A computer-assisted method for distinguishing cell activity behavior in culture medium

Abstract

The present application provides a computer-assisted method for distinguishing cell activity behaviors in a culture medium, which relates to the field of cell image processing technology and includes the following steps: obtaining a target microscopic image of a target cell at the current moment, and extracting the static features of the target cell in the target microscopic image; if the recognition confidence is lower than a first threshold, retrieving a historical image sequence of the area where the target cell is located; screening at least N candidate images in the historical image sequence, and obtaining temporal dynamic features of the target cell based on the candidate images. The temporal dynamic features include the motion trajectory, motion speed, morphological changes and periodic changes related to the activity behavior of the target cell within a certain time period; combining the temporal dynamic features with the static features to perform activity behavior matching to obtain the activity behavior of the target cell. The present application significantly improves the robustness and accuracy of cell behavior recognition in complex culture environments through the fusion of static and dynamic features.

Description

Technical Field

[0001] The present application relates to the technical field of cell image processing, and in particular to a computer-assisted method for distinguishing cell activity behaviors in a culture medium. Background Art

[0002] In cell culture experiments, accurate identification of cell activity behaviors (such as division, apoptosis, and migration) is key to assessing cell status and microenvironmental responses.

[0003] In the past, the identification of cell activity behavior relied on single-frame static features. However, in the early stages of cell division or apoptosis, morphological changes may not yet be significant, which may cause misjudgment or missed detection. Therefore, it gradually evolved to combine static features with dynamic features to identify cell activity behavior.

[0004] However, in the process of combining dynamic features, dynamic features are mostly limited to trajectory tracking, and do not fully consider the spatial positioning stability of target cells (such as coordinate offset caused by culture medium flow) and the coordinated changes of the surrounding microenvironment. This in turn leads to insufficient fusion of dynamic and static features, and poor accuracy in distinguishing cell activity behaviors. Summary of the Invention

[0005] In view of the above-mentioned defects or deficiencies in the prior art, the present application aims to provide a computer-assisted method for distinguishing cell activity behaviors in culture medium, so as to improve the accuracy of distinguishing cell activity behaviors;

[0006] The method comprises the following steps:

[0007] Acquire a target microscopic image of the target cell at the current moment, and extract static features of the target cell in the target microscopic image, wherein the static features include cell morphology, size, and texture;

[0008] Determining the recognition confidence corresponding to the static feature of the target cell; if the recognition confidence is lower than a first threshold, retrieving a historical image sequence of the area where the target cell is located;

[0009] Screening the historical image sequence to obtain at least N candidate images, wherein the candidate images are historical images having similar spatial positioning features as the region where the target cell is located; the spatial positioning features include the positioning coordinates of the target cell and the distribution of other cells around the target cell;

[0010] Based on the candidate image, obtaining the temporal dynamic characteristics of the target cell, the temporal dynamic characteristics including the movement trajectory, movement speed, and morphological changes and periodic changes associated with the activity behavior of the target cell within a certain time period;

[0011] The temporal dynamic features are combined with the static features to perform activity behavior matching to obtain the activity behavior of the target cell.

[0012] According to the technical solution provided by the present application, the temporal dynamic features are combined with the static features to perform activity behavior matching to obtain the activity behavior of the target cell, including the following steps:

[0013] Combining the temporal dynamic features with the static features to obtain fusion features;

[0014] Retrieving and traversing a behavior pattern library to obtain a reference feature that matches the fusion feature, and using the reference feature as a target reference feature, and using a reference behavior corresponding to the target reference feature as the activity behavior of the target cell;

[0015] The behavior pattern library includes multiple cell types and a behavior pattern reference table for each cell type. The behavior pattern reference table includes multiple reference features and a reference behavior corresponding to each reference feature.

[0016] According to the technical solution provided by this application, the step of screening at least N candidate images from the historical image sequence includes the following steps:

[0017] Acquiring the location coordinates of the target cell from the target microscopic image;

[0018] Extracting characteristic points of the target cell region in the target microscopic image, searching for matching points that match the characteristic points in each of the historical images, and using the region covered by the matching points in the historical images as the cell corresponding region;

[0019] Obtaining the cell coordinates in the area corresponding to the cell in each of the historical images, and obtaining the positioning coordinate distance corresponding to each of the historical images, wherein the positioning coordinate distance is the distance between the positioning coordinates and the cell coordinates;

[0020] The historical image whose positioning coordinate distance is less than a first threshold is used as a first image, and a candidate image is obtained based on the first image.

