Method and device for identifying and counting enzyme-linked spots and electronic equipment

Abstract

The invention relates to an enzyme-linked spot recognition and counting method and device and electronic equipment, and the method comprises the steps: obtaining a to-be-recognized initial enzyme-linked spot image; sequentially performing graying, morphological opening operation, threshold segmentation and morphological closing operation on the initial enzyme-linked spot image to obtain a target enzyme-linked spot image; identifying the contour of each spot in the target enzyme-linked spot image through a contour detection algorithm; and counting the contour number in the target enzyme-linked spot image to obtain the enzyme-linked spot number in the initial enzyme-linked spot image. The method solves the problems of high workload, long processing period and high error rate due to the fact that the recognition and counting of enzyme-linked spots need to be completed by human eyes at present, and can greatly reduce the test working intensity and remarkably improve the scientific research efficiency.

Description

Technical Field

[0001] The present application relates to the field of biological image recognition, and in particular to an enzyme-linked spot recognition and counting method, device and electronic equipment. Background Art

[0002] The plate reader is an advanced digital imaging and analysis instrument designed for immunology, biomedicine and basic medical research. The instrument can accurately measure and analyze cellular immune response test data, providing a new type of immune monitoring and disease research tool for scientific research, helping it to make breakthroughs in the quantitative research of cytokine secretion, antibody production and other immune response-related indicators. The working process of the plate reader is: first, use microscopic photography to take high-definition pictures of the enzyme-linked spots generated or precipitated on the bottom of each test tube in the culture plate (a test equipment composed of 96 test tubes with a diameter of 6 mm arranged in a 12×8 array plane), one picture for each test tube hole, and one test tube (corresponding to one hole) in each photo roughly presents 0-1000 spots that need to be identified and counted.

[0003] In the above process, the recognition and counting of ELISA spots need to be completed by human eyes, that is, the current plate reader only provides a high-definition image of the bottom of the test tube. The recognition and counting of ELISA spots by human eyes has the problems of large workload, long processing cycle and high error rate. Summary of the invention

[0004] The present invention provides an ELISA spot recognition and counting method to solve the problems that the current ELISA spot recognition and counting needs to be completed by human eyes, which has a large workload, a long processing cycle and a high error rate.

[0005] In a first aspect, the present invention provides a method for identifying and counting enzyme-linked spots, comprising:

[0006] Acquire an initial enzyme-linked spot image to be identified;

[0007] The initial ELISA spot image is sequentially subjected to grayscale conversion, morphological opening operation, threshold segmentation, and morphological closing operation to obtain a target ELISA spot image;

[0008] Identifying the contours of each spot in the target ELISA spot image by a contour detection algorithm;

[0009] The number of contours in the target ELISA spot image is counted to obtain the number of ELISA spots in the initial ELISA spot image.

[0010] In a second aspect, the present invention provides an enzyme-linked spot recognition and counting device, comprising:

[0011] An image acquisition module, used for acquiring an initial ELISA spot image to be identified;

[0012] An image processing module, used for sequentially performing grayscale conversion, morphological opening operation, adaptive threshold segmentation, and morphological closing operation on the initial ELISA spot image to obtain a target ELISA spot image;

[0013] A contour detection module, used to identify the contour of each spot in the target ELISA spot image by using a contour detection algorithm;

[0014] The spot counting module is used to count the number of contours in the target ELISA spot image to obtain the number of ELISA spots in the initial ELISA spot image.

[0015] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the enzyme-linked spot identification and counting method described in the first aspect.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the steps of the method for identifying and counting enzyme-linked spots described in the third aspect.

[0017] Compared with the related art, the present invention provides a method for identifying and counting enzyme-linked spots with higher accuracy and can be executed by a computer, which solves the problem that the identification and counting of enzyme-linked spots currently need to be completed by the human eye, which has the problems of large workload, long processing cycle and high error rate. It can greatly reduce the intensity of experimental work and significantly improve scientific research efficiency.

[0018] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the method for identifying and counting enzyme-linked spots provided in an embodiment of the present invention;

[0020] Figure 2 It is a structural diagram of the recognition and counting device for enzyme-linked spots provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0022] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0023] In an embodiment of the present invention, a method for identifying and counting enzyme-linked spots is provided. Figure 1 : is a flow chart of the method for identifying and counting enzyme-linked spots provided in an embodiment of the present invention, such as Figure 1 As shown, the process includes step S110, step S120, step S130 and step S140.

