A deep learning-based stem cell differentiation monitoring system

Abstract

The application relates to the field of biotechnology, and particularly relates to a stem cell differentiation monitoring system based on deep learning, which comprises a culture module, an environment adjusting module, a data acquisition module, a differentiation prediction module and an analysis module, the culture module is used for culturing stem cells and providing a place for stem cell differentiation, the environment adjusting module is used for adjusting the culture environment of the culture module, the data acquisition module is used for acquiring various parameters and images in the stem cell differentiation process, the differentiation prediction module is used for predicting the differentiation result of the stem cells, and the analysis module is used for acquiring an accuracy index of the differentiation prediction and optimizing the differentiation prediction module according to the accuracy index. The application combines the deep learning technology, monitors the stem cell differentiation, and predicts the differentiation result of the stem cells after a period of time, which is favorable for the staff to take corresponding environment adjusting measures according to the prediction result, and improves the intelligent degree of the system.

Description

Technical Field

[0001] This invention relates to the field of biotechnology, and more particularly to a stem cell differentiation monitoring system based on deep learning. Background Technology

[0002] Stem cell technology is one of the most promising cutting-edge technologies in the biomedical field today. However, monitoring the differentiation process of stem cells is a challenging task, and traditional methods are often limited by factors such as resolution, accuracy, and efficiency. Deep learning, as a key technology in artificial intelligence, possesses powerful pattern recognition and learning capabilities. In the field of biotechnology, deep learning has already been applied to monitor stem cell differentiation.

[0003] For example, the prior art disclosed in CN111986802A is an auxiliary system and method for determining the pathological differentiation grade of lung adenocarcinoma, which involves the field of deep learning technology. It includes: an image acquisition module for acquiring digital pathological images of several early-stage lung adenocarcinoma patients; an image annotation module for annotating each digital pathological image to obtain an annotated digital pathological image; a model training module for training a lung adenocarcinoma tissue growth pattern recognition model; an image prediction module for inputting the digital pathological image to be predicted into the lung adenocarcinoma tissue growth pattern recognition model to obtain the predicted lung adenocarcinoma tissue growth pattern corresponding to each lesion area; and a pathological differentiation module for calculating the proportion of tumor cells in each predicted lung adenocarcinoma tissue growth pattern, providing auxiliary reference for doctors in determining the pathological differentiation grade of lung adenocarcinoma.

[0004] Another typical example is the prior art disclosed in CN117409867A, which describes a deep learning-based iPSC directed differentiation regulation system and method. This invention, during somatic cell induction differentiation, continuously monitors the amount of stem cell apoptosis to determine the effective differentiation level, providing data support for evaluating model execution. After somatic cells are induced to differentiate to the required stem cell level, the applied biomechanical factors are removed, and the subsequent effective differentiation level of stem cells under natural conditions is statistically analyzed. This avoids errors in the output results of standard parameters caused by shortening the stem cell apoptosis cycle during biomechanical induction. The optimal biomechanical factors are then determined based on the effective differentiation level of somatic cells after induction.

[0005] Let's look at the existing technology disclosed in CN111666895A, which is a deep learning-based neural stem cell differentiation direction prediction system and method. This system combines the high-throughput cell processing capability of flow cytometry technology, creatively utilizes experimental methods to collect images of differentiated and cultured neural stem cells acquired by panoramic flow cytometer, establishes a training dataset of neural stem cell trilineage differentiation, and then uses convolutional neural networks for model training and optimization.

[0006] Currently, existing technologies using deep learning to study cell differentiation often cannot autonomously determine the accuracy of prediction results, nor can they optimize the model in a timely manner, leading to prediction errors and a lag. To address these common problems in the field, this invention was developed. Summary of the Invention

[0007] The purpose of this invention is to address the shortcomings of current systems by proposing a deep learning-based stem cell differentiation monitoring system.

[0008] To overcome the shortcomings of the prior art, the present invention adopts the following technical solution:

[0009] A deep learning-based stem cell differentiation monitoring system includes a culture module, an environment regulation module, a data acquisition module, a differentiation prediction module, and an analysis module. The culture module is used to culture stem cells and provide a site for stem cell differentiation. The environment regulation module is used to regulate the culture environment of the culture module. The data acquisition module is used to acquire various parameters and images of the culture module and the environment regulation module during the stem cell differentiation process. The differentiation prediction module is used to predict the differentiation result of stem cells based on the data acquired by the data acquisition module. The analysis module is used to obtain the accuracy index of the differentiation prediction and optimize the differentiation prediction module based on the accuracy index.

