A method, apparatus, equipment, medium, and product for denoising cell morphology images.

Abstract

This application discloses a method, apparatus, device, medium, and product for denoising cell morphology images, relating to the field of image processing technology. The method includes: acquiring a morphology image and an amplitude image of a target cell generated by probe scanning using a tapping mode atomic force microscope; performing grayscale conversion on the morphology image and the amplitude image respectively; fusing the morphology grayscale image and the amplitude grayscale image to obtain a fused image; performing nonlinear relationship fitting between the pixel values ​​of each pixel in the non-noise region of the morphology grayscale image and the corresponding pixel values ​​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; mapping the pixel values ​​of each pixel in the fused image using the mapping relationship to obtain a denoised morphology grayscale image; and performing inverse grayscale conversion on the denoised morphology grayscale image to obtain a denoised color morphology image. This application can reduce noise in cell morphology images.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a method, apparatus, device, medium and product for denoising cell morphology images. Background Technology

[0002] Cells are the basic building blocks of living organisms. Understanding cell morphology and measuring their physical properties to differentiate and analyze cell function is an important topic in scientific research. Tapping-mode atomic force microscopy (TM-AFM) probe scanning imaging offers high resolution and minimal sample damage, making it the most ideal type of atomic force microscope for cell imaging.

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

[0004] Currently, morphology images obtained from TM-AFM probe scans often exhibit scanning noise. This typically requires operators with extensive experience in cell scanning and the ability to adjust TM-AFM probe scan parameters. These operators rely on their personal experience to adjust the scanning parameters and reduce the noise in the cell morphology images. However, this noise reduction method is limited by the operator's skill in tapping atomic forces and only has a certain noise reduction effect on cell morphology images when the cell gradient variation range is small. Finding a suitable noise reduction method to effectively reduce scanning noise in TM-AFM probe scans of cells remains an obstacle to the application of TM-AFM in cell imaging. Summary of the Invention

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

[0006] To achieve the above objectives, this application provides the following solution:

[0007] Firstly, this application provides a method for denoising cell morphology images, including:

[0008] Obtain morphological and amplitude images of target cells using probe scanning in tapping mode atomic force microscopy;

[0009] The morphology image and the amplitude image are converted to grayscale to obtain a grayscale image of the morphology and a grayscale image of the amplitude.

[0010] The grayscale image of the morphology and the grayscale image of the amplitude are fused to obtain a fused image;

[0011] The pixel values ​​of each pixel in the non-noise region of the grayscale image are fitted with the corresponding pixel values ​​in the fused image using a non-linear relationship to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image; the non-noise region is the region outside the cell nucleus;

[0012] The pixel values ​​of each pixel in the fused image are mapped using the mapping formula to obtain a denoised grayscale image of the morphology.

[0013] The denoised grayscale image is subjected to inverse grayscale conversion to obtain a denoised color image.

[0014] Optionally, the grayscale conversion formulas for converting the morphology image and the amplitude image to grayscale are expressed as follows:

[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, the morphology grayscale image and the amplitude grayscale image are fused to obtain a fused image, specifically including:

[0018] The Laplacian pyramid image fusion algorithm is used to fuse the shape grayscale image and the amplitude grayscale image to obtain a fused image.

[0019] Optionally, a non-linear relationship is fitted between the pixel values ​​of each pixel in the non-noise region of the grayscale image and the corresponding pixel values ​​in the fused image to obtain a mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image, specifically including:

[0020] The first set of pixel values ​​is formed by the pixel values ​​of each pixel in the non-noise region of the grayscale image, and the second set of pixel values ​​is formed by the pixel values ​​of the corresponding pixels in the fused image.

