Method and device for calculating cell confluence and computer equipment

Abstract

The embodiment of the application is suitable for the field of biomedical and image processing technology, and provides a cell convergence degree calculation method and device and computer equipment. The method processes the adherent cell original image by using open operation and closed operation in the morphological image processing algorithm, and then combines contrast enhancement, gamma correction and other brightness balancing methods to optimize the original image, so that the pixel gradient change of the stem cell region image can be strengthened, and the stem cell image features are highlighted. Then, the cell region is locked by using the edge detection algorithm, and the complete cell region can be obtained by using the image connected domain calculation, flood fill and optimized region growth algorithms. On this basis, the stem cell image cell region segmentation and cell convergence degree calculation can be quickly realized based on the traditional algorithm. The application of the cell convergence degree calculation method provided by the embodiment of the application can quickly and accurately realize the calculation of the cell convergence degree.

Description

Technical Field

[0001] This application relates to the fields of biomedical and image processing technology, and in particular to a method, apparatus, and computer device for calculating cell confluence. Background Technology

[0002] Cell confluence refers to the ratio of the area occupied by cells to the surface area of ​​the culture after cells have adhered to the culture dish or flask and fully expanded. It is an important and necessary parameter for tracking and evaluation in primary cell culture.

[0003] Traditional methods for assessing cell confluence primarily rely on manual observation. However, judging cell confluence through manual observation requires a high level of expertise and is significantly influenced by the assessor's subjectivity. Therefore, existing technologies have developed image processing-based methods for calculating cell confluence. However, these techniques often employ clustering algorithms or construct corresponding models, resulting in high computational complexity, low efficiency, and susceptibility to data sample variations, leading to low accuracy in the final calculated confluence results. Summary of the Invention

[0004] In view of this, embodiments of this application provide a method, apparatus, and computer device for calculating cell confluence, in order to reduce the algorithmic complexity of cell confluence calculation and improve the calculation speed and accuracy of the calculation results.

[0005] A first aspect of this application provides a method for calculating cell confluence, comprising:

[0006] Images of adherent stem cells were collected.

[0007] The adherent cell image is optimized to obtain a target image. The optimization process includes enhancing the cell image features in the adherent cell image.

[0008] Cell regions in the target image are determined by edge detection;

[0009] The cell confluence of the stem cells is calculated based on the cell regions in the target image.

[0010] A second aspect of this application provides a device for calculating cell confluence, comprising:

[0011] Image acquisition module, used to acquire images of adherent cells of stem cells;

[0012] An image optimization module is used to optimize the adherent cell image to obtain a target image. The optimization process includes enhancing the cell image features in the adherent cell image.

[0013] The image segmentation module is used to determine the cell regions in the target image through edge detection;

[0014] The cell confluence calculation module is used to calculate the cell confluence of the stem cells based on the cell regions in the target image.

[0015] A third aspect of this application provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the cell confluence calculation method as described in the first aspect above.

[0016] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the cell confluence calculation method as described in the first aspect above.

[0017] A fifth aspect of this application provides a computer program product that, when run on a computer, causes the computer to execute the cell confluence calculation method described in the first aspect.

[0018] Compared with the prior art, the embodiments of this application have the following beneficial effects:

[0019] This application embodiment acquires images of adherent stem cells. After optimizing these images to obtain a target image, edge detection identifies cell regions within the target image, allowing for the calculation of stem cell confluence based on these regions. Compared to existing technologies that rely on manual observation to assess cell confluence, this application embodiment employs a more objective evaluation standard and is more suitable for large-scale production operations. Secondly, the algorithms and processing steps used in this application embodiment, compared to the simple and fast threshold segmentation in existing technologies, offer the advantage of more accurate detection of intact cell regions. Compared to more complex algorithms such as K-Means clustering, this application embodiment requires fewer parameter adjustments during application, resulting in more stable and efficient algorithms. Thirdly, applying this application embodiment eliminates the need for pre-created datasets, saving significant manpower costs and reducing computational resource requirements, thus lowering hardware requirements. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This is a schematic diagram of a method for calculating cell confluence provided in an embodiment of this application;

[0022] Figure 2 This is a schematic diagram illustrating the optimization processing of adherent cell images provided in an embodiment of this application;

[0023] Figure 3 This is a schematic diagram of a possible implementation of S103 in a method for calculating cell confluence provided in an embodiment of this application;

[0024] Figure 4 This is a schematic diagram illustrating a segmentation process for a target image provided in an embodiment of this application;

[0025] Figure 5 This is a schematic diagram of a cell confluence calculation device provided in an embodiment of this application;

[0026] Figure 6 This is a schematic diagram of a computer device provided in an embodiment of this application. Detailed Implementation

[0027] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0028] As mentioned earlier, cell confluence can be automatically calculated based on image processing techniques. For example, an improved K-Means clustering algorithm can be used to segment adherent cell microscopic images, and then the cell confluence can be calculated based on the segmented images. This type of algorithm is mainly used for calculating the confluence of umbilical cord mesenchymal stem cells. By optimizing the selection of the initial cluster centers, accurate separation of adherent irregular umbilical cord mesenchymal stem cell microscopic images from the background can be achieved. When applying the K-Means clustering algorithm, it is necessary to iteratively calculate the distance between sample points and cluster centers and continuously adjust the position of the cluster centers until the termination condition is met. Therefore, this type of algorithm has drawbacks such as sensitivity to the initial cluster centers, sensitivity to noise and outliers, and difficulty in selecting the K value. Furthermore, the above algorithm does not have sufficient robustness when facing complex situations such as changes in lighting and poor image quality, and cannot cover most application scenarios.

