Organoid passage control method, device, electronic device and computer program product

Abstract

The embodiments of the present application provide an organoid passage control method, device, electronic device and computer program product, which relate to the technical field of organoid culture. The organoid passage control method includes: based on a pre-established population structure, constructing a population proportion density matrix of organoids at each time node according to the imaging data at each time node during the organoid growth cycle; combining the population proportion density matrices of organoids at each time node to obtain a temporal population proportion density matrix of organoids; correcting the temporal population proportion density matrix of organoids according to the actual growth function of organoids to obtain a population temporal change matrix of organoids; and performing an organoid passage operation when the population temporal change matrix of organoids meets the passage condition. The embodiments of the present application can achieve the technical effect of accurately controlling the passage of organoids during the automated culture process of organoids and improving the organoid culture efficiency.

Description

Technical Field

[0001] This application relates to the technical field of organoid culture. Specifically, it relates to a method, device, electronic device, and computer program product for controlling organoid passage. Background Technique

[0002] Organoids refer to tissue analogs with a certain spatial structure formed by culturing adult stem cells or pluripotent stem cells in vitro in three dimensions (3D). Organoids can simulate real organs in terms of structure and function, maximize the simulation of in vivo tissue structure and function, and be passaged and cultured stably for a long time. They have broad application prospects in basic research on various organ physiology and pathology, drug screening and development, gene therapy, regenerative medicine, etc. Therefore, the automated technology for organoid culture has emerged accordingly.

[0003] During the automated culture process of organoids, the recognition of the growth state of organoids by machines is the key to connecting the growth cycle nodes of organoids with the automated culture process. However, existing machines are prone to controlling organoid passage too early or too late, leading to a series of problems such as reduced passage benefits, loss of organoid quantity, and poor organoid state, resulting in low organoid culture efficiency. Summary of the Invention

[0004] The purpose of the embodiments of this application is to provide a method, device, electronic device, and computer program product for controlling organoid passage, so as to accurately control organoid passage during the automated culture process of organoids and improve the technical effect of organoid culture efficiency.

[0005] In a first aspect, the embodiments of this application provide a method for controlling organoid passage, including:

[0006] Based on a pre-established clustering structure, construct a clustering proportion density matrix of the organoids at each time node during the organoid growth cycle according to the imaging data at each time node;

[0007] Combine the clustering proportion density matrices of the organoids at each time node to obtain a temporal clustering proportion density matrix of the organoids;

[0008] Modify the temporal clustering proportion density matrix of the organoids according to the actual growth function of the organoids to obtain a clustering temporal change matrix of the organoids;

[0009] When the clustering temporal change matrix of the organoids meets the passage condition, perform the passage operation of the organoids.

[0010] In the above implementation process, based on the clustering structure, a population proportion density matrix of the organoids at each time node is constructed according to the imaging data at each time node during the growth cycle of the organoids. The time-series population proportion density matrix of the organoids is obtained by combining the population proportion density matrices of the organoids at each time node. The time-series population proportion density matrix of the organoids is corrected according to the actual growth function of the organoids, and the passage operation of the organoids is only performed when the obtained population time-series change matrix of the organoids meets the passage conditions. It is possible to accurately determine whether to perform the passage operation of the organoids based on the growth time series and population characteristics of the organoids, thereby accurately controlling the passage of the organoids during the automated culture process of the organoids and improving the culture efficiency of the organoids.

[0011] Further, before constructing the population proportion density matrix of the organoids at each time node according to the imaging data at each time node during the growth cycle of the organoids based on the pre-established clustering structure, it further includes:

[0012] According to the imaging data at multiple time nodes during the growth cycle of the organoids, multiple clustering centers and two outlier critical points are determined;

[0013] Between the multiple clustering centers and the two outlier critical points, the constraint distance of each clustering center is determined;

[0014] According to the constraint distance of each clustering center, the population where each clustering center is located is divided, and the clustering structure is established.

[0015] In the above implementation process, by determining the constraint distance of each clustering center between the multiple clustering centers and the two outlier critical points determined according to the imaging data at multiple time nodes to divide the population where each clustering center is located, the clustering structure can be established quickly and accurately.

[0016] Further, the number of the multiple clustering centers is 4.

[0017] In the above implementation process, by determining four clustering centers to establish the clustering structure, the clustering structure can be simplified on the premise of ensuring accurate establishment of the clustering structure, which is beneficial to improving the subsequent data processing efficiency.

[0018] Further, before constructing the population proportion density matrix of the organoids at each time node according to the imaging data at each time node during the growth cycle of the organoids based on the pre-established clustering structure, it further includes:

[0019] According to the two outlier critical points in the clustering structure, the outlier data in the imaging data at multiple time nodes during the growth cycle of the organoids is screened and removed.

[0020] In the above implementation process, by screening and removing the outlier data in the imaging data of multiple time nodes according to two outlier critical points in the clustering structure, it is possible to accurately judge whether to perform the passage operation of the organoid, so as to accurately control the passage of the organoid in the process of automatic organoid culture and improve the organoid culture efficiency.

[0021] Further, based on the pre-established clustering structure, according to the imaging data of each time node in the growth cycle of the organoid, constructing the clustering proportion density matrix of the organoid at each time node includes:

[0022] For the imaging data of each time node, when the Euclidean distance between the imaging data of the time node and any clustering center point in the clustering structure is less than the constraint distance of the clustering center point, it is determined that the organoid corresponding to the imaging data of the time node is in the cluster where the clustering center point is located;

[0023] Statistical the proportion of the number of organoids in each cluster at the time node in the total number of organoids to obtain the clustering proportion of the organoid at the time node;

[0024] According to the clustering proportion of the organoid at the time node, construct the clustering proportion density matrix of the organoid at the time node.

[0025] In the above implementation process, by determining the number of organoids in each cluster at a single time node according to the Euclidean distance between the imaging data of a single time node and the clustering center points of multiple clusters, and statistically the clustering proportion of the organoid at a single time node to construct the clustering proportion density matrix of the organoid at a single time node, and then combining the clustering proportion density matrices of the organoid at each time node to obtain the temporal clustering proportion density matrix of the organoid, it is possible to quickly and accurately obtain the temporal clustering proportion density matrix of the organoid.

