Cell morphology graph noise reduction method, device, equipment, medium and product

Abstract

The invention discloses a cell morphology image noise reduction method and device, equipment, a medium and a product, and relates to the technical field of image processing, the method comprises the following steps: obtaining a morphology image and an amplitude image generated by scanning a target cell through a probe of a tapping mode atomic force microscope; gray level conversion is carried out on the morphology image and the amplitude image; performing image fusion on the morphology grayscale image and the amplitude grayscale image to obtain a fused image; performing non-linear relation fitting on the pixel value of each pixel point in a non-noise area in the morphology grayscale image and the pixel value of the corresponding pixel point in the fused image to obtain a mapping relational expression between the pixel value in the morphology grayscale image and the pixel value in the fused image; mapping the pixel value of each pixel point in the fused image by adopting a mapping relational expression to obtain a de-noised morphology grayscale image; and performing gray inverse conversion on the de-noised morphology gray image to obtain a de-noised color morphology image. According to the invention, the noise of the cell morphology image can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of image processing, and particularly to a method, device, equipment, medium and product for denoising cell morphology images. Background Art

[0002] Cells are the basic building blocks of organisms. Understanding cell morphology and measuring cell physical properties for cell differentiation and cell function analysis is an important topic in scientific research. Tapping-Mode Atomic Force Microscopy (TM-AFM) probe scanning imaging has high resolution and little damage to samples, making it the most ideal atomic force microscope for cell imaging in the atomic force family.

[0003] When the height gradient on the cell surface is large, the probe of TM-AFM cannot achieve rapid adjustment over a large range, resulting in noise in the tapping atomic force morphology image of the cell. During the process of contact mode scanning imaging, the probe will scratch the cell, causing large fluctuations in the piezoelectric displacement platform, and further resulting in noise in the morphology image, reducing the accuracy of the morphology image scanned by the TM-AFM probe.

[0004] Currently, when there is scanning noise in the morphology image scanned by the TM-AFM probe, an operator with rich experience in scanning cells and the ability to adjust the parameters of the TM-AFM probe usually adjusts the scanning parameters based on personal experience to reduce the scanning noise of the cell morphology image. However, this denoising method is limited by the personal ability of the operator of the tapping atomic force, and can only have a certain denoising effect on the cell morphology image when the cell gradient change range is not large. How to find a suitable denoising method to effectively reduce the scanning noise in the morphology image scanned by the TM-AFM probe of cells is an obstacle to the application of TM-AFM in cell imaging. Summary of the Invention

[0005] The purpose of the present application is to provide a method, device, equipment, medium and product for denoising cell morphology images, which can reduce the noise of cell morphology images.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In the first aspect, the present application provides a method for denoising cell morphology images, including:

[0008] Obtaining a morphology image and an amplitude image generated by scanning a target cell with a probe of a tapping-mode atomic force microscope;

[0009] Performing gray-scale conversion on the morphology image and the amplitude image respectively to obtain a morphology gray-scale image and an amplitude gray-scale image;

[0010] Perform image fusion on the morphological grayscale image and the amplitude grayscale image to obtain a fused image;

[0011] Perform non-linear relationship fitting on the pixel values of each pixel point in the non-noise region of the morphological grayscale image and the pixel values of the corresponding pixel points in the fused image to obtain the mapping relationship formula between the pixel values in the morphological grayscale image and the pixel values in the fused image; the non-noise region is the region outside the cell nucleus;

[0012] Map the pixel values of each pixel point in the fused image using the mapping relationship formula to obtain a denoised morphological grayscale image;

[0013] Perform inverse grayscale conversion on the denoised morphological grayscale image to obtain a denoised color morphological image.

[0014] Optionally, the grayscale conversion formulas for performing grayscale conversion on the morphological image and the amplitude image respectively are expressed as:

[0015] Gray=(Red*0.3+Green*0.59+Blue*0.11);

[0016] where Gray is the pixel value after grayscale conversion, Red is the red color value, Green is the green color value, and Blue is the blue color value.