[0024] Step S110, obtaining an initial ELISA spot image to be identified.

[0025] In some biological experiments, it is necessary to generate or precipitate enzyme-linked spots at the bottom of a test tube on a culture plate, and it is necessary to identify the enzyme-linked spots and count them to determine the experimental situation. The present invention needs to photograph the enzyme-linked spots at the bottom of each test tube respectively by a microphotographic method to obtain enzyme-linked spot images at the bottom of each test tube. The initial enzyme-linked spot image is an enzyme-linked spot image obtained by a microphotographic method without any image processing.

[0026] It should be noted that, depending on the biological experiment, there are different types of ELISA spots, such as proteinase-linked spots.

[0027] Step S120 , graying, morphological opening, threshold segmentation, and morphological closing are sequentially performed on the initial ELISA spot image to obtain a target ELISA spot image.

[0028] In order to facilitate the subsequent better identification of ELISA spots in the image, this step uses a series of specific image processing methods to preprocess the initial ELISA spot image in a specific order, and the target ELISA spot image is the preprocessed initial ELISA spot image.

[0029] Among them, the morphological opening operation includes erosion operation and dilation operation in sequence. The morphological opening operation can eliminate noise and remove small interference blocks without affecting the shape and structure of the main part of the original image. The morphological opening operation is performed first in preprocessing, which can effectively handle the scene of spot adhesion. The morphological closing operation includes dilation operation and erosion operation in sequence. The morphological closing operation can effectively remove the small pores inside the spots after threshold segmentation, smooth the image edges, and improve the accuracy of contour detection.

[0030] Specifically, the erosion operation can reduce the boundaries of objects in the image, remove small details or noise, and make the objects more detailed. The principle is to slide a structural element (also called a kernel or template) on the image and compare it with the pixels at the corresponding position in the image. The structural element defines the scope and shape of the erosion operation, usually a small matrix such as 3x3 or 5x5, which contains 1 and 0. When comparing, it is necessary to traverse each pixel of the input image, and for each pixel, consider a local area centered on it and the same size as the structural element. Perform an element-by-element AND operation on the pixel values ​​in the local area and the corresponding values ​​in the structural element, and then calculate the number of non-zero elements. If all corresponding positions in the local area are foreground pixels, the pixel values ​​at the corresponding positions in the output image remain as foreground values; otherwise, they are set to background values.

[0031] Repeat the above steps to construct a corresponding output image pixel value for each pixel in the input image (the ELISPOT image in the present invention). The output image finally obtained is the image after corrosion. The result of the corrosion operation is that objects or details smaller than the structural element in the ELISPOT image will be removed, and the boundaries of the spots will shrink inwards.

[0032] The dilation operation is opposite to the erosion operation. The dilation operation can expand the boundaries of objects in the image, fill small holes or connect broken parts, and make the object more complete. The principle is the same as sliding the structural element on the image, but the judgment condition is opposite to the erosion operation. For each pixel, consider the local area centered on it. Perform an element-by-element OR operation on the pixel values ​​in the local area and the corresponding values ​​in the structural element. If any pixel in the local area is a foreground pixel (that is, 1 in a binary image), the pixel value at the corresponding position in the image is set to the foreground value.

[0033] As a result of the dilation operation, the boundaries of the spots in the ELISA spot image will expand outward, small holes will be filled, and broken parts will be connected.

[0034] Threshold segmentation is a process of binarizing an image. Preferably, the threshold segmentation in the present invention adopts adaptive threshold segmentation. Adaptive threshold segmentation pays more attention to contextual relationships, divides the original image into smaller areas and uses different thresholds for segmentation, which greatly reduces the impact of shadows on the image itself. Compared with traditional global threshold segmentation (the entire image uses a unified segmentation threshold), adaptive threshold segmentation can more accurately handle the impact of lighting changes and noise, greatly improve the accuracy of image segmentation, and has significant advantages when processing images with uneven lighting or complex backgrounds.