[0010] Furthermore, the culture module includes a culture container, a culture medium supply unit, an illumination unit, and a sterilization unit. The culture container is used to contain stem cells and their culture medium. The culture medium supply unit is used to add culture medium to the culture container at regular intervals. The illumination unit is used to illuminate the culture container. The sterilization unit is used to sterilize the culture container.

[0011] Furthermore, the environmental control module includes a gas exchange unit, a temperature control unit, a pH adjustment unit, and a data transmission unit. The gas exchange unit is used to adjust the concentration of various gases in the culture container, the temperature control unit is used to control the ambient temperature of the culture container, the pH adjustment unit is used to adjust the pH value of the culture medium in the culture container, and the data transmission unit is used to send the adjustment parameters of the environmental control module to the data acquisition module.

[0012] Furthermore, the differentiation prediction module includes a data input unit, a differentiation stage identification unit, and a differentiation result prediction unit. The data input unit is used to receive various data collected by the data acquisition module. The differentiation stage identification unit is used to identify the current differentiation stage or differentiation time of the stem cells based on the data received by the data input unit. The differentiation result prediction unit is used to predict the future differentiation image of the stem cells based on the data received by the data input unit through a prediction model.

[0013] Furthermore, the analysis module includes an image comparison module, a calculation module, and a prediction model optimization module. The image comparison module is used to compare cell differentiation images at different stages and obtain image similarity. The calculation module is used to calculate the accuracy index of differentiation prediction. The prediction model optimization module is used to optimize the prediction model in the differentiation result prediction unit based on the data obtained from the differentiation prediction module, the calculation module, and the image comparison module.

[0014] Furthermore, the workflow of the differentiation monitoring system includes the following steps:

[0015] S1, the culture module, is used to culture stem cells.

[0016] S2, the data acquisition module collects various parameters and images of stem cells during the differentiation process.

[0017] S3, the differentiation stage identification unit, identifies the current differentiation stage of stem cells.

[0018] S4, the environment adjustment module adjusts the culture environment of some culture containers in the culture module.

[0019] S5, the differentiation outcome prediction unit, predicts the differentiation images of each stem cell over a future period of time.

[0020] S6, the analysis module optimizes the differentiation result prediction unit based on the acquired data.

[0021] Furthermore, the differentiation outcome prediction unit predicts the differentiation profile of individual stem cells over a future period of time by including the following steps:

[0022] S51, Input the environmental parameters of the culture environment of each stem cell, the set time, and the current differentiation image of each stem cell.

[0023] S52, the prediction model processes each input to obtain the predicted differentiation image after a set time.

[0024] Furthermore, the analysis module optimizes the differentiation result prediction unit based on the acquired data, including the following steps:

[0025] S61, the image comparison module compares the actual differentiation image and the predicted differentiation image after a set time, and obtains the image similarity index between the actual differentiation image and the corresponding predicted differentiation image of each stem cell.

[0026] S62, the calculation module calculates the secondary accuracy index and the accuracy index of differentiation prediction for each actual differentiation image based on the data collected by the data acquisition module and the actual differentiation image.

[0027] S63, determine whether the accuracy index of differentiation prediction is greater than 0. If not, the system will report an error and end the optimization. Otherwise, send the secondary accuracy index and image corresponding to each experimental group to the prediction model optimization module. The secondary accuracy index is used to characterize the accuracy of the prediction model corresponding to each experimental group. The accuracy index of differentiation prediction is used to characterize the accuracy of the prediction model corresponding to all experimental groups. The larger the index, the higher the accuracy.

[0028] S64, the prediction model optimization module labels the images of each experimental group according to the secondary accuracy index, and sends the labeled images to the differentiation result prediction unit. The differentiation result prediction unit adds the labeled images to the training set.

[0029] The beneficial effects achieved by this invention are:

[0030] 1. By combining deep learning technology to monitor stem cell differentiation and predict the differentiation results of stem cells after a period of time, staff can take corresponding environmental adjustment measures based on the prediction results, thus improving the intelligence level of the system.

[0031] 2. By setting secondary accuracy indicators, the system can autonomously judge the accuracy of different stem cell differentiation predictions. By setting accuracy indicators, it can judge the accuracy of the prediction of differentiation result prediction units and select results suitable for use as training sets. By labeling images with indicator values ​​and using them as training sets, the model can be optimized in a timely manner, which is conducive to continuously improving the model's capabilities. Attached Figure Description

[0032] The invention will be further understood from the following description taken in conjunction with the accompanying drawings. The components in the drawings are not necessarily drawn to scale, but rather the emphasis is on illustrating the principles of the embodiments. In different views, the same reference numerals designate the same parts.

