Automatic hole location positioning method based on high-throughput microporous chip

Through the automatic hole position position position position position analysis method through CCD image acquisition and AI deduction, the hole position deviation caused by micro-moving stage movement deviation and human factors in high-throughput microporous chips are solved, and the precise positioning and high accuracy of micron-level hole position are achieved Calibration improves the accuracy of single-cell screening and identification.

CN119063627AInactive Publication Date: 2024-12-03YOUDUOYAN (BEIJING) BIOTECHNOLOGY CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411229302.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-12-03
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

During the processing and installation of high-throughput microporous chips, the movement deviation of the micro-movement stage and human factors lead to micro-scale pore position deviation, which in turn affects the focal stability during the objective observation and affects the accuracy of cell signal collection and analysis.

Method used

Using the automatic positioning method of hole position based on CCD image acquisition and artificial intelligence AI deduction, the hole position of the micropore is automatically determined and revised by identifying, calibrating and adjusting the Z-axis motion of the micromovement platform, reducing the influence of human factors and improving the hole position Calibration accuracy.

Benefits of technology

The precise positioning of micron-level pores is achieved, the objective lens is avoided, and the accuracy and guarantee of high-throughput micropore chips for single-cell screening and identification are improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119063627A_ABST
    Figure CN119063627A_ABST
Patent Text Reader

Abstract

The invention provides an automatic hole location positioning method based on a high-throughput microporous chip, which comprises the following steps of: identifying the high-throughput microporous chip, and performing image acquisition by adopting a CCD (Charge Coupled Device) in the process of moving and adjusting the high-throughput microporous chip by a micro-motion platform; performing Z-axis movement adjustment on the micro-motion platform according to the definition of the image acquired by the high-flux microporous core; based on the adjusted high-throughput micropore chip on the micro-motion platform, initial identification, discrimination and calibration of the micropore at the head end are carried out; after the objective lens is adjusted, secondary identification, discrimination and calibration of the head end micropore are carried out again; analyzing and calculating the rotation angle of the high-throughput microporous chip based on the secondary calibration result; and verification and calibration are carried out by combining the rotation angle of the high-throughput microporous chip with the verification micropores. According to the invention, automatic hole site identification and positioning are realized, the influence of human factors is reduced, the influence of an out-of-focus phenomenon on cell signal collection and analysis is avoided, the hole site calibration precision can be improved, and the guarantee of a high-throughput microporous chip on single cell screening and identification is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of automatic positioning technology, and in particular to an automatic hole positioning method based on a high-throughput micro-hole chip. Background Art

[0002] High-throughput microwell chip is a technology platform for high-throughput analysis. It consists of a microwell array chip and an antibody-coated glass slide. Its main application is in cell biology research. It can complete sample preparation, reaction, separation, and detection in biological, chemical, and medical analysis processes on a micrometer-scale chip. As high-throughput microwell chips have attracted more and more attention for single-cell screening and identification, single-cell screening has extremely high demands for cell throughput. High throughput represents high diversity of screened cells.

[0003] During chip processing, the deviation of the micro-motion stage movement will cause the deviation of the micron-level high-throughput hole position on the X and Y axes, thereby causing physical distortion, and during chip installation, the influence of human factors will also cause the Z-axis deviation of the micron-level hole position, thereby causing the objective lens to lose focus when moving to different areas of the chip for observation, thereby affecting the collection and analysis of cell signals. Therefore, the present invention proposes a hole position automatic positioning method based on a high-throughput micro-well chip, which automatically realizes hole position identification and positioning, which can not only reduce the influence of human factors, avoid the phenomenon of losing focus when the objective lens moves to different areas of the chip for observation, thereby reducing the impact on the collection and analysis of cell signals, but also reduce the micron-level high-throughput hole position deviation, improve the accuracy of hole position calibration, and thereby improve the screening and identification of single cells by the high-throughput micro-well chip. Summary of the invention

[0004] The purpose of the present invention is to provide a method for automatically locating wells based on a high-throughput microwell chip to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solution: a method for automatically locating wells based on a high-throughput microwell chip, comprising:

[0006] Perform high-throughput microwell chip identification on the target position to obtain the target identification result;

[0007] According to the target recognition result, the high-throughput micro-pore core is moved by the micro-motion platform, and the image of the high-throughput micro-pore core is acquired by CCD to obtain the high-throughput micro-pore core acquisition image;

[0008] Analyze the clarity of the image collected by the high-throughput micro-hole core, determine the target position of the micro-motion platform, and then adjust the target movement of the micro-motion platform on the Z axis according to the target position of the micro-motion platform;

[0009] Using CCD to collect target images of the high-throughput microwell chip, and obtaining the first target image of the high-throughput microwell chip;

[0010] Performing preliminary identification, discrimination and calibration of the first-end micropores based on the first target image of the high-throughput micropore chip to obtain a first calibration result;

[0011] Adjusting the objective lens, and facilitating the adjusted objective lens to acquire an image again based on the first calibration result, to obtain a second target image of the high-throughput microwell chip;

[0012] Based on the second target image of the high-throughput micropore chip, the first-end micropore secondary identification, discrimination and calibration are performed to obtain the secondary calibration result;

[0013] In the secondary calibration result, the hole position data of the first end microhole is obtained, and the rotation angle of the high-throughput microhole chip is analyzed and calculated based on the hole position data of the first end microhole and the hole position data of the upper right end microhole;

[0014] The target micropore is determined, and the hole position data is revised using the rotation angle of the high-throughput micropore chip to obtain the hole position positioning data of the target micropore.

[0015] Furthermore, when the high-throughput microporous core is moved by the micro-motion platform according to the target recognition result, the X-axis direction and the Y-axis direction are kept unchanged, so that the micro-motion platform performs relative motion adjustment in the Z-axis direction according to a preset step value, and at the same time, after each relative motion adjustment, the CCD is used to collect images of the high-throughput microporous chip to obtain multiple high-throughput microporous core collection images, and the high-throughput microporous core collection images are matched and stored in combination with the Z-axis coordinates.

