Cell collection reminder method and system

Abstract

The application provides a cell collection reminding method and system, which comprises the following steps: acquiring image information in a culture container; acquiring the number of cells in the culture container and the area of the cells and the background area in the culture container according to the image information in the culture container; acquiring the cell culture time in the culture container; acquiring a collection interval corresponding to the culture time according to the cell culture time; judging whether the number of cells is in the collection interval according to the number of cells in the culture container and the collection interval; judging whether the background area in the culture container is lower than a preset collection area threshold; and generating a collection reminding instruction when it is judged that the background area is lower than the preset collection area threshold or the number of cells is in the collection interval. The method can judge whether the cells need to be collected based on the background area and the number of cells in the culture container, so as to remind the operator to collect the cells in time.

Description

Technical Field

[0001] The present application relates to the field of image recognition technology, and in particular to a cell harvesting reminder method and system. Background Art

[0002] With the advancement and development of science and technology, cell culture technology is becoming increasingly important. Using cell culture technology, a large number of cells can be obtained, and this can be used to study cell signal transduction, cell anabolism, cell growth and proliferation, etc. When conducting cell culture, containers such as culture dishes are usually used, and each container has an upper limit on the number of cells it can accommodate. When the number of cells approaches or reaches the upper limit of the container, the cell division rate will begin to slow down or even cell death will occur. Therefore, accurate cell counting can allow cells to be harvested in time when the number of cells reaches a certain number, avoiding cell death caused by the number of cells exceeding the upper limit of the number of cells that the culture dish can accommodate, thereby reducing the number of cells harvested. There is still room for improvement in cell counting in related technologies. Summary of the Invention

[0003] In view of this, it is necessary to provide a cell harvesting reminder method and system. This method can determine whether cells need to be harvested based on the background area and cell number of the culture container. If cell harvesting is required, a harvesting reminder instruction is generated to remind the operator to harvest the cells in a timely manner.

[0004] In a first aspect, an embodiment of the present application provides a cell harvesting reminder method, comprising:

[0005] Acquiring image information inside the culture container;

[0006] Acquire the number of cells in the culture container and the cell area and background area in the culture container according to the image information in the culture container;

[0007] Obtaining the cell culture time in the culture container;

[0008] Acquire a harvesting interval corresponding to the cell culture time according to the cell culture time;

[0009] determining, based on the number of cells in the culture container and the harvesting interval, whether the number of cells is within the harvesting interval;

[0010] Determining whether the background area in the culture container is lower than a preset harvesting area threshold;

[0011] When it is determined that the background area is lower than the preset harvesting area threshold or the number of cells is within the harvesting interval, a harvesting reminder instruction is generated.

[0012] In a possible implementation of the present application, the method further comprises:

[0013] extracting cell features in the image information in the culture container;

[0014] segmenting the image information in the culture container according to the cell features to obtain cell images;

[0015] performing cell counting according to the cell images.

[0016] In a possible implementation of the present application, the method further comprises:

[0017] segmenting the image information in the culture container to obtain a cell region and a background region;

[0018] calculating an area of the background region to obtain a background area.

[0019] In a possible implementation of the present application, the method further comprises:

[0020] applying a VGG convolutional neural network model, a MobileNet convolutional neural network model, or a ResNet convolutional neural network model to extract cell features.

[0021] In a possible implementation of the present application, the method further comprises:

[0022] applying an FCN model or a UNet model to segment the image information in the culture container.

[0023] In a possible implementation of the present application, the method further comprises:

[0024] obtaining a cell number interval corresponding to the cell culture time;

[0025] determining whether the cell number is in the corresponding cell number interval;

[0026] generating warning information when it is determined that the cell number is lower than the cell number interval.

[0027] In a possible implementation of the present application, the method further comprises:

[0028] applying an RNN model or an LSTM model to determine the cell growth time and the corresponding cell number interval.

[0029] In a possible implementation of the present application, the method further comprises:

[0030] obtaining a ratio of the background area and the cell area according to the cell area and the background area in the culture container;

[0031] determining whether the ratio of the background area and the cell area reaches a preset background area ratio threshold value;

[0032] generating a harvesting reminding instruction when it is determined that the ratio reaches the background area ratio threshold value.

