Cell growth monitoring method and device based on multi-band light source camera

Abstract

The present application proposes a cell growth monitoring method and device based on a multi-band light source camera, including the following steps: obtaining a cell image to be monitored, and generating a reflection spectrum curve graph for each pixel in the cell image to be monitored, obtaining a pixel matrix of each pixel in the cell image to be monitored based on the spectrum curve graph to form a first cell matrix; inserting a row transition matrix into the first cell matrix to obtain a second cell matrix, and inserting a column transition matrix into the second cell matrix to obtain a third cell matrix; obtaining the eigenvalues ​​of the third cell matrix and inputting it into a trained cell growth monitoring model to obtain growth information of the cells to be monitored. This solution obtains the reflection characteristics of each pixel under a multi-band light source and converts it into RGB information to obtain a pixel matrix, and then improves the clarity by interpolation and outputs it to the cell growth monitoring model to obtain the growth information of the cells to be monitored, thereby achieving the effect of accurate observation without staining the cells.

Description

Technical Field

[0001] The present application relates to the field of cell dynamic monitoring, and in particular to a cell growth monitoring method and device based on a multi-band light source camera. Background Art

[0002] Ordinary cameras commonly used in the market are usually equipped with standard RGB or single-band sensors, and mainly rely on visible light imaging. This method is suitable for general cell imaging tasks, such as observing cell morphology and performing basic cell counting. However, in cell imaging, the subtle structures inside cells often require higher contrast and details to be clearly distinguished. Ordinary cameras lack specialized imaging modes and are difficult to provide the required contrast and details. At the same time, the camera cannot flexibly adjust the band according to specific needs, which leads to low image quality when dealing with scenes such as identifying different types of cells or monitoring specific cell growth stages. This affects efficiency and accuracy. For example, when classifying cells, if the image is not clear enough, it may lead to misclassification. When monitoring the cell growth stage, if the subtle changes in the cells cannot be accurately captured, important growth information may be missed.

[0003] Of course, there are also cell observation techniques that use fluorescent staining to observe cells. However, some fluorescent dyes may be toxic to cells, especially in high concentrations or under long-term exposure. This may lead to cell growth inhibition or cell death, thus affecting the reliability of experimental results. Excessive light exposure may also cause photobleaching of fluorescent markers, thereby reducing signal intensity.

[0004] Therefore, how to conduct comprehensive and accurate dynamic monitoring of original living cells without destroying the original living cells is a problem that needs to be solved urgently by existing technologies. Summary of the invention

[0005] The embodiments of the present application provide a method and device for monitoring cell growth based on a multi-band light source camera. By introducing multi-band and multi-frequency optical imaging technology, and performing image processing on the imaged cell images and combining them with deep learning artificial intelligence analysis methods, the observation of cells of different types and in different states can be achieved, thereby solving the shortcomings of the prior art in terms of single information collection dimension, insufficient analysis accuracy, and lack of real-time feedback, thereby achieving more comprehensive, accurate, and efficient dynamic monitoring of cell growth.

[0006] In a first aspect, an embodiment of the present application provides a cell growth monitoring method based on a multi-band light source camera, the method comprising:

[0007] Acquire cells to be monitored, illuminate the cells to be monitored using light sources of different bands through a multi-band light source camera to obtain images of the cells to be monitored, and generate a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands;

[0008] The regional brightness of each pixel in the cell image to be monitored is obtained, the R value, G value and B value of each pixel are calculated based on the reflectance spectrum curve graph, and the R value, G value, B value and regional brightness of each pixel are used to form a 2×2 matrix as the pixel matrix of the pixel, and the pixel matrix of each pixel in the cell image to be monitored is integrated to form a first cell matrix;

[0009] Inserting a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by items in the corresponding two adjacent pixel matrices in the same row, and inserting a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by items in the corresponding two adjacent pixel matrices in the same column;

[0010] The characteristic values ​​of the third cell matrix are obtained and input into the trained cell growth monitoring model to obtain the growth information of the cells to be monitored.