[0029] Another method for calculating cell confluence is to construct a background model of high-resolution cell images and then use this model to suppress the background, thereby achieving data augmentation and applying it to cell confluence calculation. This type of method identifies image corner points based on the background-suppressed image, constructs an optical flow model by combining the corner points with consecutive frames, extracts temporal features from the suppressed image using the constructed optical flow model, and then fuses these temporal and spatial features to analyze the cell confluence of mesenchymal stem cells. However, the above algorithms are highly complex and time-consuming, and constructing the optical flow model also requires significant computation, placing high demands on the hardware.

[0030] Alternatively, a large number of sample images can be collected and divided into training, testing, and validation sets. Based on this, a cell recognition model can be constructed, and the model can be trained to identify cell regions in the sample images, completing the task of segmenting stem cells in the sample images. Cell confluence can then be calculated based on the segmentation results. However, this technique relies on a segmentation neural network model, requiring a large amount of data. Furthermore, the model training process also requires significant computational resources, placing high demands on computer hardware. Even after model training is complete, applying the model still consumes considerable computational resources. Because neural networks are black-box in nature, this technique cannot guarantee generalization when the amount of sample data is insufficient or the data is relatively homogeneous.

[0031] Therefore, to address the aforementioned problems, this application provides a method for calculating cell confluence. It utilizes morphological image processing techniques to enhance pixel gradient changes in adherent cell images, thereby enhancing the original image and highlighting cellular regions. After image enhancement, this application can identify cellular regions based on gradient changes, obtaining complete cellular regions for calculating cell confluence. Compared to the aforementioned K-Means clustering algorithm, which calculates cell confluence by iteratively calculating the distance between sample points and cluster centers, this application does not require adjusting cluster centers or selecting a K value, reducing factors affecting algorithm stability. Compared to constructing optical flow models and fusing features to analyze mesenchymal stem cell confluence, this application's algorithm has lower complexity, higher efficiency, and lower hardware requirements. Furthermore, the application process of this application does not require constructing a dataset to train a segmentation neural network model, making it more suitable for automatic, rapid, and accurate cell confluence calculation in various application scenarios.

[0032] The technical solution of this application will be described below through specific embodiments.

[0033] Reference Figure 1 The diagram illustrates a method for calculating cell confluence provided in an embodiment of this application, which may specifically include the following steps:

[0034] S101. Collect images of adherent stem cells.

[0035] It should be noted that this method can be applied to computer devices, which can automatically, quickly, and accurately calculate cell confluence by executing the various steps of the method provided in this application embodiment. That is, the executing entity of this application embodiment can be a computer device, which can be any type of device with relevant functions, such as image acquisition functions, image processing functions, and other related functions required to implement this method. This application embodiment does not limit the type of computer device.

[0036] In this embodiment of the application, the adherent cell image of the stem cell can be obtained by taking an image of the stem cell after it has adhered and grown in a culture dish or culture flask and fully expanded. The above-mentioned adherent cell image is the original image used to calculate the cell confluence, that is, the original image of the adherent cell.

[0037] In one possible implementation of this application, images of the adherent stem cells to be identified can be acquired by using a microscope at one or more time points during the cell culture process to obtain images of the adherent cells.

[0038] S102. The adherent cell image is optimized to obtain a target image. The optimization process includes enhancing the cell image features in the adherent cell image.

[0039] In this embodiment, for the acquired original image of adherent cells, the computer device can first perform image optimization processing. Based on the optimized target image, subsequent related processing and calculation steps are then performed. The optimization processing in this embodiment may include one or more types of processing to enhance the cell image features in the original image of adherent cells.

[0040] In one possible implementation of this application, the optimization of the original image of adherent cells can be performed based on opening and closing operations in morphological image processing algorithms. Furthermore, brightness equalization techniques such as contrast enhancement and gamma correction can be combined to optimize the original image, enhancing pixel gradient changes in the stem cell region and highlighting stem cell image features.

[0041] For example, when optimizing the original image of adherent cells, opening and / or closing operations can be used to optimize the original image of adherent cells to obtain the target image.

[0042] In image processing algorithms, opening is a sequential operation that performs erosion followed by dilation on an image; closing, on the other hand, performs dilation first, followed by erosion. The order of erosion and dilation in opening and closing operations is reversed.