[0033] In a second aspect, an embodiment of the present application provides a cell harvesting reminding system, comprising:

[0034] an image acquisition module, configured to acquire image information in a culture container;

[0035] a cell counting module, configured to obtain a cell number in the culture container according to the image information in the culture container;

[0036] a time acquisition module, configured to obtain a cell culture time in the culture container, and obtain a harvesting interval corresponding to the culture time according to the cell culture time;

[0037] an image segmentation module, configured to obtain a cell area and a background area in the culture container according to the image information in the culture container;

[0038] a control module, configured to determine whether the background area in the culture container is lower than a preset harvesting area threshold value, and generate a harvesting reminding instruction when it is determined that the background area is lower than the preset harvesting area threshold value or the cell number is in the harvesting interval.

[0039] In a possible implementation of the present application, the system further comprises:

[0040] a training module, configured to train the cell harvesting reminding system to accurately identify the cell number and the cell contour.

[0041] The cell harvesting reminding method and the cell harvesting reminding system provided by the embodiments of the present application can determine whether the cells need to be harvested based on the background area and the cell number of the culture container, and generate a harvesting reminding instruction to remind the operator to timely harvest the cells if the cells need to be harvested. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 A module schematic diagram of the cell harvesting reminding system provided by an embodiment of the present application.

[0043] Figure 2A cell and background segmentation schematic diagram provided by an embodiment of the present application.

[0044] Figure 3 A flowchart of a cell collection reminding method provided by an embodiment of the present application.

[0045] Main element symbol description

[0046] Cell collection reminding system 10

[0047] Control module 100

[0048] Image acquisition module 200

[0049] Cell statistics module 300

[0050] Time acquisition module 400

[0051] Image segmentation module 500

[0052] The following detailed description will further describe the present application in combination with the above-mentioned drawings. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present application will be described clearly and completely in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are some of the embodiments of the present application, but not all the embodiments of the present application.

[0054] It should be noted that "at least one" in the embodiments of the present application means one or more, and more means two or more than two. Unless otherwise defined, all technical and scientific terms used in the present application have the same meaning as understood by those skilled in the art to which the present application belongs. The terms used in the specification of the present application are only for the purpose of describing the specific embodiments of the present application, and are not intended to limit the present application.

[0055] It should be noted that in the embodiments of the present application, the words "first", "second", etc. are only used for the purpose of distinguishing description, and cannot be understood as indicating or implying relative importance, nor can it be understood as indicating or implying order. The features limited by "first", "second" can explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the words "exemplary" or "for example" are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, the words "exemplary" or "for example" are intended to present the relevant concept in a specific manner.

[0056] All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative effort are within the scope of the present application.

[0057] With the progress and development of science and technology, cell culture technology is becoming more and more important. Using cell culture technology can obtain a large number of cells, and can also study cell signal transduction, cell anabolism, cell growth and proliferation, etc. In cell culture, a culture dish or other container is usually used, and each container has an upper limit of the number of cells that can be accommodated. When the number of cells approaches or reaches the upper limit of the container, the cell culture speed will slow down or even cell death will occur, affecting the yield of cells. Therefore, accurate cell counting can collect cells in time when the number of cells reaches a certain number, avoiding cell death caused by the number of cells exceeding the upper limit of the number of cells that the culture dish can accommodate, thereby reducing the number of cells collected.

[0058] Therefore, the embodiments of the present application provide a cell collection reminding method and system, which can determine whether the cells need to be collected based on the background area of the culture container and the number of cells, and if the cell collection needs to be performed, a collection reminding instruction is generated to remind the operator to collect the cells in time.

[0059] Some embodiments of the application will be described in detail below with reference to the accompanying drawings. In the case of no conflict, the embodiments described below and the features in the embodiments can be combined with each other.