[0011] In a second aspect, an embodiment of the present application provides a cell growth monitoring device based on a multi-band light source camera, comprising:

[0012] An acquisition module is used to acquire cells to be monitored, illuminate the cells to be monitored using light sources of different bands through a multi-band light source camera to acquire images of the cells to be monitored, and generate a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands;

[0013] An integration module is used to obtain the regional brightness of each pixel in the cell image to be monitored, calculate the R value, G value and B value of each pixel based on the reflection spectrum curve graph, and use the R value, G value, B value and regional brightness of each pixel to form a 2×2 matrix as the pixel matrix of the pixel, and integrate the pixel matrix of each pixel in the cell image to be monitored to form a first cell matrix;

[0014] An insertion module is used to insert a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by items in the corresponding two adjacent pixel matrices in the same row, and to insert a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by items in the corresponding two adjacent pixel matrices in the same column;

[0015] The monitoring module is used to obtain the characteristic value of the third cell matrix and input it into the trained cell growth monitoring model to obtain the growth information of the cells to be monitored.

[0016] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a cell growth monitoring method based on a multi-band light source camera.

[0017] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute a process, and the process includes a cell growth monitoring method based on a multi-band light source camera.

[0018] The main contributions and innovations of the present invention are as follows:

[0019] The embodiment of the present application uses light sources of different wavelengths to illuminate cells to obtain the reflection characteristics absorbed by each pixel under different color spectra, and then converts the reflection characteristics obtained by each pixel into RGB information, and then uses a pre-trained cell growth monitoring model to complete the growth detection of cells, thereby achieving the effect of accurately viewing the cell growth status without fluorescently marking the cells. Specifically, the embodiment of the present application uses a multi-band light source to illuminate cells to obtain cell images. In order to solve the problem of a single dimension of information collection, the embodiment of the present application generates the RGB value of each pixel by the reverse value of each pixel in the acquired cell image under the illumination of light sources of different wavelengths, thereby achieving the purpose of viewing the cell image without fluorescently staining the cell image; in order to improve the analysis accuracy, this solution inserts a new pixel matrix between every two adjacent pixels in the cell image to enhance the clarity of the cell image, reduce the image fault caused by point selection, and retain the image information as much as possible, thereby improving the accuracy of subsequent analysis using the cell growth monitoring model.

[0020] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0022] Figure 1 is a flow chart of a cell growth monitoring method based on a multi-band light source camera according to an embodiment of the present application;

[0023] Figure 2 is a schematic diagram of a reflection spectrum curve according to an embodiment of the present application;

[0024] Figure 3 is a structural block diagram of a cell growth monitoring device based on a multi-band light source camera according to an embodiment of the present application;

[0025] Figure 4 It is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0026] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0027] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0028] Embodiment 1

[0029] The embodiment of the present application provides a cell growth monitoring method based on a multi-band light source camera, which uses light sources of different bands to illuminate cells to obtain the reflection characteristics absorbed by each pixel under different color spectra, and then converts the reflection characteristics obtained by each pixel into RGB information, and then uses a pre-trained cell growth monitoring model to complete the cell growth detection. Specifically, refer to Figure 1 , the method comprising:

[0030] Obtain cells to be monitored

[0031] Using a multi-band light source camera to illuminate the cells to be monitored using light sources of different bands to obtain an image of the cells to be monitored, and generating a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands;

[0032] The regional brightness of each pixel in the cell image to be monitored is obtained, the R value, G value and B value of each pixel are calculated based on the reflectance spectrum curve graph, and the R value, G value, B value and regional brightness of each pixel are used to form a 2×2 matrix as the pixel matrix of the pixel, and the pixel matrix of each pixel in the cell image to be monitored is integrated to form a first cell matrix;

[0033] Inserting a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by differentiation of matrix elements of two adjacent pixel matrices in the same row, and inserting a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by differentiation of matrix elements of two adjacent pixel matrices in the same column;

[0034] Get the eigenvalues ​​of the third cell matrix;

[0035] The characteristic values ​​are input into a trained cell growth monitoring model to obtain cell information of the cells to be monitored, wherein the cell growth monitoring model is trained by characteristic values ​​of different cell information and corresponding markers.