[0033] Figure 1 This is a schematic diagram of the structure of the present invention.

[0034] Figure 2 This is a flowchart of the process of the present invention.

[0035] Figure 3 This is a flowchart of the analysis module of the present invention optimizing the differentiation result prediction unit.

[0036] Figure 4 This is a flowchart illustrating the process of Embodiment 2 of the present invention. Detailed Implementation

[0037] The following specific embodiments illustrate the implementation of the present invention. Those skilled in the art can understand the advantages and effects of the present invention from the content disclosed in this specification. The present invention can be implemented or applied through other different specific embodiments, and various details in this specification can also be modified and changed based on different viewpoints and applications without departing from the spirit of the present invention. Furthermore, the accompanying drawings of the present invention are for simple illustrative purposes only and are not depictions of actual dimensions; this is stated beforehand. The following embodiments will further describe the relevant technical content of the present invention in detail, but the disclosed content is not intended to limit the scope of protection of the present invention.

[0038] Example 1: According to Figure 1 , Figure 2 and Figure 3 This embodiment provides a deep learning-based stem cell differentiation monitoring system, including a culture module, an environment regulation module, a data acquisition module, a differentiation prediction module, and an analysis module. The culture module is used to culture stem cells and provide a site for stem cell differentiation. The environment regulation module is used to regulate the culture environment of the culture module. The data acquisition module is used to collect various parameters and images of the culture module and the environment regulation module during the stem cell differentiation process. The differentiation prediction module is used to predict the differentiation result of stem cells based on the data collected by the data acquisition module. The analysis module is used to obtain the accuracy index of the differentiation prediction and optimize the differentiation prediction module based on the accuracy index.

[0039] Furthermore, the culture module includes a culture container, a culture medium supply unit, an illumination unit, and a sterilization unit. The culture container is used to contain stem cells and their culture medium. The culture medium supply unit is used to add culture medium to the culture container at regular intervals. The illumination unit is used to illuminate the culture container. The sterilization unit is used to sterilize the culture container.

[0040] Furthermore, the environmental control module includes a gas exchange unit, a temperature control unit, a pH adjustment unit, and a data transmission unit. The gas exchange unit is used to adjust the concentration of various gases in the culture container, the temperature control unit is used to control the ambient temperature of the culture container, the pH adjustment unit is used to adjust the pH value of the culture medium in the culture container, and the data transmission unit is used to send the adjustment parameters of the environmental control module to the data acquisition module.

[0041] Specifically, the adjustment parameters include, but are not limited to, temperature, pH value, and various gas concentrations.

[0042] Furthermore, the differentiation prediction module includes a data input unit, a differentiation stage identification unit, and a differentiation result prediction unit. The data input unit is used to receive various data collected by the data acquisition module. The differentiation stage identification unit is used to identify the current differentiation stage or differentiation time of the stem cells based on the data received by the data input unit. The differentiation result prediction unit is used to predict the future differentiation image of the stem cells based on the data received by the data input unit through a prediction model.

[0043] Specifically, the differentiation stage identification unit uses a deep learning model for identification, and the differentiation result prediction unit uses a prediction model to predict the differentiation result. The above models can be trained by those skilled in the art by inputting cell differentiation images from different time periods or by directly using existing models.

[0044] Furthermore, the analysis module includes an image comparison module, a calculation module, and a prediction model optimization module. The image comparison module is used to compare cell differentiation images at different stages and obtain image similarity. The calculation module is used to calculate the accuracy index of differentiation prediction. The prediction model optimization module is used to optimize the prediction model in the differentiation result prediction unit based on the data obtained from the differentiation prediction module, the calculation module, and the image comparison module.

[0045] Furthermore, the workflow of the differentiation monitoring system includes the following steps:

[0046] S1, the culture module, is used to culture stem cells.

[0047] S2, the data acquisition module collects various parameters and images of stem cells during the differentiation process.

[0048] S3, the differentiation stage identification unit, identifies the current differentiation stage of stem cells.

[0049] S4, the environment adjustment module adjusts the culture environment of some culture containers in the culture module.

[0050] S5, the differentiation outcome prediction unit, predicts the differentiation images of each stem cell over a future period of time.