[0035] Specifically, in one embodiment, the step of adaptive threshold segmentation includes: dividing the initial ELISPOT image after morphological opening operation into multiple local regions; respectively determining the local segmentation thresholds of the multiple local regions; and binarizing each local region with its own local segmentation threshold.

[0036] The local segmentation threshold is a mean adaptive threshold or a Gaussian adaptive threshold; the mean adaptive threshold of each local area is determined according to the average value of the pixels in the area; the Gaussian adaptive threshold of each local area is determined according to the weighted mean of the pixels in the area.

[0037] The size of each graphic area is determined by the parameter blockSize, which indicates the pixel range considered when calculating the local threshold. It should be an odd number so that there is a clear center pixel. The graphic area is usually a square window with a size of blockSize×blockSize, and the center of the window is located on the pixel currently being processed.

[0038] Commonly used local thresholds include mean adaptive threshold and Gaussian adaptive threshold.

[0039] Mean adaptive threshold: Calculate the average value of pixels in a local area, and then subtract a constant C as the threshold of the area. This method is simple and computationally efficient.

[0040] Gaussian adaptive threshold: Consider the weighted mean of pixels in a local area, with the weights determined by a Gaussian window. This method can better handle local illumination changes and noise.

[0041] The calculation of the local threshold value enables each region to have a threshold value adapted to its brightness, thereby being able to more accurately segment the foreground and background. The present invention can use different methods to determine the local threshold value of each local region in different embodiments. Preferably, the local threshold value uses a Gaussian adaptive threshold value.

[0042] After obtaining the local threshold of each local area, each pixel value in the local area is compared with the corresponding local threshold. If the pixel value is greater than or equal to the local threshold, it is classified as foreground. If the pixel value is less than the local threshold, it is classified as background. After adaptive threshold segmentation, the ELISA spot image is converted into a binary image, in which the foreground and background are represented by different grayscale values.

[0043] Step S130, identifying the contour of each spot in the target ELISA spot image by using a contour detection algorithm.

[0044] The ELISA spot image processed in step S120 is a binary image, in which the foreground (spot) and the background are more distinct, so it is convenient to detect the contour of the spot and identify the contour of each spot in the image.

[0045] Among them, the contour detection algorithm can be implemented by the findContours function in OpenCV

[0046] The advantage of OpenCV contour detection is that it can accurately identify and extract the boundaries of objects in the image, providing a reliable basis for subsequent image analysis.

[0047] The principle of OpenCV contour detection is: OpenCV's findContours function is a powerful tool for detecting contours from binary images. The findContours function traverses each pixel in the binary image. For each foreground pixel, the function checks its 8 neighboring pixels (or 4, depending on the connectivity type: 4-connected or 8-connected). When a foreground pixel that has not been visited is found, the pixel is considered to be the starting point of the contour. Starting from the starting point, the findContours function traces the contour along the boundary pixels. This usually involves moving along the outer or inner boundary of the contour until it returns to the starting point to form a closed contour. During the tracing process, the coordinates of each pixel on the contour are recorded to form a contour point set. The findContours function obtains all the contour point sets in the image and finally returns the contour set of the spots. The set contains the coordinates, shape, size and other information of all contours. The number of contours is the number of spots.

[0048] Step S140 , counting the number of contours in the target ELISA spot image to obtain the number of ELISA spots in the initial ELISA spot image.

[0049] After all the spot outlines in the target ELISA spot image are identified, since these spots are processed ELISA spots, the number of spot outlines is the number of ELISA spots in the initial ELISA spot image.

[0050] In summary, by the above-mentioned enzyme-linked spot recognition and counting method, the number of enzyme-linked spots in the image can be accurately identified and counted. The key point is that, first, the initial enzyme-linked spot image is successively subjected to graying, morphological opening operation, threshold segmentation and morphological closing operation and other image processing, and the target enzyme-linked spot image that can improve the accuracy of contour detection can be obtained. It should be noted that, although each individual image processing operation is an existing mature technology, the innovation of the present invention is that based on a specific processing sequence, the enzyme-linked spot image is pre-processed by the above-mentioned multiple image processing operations in sequence, and the target enzyme-linked spot image that can improve the accuracy of contour detection is finally obtained. Therefore, the present invention provides a method for recognizing and counting enzyme-linked spots with high accuracy and that can be executed by a computer, which solves the problem that the recognition and counting of the current enzyme-linked spots need to be completed by the human eye, and there are problems such as large workload, long processing cycle and high error rate, which can greatly reduce the intensity of experimental work and significantly improve scientific research efficiency.