[0021] According to the technical solution provided in this application, obtaining a candidate image based on the first image includes the following steps:

[0022] In the target microscopic image, with the target cell as the center, the number and relative position relationship of other cells within a preset radius are counted to form a distribution of other cells;

[0023] In each of the first images, taking the cell corresponding area as the center, counting the number and relative position relationship of other cells within the preset radius to form a first cell distribution of each of the first images;

[0024] Obtaining a target feature vector corresponding to the other cell distributions and a first feature vector of each of the first cell distributions, and respectively calculating a cosine similarity between each of the first feature vectors and the target feature vector;

[0025] The first image corresponding to the first feature vector having a cosine similarity greater than a second threshold is taken as a candidate image.

[0026] According to the technical solution provided by the present application, after retrieving the historical image sequence of the area where the target cell is located, the following steps are further included:

[0027] If the number of candidate images screened from the historical image sequence is less than N, determining whether the total number of historical images in the historical image sequence is a preset number, wherein the preset number is related to the time from the first introduction of the target cells into the culture dish to the present time, and the acquisition frequency of the image acquisition device;

[0028] If yes, the radius values ​​of the preset radius range are expanded in stages, and the statistics of the other cell distributions and the first cell distribution are re-executed after each expansion to obtain the updated cosine similarity corresponding to each expansion;

[0029] The historical images whose updated cosine similarity is greater than the second threshold are added as candidate images, and the above steps are repeated until the number of candidate images reaches N or the maximum number of expansion times is reached.

[0030] According to the technical solution provided by the present application, the historical image whose updated cosine similarity is greater than the second threshold is added as a candidate image, and then the following steps are further included:

[0031] If the maximum number of expansion times is reached and the number of candidate images is less than N, performing missing dynamic feature extraction on all current candidate images to obtain missing dynamic features;

[0032] Based on the missing dynamic features and the static features, the missing activity behavior of the target cell is obtained, and a confidence adjustment coefficient is added to the missing activity behavior. The confidence adjustment coefficient is positively correlated with the number of candidate images.

[0033] According to the technical solution provided by this application, the method for determining the maximum number of extensions includes the following steps:

[0034] Obtaining the current cell density value of the culture dish where the target cells are located;

[0035] Determining a maximum allowable number of expansions according to the density-expansion mapping table and the current cell density value;

[0036] The higher the current cell density value is, the smaller the maximum allowed expansion times are. The density-expansion mapping table is constructed by counting the cell distribution feature mismatch rates caused by adjacent expansion operations at different densities.

[0037] According to the technical solution provided in this application, the extraction of the static features of the target cells in the target microscopic image includes the following steps:

[0038] Dividing an annular sampling area within the outline of the target cell, wherein the annular sampling area includes at least three concentric rings;

[0039] Calculating the histogram features of the local binary pattern for each of the annular bands;

[0040] performing a differential operation on the corresponding histogram features of two adjacent annular bands to generate a differential feature vector representing a texture gradient change;

[0041] splicing the histogram features of each of the annular bands with the differential feature vector to obtain a two-dimensional texture feature;

[0042] Based on the two-dimensional texture features, the texture of the target cell is obtained.

[0043] According to the technical solution provided in this application, before extracting the static features of the target cells in the target microscopic image, the following steps are also included:

[0044] Acquiring multi-focal layer scanning data of the target cells, and constructing a three-dimensional voxel model of the target cells based on the multi-focal layer scanning data;

[0045] determining, based on the three-dimensional voxel model, whether the target cells overlap;

[0046] The method of obtaining the texture of the target cell based on the two-dimensional texture feature comprises the following steps:

[0047] If so, separating the three-dimensional boundaries of the overlapping cells that overlap with the target cell to generate a de-occluded surface topology of the target cell;

[0048] The surface topology structure and the two-dimensional texture feature are cross-dimensionally fused to generate the texture of the target cell.