[0016] Furthermore, the clarity of the high-throughput micro-hole core acquisition image is analyzed to determine the target position of the micro-motion platform, including:

[0017] The clarity of the images collected by the high-throughput micro-hole core is calculated respectively to obtain the image clarity judgment value;

[0018] Comparing the image clarity judgment values, and determining the maximum value of the image clarity judgment value;

[0019] The high-throughput micro-pore core acquisition image is locked according to the maximum value of the image clarity judgment value to obtain a target high-throughput micro-pore core acquisition image;

[0020] According to the target high-throughput micro-hole core acquisition image, the Z-axis coordinate corresponding to the target high-throughput micro-hole core acquisition image is retrieved in the storage information to determine the target position of the micro-motion platform.

[0021] Furthermore, the clarity calculation is performed for the high-throughput micro-hole core acquisition images, including:

[0022] Perform pixel analysis on the high-throughput micro-pore core acquisition image to determine the pixel points of the high-throughput micro-pore core acquisition image;

[0023] According to the pixel points of the high-throughput microporous core collection image, convolution analysis of edge detection operators in the horizontal direction and the vertical direction is performed respectively to obtain the first parameter data of the pixel point and the second parameter data of the pixel point;

[0024] Performing gradient calculation according to the first parameter data of the pixel point and the second parameter data of the pixel point to obtain a gradient value of the pixel point;

[0025] The pixel gradient value is combined with the edge detection threshold to determine the clarity judgment value of the high-throughput micro-hole core acquisition image, and the clarity judgment value of the high-throughput micro-hole core acquisition image is obtained.

[0026] Further, the first-end micropore preliminary identification, discrimination and calibration are performed based on the first target image of the high-throughput micropore chip, including:

[0027] Artificial intelligence AI deduction and self-training micropore data set model are used to perform first-end micropore query on the first target image of high-throughput micropore chip to obtain the micropore AI detection confidence value;

[0028] The first-end hole position is analyzed and judged according to the micro-hole AI detection confidence value. When the micro-hole AI detection confidence value is greater than the confidence threshold, the first-end micro-hole is determined;

[0029] Obtain the center point of the first end microhole, and perform difference analysis between the center point of the first end microhole and the center point of CCD acquisition to obtain a difference analysis result;

[0030] According to the difference analysis results, the center point of the first end microhole is moved to the CCD acquisition center point.

[0031] Furthermore, when performing secondary identification, discrimination and calibration of the first-end micropores based on the second target image of the high-throughput micropore chip, artificial intelligence AI deduction and self-training micropore data set model are used to perform secondary identification, discrimination and calibration of the first-end micropores for the second target image of the high-throughput micropore chip, including:

[0032] The self-trained micropore dataset model is called by artificial intelligence AI to perform the first-end micropore query in the second target image of the high-throughput micropore chip to obtain the micropore AI secondary detection confidence value;

[0033] According to the confidence value of the micropore AI secondary detection, the first-end micropore analysis and judgment is performed again to determine the first-end micropore and obtain the center point of the first-end micropore;

[0034] Perform secondary difference analysis on the center point of the micro-hole at the first end and the center point of CCD acquisition to obtain the secondary difference analysis result;

[0035] According to the result of the secondary difference analysis, the center point of the first end microhole is moved and adjusted to the CCD acquisition center point.

[0036] Furthermore, in the secondary calibration result, after obtaining the hole position data of the first end microhole, the hole position data of the first end microhole is saved, and the upper right end microhole is taken as the research object for preliminary identification, judgment and calibration of the upper right end microhole and secondary identification, judgment and calibration to obtain the hole position data of the upper right end microhole, and then the hole position data of the upper right end microhole is matched with the saved hole position data of the first end microhole, so as to analyze and calculate the rotation angle of the high-throughput microhole chip according to the hole position data of the first end microhole and the hole position data of the upper right end microhole.

[0037] Further, the rotation angle of the high-throughput micro-well chip is calculated based on the hole position data of the first end micro-well and the hole position data of the upper right end micro-well, including:

[0038] According to the hole position data of the first end micro-hole and the hole position data of the upper right end micro-hole, an offset analysis is performed in the X-axis direction to obtain the hole position coordinate difference in the X-axis direction;

[0039] According to the hole position data of the first end microhole and the hole position data of the upper right end microhole, an offset analysis is performed in the Y-axis direction to obtain the hole position coordinate difference in the Y-axis direction;

[0040] The rotation angle of the high-throughput microwell chip is determined by combining the hole coordinate difference in the X-axis direction and the hole coordinate difference in the Y-axis direction with trigonometric functions.

[0041] Furthermore, the rotation angle of the high-throughput microwell chip is used to revise the well position data, including:

[0042] Acquire the position information of the target microhole and obtain the theoretical hole position coordinate data of the target microhole;

[0043] The center distance is calculated according to the theoretical hole position coordinate data of the target microhole to obtain the distance between the target microhole and the center;

[0044] The target micropore angle is analyzed according to the theoretical pore position coordinate data of the target micropore, and the target micropore angle is revised using the rotation angle of the high-throughput micropore chip to obtain the revised target micropore angle;

[0045] The actual hole position coordinate data of the target microhole is calculated by combining the distance of the target microhole from the center with the revised angle of the target microhole to obtain the hole position positioning data of the target microhole.

[0046] Furthermore, the automatic hole position positioning method also includes verification analysis; the verification analysis is to select a microhole as a verification microhole for the target microhole after obtaining the hole position positioning data of multiple target microholes, identify the verification microhole, obtain the center of the verification microhole, perform difference analysis between the center point of the verification microhole and the CCD acquisition center point, obtain the verification analysis result of the verification microhole, and then make adjustments based on the verification analysis result of the verification microhole.