[0036] This scheme uses a multi-band light source to add and illuminate the monitoring area to obtain the reflection values ​​of different pixels under different bands of light sources. Since the colors of cells of different cell types and different growth states are different, the colors of each pixel are not the same. These pixels will show different absorption and reflection characteristics when facing different bands of light. This scheme analyzes the reflection values ​​of different pixels to multi-band light sources, thereby solving the problem of single dimension of information collection in the prior art. In addition, since there is a lot of multi-band reflection value information collected by different pixels, in order to avoid the increase of subsequent analysis difficulty caused by too much information, this scheme converts multiple reflection values ​​of different pixels of the image to be monitored into characteristic values ​​through analysis and processing means, and trains and uses the subsequent cell growth monitoring model in the form of characteristic values, which greatly reduces the complexity of deep learning and improves the computing speed and computing power. In addition, this scheme converts the multi-band reflection values ​​collected by different pixels into RGB values, and then uses the original differentiation technology to differentiate the corresponding values ​​of the intervals between different pixels, reducing the inevitable image faults caused by the location of the pixel points, and retaining the image information as much as possible, thereby improving the accuracy and success rate of recognition.

[0037] In the step of "selecting cells to be monitored", the cells to be monitored are living cells, and the monitoring personnel can select certain areas of the cells to be monitored as monitoring areas.

[0038] Different from the single light source camera in the prior art, the present solution uses a multi-band light source camera to illuminate the monitoring area with light sources of different bands to obtain the image of the cells to be monitored, and records the reflection value of each pixel under the illumination of light sources of different bands to generate a reflection spectrum curve of each pixel, wherein the reflection spectrum curve of the pixel is as follows: Figure 2 shown.

[0039] This solution converts the reflectance value of each pixel in different bands into RGB values ​​for processing. The advantage of this is that the reflectance value information of multiple bands can be integrated. In addition, since each pixel has different reflectance values ​​in different bands, and different cells have different reflectance and absorption bands, this solution uses the average value in each band as the average reflectance value and combines the weight of the corresponding color channel to calculate the R value, G value and B value of each pixel.

[0040] Specifically, in the step of "calculating the R value, G value and B value of each pixel point based on the reflectance spectrum curve", the R band, G band and B band are set, and the average reflectance value of each pixel point in the R band, G band and B band is obtained, and then the R value, G value and B value of each pixel point are calculated based on the average reflectance value of each pixel point in different bands and the weight value of the current band.

[0041] Furthermore, the average reflection value of each pixel in the R band is obtained to obtain the R reflection value, the average reflection value of each pixel in the G band is obtained to obtain the G reflection value, and the average reflection value of each pixel in the B band is obtained to obtain the B reflection value. The R value weight, G value weight and B value weight are set as the weight values ​​of the corresponding bands. The R value of each pixel is calculated based on the R reflection value and the R value weight of each pixel. The G value of each pixel is calculated based on the G reflection value and the G value weight of each pixel. The B value of each pixel is calculated based on the B reflection value and the B value weight of each pixel.

[0042] Specifically, the R band ranges from 600 to 700 nm, the G band ranges from 500 to 600 nm, and the B band ranges from 400 to 500 nm. That is to say, this solution obtains the average reflection value of each pixel point in the range of 600 to 700 nm as the R reflection value, obtains the average reflection value of each pixel point in the range of 500 to 600 nm as the G reflection value, and obtains the average reflection value of each pixel point in the range of 400 to 500 nm as the B reflection value.

[0043] Specifically, set the R value weight WR , set the G value weight Wg, set the B value weight Wb, then the R value calculation formula of the pixel point is:

[0044]

[0045] Among them, Red is the R value of the corresponding pixel point, Ravg is the R reflection value of the corresponding pixel point, is the R value weight, and 255 is the maximum value of the color channel.

[0046] The calculation formula of the pixel G value is:

[0047]

[0048] Among them, Green is the G value of the corresponding pixel point, Gavg is the G reflection value of the corresponding pixel point, is the G value weight, and 255 is the maximum value of the color channel.

