Reagent tube position analysis method and system for kit

Abstract

The invention discloses a reagent tube position analysis method and system for a kit, and the method comprises the steps: inputting a reagent tube image into a preset image recognition model, and outputting to obtain each target reagent tube image containing a labeling box, determining reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; according to the reagent tube standard position table, a preset position verification rule is adopted to verify the reagent tube position information of each reagent tube in each target reagent tube image, and whether each reagent tube in each target reagent tube image meets a preset requirement or not is judged; and if the at least one reagent tube does not meet the preset requirement, defining the at least one reagent tube as an abnormal reagent tube, and predicting the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy. And the possible position of the reagent tube can be marked and predicted in time, so that the problems of reagent pollution, disordered experiment steps and the like caused by dislocation of the reagent tube are effectively avoided.

Description

Technical Field

[0001] The present invention belongs to the technical field of reagent tube image recognition, and particularly relates to a method and system for analyzing the positions of reagent tubes in a reagent kit. Background Art

[0002] In many fields such as biomedicine, chemical analysis, and clinical testing, the reagent kit is a key tool for storing and transporting reagents. The correct placement and position management of the reagent tubes inside it are crucial. The position accuracy of the reagent tubes is directly related to the convenience of subsequent experimental operations, the reliability of experimental results, and the detection efficiency. For example, in an automated experimental process, the robotic arm needs to accurately grasp the reagent tubes for operations such as sample addition and pipetting. If the positions of the reagent tubes deviate, it may lead to the failure of the robotic arm to grasp, reagent contamination, or confusion in experimental procedures, thus affecting the smooth progress of the entire experimental process.

[0003] Currently, the traditional methods for managing the positions of reagent tubes in reagent kits mainly rely on manual visual inspection or simple mechanical positioning devices. Manual visual inspection is not only inefficient, but also prone to missed inspections or misinspections due to human factors (such as fatigue, negligence), and it cannot meet the requirements of large-scale and high-intensity detections. Summary of the Invention

[0004] The present invention provides a method and system for analyzing the positions of reagent tubes in a reagent kit to solve the technical problem of missed inspections or misinspections easily caused by human factors (such as fatigue, negligence).

[0005] In a first aspect, the present invention provides a method for analyzing the positions of reagent tubes in a reagent kit, including: Obtaining reagent tube images at different positions of a reagent kit located at a detection position, wherein the reagent tube images include the grooves of the reagent kit and the reagent tubes in the grooves; Inputting each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; According to a pre-constructed reagent tube standard position table, using a preset position verification rule to verify the reagent tube position information of each reagent tube in each target reagent tube image, and judging whether each reagent tube in each target reagent tube image meets the preset requirements according to the verification result, the preset requirements are: the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; If at least one reagent tube does not meet the preset requirements, then define the at least one reagent tube as an abnormal reagent tube, and predict the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain each predicted position information.

[0006] In a second aspect, the present invention provides a reagent tube position analysis system for a reagent kit, comprising: An acquisition module configured to acquire reagent tube images at different positions of a reagent kit located at a detection position, wherein the reagent tube images include grooves of the reagent kit and reagent tubes in the grooves; An output module configured to input each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; A judgment module configured to, according to a pre-constructed reagent tube standard position table, use a preset position verification rule to verify the reagent tube position information of each reagent tube in each target reagent tube image, and judge whether each reagent tube in each target reagent tube image meets a preset requirement according to the verification result, the preset requirement being that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; A prediction module configured to, if at least one reagent tube does not meet the preset requirement, define the at least one reagent tube as an abnormal reagent tube, and predict the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain each predicted position information.

[0007] In a third aspect, there is provided an electronic device, which includes: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the steps of the method for analyzing the position of a reagent tube for a reagent kit according to any embodiment of the present invention.

[0008] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the program instructions are executed by a processor, the processor is enabled to execute the steps of the method for analyzing the position of a reagent tube for a reagent kit according to any embodiment of the present invention.

