection.

[0081] S103. Construct a target matrix based on the microbead-related parameters and the target microbead rectangular area to obtain the microbead detection result. Among them, the target matrix stores the microbead-related parameters according to the arrangement of the microbeads in the target microbead rectangular area.

[0082] In this embodiment, after the detection of the microbead-related parameters is completed, a target matrix that can intuitively understand the microbead detection result will be further constructed according to the microbead-related parameters and the arrangement of the microbeads in the target microbead rectangular area. Among them, the arrangement of the microbeads in the target microbead rectangular area can be referred to Figure 8 As shown, from top to bottom, the row numbers are 1, 2, 3, 4, and from left to right, the column numbers are 1, 2, 3, 4. It should be noted that the arrangement of the microbeads in the target microbead rectangular area and the labeling method can be adjusted according to the needs of the actual application scenario, and are not limited to the directions illustrated above.

[0083] In this embodiment, the target matrix includes multiple elements, and in the elements corresponding to the microbeads in the target microbead rectangular area image, the microbead-related parameters corresponding to the microbeads are stored. So as to be able to intuitively understand the microbead detection result through the target matrix, and thus perform subsequent analysis and application.

[0084] Based on the above steps, this embodiment provides a method for detecting microbeads on a gene chip. By using a area array camera to implement the image acquisition of the target microbead rectangular area image, it can improve the image acquisition accuracy while reducing the equipment cost and usage cost of image acquisition. Using the object detection model of deep learning can learn various geometric forms of the microbeads, accurately locate them, and directly judge the brightness and darkness of the microbeads according to the pixel values of the microbead positions and the adjacent areas, which has a higher accuracy than extracting the pixel value features of the microbeads to judge the brightness and darkness. And it can provide a more intuitive detection result, which is convenient for the subsequent utilization and detection display of the gene chip microbead detection result.

[0085] According to a specific implementation manner of the embodiment of the present application, as Figure 2 shown, obtaining the target microbead rectangular area image includes:

[0086] S201. Divide the target microbead rectangular area into multiple sub-regions to be photographed, where adjacent sub-regions to be photographed include a preset overlapping area. The target microbead rectangular area includes a first side and a second side, and the length of the first side is greater than the length of the second side.

[0087] S202. Obtain the images of the sub-regions to be photographed to obtain multiple sub-images.

[0088] S203. Perform a preset splicing process on the multiple sub-images to obtain the target microbead rectangular area image.

[0089] In this embodiment, assume that the camera shooting field of view is rectangular , as Figure 9 shown, the two sides of the rectangle are the long side and the short side . In this embodiment, the first side is the long side , and the second side is the short side .

[0090] During the area division process, the long side is equally spaced and divided into columns, and the short side is equally spaced and divided into rows. It should be noted that when dividing the area in this embodiment, the target microbead rectangular area will be divided into multiple to-be-shot sub-areas with the same size. In this embodiment, the two sides corresponding to the to-be-shot sub-areas are and .

[0091] As Figure 9 shown, adjacent to-be-shot sub-areas include a preset overlapping area, and the preset overlapping area includes two types, namely the first overlapping area and the second overlapping area. Among them, the two sides corresponding to the first overlapping area are and . The two sides corresponding to the second overlapping area are and .

[0092] In the actual application process, the calculation formula for the number of columns and rows of the area division is:

[0093]

[0094]

[0095] Among them, is the number of columns, is the number of rows, is the length of the long side of the target microbead rectangular area, is the length of the short side of the target microbead rectangular area, is the length of the long side of the to-be-shot sub-area, is the length of the short side of the to-be-shot sub-area, is the length of the preset overlapping area in the long side direction of the target microbead rectangular area, is the length of the preset overlapping area in the short side direction of the target microbead rectangular area.

[0096] After the sub-areas to be photographed are divided, the image acquisition device can be controlled to acquire images of the sub-areas to be photographed, and multiple sub-images are obtained. Among them, the image acquisition device can use an area array camera or other photographic devices that can photograph the sub-images of each sub-area to be photographed, and the image acquisition device can be replaced according to the needs of the actual application scenario. After obtaining multiple sub-images, image stitching is performed based on the similar parts between the multiple sub-images, and an image of the target microbead rectangular area including the complete target microbead rectangular area can be obtained.