[0049] The calculation formula for the pixel B value is:

[0050]

[0051] Among them, Blue is the B value of the corresponding pixel, Bavg is the B reflection value of the corresponding pixel, is the B value weight, and 255 is the maximum value of the color channel.

[0052] In this scheme, by calculating the reflectance value of each pixel under light sources of different wavelengths, the image information of each pixel in the image of the monitored cells can be accurately obtained without staining the cells, thereby monitoring the growth of the living image of the monitored cells without error.

[0053] Since the regional brightness of the monitoring area will also affect the reflectance value of the monitored cells under the multi-band light source camera, this scheme takes the regional brightness and the R value, G value and B value of each pixel to form the pixel matrix of the current pixel.

[0054] For example, the pixel matrix form of each pixel is , where Red is the R value, Green is the G value, Blue is the B value, and White is the area brightness.

[0055] The pixel matrix of all pixels in the monitoring area is integrated to obtain a first pixel matrix, exemplarily,

[0056] The first pixel matrix obtained by this scheme is:

[0057]

[0058] In the first pixel matrix, n is the number of columns of the first pixel matrix, m is the number of rows of the first pixel matrix, and the number of pixel matrices in the first pixel matrix is ​​m×n.

[0059] It should be noted that since there are multiple pixel points in the monitoring area, in order to avoid the loss of information of pixel points that are not taken due to the pixel point selection method, this scheme differentiates the matrix elements of the first pixel matrix to obtain a third pixel matrix, wherein the third pixel matrix differentiates both the row elements and the column elements of the first pixel matrix.

[0060] In the step of "generating a row transition matrix from matrix elements in two adjacent pixel matrices in the same row", the row transition matrix is ​​a 2×2 matrix, and the first column of the row transition matrix is ​​the same as the second column of the previous adjacent pixel matrix, and the second column of the row transition matrix is ​​the same as the first column of the next adjacent pixel matrix.

[0061] Specifically, when a camera is used to obtain an image of the cell to be monitored, due to the problem of camera resolution, the lower the resolution, the fewer pixels are taken, and the larger the area occupied by each pixel, the more blurred the image of the cell to be monitored is. Therefore, this solution enhances the clarity of the image by regenerating a row transition matrix between two adjacent pixel matrices.

[0062] Exemplarily, the matrix changes for generating the second cell matrix of the present scheme are expressed as follows:

[0063]

[0064] That is, the row transition matrix The first column Is a pixel matrix The second column of the row transition matrix The following pixel matrix The first column and row of the transition matrix are Also the previous adjacent pixel matrix The next adjacent pixel matrix The mean value of .

[0065] In the step of "generating a column transition matrix by matrix elements in two adjacent pixel matrices in the same column", the column transition matrix is ​​a 2×2 matrix, and the first row of the column transition matrix is ​​the same as the second row of the upper adjacent pixel matrix, and the second row of the column transition matrix is ​​the same as the first row of the lower adjacent pixel matrix.

[0066] Exemplarily, the matrix changes for generating the third cell matrix are expressed as follows:

[0067]

[0068] That is, the column transition matrix The first line is the adjacent matrix above The second row of the transition matrix is ​​the same as is the adjacent matrix below The first row is the same as that of , and the column transition matrix is ​​also characterized by the upper adjacent pixel matrix The adjacent pixel matrix below The mean value of .

[0069] The final representation of the third cell matrix is:

[0070]

[0071] Wherein, a is the column of the third cell matrix, and b is the row of the third cell matrix.

[0072] Specifically, this solution can reduce image discontinuities caused by pixel point selection problems by inserting row transition matrices and column transition matrices, and improve recognition accuracy and success rate while retaining image information as much as possible.

[0073] In the step of "obtaining eigenvalues ​​of the third cell matrix", the sub-eigenvalues ​​of each sub-matrix in the third cell matrix are calculated, and the sum of each sub-eigenvalue is taken as the eigenvalue of the third cell matrix, wherein the sub-eigenvalue of each sub-matrix is ​​the weighted sum of the normalized values ​​of the R value, G value, B value and regional brightness value of the matrix elements of the current sub-matrix.