[0051] S6, the analysis module optimizes the differentiation result prediction unit based on the acquired data.

[0052] Furthermore, the differentiation outcome prediction unit predicts the differentiation profile of individual stem cells over a future period of time by including the following steps:

[0053] S51, Input the environmental parameters of the culture environment for each stem cell, set the time, and the current differentiation image of each stem cell.

[0054] Specifically, the environmental parameters include, but are not limited to, the pH value of the culture medium, the temperature value, the oxygen concentration, and the carbon dioxide concentration; specifically, the set time is set by those skilled in the art based on the required prediction results.

[0055] S52, the prediction model processes each input to obtain the predicted differentiation image after a set time.

[0056] Furthermore, the analysis module optimizes the differentiation result prediction unit based on the acquired data, including the following steps:

[0057] S61, the image comparison module compares the actual differentiation image and the predicted differentiation image after a set time, and obtains the image similarity index between the actual differentiation image and the corresponding predicted differentiation image of each stem cell.

[0058] Specifically, the image similarity index between the actual differentiated image and its corresponding predicted differentiated image can be the SSIM value of the two images. The SSIM value ranges from 1 to -1. The closer the SSIM value is to 1, the more similar the two images are. When the SSIM value is 1, it means that the two images are completely identical. The method for obtaining the SSIM value is existing technology and will not be elaborated here.

[0059] S62, the calculation module calculates the secondary accuracy index and the differentiation prediction accuracy index for each actual differentiation image based on the data collected by the data acquisition module and the actual differentiation images. The secondary accuracy index characterizes the accuracy of the prediction model for each experimental group, and to a certain extent, it reflects the accuracy of the prediction model. It is also used to select sample data for the training set. The differentiation prediction accuracy index characterizes the accuracy of the prediction model for all experimental groups; the larger the index, the higher the accuracy.

[0060] The various influencing indicators can be obtained by following these steps:

[0061] Each actual differentiation image with an SSIM value greater than the SSIM threshold and its corresponding predicted differentiation image are grouped into an experimental group; each actual differentiation image with an SSIM value less than the SSIM threshold and its corresponding predicted differentiation image are grouped into an error group.

[0062] Specifically, the SSIM threshold can be set by those skilled in the art between 0 and 1 according to the required prediction accuracy;

[0063] The predicted differentiation images of each experimental group in the time period near the predicted differentiation image are extracted from the differentiation result prediction unit as secondary predicted differentiation images of that predicted differentiation image.

[0064] Obtain the SSIM values ​​of each secondary predicted differentiation image and its corresponding actual differentiation image for each experimental group. Select the secondary predicted differentiation image and the predicted differentiation image with the largest corresponding SSIM value as the matching differentiation image, and add the secondary predicted differentiation image to the experimental group where its corresponding predicted differentiation image is located.

[0065] The secondary accuracy index for each experimental group is calculated using the following formula:

[0066] ZB = k1*CS1 + (1-k1)*CS2

[0067]

[0068] Where ZB is the secondary accuracy metric; the larger the value of this metric, the higher the accuracy. k1 is the ideal accuracy weight, CS1 is the ideal accuracy parameter, CS2 is the average accuracy parameter, and SSIM... best To match the SSIM values ​​of the differentiation image and the corresponding actual differentiation image, ssim is the SSIM threshold, e is the natural constant, t1 is the cell differentiation time corresponding to the predicted differentiation image, t2 is the cell differentiation time corresponding to the matched differentiation image, A is the number of secondary predicted differentiation images, and SSIM is... α Let t be the SSIM value of the a-th secondary predicted differentiation image and the corresponding actual differentiation image. a The differentiation time corresponds to the a-th secondary predicted differentiation image; the differentiation time involved in this scheme is the time spent on differentiation.

[0069] The accuracy index for differentiation prediction is calculated using the following formula:

[0070]

[0071] Where zb is the accuracy metric, C is the number of error groups, B is the number of experimental groups, and SSIM is the accuracy metric. c ZB is the SSIM value corresponding to the c-th error group. b This is the secondary accuracy index corresponding to the b-th experimental group.

[0072] S63, determine whether the accuracy index of differentiation prediction is greater than 0. If not, the system will report an error and end the optimization. Otherwise, send the secondary accuracy index and image corresponding to each experimental group to the prediction model optimization module.

[0073] S64, the prediction model optimization module labels the images of each experimental group according to the secondary accuracy index, and sends the labeled images to the differentiation result prediction unit. The differentiation result prediction unit adds the labeled images to the training set.