[0017] Optionally, performing image fusion on the morphological grayscale image and the amplitude grayscale image to obtain a fused image specifically includes:

[0018] Perform image fusion on the morphological grayscale image and the amplitude grayscale image using the Laplacian pyramid image fusion algorithm to obtain a fused image.

[0019] Optionally, performing non-linear relationship fitting on the pixel values of each pixel point in the non-noise region of the morphological grayscale image and the pixel values of the corresponding pixel points in the fused image to obtain the mapping relationship formula between the pixel values in the morphological grayscale image and the pixel values in the fused image specifically includes:

[0020] Form a first pixel value set from the pixel values of each pixel point in the non-noise region of the morphological grayscale image, and form a second pixel value set from the pixel values of the corresponding pixel points in the fused image;

[0021] According to the first pixel value set and the second pixel value set, use a 5th-degree polynomial regression model as the mapping relationship formula for relationship fitting to obtain the mapping relationship formula between the pixel values in the morphological grayscale image and the pixel values in the fused image;

[0022] The 5th-degree polynomial regression model is expressed as: y=a0+a1x+a2x2 +a3x 3 +a4x 4 +a5x 5 +ε;

[0023] Wherein, y represents the pixel value of a pixel point in the morphological grayscale image, x represents the pixel value of a pixel point in the fused image, ε is a random error, and a i is the i-th regression coefficient, and i ∈ [0, 1, 2, 3, 4, 5].

[0024] Optionally, according to the first pixel value set and the second pixel value set, a fifth-order polynomial regression model is used as a mapping relational expression for relationship fitting to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image, specifically including:

[0025] According to the first pixel value set and the second pixel value set, the fifth-order polynomial regression model is model-fitted by the least squares method to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image.

[0026] Optionally, according to the first pixel value set and the second pixel value set, the fifth-order polynomial regression model is model-fitted by the least squares method to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image, specifically including:

[0027] The fifth-order polynomial regression model is rewritten into a matrix form model, and the matrix form model is: Y = aX + ε;

[0028] Wherein, Y = [y1, y2,..., y N T , a = [a0, a1,..., a N T , X is a design matrix composed of the variable x and the powers of the variable x, Y is a dependent variable vector, a is a coefficient vector, and y n is the pixel value of the n-th pixel sampling point in the morphological grayscale image, and x n is the pixel value of the n-th pixel sampling point in the fused image, 1 ≤ n ≤ N, and N is the number of pixel sampling points;

[0029] According to the first pixel value set and the second pixel value set, the matrix form model is model-fitted by the least squares method to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image.

[0030] ​​In a second aspect, the present application provides a device for denoising a cell morphology image. The device for denoising a cell morphology image applies the method for denoising a cell morphology image described above. The device for denoising a cell morphology image includes:

[0031] An image acquisition module, configured to acquire a morphology image and an amplitude image generated by scanning a probe of a tapping mode atomic force microscope on a target cell;

[0032] A grayscale conversion module, configured to perform grayscale conversion on the morphology image and the amplitude image respectively to obtain a morphology grayscale image and an amplitude grayscale image;

[0033] An image fusion module, configured to perform image fusion on the morphology grayscale image and the amplitude grayscale image to obtain a fused image;

[0034] A mapping relationship determination module, configured to perform non-linear relationship fitting on the pixel values of each pixel point in the non-noise region of the morphology grayscale image and the pixel values of the corresponding pixel points in the fused image to obtain a mapping relationship between the pixel values in the morphology grayscale image and the pixel values in the fused image; the non-noise region is the region outside the cell nucleus;

[0035] A denoised morphology grayscale image determination module, configured to map the pixel values of each pixel point in the fused image by using the mapping relationship to obtain a denoised morphology grayscale image;

[0036] A denoised color morphology image determination module, configured to perform inverse grayscale conversion on the denoised morphology grayscale image to obtain a denoised color morphology image.

[0037] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the steps of the method for denoising a cell morphology image described in any one of the above.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method for denoising a cell morphology image described in any one of the above are implemented.

[0039] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method for denoising a cell morphology image described in any one of the above are implemented.