[0043] The opening operation involves subtracting the result of the opening operation from the original image to extract peak information. Opening is primarily used for bright objects on dark backgrounds, correcting for uneven lighting, removing most of the non-uniform background, and separating the foreground and background. The closing operation, on the other hand, involves subtracting the result of the closing operation from the original image to extract valley information. Closing can highlight dark details and separate any background information that may be present in the image.

[0044] In the embodiments of this application, in order to optimize the original image of adherent cells, the original image can be subjected to opening operation processing, or closing operation processing, or both opening and closing operations can be performed on the original image simultaneously.

[0045] For example, opening and closing operations can be performed sequentially on the adherent cell image to obtain a first image and a second image, respectively. That is, the first image is the image obtained after the computer device performs an opening operation on the adherent cell image, and the second image is the image obtained after the computer device performs a closing operation on the adherent cell image. Then, based on the original adherent cell image, the image obtained by subtracting the first image from the original image can be added, and the image obtained by subtracting the original image from the second image can be subtracted, thereby obtaining an optimized target image, which enhances the cell region information in the original image.

[0046] The above process can be represented as:

[0047] Target(I)=I+(I-opening(I))-(closing(I)-I)

[0048] Where Target(I) is the target image to be optimized, I represents the original image of the adherent cells, opening(I) represents the image obtained by performing an opening operation on the original adherent cell image I, i.e., the first image, and closing(I) represents the image obtained by performing a closing operation on the original adherent cell image I, i.e., the second image. Therefore, I-opening(I) represents the image obtained by subtracting the first image from the original image, and closing(I)-I represents the image obtained by subtracting the original image from the second image.

[0049] In one possible implementation of this application embodiment, after processing the original image using opening and closing operations in a morphological image processing algorithm to obtain an optimized target image, the computer device can perform subsequent processing on the target image to calculate the cell confluence degree of the stem cells. That is, the computer device can calculate the cell confluence degree of the stem cells by executing the steps shown in S103 and S104.

[0050] In another possible implementation of this application, after optimizing the original image of adherent cells using opening and / or closing operations, the computer device can further optimize the image using contrast enhancement and brightness equalization, so that the further optimized image can be used as the target image for subsequent processing.

[0051] In this embodiment, when performing contrast enhancement processing on an image, contrast enhancement algorithms such as histogram equalization and linear stretching can be used, but are not limited to. When performing brightness equalization processing on an image, brightness adjustment can be achieved based on gamma correction. The gamma value (γ) is a non-linear parameter that describes the relationship between input and output. By using a power function formula to describe the relationship between the input pixel value (Iin) and the output pixel value (Iout), brightness equalization processing of the image can be achieved. The above processing can be expressed as:

[0052] Iout = Iin γ

[0053] like Figure 2 The diagram shown is a schematic representation of an optimization process for an adherent cell image provided in an embodiment of this application. Wherein, Figure 2 Image (a) shows a schematic diagram of a primary image of an adherent cell. Figure 2 (b) shows the effect of using the aforementioned optimization methods on... Figure 2 (a) shows a schematic diagram of the target image obtained after optimizing the original image, that is... Figure 2 (b) in the text shows the... Figure 2 The optimized version (a) is shown in the image below. By comparison... Figure 2 As can be seen in (a) and (b) above, the stem cell image features are clearer and more prominent in the optimized target image. Based on Figure 2 Subsequent processing and calculations of the target image shown in (b) can yield more accurate results on cell confluence.

[0054] S103. Determine the cell regions in the target image through edge detection.

[0055] In this embodiment of the application, after optimizing the original image of adherent cells to obtain a target image containing clearer and more prominent cell image features, the computer device can use algorithms such as edge detection to lock the cell region in the target image and obtain a complete cell region that can be used to calculate the cell confluence.

[0056] In this embodiment, the process of identifying complete cell regions from a target image may include edge detection, image connected component calculation, and flooding filling. Edge detection of the target image can initially identify the edges of cell regions in the image. Based on this, image connected component calculation and flooding filling can accurately identify the foreground and background of the image, thus filtering out complete cell regions.

[0057] In one possible implementation of the embodiments of this application, such as Figure 3 As shown, determining the cell region in the target image through edge detection in S103 can specifically include the following steps S1031-S1033:

[0058] S1031. Determine the gradient intensity of each pixel in the target image through edge detection.

[0059] In this embodiment, the Sobel operator or other similar edge detection operators can be used to calculate the gradient intensity and direction of each pixel in the target image. This embodiment does not limit the specific method for calculating the gradient intensity of pixels.

[0060] S1032. Based on the gradient intensity of each pixel, determine multiple consecutive edge points in the target image, wherein the multiple consecutive edge points constitute the cell edge region in the target image.

[0061] In this embodiment of the application, the gradient intensity of each pixel can be used to determine edge points in the target image, and these edge points can constitute cell edge regions in the image.

[0062] In one possible implementation of this application, multiple potential edge points in the target image can be determined based on the gradient intensity of each pixel. Specifically, the gradient intensity of any potential edge point is at its maximum value within at least one region of the target image; that is, the potential edge point can be the pixel in the target image with the maximum gradient intensity within a certain region.