[0021] Based on the first set of pixel values ​​and the second set of pixel values, a 5-level polynomial regression model is used as the mapping relationship to fit the relationship, thereby obtaining the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

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

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

[0024] Optionally, based on the first set of pixel values ​​and the second set of pixel values, a 5-level polynomial regression model is used as the mapping expression to fit the relationship, thereby obtaining the mapping expression between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image, specifically including:

[0025] Based on the first set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the 5-level polynomial regression model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

[0026] Optionally, based on the first set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the 5th-level polynomial regression model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image, specifically including:

[0027] The 5th-level polynomial regression model is rewritten as a matrix form model, which is: Y = aX + ε;

[0028] Where Y = [y1, y2, ..., y N ] T a = [a0, a1, ..., a N ] T X is a design matrix consisting of variables x and their powers, Y is the dependent variable vector, a is the coefficient vector, and y is the design matrix consisting of variables x and their powers. n x is the pixel value of the nth pixel sampling point in the grayscale image of the shape. n Let N be the pixel value of the nth pixel sampling point in the fused image, where 1 ≤ n ≤ N, and N is the number of pixel sampling points.

[0029] Based on the first set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the matrix-form model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

[0030] Secondly, this application provides a cell morphology image denoising device, which applies the aforementioned cell morphology image denoising method, and the cell morphology image denoising device includes:

[0031] The image acquisition module is used to acquire morphological and amplitude images of target cells generated by probe scanning in tapping mode atomic force microscopy.

[0032] A grayscale conversion module is used 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] The image fusion module is used to fuse the shape grayscale image and the amplitude grayscale image to obtain a fused image;

[0034] The mapping relationship determination module is used to perform nonlinear relationship fitting between the pixel values ​​of each pixel in the non-noise region of the grayscale image and the pixel values ​​of the corresponding pixel in the fused image to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image; the non-noise region is the region outside the cell nucleus;

[0035] The denoised grayscale image determination module is used to map the pixel values ​​of each pixel in the fused image using the mapping relationship to obtain the denoised grayscale image.

[0036] The denoised color morphology image determination module is used to perform inverse grayscale conversion on the denoised morphology grayscale image to obtain the denoised color morphology image.

[0037] Thirdly, 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 steps of the cell morphology image noise reduction method described in any one of the above.

[0038] Fourthly, this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cell morphology image denoising method described above.

[0039] Fifthly, this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the cell morphology image denoising method described above.

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

[0041] This application provides a method, apparatus, device, medium, and product for denoising cell morphology images. The method involves converting and fusing cell morphology and amplitude images to grayscale. A non-linear relationship is then fitted between the pixel values ​​of each pixel in the non-noise region of the morphology grayscale image and the corresponding pixel values ​​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. This mapping relationship is used to compensate for noise generated by TM-AFM probe scanning cell imaging, effectively reducing cell morphology noise caused by large cell surface height gradients. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments 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.

[0043] Figure 1 This is a schematic flowchart of a cell morphology image noise reduction method provided in an embodiment of this application.

[0044] Figure 2 This is a schematic diagram illustrating the principle of a cell morphology image noise reduction method provided in an embodiment of this application.

[0045] Figure 3 This is a schematic diagram illustrating the principle of TM-AFM probe scanning imaging, provided in one embodiment of this application.

[0046] Figure 4 This is a schematic diagram of a cell image in an image denoising process provided in an embodiment of this application.

[0047] Figure 5 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application.

[0048] Figure labels: 1-Photodetector, 2-Laser, 3-Scanning probe, 4-Cell, 5-Substrate, 6-Piezoelectric ceramic. Detailed Implementation

[0049] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0050] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0051] This application provides a method for denoising cell morphology images, such as... Figure 1 and Figure 2 As shown, the cell morphology image noise reduction method includes:

[0052] Step 101: Obtain morphological and amplitude images of the target cells using probe scanning in tapping mode atomic force microscopy.

[0053] Step 102: Perform grayscale conversion on the morphology image and the amplitude image respectively to obtain a grayscale image of the morphology and a grayscale image of the amplitude.

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

[0055] Step 104: Perform nonlinear relationship fitting between the pixel values ​​of each pixel in the non-noise region of the grayscale image and the corresponding pixel values ​​in the fused image to obtain the mapping relationship between the pixel values ​​in the grayscale 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 in the fused image using the mapping formula to obtain a denoised grayscale image of the shape.