[0097] Based on the above steps, the gene chip microbead detection method provided in this embodiment uses an area array camera to photograph each sub-area to be photographed, which can reduce the requirements for the flatness of the gene chip surface and the perpendicularity of the image acquisition device to the chip plane. The light source can also be replaced with an LED light source with low cost and long life.

[0098] According to a specific implementation manner of the embodiment of the present application, as Figure 3 shown, performing a preset stitching process on multiple sub-images to obtain an image of the target microbead rectangular area, including:

[0099] S301, for two adjacent sub-images, determining the first adjacent area of one sub-image as the template area, and determining the second adjacent area of the other sub-image as the area to be matched.

[0100] S302, searching for a position in the area to be matched that matches the template area until a target matching position is obtained, where the target matching position is the position with the highest similarity between the area to be matched and the template area.

[0101] S303, moving the other sub-image according to the target matching position and discarding redundant partial images until the pixel points of the template area and the area to be matched are consistent.

[0102] S304, when any two adjacent sub-images are stitched, determining the stitched image as the image of the target microbead rectangular area.

[0103] In this embodiment, during the stitching process, the stitching process of any two adjacent sub-images can be completed in the way of template matching.

[0104] As Figure 10 shown in part (A), images of two adjacent sub-areas to be photographed are taken to obtain a first sub-image sub1 and a second sub-image sub2.

[0105] As Figure 10 shown in part (B), the right sub-image (right square part) of the first sub-image sub1 can be taken as the area to be matched, where the width of the right sub-image of the first sub-image sub1 is , and the height is and > , where, is the standard size of the preset overlapping area. Take the left sub-image (the left box part) of the second sub-image sub2 as the template area. Among them, the width of the left sub-image of the second sub-image sub2 is , and the height is , and , .

[0106] Based on the template area, search and match in the area to be matched, and search for all areas in the area to be matched with a width of , and a height of . Calculate the similarity between the searched area and the template area according to the following formula:

[0107]

[0108] where, is the similarity, and are the pixel coordinates in the template area, and are the pixel coordinates of the area to be matched. In the actual application process, the target matching position ( ) is the position with the maximum similarity . represents the weight value of the convolution kernel in the local offset ( , ), represents the pixel value of the image to be matched at the coordinate .

[0109] The point of the target matching position ( ) in the first sub-image sub1 corresponds to the upper left corner of the template area in the second sub-image sub2. Based on the foregoing corresponding relationship, move the second sub-image sub2 to be spliced with the first sub-image sub1 so that each pixel point in the overlapping area is basically the same, that is, as shown in part (C) of Figure 10 . It should be noted that the moving operation of the sub-image corresponding to the template area can be left and right movement or up and down movement. The specific splicing and moving operation can be set according to the needs of the actual application scenario.

[0110] As shown in part (C) of Figure 10 , after the splicing process of the two sub-images is completed, the image with consistent pixel points within the dashed box can be retained, and the image of the redundant area (that is, the image outside the dashed box) can be discarded to obtain a complete spliced image.

[0111] Based on the above steps, for the divided regions in the foregoing steps, for the multiple sub-images obtained by shooting in partitions, the pairwise splicing method described above can be used to splice them one by one, and finally an accurate target microbead rectangular region image can be obtained.

[0112] According to a specific implementation manner of an embodiment of the present application, as Figure 4 shown, before using the target detection model to process the target microbead rectangular region image to obtain microbead-related parameters, the method further includes:

[0113] S401, obtaining different gene chip images, where the gene chip images include microbeads.

[0114] S402, performing annotation on the gene chip images for microbead-related parameters.

[0115] S403, according to the annotated gene chip images, using a target detection network or a segmentation network to perform model training to obtain a target detection model.

[0116] In this embodiment, by collecting pictures of different gene chips collected on various instruments, sufficient sample images are prepared for deep learning. Among them, the image parameters such as the brightness and resolution of different pictures can also be different. In this embodiment, by collecting images of gene chips with a large number of different image parameters, the prediction accuracy of the subsequent deep learning architecture model can be improved.