[0049] According to the technical solution provided in this application, obtaining the temporal dynamic characteristics of the target cell based on the candidate image includes the following steps:

[0050] If there is no cell overlap among the target cells, a two-dimensional motion speed is obtained based on the shooting time of each of the candidate images and the cell coordinates of the target cells, and the two-dimensional motion speed is used as the motion speed of the target cells; if there is cell overlap among the target cells, the spatial motion trajectory is extracted based on the three-dimensional voxel model, and the migration acceleration and directional deflection angle of the target cells in the three-dimensional space are calculated; and the two-dimensional motion speed is corrected according to the spatial motion trajectory, the migration acceleration and the directional deflection angle to obtain the motion speed of the target cells.

[0051] Compared with the existing technology, the beneficial effects of this application are as follows: when the static feature confidence is low (such as texture blurring caused by cell overlap), this application ensures the spatiotemporal consistency of dynamic feature extraction by screening historical candidate images with similar spatial positioning features (positioning coordinates, surrounding cell distribution) as the current target cell, avoiding interference factors introduced by coordinate drift or drastic changes in the microenvironment; in addition, the temporal dynamic features not only include motion trajectories, but also cover motion speed, morphological changes and periodic changes related to active behaviors such as division and apoptosis. By fusing static features (current morphology) with dynamic features (morphological gradient trends), sub-dominant behavioral signals can be captured. For example, when the static confidence of cell size is low, if its motion speed is detected to be decreasing and the distribution of surrounding cells is gradually becoming sparse (dynamic features), the cell's apoptotic behavior can be accurately matched, greatly improving the accuracy of identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 This is a flowchart of the steps of the computer-assisted method for distinguishing cell activity behavior in culture medium provided in this application. DETAILED DESCRIPTION

[0053] The present application will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are merely for the purpose of explaining the relevant invention and are not intended to limit the invention. It should also be noted that, for ease of description, only portions relevant to the invention are shown in the accompanying drawings.

[0054] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in this application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0055] Example 1

[0056] As mentioned in the background technology, in order to solve the problems in the prior art, this application proposes a computer-assisted method for distinguishing cell activity behavior in culture medium, such as Figure 1 As shown, the following steps are included:

[0057] S1. Obtain a target microscopic image of a target cell at a current moment, and extract static features of the target cell in the target microscopic image, wherein the static features include cell morphology, size, and texture;

[0058] Specifically, a high-resolution microscopic imaging device (such as a confocal microscope) captures real-time images of target cells in a culture dish. The image acquisition frequency is set to 5 minutes per frame. An image segmentation algorithm (such as a U-Net network) is used to extract the outline of the target cells and calculate morphological parameters (such as area, perimeter, ellipticity) and dimensional parameters (major axis, minor axis).

[0059] Furthermore, the extracting of static features of the target cells in the target microscopic image comprises the following steps:

[0060] Dividing an annular sampling area within the outline of the target cell, wherein the annular sampling area includes at least three concentric rings;

[0061] Calculating the histogram features of the local binary pattern for each of the annular bands;

[0062] performing a differential operation on the corresponding histogram features of two adjacent annular bands to generate a differential feature vector representing a texture gradient change;

[0063] splicing the histogram features of each of the annular bands with the differential feature vector to obtain a two-dimensional texture feature;

[0064] Based on the two-dimensional texture features, the texture of the target cell is obtained.

[0065] Specifically, three concentric rings (R1, R2, and R3) are divided within the target cell's outline. A local binary pattern (LBP) histogram is calculated for each ring, yielding H1, H2, and H3. Adjacent rings are then differentially computed (e.g., H1-H2 and H2-H3) to generate differential vectors D1 and D2 representing the texture gradient. H1-H3 and D1-D2 are concatenated into a two-dimensional texture feature matrix. Principal component analysis (PCA) is then used to reduce the dimensionality of the target cell's texture feature vector, thereby generating static features.

[0066] S2. Determine the recognition confidence corresponding to the static feature of the target cell; if the recognition confidence is lower than a first threshold, retrieve a historical image sequence of the area where the target cell is located;

[0067] Specifically, static features are fed into a pre-trained classifier (such as a support vector machine), which outputs a recognition confidence score. A first threshold is set at 0.85. If the recognition confidence score is less than 0.85, the historical image retrieval module is triggered to retrieve a historical image sequence (approximately 24 frames) of the target cell area within the past two hours and store them in a time-stamped, ordered queue.