[0047] The present invention can automatically realize hole position identification and positioning, which can not only reduce the influence of human factors and avoid defocusing when the objective lens is moved to different areas of the chip for observation, thereby reducing the impact on cell signal collection and analysis, but also reduce micron-level high-throughput hole position deviation, improve the accuracy of hole position calibration, and improve the guarantee of high-throughput microporous chip for single cell screening and identification.

[0048] Other features and advantages of the present invention will be described in the following description, and partly become obvious from the description, or be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the application documents.

[0049] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0051] Figure 1 It is a schematic diagram of the steps of the automatic hole positioning method of the present invention;

[0052] Figure 2 Schematic diagram of a high-throughput microwell chip in the automatic well positioning method of the present invention;

[0053] Figure 3 This is an example diagram of micropore distribution of a high-throughput micropore chip in the automatic pore location method of the present invention;

[0054] Figure 4 This is a schematic diagram of step three in the hole position automatic positioning method of the present invention;

[0055] Figure 5 A schematic diagram of step A1 of step 3 in the automatic hole location method of the present invention;

[0056] Figure 6 This is a schematic diagram of step six of the hole position automatic positioning method of the present invention;

[0057] Figure 7 This is a schematic diagram of step seven of the hole position automatic positioning method of the present invention;

[0058] Figure 8 It is a schematic diagram of step eight in the hole position automatic positioning method of the present invention;

[0059] Fig. 9 This is a schematic diagram of step nine in the automatic hole positioning method described in the present invention. DETAILED DESCRIPTION

[0060] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0061] like Figure 1 As shown, an embodiment of the present invention provides a method for automatically locating wells based on a high-throughput microwell chip, comprising:

[0062] Step 1: Perform high-throughput microwell chip recognition on the target position to obtain the target recognition result;

[0063] Step 2: according to the target recognition result, the high-throughput micro-pore core is moved by the micro-motion platform, and the image of the high-throughput micro-pore core is acquired by CCD to obtain the high-throughput micro-pore core acquisition image;

[0064] Step 3: Analyze the clarity of the image collected by the high-throughput micro-hole core, determine the target position of the micro-motion platform, and then adjust the target movement of the micro-motion platform on the Z axis according to the target position of the micro-motion platform;

[0065] Step 4: Using CCD to collect target images of the high-throughput microporous chip to obtain a first target image of the high-throughput microporous chip;

[0066] Step 5: Perform preliminary identification, discrimination and calibration of the first-end micropores based on the first target image of the high-throughput micropore chip to obtain a first calibration result;

[0067] Step 6: adjusting the objective lens, and using the adjusted objective lens to acquire an image again based on the first calibration result, to obtain a second target image of the high-throughput microwell chip;

[0068] Step 7: Perform secondary identification, discrimination and calibration of the first-end micropores based on the second target image of the high-throughput micropore chip to obtain a secondary calibration result;

[0069] Step 8: In the secondary calibration result, the hole position data of the first end microhole is obtained, and the rotation angle of the high-throughput microhole chip is calculated based on the hole position data of the first end microhole and the hole position data of the upper right end microhole;

[0070] Step nine: determine the target micropore, and revise the hole position data using the rotation angle of the high-throughput micropore chip to obtain the hole position positioning data of the target micropore.

[0071] In the above technical solution, when the high-throughput microporous chip is identified for the target position, monitoring information is acquired for the target position to obtain the monitoring information of the target position, and then the target position monitoring information is analyzed to determine whether an object appears at the target position to obtain a preliminary analysis and judgment result, and the object is further identified based on the preliminary analysis and judgment result to determine the object information to obtain a preliminary object identification result, and when the object information is a high-throughput microporous chip based on the preliminary object identification result, a complete analysis is performed on the object, and when the object that appears is a complete object, a target identification result is obtained, and when the object that appears is not a complete object, the target position monitoring information within a subsequent preset time period is continued to be acquired, and a comparative analysis is performed on the target position monitoring information to determine whether subsequent adjustments have been made to the object that appears, and a secondary analysis and judgment result is obtained, and when the secondary analysis and judgment result is that the object that appears has not been subsequently adjusted, an object adjustment reminder is performed based on the target position until the object appears at the target position to meet the preset standard, and the target identification result is obtained, wherein the preset standard is usually a preset completeness of the appearance of the object at the target position, for example, the preset standard is 80% completeness of the object at the target position.

[0072] In the above technical solution, the target position usually refers to the chip clamp device, which is usually arranged on a micro-motion platform. When the high-throughput microporous chip is placed on the chip clamp device, the high-throughput microporous chip can be identified, so that the target identification result is the appearance of the high-throughput microporous chip.

[0073] In the above technical solution, when the target recognition result is the appearance of a high-throughput microporous chip, the high-throughput microporous chip is moved to the image acquisition area through the micro-motion platform, otherwise the high-throughput microporous chip recognition is continuously performed for the target position until a high-throughput microporous chip appears at the target position.

[0074] In the above technical solution, when CCD is used to collect target images for the high-throughput micro-well chip, the micro-motion platform adjusted based on the target movement collects target images for the high-throughput micro-well chip through CCD.

[0075] In the above technical solution, the upper right micropore refers to the upper right micropore in the high-throughput micropore chip, which is the rightmost micropore in the X-axis direction and the topmost micropore in the Y-axis direction of the high-throughput micropore chip.

[0076] In the above technical scheme, the hole position data of the upper right microhole is obtained in the same way as the hole position data of the head end microhole. It is only necessary to adjust the analysis object in the process of obtaining the hole position data of the head end microhole from the head end microhole to the upper right microhole to obtain the hole position data of the upper right microhole.

[0077] In the above technical solution, when adjusting the objective lens, the objective lens is controlled to switch to a 4x fine lens.