[0040] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0041] The present application provides a method, apparatus, device, medium and product for reducing noise in cell morphology images. After gray-scale conversion and fusion of the morphology image and amplitude image of the cell, a non-linear relationship fitting is performed between the pixel values of each pixel point in the non-noise region of the morphology gray-scale image and the pixel values of the corresponding pixel points in the fusion image, so as to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fusion image. According to the mapping relationship formula, the noise generated by the TM-AFM probe scanning and imaging of the cell is compensated, and the noise in the cell morphology image caused by the large height gradient on the cell surface can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0043] Figure 1 It is a schematic flowchart of a method for reducing noise in cell morphology images provided by an embodiment of the present application.

[0044] Figure 2 It is a schematic principle diagram of a method for reducing noise in cell morphology images provided by an embodiment of the present application.

[0045] Figure 3 It is a schematic principle diagram of TM-AFM probe scanning imaging provided by an embodiment of the present application.

[0046] Figure 4 It is a schematic diagram of a cell image in the image noise reduction process provided by an embodiment of the present application.

[0047] Figure 5 It is a schematic structural diagram of a computer device provided by an embodiment of the present application.

[0048] Reference numerals: 1 - photodetector, 2 - laser, 3 - scanning probe, 4 - cell, 5 - substrate, 6 - piezoelectric ceramic. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0050] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] The present application provides a method for denoising a cell morphology image, as Figure 1 and Figure 2 shown, the method for denoising a cell morphology image includes:

[0052] Step 101: Obtain a morphology image and an amplitude image generated by scanning a probe of a tapping mode atomic force microscope for a target cell.

[0053] Step 102: Perform gray-scale conversion on the morphology image and the amplitude image respectively to obtain a morphology gray-scale image and an amplitude gray-scale image.

[0054] Step 103: Perform image fusion on the morphology gray-scale image and the amplitude gray-scale image to obtain a fused image.

[0055] Step 104: Fit the pixel values of each pixel point in the non-noise region of the morphology gray-scale image with the pixel values of the corresponding pixel points in the fused image to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image; the non-noise region is the region outside the cell nucleus.

[0056] Step 105: Map the pixel values of each pixel point in the fused image using the mapping relationship formula to obtain a denoised morphology gray-scale image.

[0057] Step 106: Perform inverse gray-scale conversion on the denoised morphology gray-scale image to obtain a denoised color morphology image.

[0058] Based on the high correlation between the amplitude image and the morphology image of the cell scanned by TM-AFM, the present application preprocesses the morphology image and the amplitude image of the cell respectively, and then performs image fusion on the preprocessed morphology image and amplitude image of the cell to obtain a denoised cell fused image. The pixel values of multiple noise-free pixel points in the cell morphology image are numerically fitted with the pixel values of the corresponding pixel points in the cell fused image, so as to obtain the corresponding relationship formula between the pixel values in the cell fused image and the pixel values in the cell morphology image. Using this formula, the cell fused image can be restored to a denoised cell morphology image. Without changing the basic height information of the morphology image, the image data of the noise region in the denoised image is replaced by the image data in the fused cell image, thereby effectively reducing the noise of the morphology image. The present application can perform denoising processing on the morphology noise that appears in the TM-AFM cell scanning imaging, and further improve the quality of the TM-AFM scanning cell morphology imaging.

[0059] Among them, in an exemplary embodiment, the atomic force microscopy imaging system used for tapping mode cell scanning imaging is the AFM atomic force microscopy imaging system of the NanoWizard 3 BioScience model in the laboratory, and the model of the scanning probe used is the TAP300AL-G tapping type scanning probe. The measurement principle of the atomic force probe is as Figure 3 shown. The laser 2 emits laser light, which is converged and irradiated onto the tip surface of the scanning probe 3, and then reflected onto the photodetector 1 to detect the tip amplitude and phase of the scanning probe 3. The topography of the cell sample 4 on the substrate 5 can be accurately measured through the change in the tip amplitude of the scanning probe 3. A piezoelectric ceramic 6 is used inside the substrate 5.