[0068] S3. Screening the historical image sequence to obtain at least N candidate images, wherein the candidate images are historical images having similar spatial positioning features as the region where the target cell is located; the spatial positioning features include the positioning coordinates of the target cell and the distribution of other cells around the target cell;

[0069] Furthermore, the screening of at least N candidate images from the historical image sequence includes the following steps:

[0070] Acquiring the location coordinates of the target cell from the target microscopic image;

[0071] Extracting characteristic points of the target cell region in the target microscopic image, searching for matching points that match the characteristic points in each of the historical images, and using the region covered by the matching points in the historical images as the cell corresponding region;

[0072] Obtaining the cell coordinates in the area corresponding to the cell in each of the historical images, and obtaining the positioning coordinate distance corresponding to each of the historical images, wherein the positioning coordinate distance is the distance between the positioning coordinates and the cell coordinates;

[0073] The historical image whose positioning coordinate distance is less than a first threshold is used as a first image, and a candidate image is obtained based on the first image.

[0074] Furthermore, obtaining a candidate image based on the first image includes the following steps:

[0075] In the target microscopic image, with the target cell as the center, the number and relative position relationship of other cells within a preset radius are counted to form a distribution of other cells;

[0076] In each of the first images, taking the cell corresponding area as the center, counting the number and relative position relationship of other cells within the preset radius to form a first cell distribution of each of the first images;

[0077] Obtaining a target feature vector corresponding to the other cell distributions and a first feature vector of each of the first cell distributions, and respectively calculating a cosine similarity between each of the first feature vectors and the target feature vector;

[0078] The first image corresponding to the first feature vector having a cosine similarity greater than a second threshold is taken as a candidate image.

[0079] Specifically, the coordinates (x0, y0) of the target cell in the current image are extracted. A search is then performed in the historical images for cell regions with a Euclidean distance of less than d = 20 pixels from (x0, y0). This results in a preliminary screening of 20 first images. Next, the coordinates of other cells within a radius of r = 50 μm, centered on the target cell, are counted in the target microscopic image to generate the distribution vectors of the remaining cells. For each first image, the first cell distribution vector of the corresponding region is calculated. The cosine similarity is used to measure the degree of match between the distribution vectors of the remaining cells corresponding to the target microscopic image and the first cell distribution vector corresponding to the first image. Images with a similarity greater than a second threshold (e.g., 0.9) are retained as candidate images (N = 10).

[0080] S4. Based on the candidate image, obtaining temporal dynamic features of the target cell, wherein the temporal dynamic features include the movement trajectory, movement speed, and morphological changes and periodic changes associated with the activity behavior of the target cell within a certain time period;

[0081] Specifically, the temporal dynamic features also include the coordination of the distribution of target cells and surrounding cells, such as the appearance of gaps around cells. Time series analysis was performed on 10 candidate images: Motion trajectory: The displacement of target cells between consecutive frames was tracked by the optical flow method, and the average motion speed v=Δs / Δt was calculated; where Δs represents the displacement difference of target cells between consecutive image frames (unit: micrometers), which is calculated by tracking the change of cell center of mass coordinates by the optical flow method. For example, between two adjacent frames (t and t+5 minutes), the center of mass coordinates moved from (x1, y1) to (x2, y2), then ; Δt represents the image acquisition time interval (unit: minutes), which is determined by the preset acquisition frequency. For example, when the acquisition frequency is every 5 minutes / frame, the adjacent frames have Δt = 5 minutes.

[0082] Morphological changes: Measure the cell area change rate (ΔA / A0), where A0 represents the initial area of ​​the target cell at the reference time (unit: square micrometers). This is typically the area of ​​the cell at the earliest frame in the historical image sequence (or the starting frame of the behavioral analysis). ΔA represents the absolute difference between the current cell area and A0. If ΔA increases by 40% within 10 minutes and is accompanied by an elongated ellipse, it is marked as a division feature. Coordination analysis: Calculate changes in the gaps between surrounding cells. If the gap area expands at a rate >5% / minute, it is considered a detachment phenomenon caused by apoptosis.

[0083] S5. Combining the temporal dynamic features with the static features to perform activity behavior matching to obtain the activity behavior of the target cell.