[0026] Further, the method for correcting the temporal clustering proportion density matrix of the organoid according to the actual growth function of the organoid to obtain the temporal change matrix of the clustering of the organoid includes;

[0027] According to the actual growth function of the organoid, construct the temporal correction matrix of the organoid;

[0028] Multiply the transpose matrix of the temporal clustering proportion density matrix of the organoid by the temporal correction matrix of the organoid to obtain the temporal change matrix of the clustering of the organoid.

[0029] In the above implementation process, by constructing a timing correction matrix of the organoid according to the actual growth function of the organoid, multiplying the transpose matrix of the timing clustering proportion density matrix of the organoid by the timing correction matrix of the organoid to obtain the clustering timing change matrix of the organoid, the clustering timing change matrix of the organoid can be constructed quickly and accurately.

[0030] Further, the actual growth function of the organoid is constructed according to the average growth days of the organoid and the number of imaging stages at a single time node;

[0031] Constructing the timing correction matrix of the organoid according to the actual growth function of the organoid includes:

[0032] Substituting the average growth days of the organoid and the number of imaging stages at each time node into the actual growth function of the organoid to obtain the function values corresponding to each time node; wherein, the average growth days of the organoid are determined according to the imaging data of multiple time nodes within the growth cycle of the organoid;

[0033] Combining the function values corresponding to each time node to obtain the timing correction matrix of the organoid.

[0034] In the above implementation process, by substituting the average growth days of the organoid and the number of imaging stages at each time node into the actual growth function of the organoid and combining the obtained function values corresponding to each time node to obtain the timing correction matrix of the organoid, the timing correction matrix of the organoid can be constructed quickly and accurately.

[0035] Further, when the clustering timing change matrix of the organoid meets the passage condition, performing the passage operation of the organoid includes:

[0036] Statistically evaluating the index according to the clustering timing change matrix of the organoid;

[0037] Performing the passage operation of the organoid when the evaluation index is greater than the evaluation index threshold.

[0038] In the above implementation process, by statistically evaluating the index according to the clustering timing change matrix of the organoid and performing the passage operation of the organoid only when the evaluation index is greater than the evaluation index threshold, it is possible to accurately judge whether to perform the passage operation of the organoid based on the growth timing and clustering characteristics of the organoid, thereby accurately controlling the passage of the organoid in the automated organoid culture process and improving the organoid culture efficiency.

[0039] Further, the method further includes:

[0040] When the population time-varying matrix of the organoids satisfies the passage condition, the passage confidence is statistically calculated according to the population proportion density matrix of the organoids over time.

[0041] In the above implementation process, by statistically calculating the passage confidence according to the population proportion density matrix of the organoids over time when the population time-varying matrix of the organoids satisfies the passage condition, it is possible to further accurately determine whether to perform the passage operation of the organoids, thereby accurately controlling the passage of the organoids in the automated organoid culture process and improving the organoid culture efficiency.

[0042] Further, the organoids include tumor organoids.

[0043] In a second aspect, an organoid passage control device provided by an embodiment of the present application includes:

[0044] A matrix construction module, configured to construct a population proportion density matrix of the organoids at each time node based on a pre-established population structure and according to imaging data at each time node during the growth cycle of the organoids;

[0045] A matrix combination module, configured to combine the population proportion density matrices of the organoids at each time node to obtain a population time-varying proportion density matrix of the organoids;

[0046] A matrix correction module, configured to correct the population time-varying proportion density matrix of the organoids according to the actual growth function of the organoids to obtain a population time-varying matrix of the organoids;

[0047] A passage control module, configured to perform the passage operation of the organoids when the population time-varying matrix of the organoids satisfies the passage condition.

[0048] In a third aspect, an electronic device provided by an embodiment of the present application includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; the memory is coupled to the processor, and when the processor executes the computer program, the method described above is implemented.

[0049] In a fourth aspect, a computer program product provided by an embodiment of the present application includes instructions that, when executed by a computer, cause the computer to implement the method described above.

[0050] In a fifth aspect, a computer-readable storage medium provided by an embodiment of the present application includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method described above. Description of the Drawings

[0051] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following accompanying drawings only show some embodiments of the present application, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related accompanying drawings can be obtained based on these drawings without creative efforts.

[0052] Figure 1 It is a schematic flowchart of an organoid passage control method provided by the first embodiment of the present application;

[0053] Figure 2 It is a schematic diagram of the population structure of the organoids exemplified by the first embodiment of the present application;

[0054] Figure 3 It is a schematic diagram of constructing the population proportion density matrix of the organoids at the first time node in the first embodiment of the present application;

[0055] Figure 4 It is a schematic structural diagram of an organoid passage control device provided by the second embodiment of the present application;

[0056] Figure 5 It is a schematic structural diagram of an electronic device provided by the third embodiment of the present application. Detailed implementation manners

[0057] Next, the technical solutions in the embodiments of the present application will be described in conjunction with the accompanying drawings in the embodiments of the present application.

[0058] It should be noted that in the description of the present application, the terms "first", "second", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance. At the same time, the step numbers in the text are only for the convenience of explaining the embodiments of the present application and do not serve as a function of limiting the execution order of the steps.

[0059] Next, in conjunction with Figures 1-3 A description will be given of an organoid passage control method according to an embodiment of the present application. The method provided by the embodiment of the present application can be executed by a relevant terminal device. Hereinafter, a control device will be taken as an example of the execution subject for description.

[0060] Please refer to Figure 1 , Figure 1 It is a schematic flowchart of an organoid passage control method provided by the first embodiment of the present application. The first embodiment of the present application provides an organoid passage control method, including steps S101 to S104:

[0061] S101. Based on a pre-established clustering structure, construct a clustering proportion density matrix of the organoids at each time node according to the imaging data at each time node during the growth cycle of the organoids.

[0062] Exemplarily, according to actual application requirements, pre-establish a clustering structure, and during the automated culture process of the organoids, obtain imaging data at multiple time nodes during the growth cycle of the organoids, such as imaging area data. The imaging data at each time node may have only one data, or may have two or more data.

[0063] Based on the clustering structure, construct a clustering proportion density matrix of the organoids at each time node according to the imaging data at each time node.

[0064] For example, assume that there are four time nodes during the growth cycle of the organoids, and obtain imaging data at the four time nodes. For the imaging data at each time node, based on the clustering structure, construct a clustering proportion density matrix of the organoids at that time node according to the imaging data at that time node, so as to obtain a clustering proportion density matrix of the organoids at the four time nodes.

[0065] S102. Combine the clustering proportion density matrices of the organoids at each time node to obtain a temporal clustering proportion density matrix of the organoids.