[0117] After collecting sufficient sample images, annotate the sample images. As Figure 11 shown, use methods such as rectangular frames, center points, or circular frames for annotation. Among them, the annotation information includes the center point coordinates, the classification of bright beads or dark beads, and the gray mean value of the microbeads. It should be noted that during the annotation process, the center point coordinates can be directly calculated during annotation. As Figure 11 shown, the deep learning detects the center point of the microbead and judges the bright-dark classification of the microbead. The black dots represent the microbeads, and the square frames represent the rectangular frames for predicting the positions of the microbeads by the detection model.

[0118] Use a target detection or segmentation network for model training. It should be noted that the steps for completing model training based on deep learning can refer to the deep learning training techniques in related technologies. The target detection model trained in this embodiment can perform microbead positioning on pictures containing microbeads and output the microbead position and bright-dark classification results.

[0119] Based on the above steps, the gene chip microbead detection method proposed in this embodiment constructs a target detection model through deep learning, and then completes microbead positioning and bright-dark judgment based on the target detection model. The parallel detection efficiency is high, the speed is fast, and there is no position requirement for obtaining the image of the target microbead rectangular region. It can reduce the microbead detection cost while improving the microbead detection efficiency.

[0120] According to a specific implementation manner of an embodiment of the present application, as Figure 5 shown, a target matrix is constructed based on the microbead-related parameters and the target microbead rectangular region, and a microbead detection result is obtained, including:

[0121] S501, obtaining a target affine matrix according to the position coordinates of the target microbead rectangular region, wherein the distribution state of the target affine matrix is a horizontal and vertical state.

[0122] S502, constructing a virtual matrix according to the microbead distribution in the target microbead rectangular region, wherein the number of rows and columns of the virtual matrix corresponds to the number of microbeads in the row direction and the column direction in the microbead distribution.

[0123] S503, combining the target affine matrix and the virtual matrix, and mapping the microbead-related parameters to each element of the virtual matrix to obtain a microbead detection result. Wherein, one element corresponds to one microbead.

[0124] In this embodiment, during the detection process of the microbead-related parameters in the target microbead rectangular region, there is no need to adjust the placement position of the gene chip, and it is not required that the placement position of the gene chip is in a horizontal and vertical state. Therefore, the collected target microbead rectangular region may present a skew state as shown in part (B) of the figure. By calculating the target affine matrix according to the position coordinates of the target microbead rectangular region, as shown in part (C) of the figure, the target affine matrix can effectively cooperate with the virtual matrix to complete the mapping of the microbead-related parameters and obtain a more intuitive microbead detection result. Figure 12 of the (B) part of the figure. By calculating the target affine matrix according to the position coordinates of the target microbead rectangular region, as shown in part (C) of the figure, the target affine matrix can effectively cooperate with the virtual matrix to complete the mapping of the microbead-related parameters and obtain a more intuitive microbead detection result. Figure 12 of the (C) part of the figure, it can effectively cooperate with the virtual matrix to complete the mapping of the microbead-related parameters and obtain a more intuitive microbead detection result.

[0125] According to a specific implementation manner of an embodiment of the present application, as Figure 6 shown, obtaining a target affine matrix according to the position coordinates of the target microbead rectangular region includes:

[0126] S601, extracting four boundary lines of the target microbead rectangular region according to a preset iterative fitting algorithm.

[0127] S602, connecting the four boundary lines to obtain an edge matrix.

[0128] S603, performing an affine transformation on the edge matrix to obtain a target affine matrix.

[0129] In this embodiment, as Figure 12 shown in parts (A), (B), and (C), first, four boundary lines of the target microbead rectangular region are obtained according to a preset iterative fitting algorithm, and the intersection points of the four boundary lines are A, B, C, and D respectively. Connecting the four boundary lines to obtain an edge matrix ABCD. Then, an affine transformation is performed on the edge matrix ABCD to obtain a target affine matrix.

[0130] In this embodiment, the specific steps of the preset iterative fitting algorithm include:

[0131] First, extract the bead area The minimum value of the coordinates of the center point of the leftmost bead .

[0132] Second, perform initialization processing, screen all bead point coordinates detected by the target detection model, and screen out the set of center point coordinates that satisfy , where , > 0. Set the maximum number of iterations N, the distance threshold d, and the minimum number of inliers k.