[0084] Furthermore, combining the temporal dynamic features with the static features to perform activity behavior matching to obtain the activity behavior of the target cell comprises the following steps:

[0085] Combining the temporal dynamic features with the static features to obtain fusion features;

[0086] Retrieving and traversing a behavior pattern library to obtain a reference feature that matches the fusion feature, and using the reference feature as a target reference feature, and using a reference behavior corresponding to the target reference feature as the activity behavior of the target cell;

[0087] The behavior pattern library includes multiple cell types and a behavior pattern reference table for each cell type. The behavior pattern reference table includes multiple reference features and a reference behavior corresponding to each reference feature.

[0088] Specifically, the static features (morphological ellipticity 0.7, texture gradient peak 0.3) are combined with the dynamic features ( , where v represents the two-dimensional movement speed of the cell, which is calculated by Δs / Δt. The data (indicating a movement of 2 microns per minute and ΔA / A0 = 0.4) are fused into a joint feature vector. The reference features of "mitotic precursor cells" (ellipticity 0.65-0.75 and ΔA / A0 > 0.35) are matched in the behavioral pattern library. The behavioral judgment result is output and annotated with a confidence level of 0.92.

[0089] At this point, this embodiment completes the basic cell behavior recognition process. Because this embodiment effectively combines the dynamic and static characteristics of target cells, it greatly improves the accuracy of cell activity behavior identification.

[0090] Example 2

[0091] Based on Example 1, this embodiment can be applied to three-dimensional feature enhancement in cell overlapping scenarios. Considering that cells in a culture dish often overlap, this overlap will lead to difficulties in extracting static features of target cells and poor accuracy in analyzing temporal dynamic features. Therefore, this embodiment is proposed to solve the above problems.

[0092] Before extracting the static features of the target cells in the target microscopic image, the method further includes the following steps:

[0093] Acquiring multi-focal layer scanning data of the target cells, and constructing a three-dimensional voxel model of the target cells based on the multi-focal layer scanning data;

[0094] determining, based on the three-dimensional voxel model, whether the target cells overlap;

[0095] Specifically, when the target cell overlaps with neighboring cells, multi-focal slice scanning (10 slices with a 1μm interslice spacing) is used to reconstruct a 3D voxel model using a deconvolution algorithm. The 3D boundaries of the overlapping region are identified, and the surface topology of the target cell is separated using an active contour model.

[0096] The method of obtaining the texture of the target cell based on the two-dimensional texture feature comprises the following steps:

[0097] If so, separating the three-dimensional boundaries of the overlapping cells that overlap with the target cell to generate a de-occluded surface topology of the target cell;

[0098] The surface topology structure and the two-dimensional texture feature are cross-dimensionally fused to generate the texture of the target cell.

[0099] Specifically, the team concatenates 2D texture features (LBP histograms) with 3D surface curvature features (calculated based on surface topology using the Poisson equation) and feeds them into a convolutional neural network to generate a fused texture descriptor. For example, a 2D texture gradient peak of 0.3 and a 3D curvature rate of change of 0.15 allow the fused features to distinguish artifacts between overlapping cells.

[0100] In a preferred embodiment, obtaining the temporal dynamic characteristics of the target cell based on the candidate image comprises the following steps:

[0101] If there is no cell overlap among the target cells, a two-dimensional motion speed is obtained based on the shooting time of each of the candidate images and the cell coordinates of the target cells, and the two-dimensional motion speed is used as the motion speed of the target cells; if there is cell overlap among the target cells, the spatial motion trajectory is extracted based on the three-dimensional voxel model, and the migration acceleration and directional deflection angle of the target cells in the three-dimensional space are calculated; and the two-dimensional motion speed is corrected according to the spatial motion trajectory, the migration acceleration and the directional deflection angle to obtain the motion speed of the target cells.

[0102] Specifically, for overlapping cells, their motion trajectories in three-dimensional space are extracted. The migration acceleration in the z-axis direction (i.e., the depth direction of the culture dish) is calculated. If the migration acceleration in the z-axis direction is greater than 0.1 μm / s², the two-dimensional velocity is compensated. The compensation formula is: ,in, The three-dimensional motion speed after the two-dimensional motion speed is corrected, that is, the motion speed of the target cell. is the two-dimensional motion speed, is the migration acceleration in the z-axis direction, The time interval is used to measure the time span from the start of recording the cell movement state to the current observation point during the observation of cell movement. At the same time, adjusting the movement direction vector according to the direction deflection angle can also improve the trajectory prediction accuracy.