[0066] Exemplarily, after constructing the clustering proportion density matrices of the organoids at each time node, combine the clustering proportion density matrices of the organoids at each time node to obtain a temporal clustering proportion density matrix of the organoids.

[0067] There are multiple clusters in the clustering structure. The clustering proportion density matrix of the organoids at a single time node characterizes the clustering proportion of the organoids in the clustering structure at a single time node, and the temporal clustering proportion density matrix of the organoids characterizes the clustering proportion of the organoids in the clustering structure during the growth cycle of the organoids.

[0068] S103. Modify the temporal clustering proportion density matrix of the organoids according to the actual growth function of the organoids to obtain a temporal change matrix of the clustering of the organoids.

[0069] Exemplarily, consider the actual growth situation of the organoids during the automated culture process of the organoids, and pre-construct the actual growth function of the organoids.

[0070] After obtaining the temporal clustering proportion density matrix of the organoids, modify the temporal clustering proportion density matrix of the organoids according to the actual growth function of the organoids to obtain a temporal change matrix of the clustering of the organoids.

[0071] Since the time-series change matrix of the organoid population clusters is obtained by correcting the time-series population proportion density matrix of the organoids according to the actual growth function of the organoids, the time-series change matrix of the organoid population clusters characterizes the process of the change of the population proportion of the organoids in the population structure during the growth cycle of the organoids with the change of the actual growth time of the organoids.

[0072] S104. When the time-series change matrix of the organoid population clusters meets the passage condition, perform the passage operation on the organoids.

[0073] Exemplarily, according to the actual application requirements, preset the passage conditions. After obtaining the time-series change matrix of the organoid population clusters, determine whether the time-series change matrix of the organoid population clusters meets the passage conditions. If it is determined that the time-series change matrix of the organoid population clusters meets the passage conditions, it is considered that the growth condition of the current organoids has reached the passage requirement, and perform the passage operation on the organoids. If it is determined that the time-series change matrix of the organoid population clusters does not meet the passage conditions, it is considered that the growth condition of the current organoids has not reached the passage requirement, and do not perform the passage operation on the organoids.

[0074] In practical applications, if it is determined that the time-series change matrix of the organoid population clusters meets the passage conditions, a trigger signal can be sent to the execution device to trigger the execution device to perform the passage operation on the organoids, or a notification message can be sent to the user terminal to notify the user to manually perform the passage operation on the organoids.

[0075] In the embodiment of the present application, based on the population structure, the population proportion density matrix of the organoids at each time node during the growth cycle of the organoids is constructed according to the imaging data at each time node, the time-series population proportion density matrix of the organoids is obtained by combining the population proportion density matrices of the organoids at each time node, the time-series population proportion density matrix of the organoids is corrected according to the actual growth function of the organoids, and the passage operation on the organoids is only performed when the obtained time-series change matrix of the organoid population clusters meets the passage conditions, so that it is possible to accurately determine whether to perform the passage operation on the organoids based on the growth time series and population characteristics of the organoids, thereby realizing accurate control of the passage of the organoids in the automated organoid culture process and improving the organoid culture efficiency.

[0076] The population structure in the embodiment of the present application can be custom-built by the user, or can be established for the imaging data at multiple time nodes after obtaining the imaging data at multiple time nodes during the growth cycle of the organoids.

[0077] In an alternative embodiment, before constructing the cluster proportion density matrix of the organoids at each time node based on the pre-established cluster structure according to the imaging data at each time node during the organoid growth cycle, the method further includes: determining a plurality of cluster centers and two outlier critical points according to the imaging data at multiple time nodes during the organoid growth cycle; determining the constraint distance of each cluster center between the plurality of cluster centers and the two outlier critical points; dividing the clusters where each cluster center is located according to the constraint distance of each cluster center, and establishing a cluster structure.

[0078] As an example, after obtaining the imaging data at multiple time nodes during the organoid growth cycle, a plurality of cluster centers and two outlier critical points are determined according to the imaging data at the multiple time nodes.

[0079] In practical applications, the change characteristics of the imaging data during the organoid growth cycle, such as the area change characteristics, can be analyzed according to the imaging data at multiple time nodes, and a plurality of cluster centers and two outlier critical points can be determined according to the change characteristics of the imaging data.

[0080] The constraint distance of each cluster center is determined between the plurality of cluster centers and the two outlier critical points.

[0081] In practical applications, the constraint distance between a single imaging data and each cluster center can be determined according to the logarithmic proliferation characteristic curve of the organoid growth between the plurality of cluster centers and the two outlier critical points, so as to determine the constraint distance of each cluster center.

[0082] It can be understood that the logarithmic proliferation characteristic curve of the organoid growth refers to a curve that describes the growth of the number of cells during the organoid growth process. This curve usually presents as a curve with a changing slope, indicating that the cell growth rate changes over time. Determining the constraint distance of each cluster center according to the logarithmic proliferation characteristic curve of the organoid growth can ensure the accurate determination of the constraint distance of each cluster center.

[0083] The clusters where each cluster center is located are divided according to the constraint distance of each cluster center, and a cluster structure is established.

[0084] By determining the constraint distance of each cluster center between the plurality of cluster centers and the two outlier critical points determined according to the imaging data at multiple time nodes to divide the clusters where each cluster center is located, the embodiment of the present application can quickly and accurately establish a cluster structure.

[0085] In an alternative embodiment, the number of the plurality of cluster centers is 4.

[0086] Exemplarily, based on the imaging data at multiple time nodes, four cluster centers and two outlier critical points are determined. Between the four cluster centers and the two outlier critical points, the constraint distances of the four cluster centers are determined. According to the constraint distances of the four cluster centers, the clusters where the four cluster centers are located are correspondingly divided, and a cluster structure is established.

[0087] For example, the cluster structure is as Figure 2 shown. In Figure 2 , the constraint distances of the four cluster centers, namely Cluster_1, Cluster_2, Cluster_3, and Cluster_4, are Distance_C1, Distance_C2, Distance_C3, and Distance_C4, respectively.

[0088] In the embodiment of the present application, by determining four cluster centers to establish a cluster structure, it is possible to simplify the cluster structure while ensuring the accurate establishment of the cluster structure, which is beneficial to improving the subsequent data processing efficiency.

[0089] In an alternative embodiment, before constructing the cluster occupancy density matrix of the organoids at each time node based on the pre-established cluster structure according to the imaging data at each time node during the growth cycle of the organoids, it further includes: screening and removing the outlier data in the imaging data at multiple time nodes during the growth cycle of the organoids according to the two outlier critical points in the cluster structure.