[0063] A gradient can be understood as the intensity of a pixel change. Since there are multiple edges in a real cell image, after calculating the gradient intensity of each pixel, the computer device can identify pixels with stronger gradients or those corresponding to the maximum gradient intensity within a certain region as potential edge points.

[0064] However, not all pixels in the region where edge intensity is detected are true edge points of the cellular region. Therefore, a non-maximum suppression step is required, which involves checking each pixel to ensure that the gradient intensity of the detected edge point is the maximum within its neighborhood. If the gradient intensity of an edge point is not the maximum within its neighborhood, it needs to be suppressed to ensure that the detected edge points are continuous.

[0065] Specifically, after detecting multiple potential edge points, the gradient intensity of each potential edge point can be compared with the gradient intensity of each potential edge point in its neighborhood. By extracting each potential edge point whose gradient intensity is the maximum value in its neighborhood, multiple consecutive edge points in the target image can be obtained.

[0066] In one possible implementation of this application, to further remove potentially false edge points, gradient intensity can be binarized by setting high and low thresholds. During this process, edge points above the high threshold are considered true edge points, while those below the low threshold are considered noise. If the gradient intensity of a pixel is between the high and low thresholds, it will only be retained as an edge point if it is connected to a pixel above the high threshold; otherwise, the pixel will be suppressed or removed. The settings of the high and low thresholds can be determined according to actual needs, and this application does not limit this.

[0067] S1033. By segmenting the cell edge region, the cell region in the target image is obtained.

[0068] After identifying the true continuous edge points in the target image using the aforementioned steps, the computer device can perform segmentation and other processing on the cell edge region formed by these edge points to obtain the complete cell region in the target image.

[0069] In one possible implementation of this application embodiment, for the target image obtained after the aforementioned S1032 step, the computer device can first fill each hole region in the image with an area smaller than a first threshold by closing operation.

[0070] Specifically, for the target image processed in step S1032, the computer device can connect the various edge points in the image using a dilation algorithm to obtain cell edge regions, and then fill the small-area void regions, such as those smaller than a first threshold, using a closing operation. The above dilation and closing operation process can be iterated multiple times according to the actual needs of the target image, and this application embodiment does not limit this.

[0071] After filling the smaller hole regions, the computer device can determine the connected components in the target image after filling each smaller hole region, and fill the connected components with areas smaller than a second threshold as the image background, thus obtaining a third image. The aforementioned third image only represents the image obtained after filling the connected components with areas smaller than the second threshold as the image background, and has no other referential meaning.

[0072] Specifically, for an image after filling in smaller empty areas, a computer device can calculate the connected components in the image and, by setting a threshold (e.g., a second threshold), identify small connected components in the image with areas smaller than the second threshold. These small connected components are then filled into the background to obtain a third image. The size of the second threshold can be set according to actual needs; its specific value can be greater than, less than, or equal to the first threshold. This application does not limit this specific value.

[0073] In one possible implementation of this application, the pixels of each pixel in a small connected region with an area smaller than the second threshold can be filled with 0 as background.

[0074] In this embodiment of the application, for the third image, the computer device can continue to fill the smaller empty areas and obtain the foreground in the image through relevant processing means.

[0075] Specifically, the computer device can use a flooding algorithm to fill smaller empty areas in the third image. For example, it can fill each empty area in the third image with an area smaller than a second threshold, then invert the third image, calculate the connected components in the third image, and fill each connected component with an area smaller than the third threshold as the foreground of the image by setting a threshold, thus obtaining the fourth image. For example, by setting a threshold, the pixel value of each pixel in each small connected component in the image obtained after processing by the flooding algorithm can be filled with 1 as the foreground of the image, and the resulting image is the fourth image.

[0076] In this way, the computer device can obtain the complete cell region in the target image based on the fourth image recognition.

[0077] In one possible implementation of this application, after obtaining the fourth image, the computer device can calculate the connected components in the fourth image by inverting the image, and determine the boundary points of each connected component with an area smaller than a fourth threshold as region growing seed points. Then, based on the target image, region growing is performed using the region growing seed points to obtain the fifth image. By performing edge segmentation on the fifth image, the complete cell regions in the target image can be obtained. The aforementioned second, third, and fourth thresholds can be equal or unequal, and the specific values ​​of these thresholds can be determined according to actual needs; this application does not limit this.

[0078] In one possible implementation of this application embodiment, region growing based on region growing seed points can be performed according to the following algorithm:

[0079] (1) Scale the original image. The scaling factor can be determined according to the actual situation of the image. The original image mentioned above can be the target image obtained after image optimization processing.

[0080] (2) Formulate region growth rules based on prior knowledge. Since the background pixel variation difference in cell-free regions of the image is small, the boundary points of the connected components of the background region can be locked as seed points for region growth.

[0081] (3) The region growth step size can be set to 2, and the region growth is performed based on the eight-neighborhood criteria.