[0103] Example 3

[0104] Based on Example 1, this embodiment proposes a solution to the situation where the number of candidate images may be insufficient (possible reasons for the insufficient number: if the target cell moves very quickly and has a large displacement between different images, the number of images in the historical image whose positioning coordinates are less than the first threshold may be small, that is, the number of first images obtained is insufficient; or the distribution of cells may be affected by multiple factors. If the environment in which the cells are located changes greatly, such as being stimulated by different chemical signals at different time points, the distribution of other cells around the target cells may vary greatly between different images; or if the historical images have quality problems such as blurring and high noise, inaccurate feature point extraction or extraction failure may occur; or the image acquisition device may malfunction at a certain moment and fail to successfully output the image at that moment, etc.), which may lead to the inability to perform subsequent operations.

[0105] After retrieving the historical image sequence of the area where the target cell is located, the following steps are also included:

[0106] If the number of candidate images screened from the historical image sequence is less than N, determining whether the total number of historical images in the historical image sequence is a preset number, wherein the preset number is related to the time from the first introduction of the target cells into the culture dish to the present time, and the acquisition frequency of the image acquisition device;

[0107] If yes, the radius values ​​of the preset radius range are expanded in stages, and the statistics of the other cell distributions and the first cell distribution are re-executed after each expansion to obtain the updated cosine similarity corresponding to each expansion;

[0108] The historical images whose updated cosine similarity is greater than the second threshold are added as candidate images, and the above steps are repeated until the number of candidate images reaches N or the maximum number of expansion times is reached.

[0109] When the number of candidate images is less than N=10, the multi-level expansion mechanism is activated:

[0110] For example, we perform an initial expansion: increasing the radius r from 50 μm to 70 μm, recalculating the cell distribution similarity, and adding three candidate images. We then perform a secondary expansion: further expanding to 90 μm and adding two more candidate images. Termination condition: reaching the maximum number of expansions K = 3 (determined by looking up the density-expansion mapping table at the current cell density ρ = 200 cells / mm²).

[0111] Furthermore, after adding the historical images whose updated cosine similarity is greater than the second threshold as candidate images, the method further includes the following steps:

[0112] If the maximum number of expansion times is reached and the number of candidate images is less than N, performing missing dynamic feature extraction on all current candidate images to obtain missing dynamic features;

[0113] Based on the missing dynamic features and the static features, the missing activity behavior of the target cell is obtained, and a confidence adjustment coefficient is added to the missing activity behavior. The confidence adjustment coefficient is positively correlated with the number of candidate images.

[0114] For example, if only 8 candidate images are finally obtained, linear interpolation is performed on the missing 2 frames: based on the motion speeds v1 to v8 of the existing frames, v9'=(v7+v8) / 2 is generated (estimated using the motion speeds of the two most recent frames (and)), and v10'=v8+Δv (estimated using the motion speed and speed increment of the most recent frame, where the speed increment is determined based on factors such as the changing trend of the speeds of the previous frames or the general laws of cell movement). Among them, v7 and v8 represent the cell motion speeds corresponding to the 7th and 8th candidate images in the historical image sequence (unit: micrometers per minute), is the measured value; v9'=(v7+v8) / 2 represents the linear interpolation of the velocity of the missing 9th frame, taking the arithmetic average of the velocities of the two most recent frames (v7, v8); v10'=v8+Δv: the extrapolated estimate of the velocity of the missing 10th frame, where Δv represents the velocity increment (unit: ), determined by one of the following two methods: extrapolated based on the change trend of the speed of the previous few frames; calculated based on the mean acceleration of the historical speed sequence (such as v5~v8), (a is the average acceleration, Δt is the frame interval); according to the general law of cell movement, the preset model is obtained: the default movement law is set according to the cell type (for example, the typical acceleration range of migrating cells is 0.05-0.2 The interpolated features are combined with the measured features to obtain the missing activity behavior, which is then retrieved together with the static features and traversed through the behavior pattern library to obtain the matching result (missing activity behavior). The confidence attenuation coefficient α = 0.8 (α = actual number of frames / N) is added to the output result.