[0133] Third, start the iterative process. Randomly select two points from all data points as sample points; calculate a straight line equation based on these two sample points; calculate the distances from all data points to this straight line. If the distance is less than the threshold d, mark this point as an inlier; if the size of the current inlier set is greater than the previously recorded best inlier set, update the best model and its corresponding inlier set.

[0134] Fourth, determine whether the termination condition is satisfied. When the maximum number of iterations N is reached or enough inliers (the number reaches k) are found, stop the iteration.

[0135] Fifth, output the result. Use the inlier set corresponding to the best model to refit the straight line to obtain the final straight line equation ax + b = 0.

[0136] Sixth, iterate again, reduce the value of , repeat the initialization and perform straight line fitting. If the change ranges of a and b are less than the preset threshold δ for 2 consecutive times or more, terminate the iteration, output the straight line equation of the last time, and obtain the corresponding edge line.

[0137] Based on the above steps, the four boundary lines of the target bead rectangular area can be extracted, including the upper boundary line, the lower boundary line, the left boundary line, and the right boundary line. Calculate the four vertices of the four boundary lines. As shown in Figure 12 , the upper boundary line AB, the lower boundary line DC, the left boundary line AD, and the right boundary line BC can be obtained.

[0138] Use affine transformation to map the quadrilateral ABCD into a standard rectangle , and calculate the target affine matrix .

[0139] Based on the above steps, assuming that the photographed area is n times that of a single field of view, the distortion effect will be magnified by n times, and a large distortion effect will cause bead positioning deviation. Mapping to a standard rectangle by affine transformation can correct the optical distortion caused by the tilt of the chip placement and reduce the positioning deviation.

[0140] According to a specific implementation manner of an embodiment of the present application, as Figure 7 shown, mapping the bead-related parameters to each element of the virtual matrix to obtain the bead detection result, including:

[0141] S701, initialize the virtual matrix, and fill the preset content in the target element, where the target element is the element in the virtual matrix corresponding to the bead position in the target affine matrix;

[0142] S702, traverse the unupdated elements in the virtual matrix, and map and fill the corresponding bead-related parameters for each unupdated element, where the preset content is filled in the unupdated element.

[0143] In this embodiment, it is assumed that the beads are arranged in rows and columns (both numbered starting from 1), and the arrangement is as shown in Figure 8 part (A) of the image. Construct a virtual matrix IM with rows and columns. The content stored in each position can be expressed as , that is, it includes the light and dark classification , the center point coordinates , and the bead grayscale value .

[0144] In this embodiment, the mapping steps of the virtual matrix include:

[0145] Initialize the virtual matrix, and fill the elements whose sum of the row number and the column number is even with .

[0146] Denote the four vertex coordinates of the standard rectangle as . Assume that the center coordinates of the bead in the matrix area are ( ), its light and dark classification is , and the grayscale value is . Then the coordinates of this center point mapped to the coordinate system where the standard rectangle is located are:

[0147]

[0148] Among them, is the center coordinate of the bead in the matrix area, is the transpose of the center coordinate of the bead in the matrix area, and is the target affine matrix.

[0149] The calculation method corresponding to the row and column coordinates of the virtual matrix includes:

[0150]

[0151]

[0152]

[0153]

[0154] wherein, is the line number, is the column number, and are the row and column coordinates in the standard rectangle and and are the vertex coordinates within the region, is the column value of the virtual matrix IM, is the row value of the virtual matrix IM.

[0155] The information filled in the th row and th column of the virtual matrix IM is .

[0156] The virtual matrix IM with some element information updated is shown in Table 1.

[0157] Table 1

[0158]

[0159] Traverse all the elements that have not been updated, that is, traverse each element in the virtual matrix IM according to the row and column numbers, and find the element with the center point coordinate of , that is, the unupdated element, and add the bead-related parameters to each unupdated element.

[0160] In one embodiment, if the second element (bead center point coordinate) in the th row and th column of the virtual matrix IM is (-1, -1), then update the center point coordinate ( ) to , and further update the th row and th column of the virtual matrix IM as a whole to [0, (

[0161] In summary, this embodiment provides a method for detecting microbeads on a gene chip. By using an area array camera to collect images of the rectangular area of the target microbeads, it is possible to improve the image collection accuracy while reducing the equipment cost and usage cost of image collection. Using a target detection model based on deep learning can learn various geometric forms of microbeads, accurately locate them, and directly judge the brightness and darkness of microbeads based on the pixel values of the microbead positions and adjacent areas, with a higher accuracy rate than judging the brightness and darkness by extracting the pixel value features of microbeads. Moreover, it can provide a more intuitive detection result, facilitating the subsequent utilization and detection display of the gene chip microbead detection result.