[0074] The beneficial effects of this solution are: 1. By combining deep learning technology, the differentiation of stem cells can be monitored and the differentiation results of stem cells after a period of time can be predicted. Based on the prediction results, staff can take corresponding environmental adjustment measures, which improves the intelligence level of the system.

[0075] 2. By setting secondary accuracy indicators, the system can autonomously judge the accuracy of different stem cell differentiation predictions. By setting accuracy indicators, it can judge the accuracy of the prediction of differentiation result prediction units and select results suitable for use as training sets. By labeling images with indicator values ​​and using them as training sets, the model can be optimized in a timely manner, which is conducive to continuously improving the model's capabilities.

[0076] Example 2: Figure 4 This embodiment should be understood to include all the features of any of the foregoing embodiments, and to further improve upon them. It also includes a method for determining the impact of environmental parameters on the accuracy of differentiation prediction results, comprising the following steps:

[0077] STEP1 involves placing multiple stem cells at the same differentiation stage or at the same differentiation time into different culture modules, and culturing and differentiating the stem cells under different environments.

[0078] STEP2 uses a differentiation outcome prediction unit to predict the differentiation of stem cells over a period of time.

[0079] STEP3: Obtain actual differentiation images of stem cells over a period of time, and obtain secondary accuracy indicators for each stem cell.

[0080] STEP4: Obtain the influence index of different environmental parameters on the differentiation prediction results using the following formula.

[0081]

[0082] Among them, EF m SSIM represents the impact index of environmental parameter m, where T is the time elapsed from the start of forecasting to the end of forecasting. mt Let SSIM be the SSIM values ​​of the actual and predicted differentiated images at time t corresponding to environmental parameter m, and ZB(t) be the secondary accuracy metric derived from image data from the start of prediction to time t. m (t) represents the environmental parameter m at time t, ZB(t+Δt) is a secondary accuracy metric derived from image data from the start of prediction to time t+Δt, and CS m (t+Δt) represents the value of environmental parameter m at time t+Δt, where Δt is the interval between each prediction.

[0083] Specifically, the larger the value of the influencing indicator, the greater the impact of environmental parameters on the differentiation prediction results.

[0084] The beneficial effects of this embodiment are: by obtaining the influence index of different environmental parameters on the differentiation prediction results, it is helpful to understand the influence of different environments on the differentiation prediction results. By labeling the corresponding image with the index value and inputting it as a training set into the differentiation result prediction unit, it is helpful to improve the accuracy of differentiation result prediction.

[0085] The above-disclosed content is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Therefore, all equivalent technical changes made based on the description and drawings of the present invention are included within the scope of protection of the present invention. Furthermore, the elements therein can be updated as technology develops. The above units are merely examples, and those skilled in the art can adopt corresponding units according to actual needs when implementing this solution.