[0082] (4) Region growing based on pixel distance criteria: First, determine whether the neighboring points of the region growing seed point are background points with a pixel value of 0 in the fourth image obtained in the previous steps; then, perform region growing based on two principles. That is: if it is a background point, stop growing; if the pixel value is greater than a preset pixel threshold, stop growing and assign the pixel that meets the condition to a value of 0 as a background point.

[0083] like Figure 4 The diagram shown is a schematic representation of a target image segmentation process provided in an embodiment of this application. Figure 4 Image (a) shows the optimized target image, processed using the aforementioned steps. Figure 4 The target image shown in (a) is segmented to distinguish the foreground and background, resulting in the following image: Figure 4 As shown in (b) in the figure, that is Figure 4 Image (b) shows the fourth image from the aforementioned steps. The fourth image, i.e. Figure 4 The image shown in (b) after region growing yields the following image effect: Figure 4 As shown in (c) in the figure.

[0084] for Figure 4 In the image shown in (c), the computer device can use processing methods such as bilateral filtering and smoothing segmentation to obtain the edges of each cell region in the image, thereby determining the complete cell region in the image for the calculation of cell confluence in the next step.

[0085] In one possible implementation of this application, after completing the region growth to obtain complete cell regions, the computer device can further acquire the contour points of the cell regions in the image, and perform processing such as curve fitting on the contour points to improve the contours of the cell regions. The above-mentioned curve fitting can be implemented using algorithms including but not limited to multi-term fitting, Bezier curve fitting, etc., and this application does not limit the specific implementation.

[0086] S104. Calculate the cell confluence degree of the stem cells based on the cell regions in the target image.

[0087] In this embodiment of the application, the computer device can calculate the accurate cell confluence at the pixel level based on the segmented complete cell region.

[0088] Specifically, the computer device can calculate the total number of pixels in the target image and the total number of pixels in each cell region of the target image, and then calculate the cell confluence of stem cells based on the total number of pixels in the target image and the total number of pixels in each cell region. The above calculation process can be expressed as:

[0089]

[0090] That is, the cell confluence of stem cells can be obtained by dividing the total number of pixels in each adherent cell region of the target image by the total number of pixels in the entire target image.

[0091] This application embodiment acquires images of adherent stem cells. After optimizing these images to obtain a target image, edge detection identifies cell regions within the target image, allowing for the calculation of stem cell confluence based on these regions. Compared to existing technologies that rely on manual observation to assess cell confluence, this application embodiment employs a more objective evaluation standard and is more suitable for large-scale production operations. Secondly, the algorithms and processing steps used in this application embodiment, compared to the simple and fast threshold segmentation in existing technologies, offer the advantage of more accurate detection of intact cell regions. Compared to more complex algorithms such as K-Means clustering, this application embodiment requires fewer parameter adjustments during application, resulting in more stable and efficient algorithms. Thirdly, applying this application embodiment eliminates the need for pre-created datasets, saving significant manpower costs and reducing computational resource requirements, thus lowering hardware requirements.

[0092] It should be noted that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0093] To facilitate understanding, a complete example is provided below to illustrate the method for calculating cell confluence provided in this application. This method mainly includes steps such as image acquisition, image optimization, image segmentation, and confluence calculation. Specifically:

[0094] 1. In the image acquisition step, the adherent stem cells to be identified can be obtained as the original images of adherent cells at one or more time points during the cell culture process using a microscope.

[0095] 2. In the image optimization step, the original image is primarily processed using opening and closing operations in morphological image processing algorithms. This is combined with contrast enhancement, gamma correction, and other brightness equalization techniques to optimize the image, enhancing pixel gradient changes in the stem cell region and highlighting the stem cell image features. Related steps include:

[0096] Step 2.1: The opening operation is a sequential combination of erosion and dilation. The result of the opening operation can be subtracted from the original image to extract peak information. The opening operation is primarily used for bright objects on dark backgrounds to correct for uneven lighting, removing most of the non-uniform background and achieving foreground-background separation.

[0097] Step 2.2: The closing operation involves first performing an image dilation operation, followed by an erosion operation. By processing the image using the closing operation and then subtracting the original image, we can capture the valley information in the image, highlight the dark details in the image, and separate any background information that may exist in the image.

[0098] Step 2.3: Adding the image from step 2.1 to the original image and subtracting the image from step 2.2 enhances the information of the cell region. This process can be represented as:

[0099] Target(I)=I+(I-opening(I))-(closing(I)-I)

[0100] Where Target(I) is the target image to be optimized, I represents the original image of the adherent cells, opening(I) represents the image obtained after performing an opening operation on the original image I of the adherent cells, i.e., the first image, and closing(I) represents the image obtained after performing a closing operation on the original image I of the adherent cells, i.e., the second image.

[0101] Step 2.4, Contrast Enhancement. Contrast enhancement algorithms, including but not limited to histogram equalization and linear stretching, can be used for this purpose.