[0090] Exemplarily, considering that the outlier data cannot participate in determining whether to perform the passage operation of the organoids, after obtaining the imaging data at multiple time nodes during the growth cycle of the organoids, the outlier data in the imaging data at multiple time nodes is screened according to the two outlier critical points in the cluster structure, and the outlier data in the imaging data at multiple time nodes is removed.

[0091] In practical applications, the outlier data in the imaging data at multiple time nodes can be screened according to the distribution positions of the imaging data at multiple time nodes in the cluster structure. Specifically, it can be determined whether the imaging data at each time node is distributed at the outlier critical point. If the imaging data at any time node is distributed at the outlier critical point, it is considered that the imaging data at that time node is outlier data, and the imaging data at that time node is removed.

[0092] For example, during the growth cycles of 41 independently passaged tumor organoids, area data of 93,989 tumor organoid images were collected. At two outlier critical points in the clustering structure, area data of 20,109 tumor organoid images were excluded, and the data efficiency was 78.6%. It can be understood that for each imaging analysis result of an independent sample, discrete data distributed at the outlier critical points is excluded. By excluding discrete data in the imaging data of multiple time nodes, a clustering structure can be established based on the remaining valid imaging data of multiple time nodes.

[0093] In practical applications, it is also possible to determine whether the imaging data of each time node is abnormal data. If the imaging data of any time node is abnormal data, the imaging data of that time node is excluded to avoid interference from abnormal data.

[0094] In the embodiment of the present application, by screening outlier data in the imaging data of multiple time nodes according to two outlier critical points in the clustering structure, it is possible to accurately determine whether to perform the passaging operation of the organoids, thereby accurately controlling the passaging of organoids during the automated organoid culture process and improving the organoid culture efficiency.

[0095] In an optional embodiment, based on the pre-established clustering structure, according to the imaging data of each time node during the organoid growth cycle, a clustering proportion density matrix of the organoids at each time node is constructed, including: for the imaging data of each time node, when the Euclidean distance between the imaging data of the time node and any cluster center point in the clustering structure is less than the constraint distance of the cluster center point, it is determined that the organoid corresponding to the imaging data of the time node is in the cluster where the cluster center point is located; count the proportion of the number of organoids in each cluster at the time node in the total number of organoids to obtain the clustering proportion of the organoids at the time node; construct a clustering proportion density matrix of the organoids at the time node according to the clustering proportion of the organoids at the time node.

[0096] As an example, after the clustering structure is established, there are multiple clusters where the cluster center points are located in the clustering structure.

[0097] For the imaging data of each time node, calculate the Euclidean distance between the imaging data of the time node and each cluster center point. When the Euclidean distance between the imaging data of the time node and any cluster center point is less than the constraint distance of the cluster center point, it is determined that the organoid corresponding to the imaging data of the time node is in the cluster where the cluster center point is located.

[0098] Count the number of organoids in each subpopulation at this time node, and count the total number of organoids in multiple subpopulations at this time node. Calculate the proportion of the number of organoids in each subpopulation at this time node in the total number of organoids to obtain the subpopulation proportion of organoids at this time node.

[0099] According to the subpopulation proportion of organoids at this time node, construct the subpopulation proportion density matrix of organoids at this time node, so as to obtain the subpopulation proportion density matrix of organoids at each time node.

[0100] The subpopulation proportion of organoids at this time node includes the proportion of the number of organoids in each subpopulation at this time node in the total number of organoids. In practical applications, the proportions of the number of organoids in each subpopulation at this time node in the total number of organoids can be combined to obtain the subpopulation proportion density matrix of organoids at this time node.

[0101] Specifically, the subpopulation proportion density matrix of organoids at each time node is:

[0102]

[0103] In formula (1), ρ t is the subpopulation proportion density matrix of organoids at the t-th time node, t = {1, 2,..., T}, T represents the last time node, r t,i is the proportion of the number of organoids in the i-th subpopulation at the t-th time node in the total number of organoids, N t,i is the number of organoids in the i-th subpopulation at the t-th time node, N t,j is the number of organoids in the j-th subpopulation at the t-th time node, i, j = {1, 2,..., n}, n represents the last subpopulation in the subpopulation structure.

[0104] For example, the schematic diagram of constructing the subpopulation proportion density matrix of organoids at the 1st time node is as Figure 3 shown. In Figure 3 , there are four subpopulations in the subpopulation structure, and the subpopulation proportion of organoids at the 1st time node is {r 1,1 , r 1,2 , r 1,3 , r 1,4}, then the subpopulation proportion density matrix of organoids at the 1st time node is

[0105] After obtaining the subpopulation proportion density matrix of organoids at each time node, combine the subpopulation proportion density matrices of organoids at each time node to obtain the temporal subpopulation proportion density matrix of organoids.

[0106] Specifically, the time-series clustering proportion density matrix of the organoids is as follows:

[0107]

[0108] In formula (2), ρ is the time-series clustering proportion density matrix of the organoids, and ρ t is the clustering proportion density matrix of the organoids at the t-th time node, where t = {1, 2,..., T}, and T represents the last time node.

[0109] For example, assume there is imaging data at four time nodes during the growth cycle of the organoids, there are four clusters in the clustering structure of the organoids, and the clustering proportion density matrices of the organoids at the four time nodes are respectively and Then the time-series clustering proportion density matrix of the organoids is

[0110]

[0111] In the embodiment of the present application, by determining the number of organoids in each cluster at a single time node according to the Euclidean distance between the imaging data at a single time node and the clustering center points of multiple clusters, and statistically analyzing the clustering proportion of the organoids at a single time node to construct the clustering proportion density matrix of the organoids at a single time node, and then combining the clustering proportion density matrices of the organoids at each time node to obtain the time-series clustering proportion density matrix of the organoids, the time-series clustering proportion density matrix of the organoids can be obtained quickly and accurately.

[0112] In an optional embodiment, the method of modifying the time-series clustering proportion density matrix of the organoids according to the actual growth function of the organoids to obtain the time-series change matrix of the organoids' clustering includes: constructing a time-series correction matrix of the organoids according to the actual growth function of the organoids; multiplying the transposed matrix of the time-series clustering proportion density matrix of the organoids by the time-series correction matrix of the organoids to obtain the time-series change matrix of the organoids' clustering.