[0060] Figure 1 is a schematic diagram of the modules of the cell collection reminding system 10 provided by an embodiment of the present application. As shown in Figure 1 The cell collection reminding system 10 includes a control module 100, an image acquisition module 200, a cell counting module 300, a time acquisition module 400, and an image segmentation module 500.

[0061] In the embodiments of the present application, the image acquisition module 200 is configured to acquire image information in the culture container. It can be understood that the image information in the culture container includes the image of the culture container body and the image of the cells in the culture container. It can be understood that the image acquisition module 200 can include a camera arranged above the culture container. For example, the camera can be a high-definition camera, or a camera arranged above a microscope, to clearly capture the image information above the culture container, and the image information can distinguish the image of the cells.

[0062] Exemplarily, the image acquisition module 200 is also configured to capture still images or videos. The cells and the culture vessel generate optical images through the lens and project the optical images to the photosensitive element. The photosensitive element can be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor. In some embodiments, the image acquisition module 200 can include one or N cameras, where N is a positive integer greater than 1.

[0063] It can be understood that the cell statistics module 300 is provided with a feature extraction submodule 301 and a cell counting submodule 302. The feature extraction submodule 301 is configured to extract cell features in the image information of the culture vessel. The cell counting submodule 302 is configured to count cells according to the segmented cell images after the feature extraction submodule 301 segments the cell images, and transmit the cell counting result to the control module 100.

[0064] Exemplarily, the feature extraction submodule 301 includes, but is not limited to, a Visual Geometry Group (VGG) model, a MobileNet model, a ResNet model, and other Convolutional Neural Networks (CNN) models. It can be understood that in the embodiments of the present application, the model used by the feature extraction submodule 301 can be adjusted according to the hardware of the cell harvesting reminding system 10. Among them, using the CNN model can automatically extract the features of the cells, and can accurately identify the outline of the cells.

[0065] It can be understood that before the feature extraction submodule 301 performs feature extraction, the feature extraction submodule 301 can use a single shot multibox detection (SSD) model or the like to frame the cells. Using the SSD model can accurately identify the outline of a single cell, and after completing the cell framing, the cell features are extracted, which can accurately extract the image features of the cells, and avoid the CNN model from mistakenly identifying the features of the culture vessel body image as the image features of the cells.

[0066] It can be understood that the time acquisition module 400 is provided with a timing submodule 401. The timing submodule 401 is used to calculate the cell number interval according to the time of cell culture. For example, the timing submodule 401 can use a recurrent neural network (RNN) model to determine the cell growth time and the corresponding cell number interval. For another example, the timing submodule 401 can also use a special RNN model such as a long short-term memory (LSTM) model to determine the cell number interval.

[0067] It can be understood that, since the theoretical cell division rate (i.e. the cell growth rate in the culture container) is exponentially increasing, although the cell division rate cannot reach the theoretical value due to the influence of other factors (such as insufficient nutrients and insufficient culture container space) in the actual cell culture process, the cell division rate will increase with time. Therefore, when the control module 100 controls the image acquisition module 200 to acquire image information in the culture container, the image acquisition module 200 acquires images at an increasing frequency as time increases. For example, the image information acquisition interval can be set to 30 minutes, 30 minutes, 20 minutes, 20 minutes, 10 minutes, 10 minutes, 5 minutes, etc.

[0068] It can be understood that after the timing submodule 401 obtains the cell number interval that the cell number should be in during this period, the timing submodule 401 transmits the cell number interval to the control module 100. The control module 100 compares the cell count result transmitted by the cell counting module 300 with the cell number interval. If the cell count result is higher than the maximum value of the cell number interval, it proves that the cell culture condition is good. Then, the control module 100 further determines whether the cell number is in the preset harvesting interval. If it is in the harvesting interval, the control module 100 sends a harvesting information to prompt the user to harvest the cells. If the cell count result is in the cell number interval, it proves that the cell culture condition is normal. The control module 100 can further determine whether the cell number is in the preset harvesting interval. If it is in the harvesting interval, the control module 100 sends a harvesting reminder instruction. If the cell count result is lower than the cell number interval, it proves that the cell culture condition is abnormal, and the control module 100 sends an abnormal information to prompt the operator that the culture container may be abnormal and needs to be handled in time to reduce the loss.