[0051] In the embodiments of the present invention, a recognition and counting device for enzyme-linked spots is also provided, which is used to implement the above-mentioned embodiments and preferred embodiments, and the descriptions thereof will not be repeated. The terms "module", "unit", "subunit" etc. used below can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented with software, the implementation of hardware, or a combination of software and hardware is also possible and contemplated.

[0052] Figure 2 is a schematic diagram of an enzyme-linked spot recognition and counting device provided in an embodiment of the present invention, with reference to Figure 2 The enzyme-linked spot recognition and counting device includes: an image acquisition module, an image processing module, a contour detection module and a spot counting module.

[0053] The image acquisition module is used to acquire the initial enzyme-linked spot image to be identified.

[0054] The image processing module is used to sequentially perform grayscale conversion, morphological opening operation, adaptive threshold segmentation, and morphological closing operation on the initial ELISA spot image to obtain the target ELISA spot image.

[0055] The contour detection module is used to identify the contours of each spot in the target ELISA spot image through a contour detection algorithm.

[0056] The spot counting module is used to count the number of contours in the target ELISA spot image to obtain the number of ELISA spots in the initial ELISA spot image.

[0057] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0058] In an embodiment of the present invention, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the method for identifying and counting enzyme-linked spots provided by the present invention. The electronic device may be an enzyme-linked spot analyzer.

[0059] In an embodiment of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for identifying and counting enzyme-linked spots provided by the present invention are implemented.

[0060] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0061] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

Claims

1. A method for identifying and counting enzyme-linked spots, characterized in that: include: Acquire an initial enzyme-linked spot image to be identified; The initial ELISA spot image is sequentially subjected to grayscale conversion, morphological opening operation, threshold segmentation, and morphological closing operation to obtain a target ELISA spot image; Identifying the contours of each spot in the target ELISA spot image by a contour detection algorithm; The number of contours in the target ELISA spot image is counted to obtain the number of ELISA spots in the initial ELISA spot image.

2. The method for identifying and counting enzyme-linked spots according to claim 1, characterized in that: The morphological opening operation includes an erosion operation and a dilation operation in sequence, and the morphological closing operation includes the dilation operation and the erosion operation in sequence.

3. The method for identifying and counting enzyme-linked spots according to claim 2, characterized in that: The threshold segmentation is an adaptive threshold segmentation.

4. The method for identifying and counting enzyme-linked spots according to claim 3, characterized in that: The step of adaptive threshold segmentation comprises: Dividing the initial ELISA spot image after morphological opening operation into a plurality of local areas; respectively determining local segmentation thresholds of the plurality of local regions; Each local region is binarized using its own local segmentation threshold.

5. The method for identifying and counting enzyme-linked spots according to claim 4, characterized in that: The local segmentation threshold is a mean adaptive threshold or a Gaussian adaptive threshold; The mean adaptive threshold of each local area is determined according to the average value of pixels in the area; The Gaussian adaptive threshold of each local area is determined according to the weighted mean of the pixels in the area.

6. The method for identifying and counting enzyme-linked spots according to claim 1, characterized in that: The contour detection algorithm is implemented by the findContours function in OpenCV.

7. An enzyme-linked spot recognition and counting device, characterized in that: include: An image acquisition module, used for acquiring an initial ELISA spot image to be identified; An image processing module, used for sequentially performing grayscale conversion, morphological opening operation, adaptive threshold segmentation, and morphological closing operation on the initial ELISA spot image to obtain a target ELISA spot image; A contour detection module, used to identify the contour of each spot in the target ELISA spot image by using a contour detection algorithm; The spot counting module is used to count the number of contours in the target ELISA spot image to obtain the number of ELISA spots in the initial ELISA spot image.

8. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for identifying and counting enzyme-linked spots according to any one of claims 1 to 6.

9. The electronic device according to claim 8, characterized in that: The electronic device is an enzyme-linked spot analyzer.

10. A computer-readable 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 for identifying and counting enzyme-linked spots according to any one of claims 1 to 6 are implemented.

Images