[0113] Exemplarily, considering the actual growth situation of the organoids during the automated culture process of the organoids, the actual growth function of the organoids is pre-constructed.

[0114] After obtaining the actual growth function of the organoids, a time-series correction matrix of the organoids is constructed according to the actual growth function of the organoids.

[0115] After obtaining the time-series correction matrix of the organoids, the time-series change matrix of the organoids' clustering is obtained by combining the time-series correction matrix of the organoids and the time-series clustering proportion density matrix of the organoids.

[0116] Specifically, the transposed matrix of the time-series cluster proportion density matrix of the organoids can be multiplied by the time-series correction matrix of the organoids to obtain the time-series change matrix of the organoid clustering. The time-series change matrix of the organoid clustering is as follows:

[0117] C = ρ' × D (3);

[0118] In formula (3), C is the time-series change matrix of the organoid clustering, ρ' is the transposed matrix of the time-series cluster proportion density matrix of the organoids, ρ'=(ρ) T , ρ is the time-series cluster proportion density matrix of the organoids, and D is the time-series correction matrix of the organoids.

[0119] In the embodiments of the present application, by constructing the time-series correction matrix of the organoids according to the actual growth function of the organoids, and multiplying the transposed matrix of the time-series cluster proportion density matrix of the organoids by the time-series correction matrix of the organoids to obtain the time-series change matrix of the organoid clustering, the time-series change matrix of the organoid clustering can be constructed quickly and accurately.

[0120] In an optional embodiment, the actual growth function of the organoids is constructed according to the average growth days of the organoids and the imaging stage number at a single time node; the constructing of the time-series correction matrix of the organoids according to the actual growth function of the organoids includes: substituting the average growth days of the organoids and the imaging stage number at each time node into the actual growth function of the organoids to obtain the function values corresponding to each time node; wherein, the average growth days of the organoids are determined according to the imaging data at multiple time nodes during the growth cycle of the organoids; combining the function values corresponding to each time node to obtain the time-series correction matrix of the organoids.

[0121] Exemplarily, considering the actual growth situation of the organoids during the automated culture of the organoids, the actual growth function of the organoids is constructed in advance according to the average growth days of the organoids and the imaging stage number at a single time node.

[0122] According to the imaging data at multiple time nodes during the growth cycle of the organoids, the average growth days of the organoids are determined.

[0123] In practical applications, the average growth days corresponding to the maximum slope value in the logarithmic growth phase of the organoids in the imaging data at multiple time nodes can be used as the average growth days of the organoids.

[0124] And determine the imaging stage number at each time node.

[0125] In practical applications, the imaging stages corresponding to each time node may be the same or different. If the imaging stage corresponding to the first time node is the first imaging stage, the number of imaging stages at the first time node is 1. If the imaging stage corresponding to the second time node is the first imaging stage or the second imaging stage, the number of imaging stages at the second time node is 1 or 2, and so on, to determine the number of imaging stages at each time node.

[0126] In addition, the number of imaging stages can be converted into the actual number of culture days, and the actual culture time of the organoid at a single time node can be expressed by using the actual number of culture days instead.

[0127] Since in practical applications, usually according to a preset imaging cycle, for example, collecting organoid images every 5 days, extracting imaging data from the organoid images collected at the current time node, such as the area data of the imaging, to obtain the imaging data at the current time node, so the actual number of culture days at each time node can be calculated according to the preset imaging cycle and the number of imaging times corresponding to each time node. Specifically, multiply the number of imaging times corresponding to each time node by the preset imaging cycle to obtain the actual number of culture days at each time node. If the number of imaging times corresponding to the first time node is 1, the actual number of culture days at the first time node is 1×5 = 5 (unit: days). If the number of imaging times corresponding to the second time node is 2, the actual number of culture days at the second time node is 2×5 = 10 (unit: days), and so on, to determine the actual number of culture days at each time node.

[0128] After obtaining the average growth days of the organoid and the number of imaging stages / actual number of culture days at each time node, substitute the average growth days of the organoid and the number of imaging stages / actual number of culture days at each time node into the actual growth function of the organoid to obtain the function values corresponding to each time node.

[0129] Specifically, the actual growth function of the organoid is:

[0130]

[0131] In Equation (4), f(t) represents the actual growth function of the organoid, d t is the function value corresponding to the t-th time node, a is the average growth days of the organoid, b t is the number of imaging stages / actual number of culture days at the t-th time node, t = {1, 2,..., T}, and T represents the last time node.

[0132] Combine the function values corresponding to each time node to obtain the temporal correction matrix of the organoid.

[0133] Specifically, the temporal correction matrix of the organoid is:

[0134]

[0135] In formula (5), D is the temporal correction matrix of the organoid, and d t is the function value corresponding to the t-th time node, where t = {1, 2,..., T}, and T represents the last time node.

[0136] In the embodiment of the present application, by substituting the average growth days of the organoid and the number of imaging stages at each time node into the actual growth function of the organoid, the function values corresponding to each time node are combined to obtain the temporal correction matrix of the organoid, which can quickly and accurately construct the temporal correction matrix of the organoid.

[0137] In an alternative embodiment, when the population temporal change matrix of the organoid meets the passage condition, the passage operation of the organoid is performed, including: according to the population temporal change matrix of the organoid, statistical evaluation indicators are calculated; when the evaluation indicator is greater than the evaluation indicator threshold, the passage operation of the organoid is performed.

[0138] Exemplarily, according to actual application requirements, the passage condition is preset as the evaluation indicator calculated according to the population temporal change matrix of the organoid is greater than the evaluation indicator threshold, such as 0.

[0139] After obtaining the population temporal change matrix of the organoid, a first target element, a second target element, and a third target element are selected from the population temporal change matrix of the organoid, and the evaluation indicator is statistically calculated in combination with the first target element, the second target element, and the third target element. Among them, the first target element is an element in the population temporal change matrix of the organoid that is not affected by the logarithmic proliferation characteristics of the organoid and is in the adjustment period of the logarithmic proliferation characteristic curve of the organoid growth; the second target element is an element in the population temporal change matrix of the organoid that is not affected by the logarithmic proliferation characteristics of the organoid and is in the late logarithmic phase of the logarithmic proliferation characteristic curve of the organoid growth; the third target element is an element in the population temporal change matrix of the organoid that is not affected by the logarithmic proliferation characteristics of the organoid and is in the plateau phase of the logarithmic proliferation characteristic curve of the organoid growth.