[0074] In this solution, the eigenvalue of the third cell matrix is ​​the sum of the sub-eigenvalues ​​of each sub-matrix in the third cell matrix. In the step of "calculating the sub-eigenvalues ​​of each sub-matrix in the third cell matrix", the R value, G value, B value and regional brightness value of each sub-matrix are normalized to obtain the corresponding normalized value, and the R value feature weight, G value feature weight, B value feature weight and brightness feature weight are set. The R value feature weight, G value feature weight, B value feature weight and brightness feature weight are used to perform weighted summation on the normalized values ​​of the corresponding items in each sub-matrix to obtain the eigenvalue of each sub-matrix.

[0075] Specifically, the quotient of the R value and 255 is taken as the normalized value of the R value, the quotient of the G value and 255 is taken as the normalized value of the G value, the quotient of the B value and 255 is taken as the normalized value of the B value, and the quotient of the regional brightness value and 100 is taken as the normalized value of the regional brightness.

[0076] Exemplarily, the formula for calculating the sub-eigenvalue of each sub-matrix is ​​expressed as follows:

[0077]

[0078] in, is the R value feature weight, is the G value feature weight, is the B-value feature weight, is the brightness feature weight, It is an activation function used to output the eigenvalue. Since the upper limit of the RGB value is 255, 255 is used as the maximum value to normalize the R value, G value, and B value. The highest value of the regional brightness is 100, so 100 is used to normalize the regional brightness value. The R value feature weight, G value feature weight, and B value feature weight can be manually customized or dynamically adjusted by the computer.

[0079] The eigenvalue calculation formula for summing all sub-eigenvalues ​​to the third cell matrix is:

[0080]

[0081] Among them, a and b are used to indicate the positions of different sub-matrices. is an activation function used to output the feature value.

[0082] Specifically, this solution reduces the complexity of deep learning by transmitting the image information of the cells to be monitored in the form of feature values ​​to a pre-built cell growth monitoring model, thereby improving the model's operating speed and reducing computing power.

[0083] The cell growth monitoring model of this scheme is trained by the characteristic values ​​of different cell information and corresponding markers, wherein the cell information includes cell type and cell growth state. In other words, cells of different cell types and different cell growth states have different corresponding characteristic values, and can then be identified through the characteristic values ​​and the cell growth monitoring model.

[0084] When this solution passes the characteristic value into the cell growth monitoring model to output the cell information, the cell type and growth status of the current cells to be monitored can be known based on the cell information, thereby providing a basis for the subsequent machine recognition of the count value and cell morphology in the image.

[0085] Embodiment 2

[0086] Based on the same idea, refer to Figure 3 , the present application also proposes a cell growth monitoring method and device based on a multi-band light source camera, comprising:

[0087] An acquisition module is used to acquire cells to be monitored, illuminate the cells to be monitored using light sources of different bands through a multi-band light source camera to acquire images of the cells to be monitored, and generate a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands;

[0088] An integration module is used to obtain the regional brightness of each pixel point in the cell to be monitored, calculate the R value, G value and B value of each pixel point based on the reflection spectrum curve graph, and use the R value, G value, B value and regional brightness of each pixel point to form a 2×2 matrix as the pixel matrix of the pixel point, and integrate the pixel matrix of each pixel point in the cell to be monitored to form a first cell matrix;

[0089] An inserting module is used to insert a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by differentiating matrix elements in the corresponding two adjacent pixel matrices in the same row, and insert a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by differentiating matrix elements in the corresponding two adjacent pixel matrices in the same column;

[0090] The monitoring module is used to obtain the eigenvalues ​​of the third cell matrix and input the eigenvalues ​​into the trained cell growth monitoring model to obtain the cell information of the cells to be monitored, wherein the cell growth monitoring model is trained by the eigenvalues ​​of different cell information and corresponding markers.