[0078] In the above technical solution, if Figure 2 As shown, the high-throughput microporous chip usually has a chip length of 30 to 50 mm and a chip width of 15 to 30 mm, and the upper surface of the chip includes a functional area and a non-functional area, the non-functional area provides a larger contact area with the fixture to increase the clamping stability; the functional area is 15 to 20 mm long, the functional area is 5 to 10 mm wide, the functional area is located in the center of the chip, 3 to 8 mm from the upper and lower edges of the chip, 8 to 15 mm from the left and right edges of the chip, preferably, 5 mm from the upper and lower edges of the chip, and 10 mm from the left and right edges of the chip; the functional area includes 8 microporous arrays and 9 recognition sites, each microporous array occupies a square area of ​​5 mm*5 mm, which is used to adapt to the 4x microscope field of view recognition, and the recognition site is used for computer recognition and calibration; wherein the micropore diameter is 10um to 50um, such as Figure 3 As shown, the micropores are arranged in a regular hexagonal pattern, and the center distance between each micropore and the six adjacent micropores is equal.

[0079] The above technical solution realizes the automatic identification and positioning of the hole position of the micropores in the high-throughput micropore chip without human intervention, reduces the influence of human factors, avoids the defocusing phenomenon when the objective lens moves to different areas of the chip for observation, and thus reduces the impact on the collection and analysis of cell signals, and can reduce the micron-level high-throughput hole position deviation, improve the accuracy of hole position calibration, and thus improve the guarantee of high-throughput micropore chip for single cell screening and identification. By analyzing the clarity of the image collected by the high-throughput micropore core, the position with the highest clarity is determined, and then the objective lens focus is adaptive, which can not only lock the image acquisition position with the highest clarity and reduce the influence of defocusing, but also realize the automatic intelligent adjustment of the micro-motion stage movement without human intervention, reduce the deviation of the micro-motion stage movement deviation that will cause the micro-level high-throughput hole position on the X and Y axes, avoid physical distortion, and provide guarantee for cell screening and identification of high-throughput micropore chips. Moreover, by performing preliminary identification, judgment and calibration as well as secondary identification, judgment and calibration, the accuracy can be optimized step by step, the error of automatic hole positioning can be reduced, the accuracy of hole calibration can be guaranteed, and the deviation of hole recognition can be reduced, so that cell analysis can be performed more accurately when cells are screened and identified based on high-throughput microwell chips. In addition, the field of view can be improved by adjusting the objective lens between preliminary identification, judgment and calibration and secondary identification, judgment and calibration, so as to improve the quality of the second target image of the high-throughput microwell chip, so that the secondary identification, judgment and calibration can be performed based on a more accurate image, optimize the calibration error, improve the accuracy of calculating the rotation angle of the high-throughput microwell chip, and further ensure the accuracy of the hole positioning data of the target microwell.

[0080] In one embodiment provided by the present invention, when the high-throughput microporous core is moved by the micro-motion platform according to the target recognition result, the X-axis direction and the Y-axis direction are kept unchanged, so that the micro-motion platform performs relative motion adjustment in the Z-axis direction according to a preset step value, and at the same time, after each relative motion adjustment, the CCD is used to collect images of the high-throughput microporous chip to obtain multiple high-throughput microporous core collection images, and the high-throughput microporous core collection images are matched and stored in combination with the Z-axis coordinates.

[0081] In the above technical solution, when the micro-motion platform performs relative motion adjustment in the Z-axis direction according to the preset step value, the relative motion adjustment is performed by the same distance upward and downward in the Z-axis direction, for example, 2 cm upward and 2 cm downward respectively.

[0082] In the above technical solution, the preset step value is usually 0.01 mm, and can also be adjusted in size according to needs.

[0083] In the above technical solution, a high-throughput micro-pore core acquisition image is obtained after each step value is adjusted, and each high-throughput micro-pore core acquisition image corresponds to a Z-axis coordinate during image acquisition.

[0084] In the above technical solution, the high-throughput micropore core acquisition image is matched and stored in combination with the Z-axis coordinate. The Z-axis coordinate is the position information of the micro-motion platform on the Z-axis when the high-throughput micropore core acquisition image is acquired. When the high-throughput micropore core acquisition image is matched and stored in combination with the Z-axis coordinate, the high-throughput micropore core acquisition image and the corresponding Z-axis coordinate are stored in the running memory according to the relative motion step adjustment order.

[0085] The above technical solution moves on the Z axis while keeping the X and Y axes unchanged, avoiding the deviation of the micron-level high-throughput wells on the X and Y axes caused by the movement of the micro-motion stage, reducing the deviation in well identification, and thus reducing the impact on cell signal collection and analysis. The micro-motion platform makes relative motion adjustments in the Z axis direction according to the preset step value, so that observations can be made within a certain range of the Z axis, and the motion adjustment is made using the preset step value, which can effectively improve the observation efficiency while ensuring the comprehensiveness of the observation.

[0086] like Figure 4 As shown, in one embodiment provided by the present invention, analyzing the clarity of the high-throughput micro-hole core acquisition image and determining the target position of the micro-motion platform includes:

[0087] A1. Calculate the clarity of the high-throughput micro-hole core collected images to obtain the image clarity judgment value;

[0088] A2. Compare the image clarity judgment values ​​to determine the maximum value of the image clarity judgment value;

[0089] A3, locking the high-throughput micro-pore core acquisition image according to the maximum value of the image clarity judgment value, and obtaining the target high-throughput micro-pore core acquisition image;

[0090] A4. According to the target high-throughput micro-hole core acquisition image, the Z-axis coordinate corresponding to the target high-throughput micro-hole core acquisition image is retrieved from the storage information to determine the target position of the micro-motion platform.

[0091] In the above technical solution, when the clarity calculation is performed for each stored high-throughput micro-pore core acquisition image, the same clarity calculation method is used to perform clarity calculation for each high-throughput micro-pore core acquisition image in the running memory.

[0092] In the above technical solution, when comparing the image clarity judgment values, the larger values ​​are screened out by comparing the image clarity judgment values ​​in pairs, thereby obtaining the maximum value of the image clarity judgment value.