[0140] Specifically, the evaluation indicator = the sum of (the second target element + the third target element) - the first target element.

[0141] Since the population temporal change matrix of the organoid is:

[0142] C = ρ′ × D(3);

[0143] In formula (3), C is the population temporal change matrix of the organoid, ρ′ is the transposed matrix of the temporal population proportion density matrix of the organoid, and ρ′ = (ρ) T, ρ is the time-series clustering proportion density matrix of the organoids, and D is the time-series correction matrix of the organoids.

[0144] The time-series correction matrix of the organoids is:

[0145]

[0146] In Equation (5), D is the time-series correction matrix of the organoids, and d t is the function value corresponding to the t-th time node, where t = {1, 2,..., T}, and T represents the last time node.

[0147] Therefore, the time-series change matrix of the organoid clustering is a matrix with n rows and 1 column.

[0148] For example, assuming that the clustering structure has four clusters, the time-series change matrix of the organoid clustering is The element c 1,1 in the first row and first column of the time-series change matrix of the organoid clustering can be selected as the first target element, and the elements c 3,1 and c 4,1 in the last two rows of the first column are selected as the second target element and the third target element respectively, and the statistical evaluation index Δ = (c 3,1 + c 4,1 ) - c 1,1 .

[0149] After obtaining the evaluation index, compare the evaluation index with the evaluation index threshold. If the evaluation index is greater than the evaluation index threshold, it is considered that the growth of the current organoids has reached the subculture requirement, and the subculture operation of the organoids is performed. If the evaluation index is less than or equal to the evaluation index threshold, it is considered that the growth of the current organoids has not reached the subculture requirement, and the subculture operation of the organoids is not performed.

[0150] In the embodiments of the present application, by statistically evaluating the index according to the time-series change matrix of the organoid clustering and performing the subculture operation of the organoids only when the evaluation index is greater than the evaluation index threshold, it is possible to accurately determine whether to perform the subculture operation of the organoids based on the growth time series and clustering characteristics of the organoids, thereby accurately controlling the subculture of the organoids in the automated culture process of the organoids and improving the culture efficiency of the organoids.

[0151] In an alternative embodiment, the method further includes step S105:

[0152] S105. When the time-series change matrix of the organoid clustering meets the subculture condition, statistically calculate the subculture confidence according to the time-series clustering proportion density matrix of the organoids.

[0153] Exemplarily, when the time-series change matrix of the organoid population clustering meets the passage condition, for example, when the evaluation index calculated based on the time-series change matrix of the organoid population clustering is greater than the evaluation index threshold, the fourth target element, the fifth target element, the sixth target element, and the seventh target element are also selected from the time-series population proportion density matrix of the organoids. The passage confidence is calculated by combining the fourth target element, the fifth target element, the sixth target element, and the seventh target element. Among them, the fourth target element is the element in the time-series population proportion density matrix of the organoids corresponding to the first target element and the first time node, the fifth target element is the element in the time-series population proportion density matrix of the organoids corresponding to the first target element and the last time node, the sixth target element is the element in the time-series population proportion density matrix of the organoids corresponding to the second target element and the last time node, and the seventh target element is the element in the time-series population proportion density matrix of the organoids corresponding to the third target element and the last time node.

[0154] Specifically, the passage confidence = [((the fourth target element - the fifth target element) / the fourth target element) + (the sixth target element + the seventh target element)] / 2.

[0155] In practical applications, since the population proportion density matrix of the organoids at each time node is:

[0156]

[0157] In formula (1), ρ t is the population proportion density matrix of the organoids at the t-th time node, where t = {1, 2,..., T}, T represents the last time node, and r t,i is the proportion of the number of organoids in the i-th population at the t-th time node in the total number of organoids. N t,i is the number of organoids in the i-th population at the t-th time node, and N t,j is the number of organoids in the j-th population at the t-th time node, where i, j = {1, 2,..., n}, and n represents the last population in the population structure.

[0158] The time-series population proportion density matrix of the organoids is:

[0159]

[0160] In formula (2), ρ is the time-series population proportion density matrix of the organoids, and ρ t is the population proportion density matrix of the organoids at the t-th time node, where t = {1, 2,..., T}, and T represents the last time node.

[0161] Therefore, the time-series clustering proportion density matrix of the organoids is a matrix with T rows and n columns, and the time-series clustering proportion density matrix of the organoids is

[0162] For example, assume there is imaging data at four time nodes during the growth cycle of the organoids, and there are four clusters in the clustering structure. The statistical evaluation index Δ=(c 3,1 +c 4,1 )-c 1,1 , then the time-series clustering proportion density matrix of the organoids is The element r 1,1 in the first row and first column can be selected from the time-series clustering proportion density matrix of the organoids as the fourth target element, and the element r 4，1 in the fourth row and first column is selected as the fifth target element. The elements r 4,3 and r 4,4 in the last two columns of the fourth row are respectively selected as the sixth target element and the seventh target element to statistically calculate the passage confidence

[0163] After statistically calculating the passage confidence, directly send the passage confidence to the user terminal, so that the user can determine the confidence of the sample passage, and can also reconfirm whether to perform the passage operation of the organoids according to the passage confidence and return the corresponding indication information.

[0164] In practical applications, the confidence threshold can also be preset according to actual application requirements, such as 75%.

[0165] After obtaining the evaluation index and the passage confidence, compare the evaluation index with the evaluation index threshold, and compare the passage confidence with the confidence threshold. If the evaluation index is greater than the evaluation index threshold and the passage confidence is greater than the confidence threshold, it is considered that the growth condition of the current organoids has reached the passage requirement, and the passage operation of the organoids is performed. If the evaluation index is less than or equal to the evaluation index threshold or the passage confidence is less than or equal to the confidence threshold, it is considered that the growth condition of the current organoids has not reached the passage requirement, and the passage operation of the organoids is not performed.

[0166] In the embodiment of the present application, when the clustering time-series change matrix of the organoids meets the passage condition, the passage confidence is statistically calculated according to the time-series clustering proportion density matrix of the organoids, which can further accurately determine whether to perform the passage operation of the organoids, so as to accurately control the passage of the organoids during the automated culture process of the organoids and improve the organoid culture efficiency.

[0167] In an alternative embodiment, the organoids include tumor organoids.

[0168] Exemplarily, according to actual application requirements, the organoids can be any one of tumor organoids, liver cancer organoids, lung cancer organoids, kidney organoids, etc.