[0102] Step 2.5, Brightness Equalization. Image brightness equalization can be achieved based on gamma correction. Gamma is a non-linear parameter used to describe the relationship between input and output. A power function formula can be used to describe the relationship between the input pixel value (Iin) and the output pixel value (Iout), where γ is the Gamma value. The relevant formula can be expressed as follows:

[0103] Iout = Iin γ

[0104] Figure 2 A schematic diagram illustrates the optimization processing of adherent cell images using steps 2.1-2.5 described above. Wherein, Figure 2 Image (a) shows the original image of adherent cells. Figure 2 (b) shows the process of performing steps 2.1-2.5 as described above. Figure 2 (a) shows the result of optimizing the original image to obtain the target image.

[0105] 3. In the image segmentation step, edge detection algorithms can be used to locate cell regions, and algorithms such as image connected component calculation and flooding filling can be used to obtain complete cell regions. Related steps include:

[0106] Step 3.1: The Sobel operator or other similar edge detection operators can be used to calculate the gradient intensity and direction of each pixel in the target image. By determining the location of pixels in the target image with strong gradient intensity changes or the maximum gradient intensity change in a certain region, these pixels can be identified as potential edge points.

[0107] Step 3.2: In the region where edge intensity is detected, not all pixels are true edge points. Therefore, a non-maximum suppression step is needed, which involves checking each edge point to ensure that its gradient intensity is the maximum value in its neighborhood. If not, the pixel can be suppressed, thus ensuring that the detected edge points are continuous.

[0108] Step 3.3: To further remove false edge points, gradient strength can be binarized by setting high and low thresholds. Edge points with gradient strengths higher than the high threshold can be considered true edge points, while those lower than the low threshold are considered noise. If a pixel's gradient strength is between the high and low thresholds, it will only be retained as an edge point if it is connected to a pixel with a gradient strength higher than the high threshold.

[0109] Step 3.4: Connect the cell edge regions obtained in Step 3.3 using a dilation algorithm, and fill the smaller holes within them using a closing operation. These smaller holes can be regions with an area smaller than the aforementioned first threshold. During this process, multiple iterations of the dilation algorithm and closing operation can be performed according to the actual needs of the image.

[0110] Step 3.5: Based on the binary image obtained in Step 3.4, by calculating the connected components, a threshold can be set, such as the aforementioned second threshold, to fill the pixels in each small connected component, independent of the large connected component, with 0 as the background. Here, a large connected component can refer to a connected component with an area greater than the aforementioned second threshold, and a small connected component can refer to a connected component with an area less than the second threshold. The image obtained in this step is the third image in the aforementioned embodiment.

[0111] Step 3.6: Based on the binary image obtained in Step 3.5, i.e., the third image, a flooding algorithm can be used to fill smaller holes. After image inversion, connected components in the image are calculated. By setting a threshold, such as a third threshold, the pixel values ​​of each pixel in the small connected components of the image obtained after the flooding algorithm are filled with 1 as the foreground of the image. The image obtained in this step is the fourth image in the aforementioned embodiment.

[0112] Step 3.7: Based on the binary image obtained in Step 3.6 (i.e., the fourth image), the image is inverted again to calculate the connected components in the image. Then, by setting a threshold, such as a fourth threshold, the boundary points of connected components with areas smaller than the fourth threshold are considered as seed points for region growing. Thus, region growing can be performed on the original image using these seed points. The original image used for region growing can be the optimized target image. The region growing algorithm can be as follows:

[0113] (1) Scale the original image. The scaling factor can be determined according to the actual situation of the image. The original image mentioned above can be the target image obtained after image optimization processing.

[0114] (2) Formulate region growth rules based on prior knowledge. Since the background pixel variation difference in cell-free regions of the image is small, the boundary points of the connected components of the background region can be locked as seed points for region growth.

[0115] (3) The region growth step size can be set to 2, and the region growth is performed based on the eight-neighborhood criteria.

[0116] (4) Region growing based on pixel distance criteria: First, determine whether the neighboring points of the region growing seed point are background points with a pixel value of 0 in the fourth image obtained in the previous steps; then, perform region growing based on two principles. That is: if it is a background point, stop growing; if the pixel value is greater than a preset pixel threshold, stop growing and assign the pixel that meets the condition to a value of 0 as a background point.

[0117] Figure 4 A schematic diagram illustrating the processing of the target image using steps 3.1-3.7 described above is shown. Wherein, Figure 4 Image (a) shows the target image after optimization. Figure 4 Image (b) shows the binary image obtained after processing in step 3.6, i.e., the fourth image. Figure 4 (c) in the image shows the image obtained after region growing.

[0118] Step 3.8: Use bilateral filtering to smooth the edges of the segmented result to obtain the complete cell region in the image.