[0009] The reagent tube position analysis method and system for a reagent kit of the present application utilize an image recognition model to automatically acquire and analyze reagent tube images, quickly determine the reagent tube position information. Compared with traditional manual visual inspection, it greatly shortens the position detection time and realizes the efficient recognition of the reagent tube position. At the same time, this method can be seamlessly docked with automated experimental equipment (such as a robotic arm), providing accurate position guidance for subsequent automated operations, significantly improving the automation level of the entire detection process, enabling large-scale and high-intensity detection tasks to be efficiently completed. And by constructing a two-dimensional coordinate system and performing position verification according to a preset reagent tube standard position table, this solution can accurately judge whether the reagent tube position meets the requirements. Once an abnormal reagent tube is found, it can be marked in time and its possible position can be predicted, effectively avoiding problems such as reagent contamination and experimental procedure confusion caused by reagent tube misalignment, ensuring the accuracy of experimental operations from the source, and thus improving the reliability and repeatability of experimental results. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0011] Figure 1 It is a flowchart of a reagent tube position analysis method for a reagent kit provided by an embodiment of the present invention; Figure 2 It is a structural block diagram of a reagent tube position analysis system for a reagent kit provided by an embodiment of the present invention; Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0013] Please refer to Figure 1 , which shows a flowchart of a reagent tube position analysis method for a reagent kit of the present application.

[0014] As Figure 1 shown, the reagent tube position analysis method for a reagent kit specifically includes the following steps: Step S101: Obtain reagent tube images at different positions of a reagent kit located at a detection position, where the reagent tube images include the grooves of the reagent kit and the reagent tubes in the grooves.

[0015] Step S102: Input each reagent tube image into a preset image recognition model. The image recognition model outputs each target reagent tube image containing a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system.

[0016] In this step, input a certain reagent tube image into the image recognition model. The image recognition model annotates the reagent tube label and the groove in the reagent tube image to obtain a first bounding box containing the reagent tube label and a second bounding box containing the groove, where a certain reagent tube image is any one of the reagent tube images; the image recognition model outputs a certain target reagent tube image containing each first bounding box and each second bounding box, where the reagent tube label is located on the reagent tube; construct a two-dimensional coordinate system, and determine the first coordinate position of each first bounding box and the second coordinate position of each second bounding box in a certain target reagent tube image according to the two-dimensional coordinate system, where the vertex of a certain target reagent tube image coincides with the origin of the two-dimensional coordinate system, and the edge line of a certain reagent tube image is aligned with the axis of the two-dimensional coordinate system; associate a certain first bounding box and a certain second target bounding box with the shortest distance between them, and define the first coordinate position in a certain first bounding box as the reagent tube position information of the reagent tube where a certain second target bounding box is located.

[0017] It should be noted that the image recognition model can be obtained by training a neural network with training samples and bounding boxes for annotating the training samples.

[0018] Step S103: According to a pre-constructed reagent tube standard position table, use a preset position verification rule to verify the reagent tube position information of each reagent tube in each target reagent tube image, and determine whether each reagent tube in each target reagent tube image meets the preset requirements according to the verification result. The preset requirement is that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table.

[0019] In this step, the reagent tube position information of each reagent tube in a certain target reagent tube image is compared with the reagent tube standard position information in the reagent tube standard position table; if the comparison result of the reagent tube position information of at least one reagent tube is consistent with the reagent tube standard position information in the reagent tube standard position table, then the at least one reagent tube is positioned as a standard reagent tube, and the groove where the standard reagent tube is located is defined as a standard groove; the standard groove is determined in another target reagent tube image according to the sorting position of the standard groove in the certain target reagent tube image, and the reagent tube position information of other reagent tubes in the other target reagent tube image is compared with the reagent tube standard position information in the reagent tube standard position table, where the other reagent tubes are the reagent tubes in the other target reagent tube image excluding the standard reagent tube in the standard groove.