[0069] It can be understood that the image segmentation module 500 is configured to process the image in the culture container according to the cell features obtained by the feature extraction submodule 301, so as to realize the segmentation of the cells and the background. For example, the image segmentation module 500 can use a fully convolutional network (FCN) model or a neural network model based on a fully convolutional network such as a UNet model to realize image segmentation.

[0070] For example, after obtaining the image in the culture container, the image segmentation module 500 segments the image and distinguishes the cell region and the background region according to the segmentation result. The image segmentation module 500 is further configured to calculate the ratio of the background region to the cell region. If the ratio of the background region to the cell region is higher than a preset ratio threshold in the image segmentation module 500, a reminder signal is generated to the control module 100. The control module 100 generates a collection reminder instruction according to the received reminder signal to remind the operator to collect the cells.

[0071] It can be understood that after distinguishing the cell region and the background region, the image segmentation module 500 is further configured to calculate the area of the background region, and set a corresponding threshold according to the corresponding ratio or area. When the ratio or area reaches the threshold, a reminder signal is generated to the control module 100.

[0072] Please refer to Figure 2 , Figure 2 is a schematic diagram of cell and background segmentation provided by an embodiment of the present application. Figure 2 (a) is an image in the culture container before segmentation, Figure 2 (b) is an image in the culture container after segmentation.

[0073] As Figure 2 shown, after completing the cell segmentation, the image segmentation module 500 can clearly distinguish the region to which the cells belong and the corresponding background region. As described above, the control module 100 is configured to generate a collection reminder instruction according to the reminder signal generated by the image segmentation module 500 to remind the operator to collect the cells.

[0074] It can be understood that the control module 100 issues a collection information when the background area of the culture container is lower than a cell collection area threshold or the number of cells is higher than a cell collection threshold, to prompt the user to collect the cells.

[0075] It can be understood that the cell collection reminder system 10 further comprises a training module (not shown in the figure). The training module is configured to train the cell collection reminder system 10, so that the cell collection reminder system 10 can accurately identify the number of cells and the outline of the cells.

[0076] In the embodiment of the present application, the cell harvesting reminding system 10 can determine whether the cells need to be harvested based on the background area or the cell number of the culture container. If the cell harvesting needs to be performed, a harvesting reminding instruction is generated to remind the operator to perform the cell harvesting in time. It can be understood that the cell harvesting reminding system 10 can also alarm when the cell number is detected to be abnormal to prompt the operator to check in time.

[0077] Figure 3 is a schematic diagram of a cell harvesting reminding method provided by an embodiment of the present application. As shown in Figure 3 , the cell harvesting reminding method at least includes the following steps.

[0078] S100: Obtain image information in the culture container.

[0079] It can be understood that in step S100, the image information in the culture container can be obtained by the image acquisition module 200. The acquisition method of the image information is described in the image acquisition module 200 and its related description in Figure 1 , which will not be repeated here.

[0080] S200: Obtain the cell number in the culture container.

[0081] It can be understood that in step S200, the cell number in the culture container can be obtained by the cell counting module 300. The acquisition method of the cell number is described in Figure 1 , which will not be repeated here.

[0082] S300: Obtain the cell area and the background area in the culture container.

[0083] It can be understood that in step S300, the cell area and the background area in the culture container can be obtained by the image segmentation module 500. The acquisition method of the cell area and the background area is described in Figure 1 , which will not be repeated here.

[0084] S400: Determine whether the background area is lower than the harvesting area threshold.

[0085] It can be understood that in step S400, the control module 100 can determine whether the background area is lower than the harvesting area threshold. The determination method is described in Figure 1 , which will not be repeated here.

[0086] S500: Obtain the cell culture time.

[0087] It can be understood that in step S500, the cell culture time can be obtained by the time acquisition module 400. The acquisition method of the time is described in Figure 1 , which will not be repeated here.

[0088] S600: determining whether the cell number reaches a harvesting number threshold.