[0093] In the above technical solution, the high-throughput micro-hole core acquisition image corresponding to the maximum value of the image clarity judgment value is the clearest image.

[0094] The above technical solution determines the optimal position of Z-axis movement through the clarity of the image collected by the high-throughput micropore core, so that subsequent analysis and processing can be carried out based on clearer images, avoiding the difficulty of micropore positioning caused by defocusing of the objective lens, and improving the quality of the first target image of the high-throughput micropore chip and the second target image of the high-throughput micropore chip, providing more accurate information for subsequent recognition, judgment and correction, ensuring calibration accuracy, and thereby improving the accuracy of automatic hole positioning.

[0095] like Figure 5 As shown, in one embodiment provided by the present invention, the clarity calculation is performed for the high-throughput micro-hole core acquisition images respectively, including:

[0096] B1. Perform pixel analysis on the high-throughput micro-pore core acquisition image to determine the pixel points of the high-throughput micro-pore core acquisition image;

[0097] B2. Perform convolution analysis of edge detection operators in the horizontal direction and the vertical direction respectively according to the pixel points of the high-throughput microporous core acquisition image to obtain the first parameter data of the pixel point and the second parameter data of the pixel point;

[0098] B3, performing gradient calculation according to the first parameter data of the pixel point and the second parameter data of the pixel point to obtain a gradient value of the pixel point;

[0099] B4. The pixel gradient value is combined with the edge detection threshold to determine the clarity judgment value of the high-throughput micro-pore core acquisition image, thereby obtaining the clarity judgment value of the high-throughput micro-pore core acquisition image.

[0100] In the above technical solution, when performing convolution analysis of edge detection operators in the horizontal direction and the vertical direction respectively according to the high-throughput microporous core collected image pixels, the convolution of the edge detection operator in the horizontal direction is obtained according to the edge detection convolution kernel to obtain the first parameter data of the pixel point, and the convolution of the edge detection operator in the vertical direction is obtained according to the edge detection convolution kernel to obtain the second parameter data of the pixel point, wherein the edge detection convolution kernel includes the edge detection convolution kernel j in the horizontal direction. x and vertical edge detection convolution kernel j y , j x That is the first parameter data of the pixel point, expressed as: j y That is the second parameter data of the pixel point, expressed as:

[0101] In the above technical solution, the edge detection threshold is determined based on the distribution of objects in the image collected by the high-throughput micro-hole core.

[0102] In the above technical solution, when the gradient is calculated according to the first parameter data of the pixel point and the second parameter data of the pixel point, the gradient value of the pixel point is obtained by the following formula:

[0103]

[0104] Among them, J(x,y) is the gradient value of the pixel point (x,y), j x (x, y) is the first parameter data of the pixel point (x, y), j y (x, y) is the second parameter data of the pixel point (x, y).

[0105] In the above technical solution, the pixel gradient value is combined with the edge detection threshold to determine the clarity judgment value, and the pixel points that meet the edge range are screened according to the edge detection threshold. Then, the pixel gradient values ​​of the pixel points that meet the edge range are accumulated to obtain the image clarity judgment value R(f) of the high-throughput microporous core acquisition image, that is: R(f) = ∑ y ∑ x |J(x,y)|.

[0106] The above technical scheme quantifies the quality of the high-throughput micropore core acquisition image, so that the better position of the high-throughput micropore core acquisition image during acquisition can be determined by the size of the clarity, and can efficiently realize automatic intelligent determination without human participation, thereby ensuring the accuracy of the target position of the micro-motion platform, reducing the target movement adjustment error, and reducing the impact of the defocus phenomenon, so that subsequent analysis and processing can be based on the image with clear angles, reducing the error caused by image pixels, and avoiding the problem of difficulty in micropore positioning caused by defocusing of the objective lens; and the gradient between pixel points is used for clarity analysis, so that the clarity judgment value of the high-throughput micropore core acquisition image can be determined more comprehensively based on the high-throughput micropore core acquisition image, thereby improving the accuracy of the clarity judgment value of the high-throughput micropore core acquisition image.

[0107] like Figure 6 As shown, in one embodiment provided by the present invention, preliminary identification, discrimination and calibration of the first end micropores are performed based on the first target image of the high-throughput micropore chip, including:

[0108] C1. Use artificial intelligence AI deduction and self-training micropore data set model to perform first-end micropore query on the first target image of high-throughput micropore chip to obtain the micropore AI detection confidence value;

[0109] C2. Analyze and judge the first-end hole position according to the micro-hole AI detection confidence value. When the micro-hole AI detection confidence value is greater than the confidence threshold, the first-end micro-hole is determined;

[0110] C3, obtaining the center point of the first end microhole, and performing difference analysis between the center point of the first end microhole and the center point of CCD acquisition to obtain a difference analysis result;

[0111] C4. Move the center point of the first end microhole to the CCD acquisition center point according to the difference analysis results.

[0112] In the above technical solution, the confidence threshold is preset and is usually set to 0.95.

[0113] In the above technical solution, the self-training micropore data set model is obtained by learning and training after marking a large number of chip hole position images. The AI ​​artificial intelligence will use this model to find micropores in the image data collected by the CCD and return a confidence value to determine whether the image is a first-end micropore.

[0114] The above technical solution realizes preliminary recognition and calibration of the first-end micropores of the high-throughput micropore chip by performing preliminary recognition, discrimination and calibration of the first-end micropores based on the high-throughput micropore chip on the adjusted micro-motion platform. Artificial intelligence AI deduction and self-training micropore data set model are used to perform micropore query on the chip adjustment collected image, realizing the combination of self-training micropore data set model and artificial intelligence, realizing automatic recognition, discrimination and calibration, and being able to quickly and accurately determine the first-end micropores, and then realizing calibration with the first-end hole position as the research object, thereby improving the efficiency of recognition, discrimination and calibration, and ensuring the accuracy of recognition, discrimination and calibration.