[0091] Embodiment 3

[0092] This embodiment also provides an electronic device, referring to Figure 4 , comprises a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to execute the steps in any of the above method embodiments.

[0093] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0094] Among them, the memory 404 may include a large capacity memory 404 for data or instructions. For example, but not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a tape, or a universal serial bus (USB) drive, or a combination of two or more of these. In appropriate cases, the memory 404 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 404 may be inside or outside the data processing device. In a specific embodiment, the memory 404 is a non-volatile memory. In a specific embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. In appropriate circumstances, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM may be a fast page mode dynamic random access memory 404 (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0095] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .

[0096] The processor 402 reads and executes the computer program instructions stored in the memory 404 to implement any one of the cell growth monitoring methods based on the multi-band light source camera in the above embodiments.

[0097] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .

[0098] The transmission device 406 can be used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0099] The input / output device 408 is used to input or output information. In this embodiment, the input information may be an image of the cell to be monitored, a reflection spectrum curve graph, etc., and the output information may be growth information of the cell to be monitored, etc.

[0100] Optionally, in this embodiment, the processor 402 may be configured to perform the following steps through a computer program:

[0101] Acquire cells to be monitored, illuminate the cells to be monitored using light sources of different bands through a multi-band light source camera to obtain images of the cells to be monitored, and generate a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands;

[0102] The regional brightness of each pixel in the cell image to be monitored is obtained, the R value, G value and B value of each pixel are calculated based on the reflectance spectrum curve graph, and the R value, G value, B value and regional brightness of each pixel are used to form a 2×2 matrix as the pixel matrix of the pixel, and the pixel matrix of each pixel in the cell image to be monitored is integrated to form a first cell matrix;

[0103] Inserting a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by differentiation of matrix elements in corresponding two adjacent pixel matrices in the same row, and inserting a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by differentiation of matrix elements in corresponding two adjacent pixel matrices in the same column;

[0104] The characteristic values ​​of the third cell matrix are obtained, and the characteristic values ​​are input into the trained cell growth monitoring model to obtain the cell information of the cells to be monitored, wherein the cell growth monitoring model is trained by the characteristic values ​​of different cell information and corresponding markers.

[0105] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0106] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0107] Embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, at this point, it should be noted that, for example, Figure 4 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or storage blocks implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. Physical media are non-transitory media.

[0108] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0109] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A cell growth monitoring method based on a multi-band light source camera, characterized in that: The following steps are involved: Obtain cells to be monitored; Using a multi-band light source camera to illuminate the cells to be monitored using light sources of different bands to obtain an image of the cells to be monitored, and generating a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands; The regional brightness of each pixel in the cell image to be monitored is obtained, and the R value, G value and B value of each pixel are calculated based on the reflectance spectrum curve graph, wherein the R band, G band and B band are set, and the average reflectance value of each pixel in the R band, G band and B band is obtained, and the R value, G value and B value of each pixel are calculated by the average reflectance value of each pixel in different bands and the weight value of the current band, and the R value, G value, B value and regional brightness of each pixel are used to form a 2×2 matrix as the pixel matrix of the pixel, and the pixel matrix of each pixel in the cell image to be monitored is integrated to form a first cell matrix; Inserting a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by differentiation of matrix elements in corresponding two adjacent pixel matrices in the same row, and inserting a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by differentiation of matrix elements in corresponding two adjacent pixel matrices in the same column; Obtaining eigenvalues ​​of the third cell matrix, wherein the sub-eigenvalues ​​of each sub-matrix in the third cell matrix are calculated, and the sum of each sub-eigenvalue is taken as the eigenvalue of the third cell matrix, wherein the sub-eigenvalue of each sub-matrix is ​​the weighted sum of the normalized values ​​of the R value, the G value, the B value and the regional brightness value of the matrix element of the current sub-matrix; The characteristic values ​​are input into a trained cell growth monitoring model to obtain cell information of the cells to be monitored, wherein the cell growth monitoring model is trained by characteristic values ​​of different cell information and corresponding markers.