[0060] Among them, in step 102, the gray conversion formulas for performing gray conversion on the topography image and the amplitude image are respectively expressed as: Gray = (Red * 0.3 + Green * 0.59 + Blue * 0.11).

[0061] Among them, Gray is the pixel value after gray conversion, Red is the red color value, Green is the green color value, and Blue is the blue color value. Figure 4 Part (a) in it is the topography image obtained by TM-AFM scanning the cell, Figure 4 Part (b) in it is the amplitude image obtained by TM-AFM scanning the cell, Figure 4 Part (c) in it is the corresponding topography gray image of part (a), Figure 4 Part (d) in it is the corresponding amplitude gray image of part (b).

[0062] Among them, step 103 specifically includes: using a 6-layer Laplacian pyramid image fusion algorithm to perform image fusion on the topography gray image and the amplitude gray image to obtain a fused image. The fused image is as Figure 4 shown in part (e).

[0063] Among them, step 104 specifically includes: forming a first pixel value set from the pixel values of each pixel point in the non-noise region of the topography gray image, and forming a second pixel value set from the pixel values of the corresponding pixel points in the fused image. The pixel points in the first pixel value set and the pixel points in the second pixel value set correspond one by one.

[0064] According to the first pixel value set and the second pixel value set, a 5th-order polynomial regression model is used as the mapping relational expression for relationship fitting to obtain the mapping relational expression between the pixel values in the topography gray image and the pixel values in the fused image.

[0065] The 5th-order polynomial regression model is expressed as: y = a0 + a1x + a2x 2 + a3x 3 + a4x4 + a5x 5 + ε。

[0066] Wherein, y represents the pixel value of a pixel point in the morphological grayscale image, x represents the pixel value of a pixel point in the fused image, ε is a random error, and a i is the i-th regression coefficient, where i ∈ [0, 1, 2, 3, 4, 5].

[0067] Wherein, based on the first pixel value set and the second pixel value set, a 5th-degree polynomial regression model is used as a mapping relational expression for relationship fitting to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image, specifically including:[[]]

[0068] Based on the first pixel value set and the second pixel value set, the least squares method is used to perform model fitting on the 5th-degree polynomial regression model to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image. More specifically, the 5th-degree polynomial regression model is rewritten into a matrix form model, and the matrix form model is: Y = aX + ε.[[]]

[0069] Wherein, Y = [y1, y2,..., y N [[]] T , a = [a0, a1,..., a N [[]] T , X is a design matrix composed of the variable x and the powers of the variable x. The first column of the design matrix is all 1, the second column is x1, x2,..., x N , the third column is and so on until the sixth column Y is a dependent variable vector, a is a coefficient vector, y n is the pixel value of the n-th pixel sampling point in the morphological grayscale image, x n is the pixel value of the n-th pixel sampling point in the fused image, where 1 ≤ n ≤ N, and N is the number of pixel sampling points.[[]]

[0070] Based on the first pixel value set and the second pixel value set, the least squares method is used to perform model fitting on the matrix form model to obtain the mapping relational expression between the pixel value in the morphological grayscale image and the pixel value in the fused image.[[]]

[0071] The purpose of simulation fitting is to find a set of regression coefficients to minimize the sum of squared residuals where is the predicted value. According to mathematical derivation, the optimal solution is the vector composed of each regression coefficient.[[]]

[0072] According to the optimal solution the mapping relationship formula for determining the pixel values of the fused grayscale image and the morphological grayscale image can be obtained as in is the estimated value of the regression coefficient of the optimal solution obtained from the previous calculation.

[0073] In an exemplary embodiment, y = 75.67 + 3.28x - 3.56x 2 + 0.043x 3 - 3.47×10 -3 x 4 + 4.52×10 -4 x 5 .

[0074] Wherein, step 105 specifically includes: according to the grayscale conversion formula, performing grayscale inverse conversion on the denoised morphological grayscale image to obtain a denoised color morphological image. The denoised morphological grayscale image is as shown in part (f) of Figure 4 and the denoised color morphological image is as shown in part (g) of Figure 4 .