Claims

1. A deep learning-based stem cell differentiation monitoring system, characterized by, The system includes a culture module, an environment regulation module, a data acquisition module, a differentiation prediction module, and an analysis module. The culture module is used to culture stem cells and provide a site for stem cell differentiation. The environment regulation module is used to regulate the culture environment of the culture module. The data acquisition module is used to collect various parameters and images of the culture module and the environment regulation module during the stem cell differentiation process. The differentiation prediction module is used to predict the differentiation results of stem cells based on the data collected by the data acquisition module. The analysis module is used to obtain the accuracy index of the differentiation prediction and optimize the differentiation prediction module based on the accuracy index. The differentiation prediction module includes a data input unit, a differentiation stage identification unit, and a differentiation result prediction unit. The data input unit is used to receive various data collected by the data acquisition module. The differentiation stage identification unit is used to identify the current differentiation stage or differentiation time of the stem cells based on the data received by the data input unit. The differentiation result prediction unit is used to predict the future differentiation image of the stem cells based on the data received by the data input unit through a prediction model. The analysis module includes an image comparison module, a calculation module, and a prediction model optimization module. The image comparison module is used to compare cell differentiation images at different stages and obtain image similarity. The calculation module is used to calculate the accuracy index of differentiation prediction. The prediction model optimization module is used to optimize the prediction model in the differentiation result prediction unit based on the data obtained from the differentiation prediction module, the calculation module, and the image comparison module. The workflow of the differentiation monitoring system includes the following steps: S1, the culture module is used to culture stem cells; S2, the data acquisition module collects various parameters and images of stem cells during the differentiation process; S3, the differentiation stage identification unit identifies the current differentiation stage of stem cells; S4, the environment control module adjusts the culture environment of some culture containers in the culture module; S5, the differentiation outcome prediction unit predicts the differentiation image of each stem cell over a period of time in the future; S6, the analysis module optimizes the differentiation result prediction unit based on the acquired data; The differentiation outcome prediction unit predicts the differentiation images of individual stem cells over a future period of time by including the following steps: S51, Input the environmental parameters of the culture environment of each stem cell, the set time, and the current differentiation image of each stem cell; S52, The prediction model processes each input to obtain the predicted differentiation image after a set time. The analysis module optimizes the differentiation result prediction unit based on the acquired data, including the following steps: S61, The image comparison module compares the actual differentiation image and the predicted differentiation image after a set time, and obtains the image similarity index of the actual differentiation image and the corresponding predicted differentiation image of each stem cell. S62, the calculation module calculates the secondary accuracy index and the differentiation prediction accuracy index corresponding to each actual differentiation image based on the data collected by the data acquisition module and the actual differentiation images. The secondary accuracy index is used to characterize the accuracy of the prediction model corresponding to each experimental group. The differentiation prediction accuracy index is used to characterize the accuracy of the prediction model corresponding to all experimental groups. The larger the index, the higher the accuracy. The various influencing indicators can be obtained by following these steps: Each actual differentiation image with an SSIM value greater than the SSIM threshold and its corresponding predicted differentiation image are grouped into an experimental group; each actual differentiation image with an SSIM value less than the SSIM threshold and its corresponding predicted differentiation image are grouped into an error group; the predicted differentiation images in the time period near the predicted differentiation image of each experimental group are extracted from the differentiation result prediction unit as the secondary predicted differentiation images of that predicted differentiation image. Obtain the SSIM values ​​of each secondary predicted differentiation image and its corresponding actual differentiation image for each experimental group. Select the secondary predicted differentiation image and the predicted differentiation image with the largest corresponding SSIM value among the predicted differentiation images as the matching differentiation image. Add the secondary predicted differentiation image to the experimental group where its corresponding predicted differentiation image is located. The secondary accuracy index for each experimental group is calculated using the following formula: ； ； ； ； in, This is a secondary accuracy indicator; the higher the value, the greater the accuracy. For ideal accuracy weighting, For ideal accuracy parameters, This is the average accuracy parameter. To match the SSIM values ​​of the differentiated image with the corresponding actual differentiated image, ssim is the SSIM threshold, and e is the natural constant. To predict the differentiation time of cells corresponding to differentiation images, To match the cell differentiation time corresponding to the differentiation image, A is the number of secondary predicted differentiation images. Let SSIM be the SSIM value of the a-th secondary predicted differentiation image and the corresponding actual differentiation image. Let be the differentiation time corresponding to the a-th secondary predicted differentiation image; the differentiation times involved in this scheme are all the time elapsed during differentiation. The accuracy index for differentiation prediction is calculated using the following formula: ； in, For accuracy metrics, C represents the number of incorrect groups, and B represents the number of experimental groups. The SSIM value corresponding to the c-th error group. This represents the secondary accuracy index corresponding to the b-th experimental group; S63, determine whether the accuracy index of differentiation prediction is greater than 0. If not, the system will report an error and end the optimization. Otherwise, send the secondary accuracy index and image corresponding to each experimental group to the prediction model optimization module. S64, the prediction model optimization module labels the images of each experimental group according to the secondary accuracy index, and sends the labeled images to the differentiation result prediction unit. The differentiation result prediction unit adds the labeled images to the training set.

2. The stem cell differentiation monitoring system based on deep learning according to claim 1, wherein, The culture module includes a culture container, a culture medium supply unit, an illumination unit, and a sterilization unit. The culture container is used to contain stem cells and their culture medium. The culture medium supply unit is used to add culture medium to the culture container at regular intervals. The illumination unit is used to illuminate the culture container. The sterilization unit is used to sterilize the culture container. 3.The deep learning-based stem cell differentiation monitoring system of claim 2, wherein The environmental control module includes a gas exchange unit, a temperature control unit, a pH adjustment unit, and a data transmission unit. The gas exchange unit is used to adjust the concentration of various gases in the culture container. The temperature control unit is used to control the ambient temperature of the culture container. The pH adjustment unit is used to adjust the pH value of the culture medium in the culture container. The data transmission unit is used to send the adjustment parameters of the environmental control module to the data acquisition module.

Images