[0115] like Figure 7 As shown, in one embodiment provided by the present invention, when performing secondary identification, discrimination and calibration of the first-end micropores based on the second target image of the high-throughput micropore chip, artificial intelligence AI deduction and self-training micropore data set model are used to perform secondary identification, discrimination and calibration of the first-end micropores for the second target image of the high-throughput micropore chip, including:

[0116] D1. Use artificial intelligence AI to call the self-trained micropore data set model to perform the first-end micropore query in the second target image of the high-throughput micropore chip to obtain the micropore AI secondary detection confidence value;

[0117] D2. According to the confidence value of the micropore AI secondary detection, the first-end micropore analysis and judgment are performed again to determine the first-end micropore and obtain the center point of the first-end micropore;

[0118] D3, performing secondary difference analysis on the center point of the micro-hole at the first end and the center point of CCD acquisition to obtain the secondary difference analysis result;

[0119] D4. According to the result of the secondary difference analysis, the center point of the first end microhole is moved and adjusted to the CCD acquisition center point.

[0120] In the above technical solution, when the micropore center point is moved and adjusted to the CCD acquisition center point according to the secondary difference analysis result, the X-axis and Y-axis are moved in combination with the secondary difference data to move the micropore center point to the CCD acquisition center point.

[0121] In the above technical solution, the steps of secondary identification, judgment and calibration of the first-end micropores based on the second target image of the high-throughput micropore chip are roughly the same as the steps of preliminary identification, judgment and calibration of the first-end micropores based on the high-throughput micropore chip on the adjusted micro-motion platform.

[0122] In the above technical solution, when the center point of the first end micropore is subjected to difference analysis with the center point of CCD acquisition, the accuracy of the difference analysis is higher than the accuracy of the difference analysis in the process of preliminary identification, judgment and calibration of the first end micropore based on the high-throughput micropore chip on the adjusted micro-motion platform.

[0123] The above technical scheme realizes secondary identification, judgment and calibration of the first calibration result, further reduces the error of the first calibration result, optimizes the calibration deviation of the high-throughput micropore chip, and makes it possible to obtain the hole position data of the first end micropore more accurately, thereby improving the accuracy of the rotation angle of the high-throughput micropore chip, thereby reducing the error when locating the target micropore hole position, ensuring the accuracy of the hole position positioning data of the target micropore, and improving the accuracy of automatic hole position positioning.

[0124] In one embodiment provided by the present invention, in the secondary calibration result, after obtaining the hole position data of the first end microhole, the hole position data of the first end microhole is saved, and at the same time, the upper right end microhole is taken as a research object for preliminary identification, judgment and calibration of the upper right end microhole and secondary identification, judgment and calibration to obtain the hole position data of the upper right end microhole, and then the hole position data of the upper right end microhole is matched with the saved hole position data of the first end microhole, so as to analyze and calculate the rotation angle of the high-throughput microhole chip according to the hole position data of the first end microhole and the hole position data of the upper right end microhole.

[0125] In the above technical scheme, the steps of taking the upper right end microhole as the research object and acquiring the hole position data of the upper right end microhole are similar to the steps of acquiring the hole position data of the first end microhole. It is only necessary to adjust the research object in the step of acquiring the hole position data of the first end microhole from the first end microhole to the upper right end microhole.

[0126] The above technical solution saves the hole position data of the microhole at the first end, making it convenient to match after waiting for the hole position data of the microhole at the upper right end to be obtained, avoiding data confusion, ensuring the orderly implementation of the automatic hole positioning method, avoiding data confusion that leads to errors in the calculation of the rotation angle of the high-throughput microhole chip, and reducing the error probability of the rotation angle of the high-throughput microhole chip.

[0127] like Figure 8 As shown, in one embodiment provided by the present invention, the rotation angle of the high-throughput micropore chip is calculated based on the hole position data of the first end micropore and the hole position data of the upper right end micropore, including:

[0128] E1. Perform an offset analysis in the X-axis direction based on the hole position data of the first end microhole and the hole position data of the upper right end microhole to obtain the hole position coordinate difference in the X-axis direction;

[0129] E2. Perform an offset analysis in the Y-axis direction based on the hole position data of the first end microhole and the hole position data of the upper right end microhole to obtain the hole position coordinate difference in the Y-axis direction;

[0130] E3. Determine the rotation angle of the high-throughput microwell chip by combining the X-axis coordinate difference and the Y-axis coordinate difference with trigonometric functions.

[0131] In the above technical solution, when the X-axis direction hole position coordinate difference and the Y-axis direction hole position coordinate difference are combined with trigonometric functions to determine the rotation angle of the high-throughput microwell chip, α=arctan((P wy -P sy ) / (P wx -P sx )) to obtain the rotation angle α of the high-throughput microwell chip, where P wy -P sy is the hole coordinate difference in the Y-axis direction, P wx -P sx is the coordinate difference of the hole position in the X-axis direction, P wy and P wx are the Y-axis coordinate data and X-axis coordinate data of the hole position data of the upper right microhole, P sy and P sx They are respectively the Y-axis coordinate data and the X-axis coordinate data of the hole position data of the first end microhole.

[0132] The above technical solution calculates the rotation angle of the high-throughput microporous chip and digitizes the deviation of the position of the high-throughput microporous chip during the processing of the high-throughput microporous chip, so that the influence of the position deviation of the high-throughput microporous chip is taken into account when the hole position is automatically positioned, thereby improving the accuracy of the automatic hole position positioning. Moreover, determining the rotation angle of the high-throughput microporous chip in the form of coordinate data can not only quickly obtain the rotation angle of the high-throughput microporous chip, but also is very simple and not prone to calculation errors, thereby ensuring the correctness of the rotation angle of the high-throughput microporous chip.