[0119] 4. In the confluence calculation step, cell confluence can be calculated at the pixel level based on the clinical cell confluence calculation formula. Specifically, based on the processing of the aforementioned steps, adherent cell region information can be obtained. By calculating the total number of pixels in the adherent cell region and the total number of pixels in the entire image, the accurate cell confluence can be obtained by dividing the former by the latter. The above calculation process can be expressed as:

[0120]

[0121] This application embodiment processes the original image of adherent cells using opening and closing operations in morphological image processing algorithms, and then optimizes the original image using brightness equalization techniques such as contrast enhancement and gamma correction. This enhances the pixel gradient changes in the stem cell region image, highlighting the stem cell image features. Then, by using an edge detection algorithm to locate the cell region, and through algorithms such as image connected component calculation, flooding filling, and optimized region growing, the complete cell region can be obtained. Based on this, stem cell image cell region segmentation and cell confluence calculation can be quickly achieved using traditional algorithms. Applying the cell confluence calculation method provided in this application embodiment allows for rapid and accurate calculation of cell confluence.

[0122] Reference Figure 5 The diagram illustrates a cell confluence calculation device provided in an embodiment of this application, which may specifically include an image acquisition module 501, an image optimization module 502, an image segmentation module 503, and a cell confluence calculation module 504, wherein:

[0123] Image acquisition module 501 is used to acquire images of adherent cells of stem cells;

[0124] Image optimization module 502 is used to optimize the adherent cell image to obtain a target image. The optimization process includes enhancing the cell image features in the adherent cell image.

[0125] Image segmentation module 503 is used to determine cell regions in the target image through edge detection;

[0126] The cell confluence calculation module 504 is used to calculate the cell confluence of the stem cells based on the cell regions in the target image.

[0127] In one possible implementation of this application embodiment, the image optimization module 502 may be used to: perform optimization processing on the adherent cell image using opening and / or closing operations to obtain a target image.

[0128] For example, the image optimization module 502 can be used to: sequentially perform opening and closing operations on the adherent cell image to obtain a first image and a second image respectively; based on the adherent cell image, add the image obtained by subtracting the first image from the adherent cell image, and subtract the image obtained by subtracting the adherent cell image from the second image to obtain the target image.

[0129] In another possible implementation of this application embodiment, the image segmentation module 503 may be specifically used to: determine the gradient intensity of each pixel in the target image through edge detection; determine multiple consecutive edge points in the target image based on the gradient intensity of each pixel, wherein the multiple consecutive edge points constitute a cell edge region in the target image; and obtain the cell region in the target image by segmenting the cell edge region.

[0130] In one example, the image segmentation module 503 can be used to: determine multiple potential edge points in the target image based on the gradient intensity of each pixel, wherein the gradient intensity of any potential edge point is at its maximum value in at least one region of the target image; compare the gradient intensity of each potential edge point with the gradient intensity of each potential edge point in its neighborhood; and extract each potential edge point whose gradient intensity is at its maximum value in its neighborhood to obtain multiple consecutive edge points in the target image.

[0131] In another example, the image segmentation module 503 can also be used to: fill each hole region with an area smaller than a first threshold by performing a closing operation; determine the connected components in the target image after filling each hole region, and fill each connected component with an area smaller than a second threshold as the image background to obtain a third image; calculate the connected components in the third image after performing an inversion operation on the third image, and fill each connected component with an area smaller than a third threshold as the image foreground to obtain a fourth image; and identify cell regions in the target image based on the fourth image.

[0132] In another example, the image segmentation module 503 can also be used to: calculate the connected components in the fourth image after performing an inversion operation on the fourth image, and determine the boundary points of each connected component with an area less than a fourth threshold as region growth seed points; perform region growth using the region growth seed points on the target image to obtain a fifth image; and perform edge segmentation on the fifth image to obtain the cell regions in the target image.

[0133] In another possible implementation of this application embodiment, the cell confluence calculation module 504 may be used to: calculate the total number of pixels in the target image and the total number of pixels in the cell region respectively; and calculate the cell confluence of the stem cells based on the total number of pixels in the target image and the total number of pixels in the cell region.

[0134] This application provides a cell confluence calculation device, which can be used to implement the steps in the aforementioned method embodiments.

[0135] As the apparatus embodiments are basically similar to the method embodiments, they are described in a relatively simple manner. For relevant details, please refer to the description in the method embodiment section.

[0136] Reference Figure 6 The diagram illustrates a computer device provided in an embodiment of this application. Figure 6 As shown, the computer device 600 in this embodiment includes: a processor 610, a memory 620, and a computer program 621 stored in the memory 620 and executable on the processor 610. When the processor 610 executes the computer program 621, it implements the steps in various embodiments of the cell confluence calculation method described above, for example... Figure 1 Steps S101 to S104 are shown. Alternatively, when the processor 610 executes the computer program 621, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 4 The functions of modules 401 to 404 are shown.

[0137] For example, the computer program 621 can be divided into one or more modules / units, which are stored in the memory 620 and executed by the processor 610 to complete this application. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, which can be used to describe the execution process of the computer program 621 in the computer device 600. For example, the computer program 621 can be divided into an image acquisition module, an image optimization module, an image segmentation module, and a cell confluence calculation module, with the specific functions of each module as follows:

[0138] Image acquisition module, used to acquire images of adherent cells of stem cells;

[0139] An image optimization module is used to optimize the adherent cell image to obtain a target image. The optimization process includes enhancing the cell image features in the adherent cell image.