2. The cell growth monitoring method based on a multi-band light source camera according to claim 1, characterized in that: Get the average reflection value of each pixel in the R band to obtain the R reflection value, get the average reflection value of each pixel in the G band to obtain the G reflection value, get the average reflection value of each pixel in the B band to obtain the B reflection value, set the R value weight, G value weight and B value weight, calculate the R value of each pixel based on the R reflection value and the R value weight of each pixel, calculate the G value of each pixel based on the G reflection value and the G value weight of each pixel, and calculate the B value of each pixel based on the B reflection value and the B value weight of each pixel.

3. The cell growth monitoring method based on a multi-band light source camera according to claim 1, characterized in that: In the step of "a row transition matrix is ​​generated by differentiating matrix elements in two adjacent pixel matrices corresponding to the same row", the row transition matrix is ​​a 2×2 matrix, and the first column of the row transition matrix is ​​the same as the second column of the previous adjacent pixel matrix, and the second column of the row transition matrix is ​​the same as the first column of the next adjacent pixel matrix.

4. The cell growth monitoring method based on a multi-band light source camera according to claim 1, characterized in that: In the step of "generating a column transition matrix by differentiating matrix elements in two adjacent pixel matrices corresponding to the same column", the column transition matrix is ​​a 2×2 matrix, and the first row of the column transition matrix is ​​the same as the second row of the upper adjacent pixel matrix, and the second row of the column transition matrix is ​​the same as the first row of the lower adjacent pixel matrix.

5. The cell growth monitoring method based on a multi-band light source camera according to claim 1, characterized in that: The cell information of the cells to be monitored includes cell type and cell growth status.

6. A cell growth monitoring device based on a multi-band light source camera, characterized in that: The following steps are involved: An acquisition module is used to acquire cells to be monitored, illuminate the cells to be monitored using light sources of different bands through a multi-band light source camera to acquire images of the cells to be monitored, and generate a reflection spectrum curve graph for each pixel in the image of the cells to be monitored, wherein the reflection spectrum curve graph represents the reflection value of the corresponding pixel under the illumination of light sources of different bands; An integration module is used to obtain the regional brightness of each pixel in the cell image to be monitored, and calculate the R value, G value and B value of each pixel based on the reflectance spectrum curve graph, wherein the R band, G band and B band are set, and the average reflectance value of each pixel in the R band, G band and B band is obtained, and the R value, G value and B value of each pixel are calculated by the average reflectance value of each pixel in different bands and the weight value of the current band, and the R value, G value, B value and regional brightness of each pixel are used to form a 2×2 matrix as the pixel matrix of the pixel, and the pixel matrix of each pixel in the cell image to be monitored is integrated to form a first cell matrix; An inserting module is used to insert a row transition matrix between every two adjacent pixel matrices in each row of the first cell matrix to obtain a second cell matrix, wherein the row transition matrix is ​​generated by differentiating matrix elements in the corresponding two adjacent pixel matrices in the same row, and insert a column transition matrix between every two adjacent pixel matrices in each column of the second cell matrix to obtain a third cell matrix, wherein the column transition matrix is ​​generated by differentiating matrix elements in the corresponding two adjacent pixel matrices in the same column; The monitoring module is used to obtain the eigenvalue of the third cell matrix, wherein the sub-eigenvalue of each sub-matrix in the third cell matrix is ​​calculated, and the sum of each sub-eigenvalue is taken as the eigenvalue of the third cell matrix, wherein the sub-eigenvalue of each sub-matrix is ​​the weighted sum of the normalized values ​​of the R value, G value, B value and regional brightness value of the matrix element of the current sub-matrix, and the eigenvalue is input into the trained cell growth monitoring model to obtain the cell information of the cell to be monitored, wherein the cell growth monitoring model is trained by the eigenvalues ​​of different cell information and corresponding markers.

7. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the cell growth monitoring method based on a multi-band light source camera as described in any one of claims 1-5.

8. A readable storage medium, characterized in that: The readable storage medium stores a computer program, which includes a program code for controlling a process to execute a process, wherein the process includes a cell growth monitoring method based on a multi-band light source camera according to any one of claims 1-5.

Images