[0057] Step 106: Perform inverse grayscale conversion on the denoised grayscale image to obtain a denoised color image.

[0058] This application leverages the high correlation between amplitude and morphology images of cells scanned using TM-AFM. It preprocesses both the morphology and amplitude images separately, then fuses them to obtain a denoised fused cell image. By numerically fitting the pixel values ​​of multiple noise-free pixels in the morphology image to the corresponding pixel values ​​in the fused cell image, a formula is derived to establish the correspondence between pixel values ​​in the fused cell image and those in the morphology image. This formula allows the fused cell image to be reconstructed into a denoised cell morphology image. The denoised image retains the basic height information of the morphology image while replacing the image data in noisy areas with image data from the fused cell image, effectively reducing noise in the morphology image. This application can reduce morphology noise in TM-AFM cell scanning imaging, thereby improving the quality of TM-AFM cell morphology imaging.

[0059] In one exemplary embodiment, the atomic force microscopy (AFM) system used for tapping mode cell scanning imaging is a laboratory NanoWizard 3 BioScience AFM system, and the scanning probe used is a TAP300AL-G tapping scanning probe. The principle of atomic force probe measurement is as follows: Figure 3 As shown, laser 2 emits laser light, which is focused onto the tip surface of scanning probe 3 and then reflected to photodetector 1 to detect the tip amplitude and phase of scanning probe 3. The morphology of cell sample 4 on substrate 5 can be accurately measured by the change in tip amplitude of scanning probe 3. Piezoelectric ceramic 6 is used in substrate 5.

[0060] In step 102, the grayscale conversion formula for converting the morphology image and the amplitude image to grayscale is expressed as: Gray = (Red * 0.3 + Green * 0.59 + Blue * 0.11).

[0061] 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. Figure 4 Part (a) shows the morphological images of cells obtained by TM-AFM scanning. Figure 4 Part (b) shows the amplitude image obtained from TM-AFM scanning of cells. Figure 4 Part (c) is the grayscale image of the morphology corresponding to part (a). Figure 4 Part (d) is the amplitude grayscale image corresponding to part (b).

[0062] Specifically, step 103 includes: using a 6-layer Laplacian pyramid image fusion algorithm to fuse the shape grayscale image and the amplitude grayscale image to obtain a fused image. The fused image is shown below. Figure 4 As shown in section (e).

[0063] Specifically, step 104 includes: forming a first pixel value set from the pixel values ​​of each pixel in the non-noise region of the grayscale image, and forming a second pixel value set from the pixel values ​​of corresponding pixels in the fused image. The pixels in the first pixel value set correspond one-to-one with the pixels in the second pixel value set.

[0064] Based on the first set of pixel values ​​and the second set of pixel values, a 5-level polynomial regression model is used as the mapping relationship to fit the relationship, thereby obtaining the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

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

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

[0067] Specifically, based on the first pixel value set and the second pixel value set, a 5-level polynomial regression model is used as the mapping relationship formula to fit the relationship, thereby obtaining the mapping relationship formula between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image, including:

[0068] Based on the first set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the 5-level polynomial regression model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image. More specifically, the 5-level polynomial regression model is rewritten as a matrix model, which is: Y = aX + ε.

[0069] Where Y = [y1, y2, ..., y N ] T a = [a0, a1, ..., a N ] T X is a design matrix consisting of variables x and their powers. The first column of the design matrix is ​​all 1s, and the second column contains x1, x2, ..., x. N The third column is And so on until the sixth column. Y is the dependent variable vector, a is the coefficient vector, and y n x is the pixel value of the nth pixel sampling point in the grayscale image of the shape. n Let be the pixel value of the nth 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 set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the matrix-form model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

[0071] The goal of simulation fitting is to find a set of regression coefficients that result in a sum of squared residuals. Minimum, of which This is a predicted value. Based on mathematical derivation, the optimal solution... This is a vector composed of the regression coefficients.