[0169] Please refer to Figure 4 , Figure 4 which is a schematic structural diagram of an organoid passage control device provided in the second embodiment of the present application. The second embodiment of the present application provides an organoid passage control device, including: a matrix construction module 201, configured to construct a population proportion density matrix of organoids at each time node based on the imaging data at each time node during the organoid growth cycle according to a pre-established population structure; a matrix combination module 202, configured to combine the population proportion density matrices of organoids at each time node to obtain a temporal population proportion density matrix of organoids; a matrix correction module 203, configured to correct the temporal population proportion density matrix of organoids according to the actual growth function of organoids to obtain a population temporal change matrix of organoids; and a passage control module 204, configured to perform a passage operation on the organoids when the population temporal change matrix of the organoids meets the passage condition.

[0170] In an alternative embodiment, the matrix construction module 201 is further configured to, before constructing the population proportion density matrix of organoids at each time node based on the imaging data at each time node during the organoid growth cycle according to the pre-established population structure, determine a plurality of clustering center points and two outlier critical points according to the imaging data at multiple time nodes during the organoid growth cycle; determine the constraint distance of each clustering center point between the plurality of clustering center points and the two outlier critical points; and divide the populations where each clustering center point is located according to the constraint distance of each clustering center point to establish a population structure.

[0171] In an alternative embodiment, the number of the plurality of clustering center points is 4.

[0172] In an alternative embodiment, the matrix construction module 201 is further configured to, before constructing the population proportion density matrix of organoids at each time node based on the imaging data at each time node during the organoid growth cycle according to the pre-established population structure, screen and remove outlier data from the imaging data at multiple time nodes during the organoid growth cycle according to the two outlier critical points in the population structure.

[0173] In an alternative embodiment, based on the pre-established clustering structure, according to the imaging data at each time node during the growth cycle of the organoid, constructing a population proportion density matrix of the organoid at each time node includes: for the imaging data at each time node, when the Euclidean distance between the imaging data at the time node and any clustering center point in the clustering structure is less than the constraint distance of the clustering center point, determining that the organoid corresponding to the imaging data at the time node is in the population where the clustering center point is located; counting the proportion of the number of organoids in each population at the time node in the total number of organoids to obtain the population proportion of the organoid at the time node; and constructing a population proportion density matrix of the organoid at the time node according to the population proportion of the organoid at the time node.

[0174] In an alternative embodiment, modifying the temporal population proportion density matrix of the organoid according to the actual growth function of the organoid to obtain a population temporal change matrix of the organoid includes: constructing a temporal correction matrix of the organoid according to the actual growth function of the organoid; multiplying the transposed matrix of the temporal population proportion density matrix of the organoid by the temporal correction matrix of the organoid to obtain a population temporal change matrix of the organoid.

[0175] In an alternative embodiment, the actual growth function of the organoid is constructed according to the average growth days of the organoid and the imaging stages at a single time node; constructing a temporal correction matrix of the organoid according to the actual growth function of the organoid includes: substituting the average growth days of the organoid and the imaging stages at each time node into the actual growth function of the organoid to obtain the function values corresponding to each time node; wherein, the average growth days of the organoid are determined according to the imaging data at multiple time nodes during the growth cycle of the organoid; and combining the function values corresponding to each time node to obtain a temporal correction matrix of the organoid.

[0176] In an alternative embodiment, when the population temporal change matrix of the organoid meets the passage condition, performing a passage operation on the organoid includes: statistically evaluating an evaluation index according to the population temporal change matrix of the organoid; and performing a passage operation on the organoid when the evaluation index is greater than the evaluation index threshold.

[0177] In an alternative embodiment, the passage control module 204 is further configured to: when the population temporal change matrix of the organoid meets the passage condition, statistically calculate a confidence level according to the temporal population proportion density matrix of the organoid.

[0178] In an alternative embodiment, the organoid includes a tumor organoid.

[0179] The implementation processes of the functions and roles of each module in the above device are specifically detailed in the implementation processes of the corresponding steps in the above method, and will not be repeated here.

[0180] Please refer to Figure 5 , Figure 5 which is a schematic structural diagram of an electronic device provided by the third embodiment of the present application. The third embodiment of the present application provides an electronic device 30, including a processor 301, a memory 302, and a computer program stored in the memory 302 and configured to be executed by the processor 301; the memory 302 is coupled to the processor 301, and when the processor 301 executes the computer program, it implements the method described in the first embodiment of the present application and can achieve the same beneficial effects.

[0181] Among them, when the processor 301 reads the computer program from the memory 302 through the bus 303 and executes the computer program, it can implement the method described in the first embodiment of the present application.

[0182] The processor 301 can process digital signals and can include various computing structures. For example, a complex instruction set computer structure, a reduced instruction set computer structure, or a structure that implements a combination of multiple instruction sets. In some examples, the processor 301 can be a microprocessor.

[0183] The memory 302 can be used to store instructions executed by the processor 301 or data related to the instruction execution process. These instructions and / or data can include code for implementing some or all of the functions of one or more modules described in the embodiments of the present application. The processor 301 of this embodiment can be used to execute the instructions in the memory 302 to implement the method described in the first embodiment of the present application. The memory 302 includes dynamic random access memory, static random access memory, flash memory, optical memory, or other memories well-known to those skilled in the art.

[0184] The fourth embodiment of the present application provides a computer program product. The computer program product includes instructions that, when executed by a computer, cause the computer to implement the method described in the first embodiment of the present application and can achieve the same beneficial effects.

[0185] The method described in the first embodiment of the present application can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the process or function described in the first embodiment of the present application is executed in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user device, a core network device, an OAM (Open Application Model), or other programmable devices.

[0186] The computer program or instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer program or instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless manner. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or a data center integrating one or more available media. The available medium may be a magnetic medium, such as a floppy disk, a hard disk, or a magnetic tape; it may also be an optical medium, such as a digital video disc; or it may be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0187] The fifth embodiment of the present application provides a computer-readable storage medium, which includes a stored computer program; wherein, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the method described in the first embodiment of the present application and can achieve the same beneficial effects.