[0115] Furthermore, the method for determining the maximum number of extensions includes the following steps:

[0116] Obtaining the current cell density value of the culture dish where the target cells are located;

[0117] Determining a maximum allowable number of expansions according to the density-expansion mapping table and the current cell density value;

[0118] The higher the current cell density value is, the smaller the maximum allowed expansion times are. The density-expansion mapping table is constructed by counting the cell distribution feature mismatch rates caused by adjacent expansion operations at different densities.

[0119] Specifically, this embodiment proposes a solution for optimized screening under high-density culture. Through a large number of experiments or data statistics, the mismatch rate when performing expansion operations at different cell densities is obtained (mismatch rate β = number of mismatched cells / total number of cells), and then the maximum allowable number of expansions corresponding to different densities is determined to form a density-expansion mapping table.

[0120] For example, when cell density ρ > 500 cells / mm², the maximum number of expansions, K = 1, is limited according to the density-expansion mapping table. A distribution feature mismatch rate assessment is introduced during the screening process: expansion is terminated when β > 0.2 to prevent noise introduced by excessive radius expansion. In this case, a static feature weighting strategy is prioritized, adjusting the static feature weight from 0.5 to 0.7 during behavior matching.

[0121] Table 1

[0122]

[0123] As shown in Table 1, the recognition accuracy of the traditional cell activity behavior identification method is compared with the method mentioned in this application. It can be seen that in the four different scenarios, the accuracy of the scheme mentioned in this application has been improved. Through static-dynamic feature fusion, three-dimensional modeling compensation and intelligent expansion mechanism, the robustness and accuracy of cell behavior recognition in complex culture environments are significantly improved.

[0124] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. The above is only the preferred implementation method of this application. It should be pointed out that due to the limitations of textual expression, there are objectively infinite specific structures. For ordinary technicians in this technical field, without departing from the principles of the present invention, they can also make several improvements, modifications or changes, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the inventive concept and technical solution to other occasions without improvement, should be regarded as the scope of protection of this application.

Claims

1. A computer-assisted method for distinguishing cell activity behavior in culture medium, characterized in that: The following steps are involved: Acquire a target microscopic image of the target cell at the current moment, and extract static features of the target cell in the target microscopic image, wherein the static features include cell morphology, size, and texture; Determining the recognition confidence corresponding to the static feature of the target cell; if the recognition confidence is lower than a first threshold, retrieving a historical image sequence of the area where the target cell is located; Screening the historical image sequence to obtain at least N candidate images, wherein the candidate images are historical images having similar spatial positioning features to the region where the target cell is located; The spatial positioning features include the positioning coordinates of the target cell and the distribution of other cells around the target cell; Based on the candidate image, obtaining the temporal dynamic characteristics of the target cell, the temporal dynamic characteristics including the movement trajectory, movement speed, and morphological changes and periodic changes associated with the activity behavior of the target cell within a certain time period; The temporal dynamic features are combined with the static features to perform activity behavior matching to obtain the activity behavior of the target cell.

2. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 1, characterized in that: The combining of the temporal dynamic features with the static features to perform activity behavior matching to obtain the activity behavior of the target cell comprises the following steps: Combining the temporal dynamic features with the static features to obtain fusion features; Retrieving and traversing a behavior pattern library to obtain a reference feature that matches the fusion feature, and using the reference feature as a target reference feature, and using a reference behavior corresponding to the target reference feature as the activity behavior of the target cell; The behavior pattern library includes multiple cell types and a behavior pattern reference table for each cell type. The behavior pattern reference table includes multiple reference features and a reference behavior corresponding to each reference feature.

3. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 1, characterized in that: The step of screening the historical image sequence to obtain at least N candidate images comprises the following steps: Acquiring the location coordinates of the target cell from the target microscopic image; Extracting characteristic points of the target cell region in the target microscopic image, searching for matching points that match the characteristic points in each of the historical images, and using the region covered by the matching points in the historical images as the cell corresponding region; Obtaining the cell coordinates in the area corresponding to the cell in each of the historical images, and obtaining the positioning coordinate distance corresponding to each of the historical images, wherein the positioning coordinate distance is the distance between the positioning coordinates and the cell coordinates; The historical image whose positioning coordinate distance is less than a first threshold is used as a first image, and a candidate image is obtained based on the first image.

4. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 3, characterized in that: The step of obtaining a candidate image based on the first image comprises the following steps: In the target microscopic image, with the target cell as the center, the number and relative position relationship of other cells within a preset radius are counted to form a distribution of other cells; In each of the first images, taking the cell corresponding area as the center, counting the number and relative position relationship of other cells within the preset radius to form a first cell distribution of each of the first images; Obtaining a target feature vector corresponding to the other cell distributions and a first feature vector of each of the first cell distributions, and respectively calculating a cosine similarity between each of the first feature vectors and the target feature vector; The first image corresponding to the first feature vector having a cosine similarity greater than a second threshold is taken as a candidate image.

5. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 4, characterized in that: After retrieving the historical image sequence of the area where the target cell is located, the following steps are also included: If the number of candidate images screened from the historical image sequence is less than N, determining whether the total number of historical images in the historical image sequence is a preset number, wherein the preset number is related to the time from the first introduction of the target cells into the culture dish to the present time, and the acquisition frequency of the image acquisition device; If yes, the radius values ​​of the preset radius range are expanded in stages, and the statistics of the other cell distributions and the first cell distribution are re-executed after each expansion to obtain the updated cosine similarity corresponding to each expansion; The historical images whose updated cosine similarity is greater than the second threshold are added as candidate images, and the above steps are repeated until the number of candidate images reaches N or the maximum number of expansion times is reached.

6. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 5, characterized in that: After the historical image having the updated cosine similarity greater than the second threshold is added as a candidate image, the method further includes the following steps: If the maximum number of expansion times is reached and the number of candidate images is less than N, performing missing dynamic feature extraction on all current candidate images to obtain missing dynamic features; Based on the missing dynamic features and the static features, the missing activity behavior of the target cell is obtained, and a confidence adjustment coefficient is added to the missing activity behavior. The confidence adjustment coefficient is positively correlated with the number of candidate images.

7. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 5, characterized in that: The method for determining the maximum number of extensions comprises the following steps: Obtaining the current cell density value of the culture dish where the target cells are located; Determining a maximum allowable number of expansions according to the density-expansion mapping table and the current cell density value; The higher the current cell density value is, the smaller the maximum allowed expansion times are. The density-expansion mapping table is constructed by counting the cell distribution feature mismatch rates caused by adjacent expansion operations at different densities.

8. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 1, characterized in that: The step of extracting the static features of the target cells in the target microscopic image comprises the following steps: Dividing an annular sampling area within the outline of the target cell, wherein the annular sampling area includes at least three concentric rings; Calculating the histogram features of the local binary pattern for each of the annular bands; performing a differential operation on the corresponding histogram features of two adjacent annular bands to generate a differential feature vector representing a texture gradient change; splicing the histogram features of each of the annular bands with the differential feature vector to obtain a two-dimensional texture feature; Based on the two-dimensional texture features, the texture of the target cell is obtained.

9. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 8, characterized in that: Before extracting the static features of the target cells in the target microscopic image, the method further includes the following steps: Acquiring multi-focal layer scanning data of the target cells, and constructing a three-dimensional voxel model of the target cells based on the multi-focal layer scanning data; determining, based on the three-dimensional voxel model, whether the target cells overlap; The method of obtaining the texture of the target cell based on the two-dimensional texture feature comprises the following steps: If so, separating the three-dimensional boundaries of the overlapping cells that overlap with the target cell to generate a de-occluded surface topology of the target cell; The surface topology structure and the two-dimensional texture feature are cross-dimensionally fused to generate the texture of the target cell.

10. The computer-aided method for distinguishing cell activity behavior in culture medium according to claim 9, characterized in that: The step of obtaining the temporal dynamic characteristics of the target cell based on the candidate image comprises the following steps: If there is no cell overlap among the target cells, a two-dimensional motion speed is obtained based on the shooting time of each of the candidate images and the cell coordinates of the target cells, and the two-dimensional motion speed is used as the motion speed of the target cells; if there is cell overlap among the target cells, the spatial motion trajectory is extracted based on the three-dimensional voxel model, and the migration acceleration and directional deflection angle of the target cells in the three-dimensional space are calculated; and the two-dimensional motion speed is corrected according to the spatial motion trajectory, the migration acceleration and the directional deflection angle to obtain the motion speed of the target cells.

Images