[0162] Based on the same inventive concept, an embodiment of the present application also provides a gene chip microbead detection device for implementing the above-mentioned gene chip microbead detection method. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the gene chip microbead detection device provided below can refer to the limitations on the gene chip microbead detection method in the above text and will not be elaborated here.

[0163] In one embodiment, referring to Figure 13 , this embodiment also provides a gene chip microbead detection device 1300, including: an acquisition module 1310, a detection module 1320, and an output module 1330, where:

[0164] The acquisition module 1310 is configured to acquire an image of the rectangular area of the target microbeads, where the image of the rectangular area of the target microbeads is formed by splicing a plurality of sub-images, and the sub-images cover partial areas of the rectangular area of the target microbeads;

[0165] The detection module 1320 is configured to process the image of the rectangular area of the target microbeads by using a target detection model to obtain microbead-related parameters, where the target detection model is a model trained based on deep learning, and the microbead-related parameters include the microbead position, the microbead brightness and darkness classification result, and the gray-scale mean value of the microbead area;

[0166] The output module 1330 is configured to construct a target matrix based on the microbead-related parameters and the rectangular area of the target microbeads to obtain a microbead detection result, where the target matrix stores the microbead-related parameters according to the arrangement of the microbeads in the rectangular area of the target microbeads.

[0167] In one of the embodiments, the acquisition module 1310 is specifically configured to divide the rectangular area of the target microbeads to obtain a plurality of sub-areas to be photographed, where adjacent sub-areas to be photographed include a preset overlapping area, the rectangular area of the target microbeads includes a first side and a second side, and the length of the first side is greater than the length of the second side; acquire images of the sub-areas to be photographed to obtain a plurality of sub-images; and perform a preset splicing process on the plurality of sub-images to obtain an image of the rectangular area of the target microbeads.

[0168] In one embodiment, the obtaining module 1310 is specifically configured to, for two adjacent sub-images, determine the first adjacent region of one sub-image as the template region, and determine the second adjacent region of the other sub-image as the region to be matched; search for the position that matches the template region in the region to be matched until the target matching position is obtained, where the target matching position is the position with the highest similarity between the region to be matched and the template region; move the other sub-image according to the target matching position, and discard the redundant partial image until the pixel points of the template region and the region to be matched are consistent; when any two adjacent sub-images are both stitched, determine the stitched image as the target micro-bead rectangular region image.

[0169] In one embodiment, the detecting module 1320 is specifically configured to obtain different gene chip images, where the gene chip images include micro-beads; perform micro-bead related parameter annotation on the gene chip images; according to the annotated gene chip images, use a target detection network or a segmentation network for model training to obtain a target detection model.

[0170] In one embodiment, the output module 1330 is specifically configured to obtain a target affine matrix according to the position coordinates of the target micro-bead rectangular region, where the distribution state of the target affine matrix is horizontal and vertical; construct a virtual matrix according to the micro-bead distribution in the target micro-bead rectangular region, where the number of rows and columns of the virtual matrix corresponds to the number of micro-beads in the row direction and column direction in the micro-bead distribution; combine the target affine matrix and the virtual matrix, and map the micro-bead related parameters to each element of the virtual matrix to obtain a micro-bead detection result, where one element corresponds to one micro-bead.

[0171] In one embodiment, the output module 1330 is specifically configured to extract four boundary lines of the target micro-bead rectangular region according to a preset iterative fitting algorithm; connect the four boundary lines to obtain an edge matrix; perform an affine transformation on the edge matrix to obtain a target affine matrix.

[0172] In one embodiment, the output module 1330 is specifically configured to initialize the virtual matrix, and fill a preset content in the target element, where the target element is the element in the virtual matrix corresponding to the micro-bead position in the target affine matrix; traverse the unupdated elements in the virtual matrix, and map and fill the corresponding micro-bead related parameters for each unupdated element, where the unupdated elements are filled with the preset content.