[0140] The image segmentation module is used to determine the cell regions in the target image through edge detection;

[0141] The cell confluence calculation module is used to calculate the cell confluence of the stem cells based on the cell regions in the target image.

[0142] The computer device 600 may be a device capable of implementing the steps in the foregoing method embodiments. The computer device 600 may be a desktop computer, a cloud server, or other computing device. The computer device 600 may include, but is not limited to, a processor 610 and a memory 620. Those skilled in the art will understand that... Figure 6This is merely one example of computer device 600 and does not constitute a limitation on computer device 600. It may include more or fewer components than shown, or combine certain components, or different components. For example, computer device 600 may also include input / output devices, network access devices, buses, etc.

[0143] The processor 610 can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0144] The memory 620 can be an internal storage unit of the computer device 600, such as a hard disk or RAM of the computer device 600. The memory 620 can also be an external storage device of the computer device 600, such as a plug-in hard disk, Smart Media Card (SMC), Secure Digital (SD) card, Flash Card, etc., equipped on the computer device 600. Furthermore, the memory 620 can include both internal and external storage units of the computer device 600. The memory 620 is used to store the computer program 621 and other programs and data required by the computer device 600. The memory 620 can also be used to temporarily store data that has been output or will be output.

[0145] This application also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the cell confluence calculation method as described in the foregoing embodiments.

[0146] This application also discloses a computer-readable storage medium storing a computer program that, when executed by a processor, implements the cell confluence calculation method as described in the foregoing embodiments.

[0147] This application also discloses a computer program product that, when run on a computer, causes the computer to execute the cell confluence calculation method described in the foregoing embodiments.

[0148] The embodiments described above are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for calculating cell confluence, characterized in that, include: Images of adherent stem cells were collected. The adherent cell image is optimized to obtain a target image. The optimization process includes performing opening and closing operations on the adherent cell image sequentially based on morphological image processing algorithms, and combining brightness equalization methods to enhance the pixel gradient changes in the cell region image of the adherent cell image. The gradient intensity of each pixel in the target image is determined by edge detection. Based on the gradient intensity of each pixel, multiple consecutive edge points in the target image are determined. These multiple consecutive edge points constitute the cell edge region in the target image. The cell edge region is segmented to obtain the cell region in the target image. The edge points are determined by gradient intensity binarization. The gradient intensity of any retained edge point is the maximum value in its neighborhood. Based on the cell regions in the target image, the cell confluence of the stem cells is calculated; The optimization processing of the adherent cell image to obtain the target image includes: The images of adherent cells are sequentially subjected to opening and closing operations to obtain the first image and the second image, respectively. The target image is obtained by adding the image obtained by subtracting the first image from the adherent cell image, and subtracting the image obtained by subtracting the adherent cell image from the second image, based on the adherent cell image.

2. The method according to claim 1, characterized in that, The step of determining multiple consecutive edge points in the target image based on the gradient intensity of each pixel includes: Based on the gradient intensity of each pixel, a plurality of potential edge points in the target image are determined, wherein the gradient intensity of any potential edge point is at its maximum value in at least one region of the target image; Compare the gradient intensity of each potential edge point with the gradient intensity of each potential edge point in its neighborhood; Extract each potential edge point whose gradient intensity is the maximum value in its neighborhood to obtain multiple consecutive edge points in the target image.

3. The method according to claim 1 or 2, characterized in that, The step of segmenting the cell edge region to obtain the cell region in the target image includes: Fill in the void regions whose area is less than the first threshold by performing a closing operation; Determine the connected components in the target image after filling each of the said hole regions, and fill each connected component with an area smaller than the second threshold as the image background to obtain the third image; After inverting the third image, the connected components in the third image are calculated, and each connected component with an area smaller than the third threshold is filled as the foreground of the image to obtain the fourth image. Cell regions in the target image are identified based on the fourth image.

4. The method according to claim 3, characterized in that, The step of identifying cell regions in the target image based on the fourth image includes: After inverting the fourth image, the connected components in the fourth image are calculated, and the boundary points of each connected component with an area less than the fourth threshold are determined as region growth seed points. Based on the target image, region growth is performed using the region growth seed points to obtain the fifth image; Edge segmentation is performed on the fifth image to obtain the cell regions in the target image.

5. The method according to any one of claims 1, 2, or 4, characterized in that, The calculation of the cell confluence degree of the stem cells based on the cell regions in the target image includes: Calculate the total number of pixels in the target image and the total number of pixels in the cell region, respectively. The cell confluence degree of the stem cells is calculated based on the total number of pixels in the target image and the total number of pixels in the cell region.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method for calculating cell confluence as described in any one of claims 1-5.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the method for calculating cell confluence as described in any one of claims 1-5.

Images