[0020] In a specific embodiment, after judging whether each reagent tube in each target reagent tube image meets the preset requirements according to the verification result, if each reagent tube in each target reagent tube image meets the preset requirements, the reagent tube position information of each reagent tube is directly uploaded.

[0021] Step S104, if at least one reagent tube does not meet the preset requirements, the at least one reagent tube is defined as an abnormal reagent tube, and the reagent tube position information of each abnormal reagent tube is predicted according to a preset position generation strategy to obtain each predicted position information.

[0022] In this step, each abnormal reagent tube in the same target reagent tube image is divided into the same abnormal reagent tube set to obtain an abnormal reagent tube set corresponding to each target reagent tube image; an abnormal reagent tube set with the smallest number of abnormal reagent tubes is selected from each abnormal reagent tube set and defined as a target abnormal reagent tube set; it is judged whether the number of abnormal reagent tubes in the target abnormal reagent tube set is greater than a preset threshold; if it is not greater than the preset threshold, the reagent tube position information of the abnormal reagent tubes in the target abnormal reagent tube set is directly defined as the predicted position information; if it is greater than the preset threshold, at least one predicted position information combination of each abnormal reagent tube is generated by arbitrarily combining the reagent tube position information of each abnormal reagent tube in the target reagent tube image corresponding to the target abnormal reagent tube set.

[0023] In summary, the method of the present application automatically obtains and analyzes the reagent tube image using an image recognition model, quickly determines the position information of the reagent tube, and significantly shortens the position detection time compared with traditional manual visual inspection, achieving efficient recognition of the reagent tube position. At the same time, this method can be seamlessly docked with automated experimental equipment (such as a robotic arm), providing accurate position guidance for subsequent automated operations, significantly improving the automation level of the entire detection process, enabling large-scale and high-intensity detection tasks to be efficiently completed. Moreover, by constructing a two-dimensional coordinate system and performing position verification based on a preset standard position table of reagent tubes, this solution can accurately determine whether the position of the reagent tube meets the requirements. Once an abnormal reagent tube is found, it can be marked in time and its possible position can be predicted, effectively avoiding problems such as reagent contamination and experimental procedure chaos caused by reagent tube misalignment, ensuring the accuracy of experimental operations from the source, and thus improving the reliability and repeatability of experimental results.

[0024] Implement real-time monitoring and abnormal warning: This solution can perform real-time monitoring on the position of reagent tubes in the reagent kit. Once an abnormal position of the reagent tube is detected, the warning mechanism is immediately triggered and the predicted position information is generated. This real-time feedback mechanism enables the operator to take corrective measures in time, avoiding subsequent problems caused by reagent tube misalignment, and further improving the safety and stability of the experimental process. Please refer to Figure 2 , which shows a structural block diagram of a reagent tube position analysis system for a reagent kit according to the present application.

[0025] As Figure 2 shown, the reagent tube position analysis system 200 includes an acquisition module 210, an output module 220, a judgment module 230, and a prediction module 240.

[0026] Among them, the acquisition module 210 is configured to acquire reagent tube images at different positions of a reagent kit located at a detection position, where the reagent tube images include the grooves of the reagent kit and the reagent tubes in the grooves; the output module 220 is configured to input each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; the judgment module 230 is configured to, according to a pre-constructed reagent tube standard position table, use a preset position verification rule to verify the reagent tube position information of each reagent tube in each target reagent tube image, and determine whether each reagent tube in each target reagent tube image meets a preset requirement according to the verification result, where the preset requirement is that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; the prediction module 240 is configured to, if at least one reagent tube does not meet the preset requirement, define the at least one reagent tube as an abnormal reagent tube, and predict the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain each predicted position information.