[0075] The cell surface is soft. When using a TM-AFM probe to scan and image the cell, the amplitude set between the probe and the cell should be as small as possible. In the central region of the cell, when the vertical height drop is large, the piezoelectric platform on which the cell is placed cannot quickly achieve real-time adjustment, and the probe may come into contact with the cell surface, resulting in scanning noise in the cell morphological image. This application can effectively solve the problem of noise caused by excessive gradient changes in the central region of the cell when using a TM-AFM probe to scan and image the morphology of biological cells, and effectively compensates for the noise error generated by the current TM-AFM probe scanning cell imaging method.

[0076] In addition, before each image denoising, this application also performs grayscale transformation on the morphological image and the amplitude image using the same formula, so that the pixel mapping of the subsequent morphological image and amplitude image and the conversion of the fused image into the morphological image are carried out according to a unified standard, improving the effect of image denoising and ensuring the accuracy of converting the fused image into the morphological image.

[0077] Based on the same inventive concept, the embodiment of this application also provides a cell morphological image denoising device for implementing the cell morphological image denoising method involved above. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the cell morphological image denoising device provided below can refer to the limitations on the cell morphological image denoising method in the above text, and will not be repeated here.

[0078] In an exemplary embodiment, this application provides a cell morphological image denoising device including:

[0079] An image acquisition module, configured to obtain a topography image and an amplitude image generated by scanning a probe of a tapping mode atomic force microscope for a target cell.

[0080] A grayscale conversion module, configured to perform grayscale conversion on the topography image and the amplitude image respectively to obtain a topography grayscale image and an amplitude grayscale image.

[0081] An image fusion module, configured to perform image fusion on the topography grayscale image and the amplitude grayscale image to obtain a fused image.

[0082] A mapping relation formula determination module, configured to perform non-linear relation fitting on pixel values of each pixel point in a non-noise area of the topography grayscale image and pixel values of corresponding pixel points in the fused image to obtain a mapping relation formula between pixel values in the topography grayscale image and pixel values in the fused image; the non-noise area is an area outside the cell nucleus.

[0083] A denoised topography grayscale image determination module, configured to map pixel values of each pixel point in the fused image by using the mapping relation formula to obtain a denoised topography grayscale image.

[0084] A denoised color topography image determination module, configured to perform inverse grayscale conversion on the denoised topography grayscale image to obtain a denoised color topography image.

[0085] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal, and its internal structure diagram may be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store cell topography map noise reduction data. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for reducing noise in a cell topography map.

[0086] Those skilled in the art can understand, Figure 5The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0087] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0088] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0089] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0090] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0091] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, data processing logics of programmable logics, etc., without limitation.

[0092] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, 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, it should be considered to be within the scope described in this specification.

[0093] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for denoising a cell morphology map, characterized in that, The method for denoising the cell morphology image includes: Obtaining a morphology image and an amplitude image generated by scanning a probe of a tapping-mode atomic force microscope for a target cell; Performing gray-scale conversion on the morphology image and the amplitude image respectively to obtain a morphology gray-scale image and an amplitude gray-scale image; Performing image fusion on the morphology gray-scale image and the amplitude gray-scale image to obtain a fused image; Performing non-linear relationship fitting on the pixel values of each pixel point in the non-noise region of the morphology gray-scale image and the pixel values of the corresponding pixel points in the fused image to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image; the non-noise region is the region outside the cell nucleus; Mapping the pixel values of each pixel point in the fused image by using the mapping relationship formula to obtain a denoised morphology gray-scale image; Performing inverse gray-scale conversion on the denoised morphology gray-scale image to obtain a denoised color morphology image.

2. The method for reducing noise in a cell morphology map according to claim 1, wherein The gray-scale conversion formula for performing gray-scale conversion on the morphology image and the amplitude image respectively is expressed as: Gray = (Red * 0.3 + Green * 0.59 + Blue * 0.11); where Gray is the pixel value after gray-scale conversion, Red is the red color value, Green is the green color value, and Blue is the blue color value.