[0173] In summary, this embodiment provides a gene chip bead detection device. By using an area array camera to collect images of the rectangular area of the target beads, it is possible to improve the image acquisition accuracy while reducing the equipment cost and usage cost of image acquisition. The object detection model using deep learning can learn various geometric forms of the beads, accurately locate them, and directly judge the brightness and darkness of the beads based on the pixel values of the bead positions and the pixels in adjacent areas, with a higher accuracy than judging the brightness and darkness by extracting the pixel value features of the beads. Moreover, it can provide a more intuitive detection result, facilitating the subsequent utilization and detection display of the gene chip bead detection results.

[0174] Figure 13 For the specific implementation manner of the device shown, reference may be made to the specific implementation manner in the foregoing method embodiment, which will not be elaborated herein.

[0175] In addition, an embodiment of the present application further provides an electronic device, where the electronic device includes:

[0176] at least one processor; and,

[0177] a memory communicatively connected to the at least one processor; wherein,

[0178] the memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the gene chip bead detection method in the foregoing method embodiment.

[0179] An embodiment of the present application further provides a non-transitory computer-readable storage medium, which stores computer instructions for causing the computer to execute the gene chip bead detection method in the foregoing method embodiment.

[0180] It should be noted that the computer-readable medium in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. Examples of computer-readable storage media may include, but are not limited to: electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0181] In the present disclosure, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0182] The above computer-readable medium can be included in the above electronic device; or it can exist separately without being assembled into the electronic device.

[0183] The above computer-readable medium carries one or more programs, which, when executed by the electronic device, cause the electronic device to: obtain an image of a target microbead rectangular region, where the image of the target microbead rectangular region is formed by splicing a plurality of sub-images, and the sub-images cover partial regions of the target microbead rectangular region; process the image of the target microbead rectangular region using a target detection model to obtain microbead-related parameters, where the target detection model is a model trained based on deep learning, and the microbead-related parameters include microbead positions, microbead brightness and darkness classification results, and the average gray value of the microbead region; construct a target matrix based on the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result, where the target matrix stores the microbead-related parameters according to the arrangement of the microbeads in the target microbead rectangular region.

[0184] Computer program code for performing the operations of the present disclosure can be written in one or more programming languages or combinations thereof. The above programming languages include object-oriented programming languages - such as Java, Smalltalk, C++, and also include conventional procedural programming languages - such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or can be connected to an external computer (for example, by connecting through an Internet service provider via the Internet).

[0185] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions denoted in the blocks may occur in an order different from that denoted in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0186] The units described in the embodiments of the present application can be implemented in software or in hardware. In some cases, the name of the unit does not constitute a limitation on the unit itself.

[0187] It should be understood that the various parts of the present disclosure can be implemented by hardware, software, firmware, or a combination thereof.

[0188] As described above, the above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present disclosure should be covered by the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A method for detecting gene chip microbeads, characterized in that, Including: Obtain an image of a target microbead rectangular region, where the image of the target microbead rectangular region is formed by splicing a plurality of sub-images, and the sub-images cover partial regions of the target microbead rectangular region; Process the image of the target microbead rectangular region by using a target detection model to obtain microbead-related parameters, where the target detection model is a model trained based on deep learning, and the microbead-related parameters include microbead positions, microbead brightness and darkness classification results, and microbead region gray-scale means; Construct a target matrix according to the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result, where the target matrix stores the microbead-related parameters according to the arrangement of microbeads in the target microbead rectangular region; The obtaining the image of the target microbead rectangular region includes: Perform region division on the target microbead rectangular region to obtain a plurality of sub-regions to be photographed, where adjacent sub-regions to be photographed include a preset overlapping region, the target microbead rectangular region includes a first side and a second side, and the length of the first side is greater than the length of the second side; Obtain images of the sub-regions to be photographed to obtain a plurality of sub-images; where the sub-images are obtained by photographing the sub-regions to be photographed by a planar array camera; Perform a preset splicing process on the plurality of sub-images to obtain the image of the target microbead rectangular region; The constructing a target matrix according to the microbead-related parameters and the target microbead rectangular region to obtain a microbead detection result includes: Obtain a target affine matrix according to the position coordinates of the target microbead rectangular region, where the distribution state of the target affine matrix is a horizontal and vertical state; Construct a virtual matrix according to the microbead distribution in the target microbead rectangular region, where the number of rows and columns of the virtual matrix corresponds to the number of microbeads in the row direction and column direction in the microbead distribution; Combine the target affine matrix and the virtual matrix, and map the microbead-related parameters to each element of the virtual matrix to obtain the microbead detection result, where one element corresponds to one microbead.