[0188] In summary, the embodiments of the present application provide an organoid passage control method, apparatus, electronic device, and computer program product. The organoid passage control method includes: based on a pre-established clustering structure, constructing a clustering proportion density matrix of the organoids at each time node during the growth cycle of the organoids according to the imaging data at each time node; combining the clustering proportion density matrices of the organoids at each time node to obtain a temporal clustering proportion density matrix of the organoids; correcting the temporal clustering proportion density matrix of the organoids according to the actual growth function of the organoids to obtain a clustering temporal change matrix of the organoids; and performing the passage operation of the organoids when the clustering temporal change matrix of the organoids meets the passage condition. By constructing the clustering proportion density matrix of the organoids at each time node based on the clustering structure according to the imaging data at each time node during the growth cycle of the organoids, combining the clustering proportion density matrices of the organoids at each time node to obtain the temporal clustering proportion density matrix of the organoids, correcting the temporal clustering proportion density matrix of the organoids according to the actual growth function of the organoids, and performing the passage operation of the organoids only when the obtained clustering temporal change matrix of the organoids meets the passage condition, the embodiments of the present application can accurately determine whether to perform the passage operation of the organoids based on the growth time sequence and clustering characteristics of the organoids, so as to accurately control the passage of the organoids during the automated culture process of the organoids and improve the culture efficiency of the organoids.

[0189] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of devices, methods, and computer program products according to multiple embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code, and the module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system that performs the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0190] In addition, each functional module in various embodiments of this application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0191] If the described function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, etc., which can store program codes.

[0192] The above are only embodiments of the present application and are not intended to limit the protection scope of the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application. It should be noted that similar reference numerals and letters indicate similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings.

[0193] As described above, the above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, and all should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

[0194] It should be noted that in this text, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

Claims

1. A method for controlling organoid passage, characterized in that: include: Based on the pre-established clustering structure, and according to the imaging data at each time point in the growth cycle of the organoid, a clustering density matrix of the organoid at each time point is constructed; Combining the clustering proportion density matrix of the organoid at each time node to obtain the temporal clustering proportion density matrix of the organoid; The time series clustering density matrix of the organoid is corrected according to the actual growth function of the organoid to obtain the time series change matrix of the clustering of the organoid; wherein the actual growth function of the organoid is constructed according to the average growth days of the organoid and the number of imaging stages or the actual culture days at a single time node; the average growth days of the organoid is determined according to the imaging data of multiple time nodes in the growth cycle of the organoid; When the clustering time-series change matrix of the organoid meets the passaging conditions, the passaging operation of the organoid is performed.

2. The method according to claim 1, characterized in that Before constructing the clustering density matrix of the organoid at each time node based on the imaging data at each time node in the growth cycle of the organoid based on the pre-established clustering structure, the method further includes: Determining multiple cluster center points and two outlier critical points based on the imaging data at multiple time points during the growth cycle of the organoid; Determining a constraint distance of each cluster center point between the plurality of cluster center points and the two outlier critical points; According to the constraint distance of each cluster center point, the clusters where each cluster center point is located are divided to establish the cluster structure.

3. The method according to claim 2, characterized in that The number of the multiple cluster center points is 4.

4. The method according to claim 1, characterized in that: Before constructing the clustering density matrix of the organoid at each time node based on the imaging data at each time node in the growth cycle of the organoid based on the pre-established clustering structure, the method further includes: According to the two outlier critical points in the clustering structure, outlier data in the imaging data at multiple time points in the organoid growth cycle are screened and eliminated.

5. The method according to claim 1, characterized in that The method of constructing a clustering density matrix of the organoid at each time node based on the pre-established clustering structure and the imaging data at each time node in the organoid growth cycle includes: For the imaging data at each time node, when the Euclidean distance between the imaging data at the time node and any cluster center point in the clustering structure is less than the constraint distance of the cluster center point, determining that the organoid corresponding to the imaging data at the time node is in the cluster where the cluster center point is located; Counting the proportion of the number of organoids in each group at the time node to the total number of organoids, to obtain the grouping proportion of the organoid at the time node; According to the clustering proportions of the organoids at the time nodes, a density matrix of the clustering proportions of the organoids at the time nodes is constructed.

6. The method according to claim 1, characterized in that The step of correcting the temporal clustering proportion density matrix of the organoid according to the actual growth function of the organoid to obtain the temporal clustering change matrix of the organoid includes: constructing a timing correction matrix of the organoid according to the actual growth function of the organoid; The transposed matrix of the temporal clustering proportion density matrix of the organoid is multiplied by the temporal correction matrix of the organoid to obtain the temporal clustering change matrix of the organoid.

7. The method according to claim 6, characterized in that The actual growth function of the organoid is constructed based on the average growth days of the organoid and the number of imaging stages at a single time node; The step of constructing a timing correction matrix of the organoid according to the actual growth function of the organoid comprises: Substituting the average growth days of the organoid and the number of imaging stages at each time node into the actual growth function of the organoid to obtain the function value corresponding to each time node; The function values ​​corresponding to the various time nodes are combined to obtain a timing correction matrix of the organoid.

8. The method according to claim 1, characterized in that When the clustering time series change matrix of the organoid meets the subculture condition, performing the subculture operation of the organoid includes: Statistically evaluating indicators based on the temporal change matrix of the organoid clustering; When the evaluation index is greater than the evaluation index threshold, the organoid is passaged.

9. The method according to claim 1, characterized in that: Also includes: When the temporal change matrix of the organoid clustering satisfies the passage condition, the passage confidence is calculated according to the temporal clustering proportion density matrix of the organoid.

10. The method according to any one of claims 1 to 9, characterized in that: The organoids include tumor organoids.

11. An organoid passage control device, characterized in that: include: A matrix construction module, for constructing a clustering density matrix of the organoid at each time node based on the imaging data at each time node during the growth cycle of the organoid, based on a pre-established clustering structure; A matrix combination module, used to combine the clustering proportion density matrix of the organoid at each time node to obtain the temporal clustering proportion density matrix of the organoid; A matrix correction module, used to correct the temporal clustering proportion density matrix of the organoid according to the actual growth function of the organoid, so as to obtain the temporal clustering change matrix of the organoid; wherein the actual growth function of the organoid is constructed according to the average growth days of the organoid, and the number of imaging stages or the actual culture days at a single time node; the average growth days of the organoid is determined according to the imaging data of multiple time nodes within the growth cycle of the organoid; A subculture control module is used to perform the subculture operation of the organoid when the clustering time-series change matrix of the organoid meets the subculture conditions.

12. An electronic device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor; the memory is coupled to the processor, and the processor implements the method according to any one of claims 1 to 10 when executing the computer program.

13. A computer program product, characterized in that The computer program product comprises instructions which, when executed by a computer, cause the computer to implement the method according to any one of claims 1 to 10.

Images