[0027] It should be understood that Figure 2 the modules described in Figure 1 correspond to the respective steps in the method described in Figure 2 Accordingly, the operations, features, and corresponding technical effects described above for the method also apply to

[0028] the modules in and will not be elaborated herein. Acquire reagent tube images at different positions of a reagent kit located at a detection position, where the reagent tube images include the grooves of the reagent kit and the reagent tubes in the grooves; Input each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determine the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; According to a pre-constructed standard position table of reagent tubes, the reagent tube position information of each reagent tube in each of the target reagent tube images is verified using a preset position verification rule, and it is determined whether each reagent tube in each of the target reagent tube images meets the preset requirements according to the verification results. The preset requirements are that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; If at least one reagent tube does not meet the preset requirements, then the at least one reagent tube is defined as an abnormal reagent tube, and the reagent tube position information of each abnormal reagent tube is predicted according to a preset position generation strategy to obtain respective predicted position information.

[0029] A computer-readable storage medium may include a storage program area and a storage data area. Among them, the storage program area can store an operating system and application programs required for at least one function; the storage data area can store data created according to the use of the reagent tube position analysis system for the reagent kit, etc. In addition, the computer-readable storage medium may include high-speed random access memory, and may also include memories, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the computer-readable storage medium may optionally include a memory remotely provided with respect to the processor, and these remote memories can be connected to the reagent tube position analysis system for the reagent kit through a network. Examples of the above network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] Figure 3 is a schematic structural diagram of the electronic device provided by an embodiment of the present invention. As Figure 3 shown, the device includes: a processor 310 and a memory 320. The electronic device may further include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330, and the output device 340 can be connected through a bus or other means. Figure 3 Taking the connection through the bus as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements the reagent tube position analysis method for the reagent kit in the above method embodiment. The input device 330 can receive input digital or character information, and generate key signal inputs related to user settings and function controls of the reagent tube position analysis system for the reagent kit. The output device 340 may include display devices such as a display screen.

[0031] The above electronic device can execute the method provided by the embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. For technical details not described in detail in this embodiment, reference can be made to the method provided by the embodiment of the present invention.

[0032] As an implementation manner, the above electronic device is applied to a reagent tube position analysis system for a reagent kit and is used for a client, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to: Obtain reagent tube images at different positions of a reagent kit located at a detection position, wherein the reagent tube images include grooves of the reagent kit and reagent tubes in the grooves; Input each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; According to a pre-constructed reagent tube standard position table, use a preset position verification rule to verify the reagent tube position information of each reagent tube in each target reagent tube image, and determine whether each reagent tube in each target reagent tube image meets a preset requirement according to the verification result, where the preset requirement is that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; If at least one reagent tube does not meet the preset requirement, define the at least one reagent tube as an abnormal reagent tube, and predict the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain each predicted position information.

[0033] Through the description of the above implementation manners, those skilled in the art can clearly understand that each implementation manner can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on such an understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiments.

[0034] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for analyzing the position of reagent tubes in a kit, characterized in that, Including: Obtaining reagent tube images at different positions of a reagent kit located at a detection position, where the reagent tube images include grooves of the reagent kit and reagent tubes in the grooves; Inputting each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; According to a pre-constructed reagent tube standard position table, using a preset position verification rule to verify the reagent tube position information of each reagent tube in each target reagent tube image, and judging whether each reagent tube in each target reagent tube image meets a preset requirement according to the verification result, the preset requirement is that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; If at least one reagent tube does not meet the preset requirement, defining the at least one reagent tube as an abnormal reagent tube, and predicting the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain each predicted position information.

2. The reagent tube position analysis method for a reagent kit according to claim 1, characterized in that The step of inputting each reagent tube image into a preset image recognition model, where the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system includes: Inputting a certain reagent tube image into the image recognition model, the image recognition model annotates the reagent tube label and the groove in the reagent tube image to obtain a first bounding box including the reagent tube label and a second bounding box including the groove, where the certain reagent tube image is any one of the reagent tube images; The image recognition model outputs a certain target reagent tube image including each first bounding box and each second bounding box, where the reagent tube label is located on the reagent tube; Constructing a two-dimensional coordinate system, and determining the first coordinate position of each first bounding box and the second coordinate position of each second bounding box in the certain target reagent tube image according to the two-dimensional coordinate system, where the vertex of the certain target reagent tube image coincides with the origin of the two-dimensional coordinate system, and the edge line of the certain reagent tube image is aligned with the axis of the two-dimensional coordinate system; Associating a certain first bounding box and a certain second target bounding box with the shortest distance between them, and defining the first coordinate position in the certain first bounding box as the reagent tube position information of the reagent tube where the certain second target bounding box is located.