[0133] like Fig. 9 As shown, in one embodiment provided by the present invention, the rotation angle of the high-throughput micro-well chip is used to revise the well position data, including:

[0134] S1, obtaining the position information of the target microhole and obtaining the theoretical hole position coordinate data of the target microhole;

[0135] S2, calculating the center distance according to the theoretical hole position coordinate data of the target microhole to obtain the distance between the target microhole and the center;

[0136] S3, analyzing the target micropore angle according to the theoretical pore position coordinate data of the target micropore, and revising the target micropore angle using the rotation angle of the high-throughput micropore chip to obtain a revised target micropore angle;

[0137] S4. Calculate the actual hole position coordinate data of the target microhole by combining the distance from the center of the target microhole with the revised angle of the target microhole to obtain the hole position positioning data of the target microhole.

[0138] In the above technical solution, when calculating the center distance according to the theoretical hole position coordinate data of the target microhole, Get the distance △L from the center of the target micropore, where P ly and P lx It is the theoretical hole position coordinate data of the target microhole.

[0139] In the above technical solution, the target micropore angle is analyzed according to the theoretical pore coordinate data of the target micropore, and the target micropore angle is revised using the rotation angle of the high-throughput micropore chip. The target micropore revised angle β is obtained by the following formula:

[0140] β=arctan(P ly / p lx )+α

[0141] Wherein, α is the rotation angle of the high-throughput microwell chip.

[0142] In the above technical solution, the distance from the target microhole to the center is combined with the target microhole revised angle to calculate the actual hole coordinate data of the target microhole, through rx = △Lcos (arctan (P ly / p lx )+α) to obtain the X-axis actual hole coordinate data of the target microhole, and through ry=△Lsin(arctan(P ly / p lx )+α) to obtain the actual hole position coordinate data of the target microhole on the Y axis.

[0143] The above technical scheme enables the hole position data to be revised directly using the rotation angle of the high-throughput micropore chip when positioning the target micropore, thereby obtaining the actual hole coordinates of the target micropore, and can effectively eliminate the placement deviation of the high-throughput micropore chip on the chip fixture device. It can not only ensure the accuracy of hole positioning, but also increase the accuracy of the hole positioning data, thereby improving the accuracy of automatic hole positioning.

[0144] In one embodiment provided by the present invention, the automatic hole position positioning method also includes verification analysis; the verification analysis is to select a microhole as a verification microhole for the target microhole after obtaining the hole position positioning data of multiple target microholes, identify the verification microhole, obtain the center of the verification microhole, perform difference analysis between the center point of the verification microhole and the CCD acquisition center point, obtain the verification analysis result of the verification microhole, and then make adjustments based on the verification analysis result of the verification microhole.

[0145] In the above technical solution, each microwell in the high-throughput microwell chip can be used as a target microwell for automatic hole position positioning.

[0146] In the above technical solution, when a micropore is selected as a verification micropore for a target micropore, any one of the multiple target micropores is selected as a verification micropore to verify the hole position positioning data.

[0147] In the above technical solution, when adjustment is made according to the verification analysis result of the verification micropore, if the verification analysis result of the verification micropore is a difference analysis result whose value is 0, no adjustment is required; if the verification analysis result of the verification micropore is a difference analysis result whose value is not 0, the center point of the verification micropore is moved to the CCD acquisition center point according to the difference analysis result.

[0148] In the above technical scheme, when identifying the verification micropores, artificial intelligence AI deduction and self-training micropore data set model are used to verify the micropore identification and discrimination for the second target image of the high-throughput micropore chip to obtain the micropore AI detection confidence value; then a judgment is made based on the micropore AI detection confidence value, and when the micropore AI detection confidence value is greater than the confidence threshold, the verification micropore is determined; and then the center point of the verification micropore is obtained, thereby obtaining the verification micropore center point.

[0149] The above technical solution further ensures the accuracy of the hole position positioning data of the target micropores by using verification micropores for verification, effectively improves the precision of the hole position positioning of the target micropores, and thus ensures the comprehensiveness and accuracy of cell screening and identification based on high-throughput micropore chips.

[0150] Those skilled in the art should understand that the first and second in the present invention merely refer to different application stages.

[0151] Other embodiments of the present disclosure will be readily apparent to those skilled in the art after considering the specification and practicing the disclosure disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the following claims.

[0152] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for automatic well positioning based on a high-throughput microwell chip, characterized in that: include: Perform high-throughput microwell chip identification on the target position to obtain the target identification result; According to the target recognition result, the high-throughput micro-pore core is moved by the micro-motion platform, and the image of the high-throughput micro-pore core is acquired by CCD to obtain the high-throughput micro-pore core acquisition image; Analyze the clarity of the image collected by the high-throughput micro-hole core, determine the target position of the micro-motion platform, and then adjust the target movement of the micro-motion platform on the Z axis according to the target position of the micro-motion platform; Using CCD to collect target images of the high-throughput microwell chip, and obtaining the first target image of the high-throughput microwell chip; Performing preliminary identification, discrimination and calibration of the first-end micropores based on the first target image of the high-throughput micropore chip to obtain a first calibration result; Adjusting the objective lens, and facilitating the adjusted objective lens to acquire an image again based on the first calibration result, to obtain a second target image of the high-throughput microwell chip; Based on the second target image of the high-throughput micropore chip, the first-end micropore secondary identification, discrimination and calibration are performed to obtain the secondary calibration result; In the secondary calibration result, the hole position data of the first end microhole is obtained, and the rotation angle of the high-throughput microhole chip is analyzed and calculated based on the hole position data of the first end microhole and the hole position data of the upper right end microhole; The target micropore is determined, and the hole position data is revised using the rotation angle of the high-throughput micropore chip to obtain the hole position positioning data of the target micropore.

2. The automatic hole positioning method according to claim 1, characterized in that: When the high-throughput microporous core is moved by the micro-motion platform according to the target recognition result, the X-axis direction and the Y-axis direction are kept unchanged, so that the micro-motion platform performs relative motion adjustment in the Z-axis direction according to the preset step value, and at the same time, after each relative motion adjustment, the CCD is used to collect images for the high-throughput microporous chip to obtain multiple high-throughput microporous core collection images, and the high-throughput microporous core collection images are matched and stored in combination with the Z-axis coordinates.