2. The method according to claim 1, characterized in that The performing a preset splicing process on the plurality of sub-images to obtain the image of the target microbead rectangular region includes: For two adjacent sub-images, determine a first adjacent region of one sub-image as a template region, and determine a second adjacent region of the other sub-image as a region to be matched; Search for a position in the region to be matched that matches the template region until a target matching position is obtained, where the target matching position is the position with the maximum similarity between the region to be matched and the template region; Move the other sub-image according to the target matching position and discard redundant partial images until the pixel points of the template region and the region to be matched are consistent; When any two adjacent sub-images are spliced, determine the spliced image as the image of the target microbead rectangular region.

3. The method according to claim 1, characterized in that, Before the processing the image of the target microbead rectangular region by using the target detection model to obtain the microbead-related parameters, the method further includes: Obtain different gene chip images, where the gene chip images include microbeads; Annotate the gene chip image with bead-related parameters; According to the annotated gene chip image, use an object detection network or a segmentation network for model training to obtain the object detection model.

4. The method according to claim 1, characterized in that, The obtaining of the target affine matrix according to the position coordinates of the target bead rectangular region includes: Extract four boundary lines of the target bead rectangular region according to a preset iterative fitting algorithm; Connect the four boundary lines to obtain an edge matrix; Perform an affine transformation on the edge matrix to obtain the target affine matrix.

5. The method according to claim 1, characterized in that The mapping of the bead-related parameters to each element of the virtual matrix to obtain the bead detection result includes: Initialize the virtual matrix and fill a preset content in the target elements, where the target elements are the elements in the virtual matrix corresponding to the bead positions in the target affine matrix; Traverse the unupdated elements in the virtual matrix, and map and fill the corresponding bead-related parameters for each unupdated element, where the preset content is filled in the unupdated elements.

6. A gene chip bead detection device, characterized in that, including: An acquisition module, configured to acquire an image of a target bead rectangular region, where the image of the target bead rectangular region is formed by splicing a plurality of sub-images, and the sub-images cover partial regions of the target bead rectangular region; A detection module, configured to process the image of the target bead rectangular region by using an object detection model to obtain bead-related parameters, where the object detection model is a model trained based on deep learning, and the bead-related parameters include bead positions, bead brightness and darkness classification results, and bead region gray scale means; An output module, configured to construct a target matrix according to the bead-related parameters and the target bead rectangular region to obtain a bead detection result, where the target matrix stores the bead-related parameters according to the arrangement of the beads in the target bead rectangular region; The acquisition module is specifically configured to divide the target bead rectangular region into a plurality of sub-regions to be photographed, where adjacent sub-regions to be photographed include a preset overlapping region, the target bead rectangular region includes a first side and a second side, and the length of the first side is greater than the length of the second side; acquire images of the sub-regions to be photographed to obtain a plurality of sub-images; where the sub-images are obtained by photographing the sub-regions to be photographed by a planar array camera; perform a preset splicing process on the plurality of sub-images to obtain the image of the target bead rectangular region; The output module is specifically configured to obtain a target affine matrix according to the position coordinates of the target bead rectangular region, where the distribution state of the target affine matrix is a horizontal and vertical state; construct a virtual matrix according to the bead distribution in the target bead rectangular region, where the number of rows and columns of the virtual matrix corresponds to the number of beads in the bead distribution in the row direction and the column direction; combine the target affine matrix and the virtual matrix, and map the bead-related parameters to each element of the virtual matrix to obtain the bead detection result, where one element corresponds to one bead.

7. An electronic device, characterized in that, including: At least one processor; and, A memory communicatively connected to the at least one processor; where, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the gene chip bead detection method according to any one of the preceding claims 1-5.

8. A non-transitory computer-readable storage medium, characterized in that, The non-transitory computer-readable storage medium stores computer instructions for causing the computer to execute the gene chip bead detection method according to any one of the preceding claims 1-5.

Images