3. A reagent tube position analysis method for a reagent kit according to claim 1, characterized in that, The step of verifying the reagent tube position information of each reagent tube in each target reagent tube image according to a pre-constructed reagent tube standard position table by using a preset position verification rule includes: Comparing the reagent tube position information of each reagent tube in a certain target reagent tube image with the reagent tube standard position information in the reagent tube standard position table; If the comparison result of the reagent tube position information of at least one reagent tube with the reagent tube standard position information in the reagent tube standard position table is consistent, then position the at least one reagent tube as a standard reagent tube, and define the groove where the standard reagent tube is located as a standard groove; Determine the standard groove in another target reagent tube image according to the sorting position of the standard groove in a certain target reagent tube image, and compare the reagent tube position information of other reagent tubes in the other target reagent tube image with the reagent tube standard position information in the reagent tube standard position table, where the other reagent tubes are the reagent tubes in the other target reagent tube image excluding the standard reagent tube in the standard groove.

4. A reagent tube position analysis method for a reagent kit according to claim 1, characterized in that, After judging whether each reagent tube in each target reagent tube image meets the preset requirements according to the verification result, the method further includes: If each reagent tube in each target reagent tube image meets the preset requirements, directly upload the reagent tube position information of each reagent tube.

5. A method for analyzing the position of reagent tubes for a kit according to claim 1, characterized in that, The predicting the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain each predicted position information includes: Dividing each abnormal reagent tube in the same target reagent tube image into the same abnormal reagent tube set to obtain an abnormal reagent tube set corresponding to each target reagent tube image; Selecting an abnormal reagent tube set with the smallest number of abnormal reagent tubes from each abnormal reagent tube set and defining it as a target abnormal reagent tube set; Judging whether the number of abnormal reagent tubes in the target abnormal reagent tube set is greater than a preset threshold; If it is not greater than the preset threshold, directly define the reagent tube position information of the abnormal reagent tubes in the target abnormal reagent tube set as the predicted position information; If it is greater than the preset threshold, generate at least one predicted position information combination of each abnormal reagent tube according to any combination of the reagent tube position information of each abnormal reagent tube in the target reagent tube image corresponding to the target abnormal reagent tube set.

6. A reagent tube position analysis system for a kit, characterized in that, Including: An acquisition module configured to acquire reagent tube images at different positions of a reagent kit located at a detection position, where the reagent tube images include grooves of the reagent kit and reagent tubes in the grooves; An output module configured to input each reagent tube image into a preset image recognition model, the image recognition model outputs each target reagent tube image including a bounding box, and determines the reagent tube position information of each reagent tube in each target reagent tube image according to a preset two-dimensional coordinate system; A judgment module configured to verify the reagent tube position information of each reagent tube in each target reagent tube image according to a pre-constructed reagent tube standard position table by using a preset position verification rule, and judge whether each reagent tube in each target reagent tube image meets the preset requirements according to the verification result, where the preset requirement is that the reagent tube position information is the same as the reagent tube standard position information in the reagent tube standard position table; A prediction module, configured to define the at least one reagent tube as an abnormal reagent tube if at least one reagent tube does not meet the preset requirements, and predict the reagent tube position information of each abnormal reagent tube according to a preset position generation strategy to obtain respective predicted position information.

7. An electronic device, characterized in that, Comprising: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, the method according to any one of claims 1 to 5 is implemented.

Images