3. The method for reducing noise in a cell morphology map according to claim 1, characterized in that, Performing image fusion on the morphology gray-scale image and the amplitude gray-scale image to obtain a fused image, specifically including: Performing image fusion on the morphology gray-scale image and the amplitude gray-scale image by using the Laplacian pyramid image fusion algorithm to obtain a fused image.

4. The cell morphology map noise reduction method according to claim 1, wherein Performing non-linear relationship fitting on the pixel values of each pixel point in the non-noise region of the morphology gray-scale image and the pixel values of the corresponding pixel points in the fused image to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image, specifically including: Constituting a first pixel value set from the pixel values of each pixel point in the non-noise region of the morphology gray-scale image, and constituting a second pixel value set from the pixel values of the corresponding pixel points in the fused image; According to the first pixel value set and the second pixel value set, using a fifth-degree polynomial regression model as the mapping relationship formula for relationship fitting to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image; The 5th-degree polynomial regression model is expressed as: y = a0 + a1x + a2x 2 + a3x 3 + a4x 4 + a5x 5 + ε; where y represents the pixel value of a pixel point in the morphology grayscale image, x represents the pixel value of a pixel point in the fusion image, ε is a random error, and a i is the i-th regression coefficient, where i ∈ [0, 1, 2, 3, 4, 5].

5. The method for reducing noise in a cell morphology map according to claim 4, wherein According to the first pixel value set and the second pixel value set, using a fifth-degree polynomial regression model as the mapping relationship formula for relationship fitting to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image, specifically including: According to the first pixel value set and the second pixel value set, using the least squares method to perform model fitting on the fifth-degree polynomial regression model to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image.

6. The method for reducing noise in a cell morphology map according to claim 5, wherein, According to the first pixel value set and the second pixel value set, using the least squares method to perform model fitting on the fifth-degree polynomial regression model to obtain a mapping relationship formula between the pixel values in the morphology gray-scale image and the pixel values in the fused image, specifically including: Rewrite the 5th-degree polynomial regression model into a matrix form model, where the matrix form model is: Y = aX + ε; where Y = [y1, y2,..., y N T , a = [a0, a1,..., a N T , X is a design matrix composed of the variable x and the powers of the variable x, Y is a dependent variable vector, a is a coefficient vector, y n is the pixel value of the nth pixel sampling point in the morphological grayscale image, x n is the pixel value of the nth pixel sampling point in the fused image, 1 ≤ n ≤ N, and N is the number of pixel sampling points;​​ According to the first pixel value set and the second pixel value set, use the least squares method to perform model fitting on the matrix form model to obtain the mapping relationship formula between the pixel values in the morphological gray-scale image and the pixel values in the fused image.

7. A cell morphology map noise reduction device, characterized in that, The cell morphological map noise reduction device applies the cell morphological map noise reduction method described in any one of claims 1-6. The cell morphological map noise reduction device includes: An image acquisition module for acquiring a morphological image and an amplitude image generated by scanning a probe of a tapping mode atomic force microscope on a target cell; A gray-scale conversion module for respectively performing gray-scale conversion on the morphological image and the amplitude image to obtain a morphological gray-scale image and an amplitude gray-scale image; An image fusion module for performing image fusion on the morphological gray-scale image and the amplitude gray-scale image to obtain a fused image; A mapping relationship formula determination module for performing non-linear relationship fitting on the pixel values of each pixel point in the non-noise area of the morphological gray-scale image and the pixel values of the corresponding pixel points in the fused image to obtain the mapping relationship formula between the pixel values in the morphological gray-scale image and the pixel values in the fused image; the non-noise area is the area outside the cell nucleus; A denoised morphological gray-scale image determination module for mapping the pixel values of each pixel point in the fused image using the mapping relationship formula to obtain a denoised morphological gray-scale image; A denoised color morphological image determination module for performing inverse gray-scale conversion on the denoised morphological gray-scale image to obtain a denoised color morphological image.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the cell morphological map noise reduction method described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the cell morphological map noise reduction method described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the cell morphological map noise reduction method described in any one of claims 1-6.

Images