[0089] It can be understood that in step S600, the control module 100 can determine whether the cell number reaches a harvesting number threshold, and the harvesting number threshold can be obtained in the manner as described in the above embodiment. Figure 1 Here, details are not described again.

[0090] S700: generating a harvesting reminding instruction.

[0091] It can be understood that in step S700, the control module 100 can generate a harvesting reminding instruction to remind the operator to harvest the cells, and the generation manner of the harvesting reminding instruction can be understood in the manner as described in the above embodiment. Figure 1 Here, details are not described again.

[0092] Those skilled in the art should recognize that the above embodiments are only used to illustrate the present application, and are not used as a limitation to the present application, and as long as the above embodiments are within the scope of the spirit of the present application, the appropriate changes and variations of the above embodiments are within the scope of the present application.

Claims

1. A cell harvesting reminder method, characterized in that: include: Acquiring image information inside the culture container; Obtaining the number of cells in the culture container and the cell area and background area in the culture container based on the image information in the culture container, including: extracting cell features from the image information in the culture container; segmenting the image information in the culture container based on the cell features to obtain cell images; counting cells based on the cell images; segmenting the image information in the culture container to obtain cell areas and background areas; and calculating the area of ​​the background area to obtain background area. Obtaining the cell culture time in the culture container; Acquire a harvesting interval corresponding to the cell culture time according to the cell culture time; determining, based on the number of cells in the culture container and the harvesting interval, whether the number of cells is within the harvesting interval; Determining whether the background area in the culture container is lower than a preset harvesting area threshold; When it is determined that the background area is lower than the preset harvesting area threshold or the number of cells is within the harvesting interval, a harvesting reminder instruction is generated.

2. The cell harvesting reminder method according to claim 1, wherein: The step of extracting cell features from the image information in the culture container includes: Apply VGG convolutional neural network model, MobileNet convolutional neural network model or ResNet convolutional neural network model to extract cell features.

3. The cell harvesting reminder method according to claim 1, wherein: The segmenting of the image information in the culture container includes: Apply an FCN model or a UNet model to segment the image information in the culture container.

4. The cell harvesting reminder method according to claim 1, wherein: After obtaining the harvesting interval corresponding to the cell culture time according to the cell culture time, the method further includes: Obtaining a cell number interval corresponding to the cell culture time; Determining whether the cell number is within the corresponding cell number interval; When it is determined that the cell number is lower than the cell number range, a warning message is generated.

5. The cell harvesting reminder method according to claim 4, wherein: The obtaining of the cell number interval corresponding to the cell culture time includes: An RNN model or an LSTM model is applied to determine the cell growth time and the corresponding cell number interval.

6. The cell harvesting reminder method according to claim 1, wherein: The method further comprises: Obtaining a ratio of the background area to the cell area according to the cell area and the background area in the culture container; Determining whether the ratio of the background area to the cell area reaches a preset background area ratio threshold; When it is determined that the ratio reaches the background area ratio threshold, a harvest reminder instruction is generated.

7. A cell harvesting reminder system, characterized in that: include: An image acquisition module is used to acquire image information in the culture container; a cell counting module, configured to obtain the number of cells in the culture container based on the image information in the culture container; a time acquisition module, configured to acquire the cell culture time in the culture container, and acquire a harvesting interval corresponding to the culture time according to the cell culture time; an image segmentation module, configured to obtain a cell area and a background area in the culture container based on the image information in the culture container, comprising: extracting cell features from the image information in the culture container; segmenting the image information in the culture container based on the cell features to obtain a cell image; counting cells based on the cell image; segmenting the image information in the culture container to obtain a cell area and a background area; and calculating the area of ​​the background area to obtain a background area; The control module is configured to determine whether the background area in the culture container is lower than a preset harvesting area threshold; and generate a harvesting reminder instruction when it is determined that the background area is lower than the preset harvesting area threshold or the number of cells is within the harvesting range.

8. The cell harvesting reminder system according to claim 7, wherein: The system further comprises: The training module is used to train the cell collection reminder system to identify the number of cells and the outline of cells.

Images