3. The automatic hole positioning method according to claim 2, characterized in that: Analyze the clarity of high-throughput micro-hole core acquisition images and determine the target position of the micro-motion platform, including: The clarity of the images collected by the high-throughput micro-hole core is calculated respectively to obtain the image clarity judgment value; Comparing the image clarity judgment values, and determining the maximum value of the image clarity judgment value; The high-throughput micro-pore core acquisition image is locked according to the maximum value of the image clarity judgment value to obtain a target high-throughput micro-pore core acquisition image; According to the target high-throughput micro-hole core acquisition image, the Z-axis coordinate corresponding to the target high-throughput micro-hole core acquisition image is retrieved in the storage information to determine the target position of the micro-motion platform.

4. The automatic hole positioning method according to claim 3, characterized in that: The clarity calculations are performed for high-throughput micro-hole core acquisition images, including: Perform pixel analysis on the high-throughput micro-pore core acquisition image to determine the pixel points of the high-throughput micro-pore core acquisition image; According to the pixel points of the high-throughput microporous core collected image, convolution analysis of edge detection operators in the horizontal direction and the vertical direction is performed respectively to obtain the first parameter data of the pixel point and the second parameter data of the pixel point; Performing gradient calculation according to the first parameter data of the pixel point and the second parameter data of the pixel point to obtain a gradient value of the pixel point; The pixel gradient value is combined with the edge detection threshold to determine the clarity judgment value of the high-throughput micro-hole core acquisition image, and the clarity judgment value of the high-throughput micro-hole core acquisition image is obtained.

5. The automatic hole positioning method according to claim 1, characterized in that: Based on the first target image of the high-throughput microwell chip, the first-end microwell preliminary identification, judgment and calibration are performed, including: Artificial intelligence AI deduction and self-training micropore data set model are used to perform first-end micropore query on the first target image of high-throughput micropore chip to obtain the micropore AI detection confidence value; The first-end hole position is analyzed and judged according to the micro-hole AI detection confidence value. When the micro-hole AI detection confidence value is greater than the confidence threshold, the first-end micro-hole is determined; Obtain the center point of the first end microhole, and perform difference analysis between the center point of the first end microhole and the center point of CCD acquisition to obtain a difference analysis result; According to the difference analysis results, the center point of the first end microhole is moved to the CCD acquisition center point.

6. The automatic hole positioning method according to claim 1, characterized in that: When performing secondary identification, judgment and calibration of the first-end micropores based on the second target image of the high-throughput micropore chip, artificial intelligence AI deduction and self-training micropore data set model are used to perform secondary identification, judgment and calibration of the first-end micropores for the second target image of the high-throughput micropore chip, including: The self-trained micropore dataset model is called by artificial intelligence AI to perform the first-end micropore query in the second target image of the high-throughput micropore chip to obtain the micropore AI secondary detection confidence value; According to the confidence value of the micropore AI secondary detection, the first-end micropore analysis and judgment are performed again to determine the first-end micropore and obtain the center point of the first-end micropore; Perform secondary difference analysis on the center point of the micro-hole at the first end and the center point of CCD acquisition to obtain the secondary difference analysis result; According to the result of the secondary difference analysis, the center point of the first end microhole is moved and adjusted to the CCD acquisition center point.

7. The automatic hole positioning method according to claim 1, characterized in that: In the secondary calibration result, after obtaining the hole position data of the first end microhole, the hole position data of the first end microhole is saved, and the upper right end microhole is taken as the research object for preliminary identification, judgment and calibration of the upper right end microhole and secondary identification, judgment and calibration to obtain the hole position data of the upper right end microhole, and then the hole position data of the upper right end microhole is matched with the saved hole position data of the first end microhole, so as to analyze and calculate the rotation angle of the high-throughput microhole chip according to the hole position data of the first end microhole and the hole position data of the upper right end microhole.

8. The automatic hole positioning method according to claim 7, characterized in that: The rotation angle of the high-throughput microwell chip is calculated based on the hole position data of the first end microwell and the hole position data of the upper right end microwell, including: According to the hole position data of the first end micro-hole and the hole position data of the upper right end micro-hole, an offset analysis is performed in the X-axis direction to obtain the hole position coordinate difference in the X-axis direction; According to the hole position data of the first end microhole and the hole position data of the upper right end microhole, an offset analysis is performed in the Y-axis direction to obtain the hole position coordinate difference in the Y-axis direction; The rotation angle of the high-throughput microwell chip is determined by combining the hole coordinate difference in the X-axis direction and the hole coordinate difference in the Y-axis direction with trigonometric functions.

9. The automatic hole positioning method according to claim 1, characterized in that: The rotation angle of the high-throughput microwell chip is used to revise the well position data, including: Acquire the position information of the target microhole and obtain the theoretical hole position coordinate data of the target microhole; The center distance is calculated according to the theoretical hole position coordinate data of the target microhole to obtain the distance between the target microhole and the center; The target micropore angle is analyzed according to the theoretical pore position coordinate data of the target micropore, and the target micropore angle is revised using the rotation angle of the high-throughput micropore chip to obtain the revised target micropore angle; The actual hole position coordinate data of the target microhole is calculated by combining the distance of the target microhole from the center with the revised angle of the target microhole to obtain the hole position positioning data of the target microhole.

10. The automatic hole positioning method according to claim 1, characterized in that: The automatic hole position positioning method also includes verification analysis; the verification analysis is to select a microhole as a verification microhole for the target microhole after obtaining the hole position positioning data of multiple target microholes, identify the verification microhole, obtain the center of the verification microhole, perform difference analysis on the center point of the verification microhole and the CCD acquisition center point, obtain the verification analysis result of the verification microhole, and then make adjustments based on the verification analysis result of the verification microhole.