[0072] According to the optimal solution The mapping relationship between the pixel values ​​of the fused grayscale image and the morphology grayscale image can then be determined as follows: Inside These are the estimated regression coefficients of the optimal solution obtained from the previous calculations.

[0073] In one 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] Step 105 specifically includes: performing an inverse grayscale conversion on the denoised grayscale image of the morphology according to the grayscale conversion formula to obtain a denoised color morphology image. The denoised grayscale image of the morphology is shown below. Figure 4 As shown in section (f), the denoised color topography image is as follows: Figure 4 As shown in section (g).

[0075] Cell surfaces are soft, and when using TM-AFM probes for cell scanning imaging, the amplitude between the probe and the cell should be as small as possible. In the central region of the cell, where there is a significant vertical drop, the piezoelectric platform for placing the cell cannot be quickly adjusted in real time, and the probe may come into contact with the cell surface, resulting in scanning noise in the cell morphology image. This application effectively solves the noise problem caused by excessive gradient changes in the central region of the cell when using TM-AFM probes for scanning cell morphology imaging, effectively compensating for the noise errors generated by current TM-AFM probe cell scanning imaging methods.

[0076] In addition, before each image denoising process, this application performs grayscale transformation on the topography image and amplitude image using the same formula. This ensures a unified standard for subsequent pixel mapping and fusion image conversion of the topography image and amplitude image, thereby improving the denoising effect and ensuring the accuracy of the fusion image conversion into a topography image.

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

[0078] In one exemplary embodiment, this application provides a cell morphology image noise reduction device comprising:

[0079] The image acquisition module is used to acquire morphological and amplitude images of target cells generated by probe scanning in tapping mode atomic force microscopy.

[0080] The grayscale conversion module is used to perform grayscale conversion on the morphology image and the amplitude image respectively to obtain a morphology grayscale image and an amplitude grayscale image.

[0081] The image fusion module is used to fuse the shape grayscale image and the amplitude grayscale image to obtain a fused image.

[0082] The mapping relationship determination module is used to perform nonlinear relationship fitting between the pixel values ​​of each pixel in the non-noise region of the grayscale image and the pixel values ​​of the corresponding pixel in the fused image to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image; the non-noise region is the region outside the cell nucleus.

[0083] The denoised grayscale image determination module is used to map the pixel values ​​of each pixel in the fused image using the mapping relationship to obtain the denoised grayscale image.

[0084] The denoised color morphology image determination module is used to perform inverse grayscale conversion on the denoised morphology grayscale image to obtain the denoised color morphology image.

[0085] In one exemplary embodiment, a computer device is provided, which may be a server or a terminal, and its internal structure diagram may be as follows. Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores cell morphology image denoising data. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When the computer program is executed by the processor, it implements a cell morphology image denoising method.

[0086] Those skilled in the art will understand that Figure 5The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In an exemplary embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps in the above-described method embodiments.

[0087] In one exemplary embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[0088] In one exemplary embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above-described method embodiments.

[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 used for analysis, data stored, data displayed, 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 the relevant data must comply with relevant regulations.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM).

[0091] The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic units, data processing logic units, etc., and are not limited to these.

[0092] The technical features of the above embodiments can be combined in any way. For the sake of brevity, 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.

[0093] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for denoising cell morphology images, characterized in that, The cell morphology image noise reduction method includes: Obtain morphological and amplitude images of target cells using probe scanning in tapping mode atomic force microscopy; The morphology image and the amplitude image are converted to grayscale to obtain a grayscale image of the morphology and a grayscale image of the amplitude. The grayscale image of the morphology and the grayscale image of the amplitude are fused to obtain a fused image; The pixel values ​​of each pixel in the non-noise region of the grayscale image are fitted with the corresponding pixel values ​​in the fused image using a non-linear relationship to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image; the non-noise region is the region outside the cell nucleus; The pixel values ​​of each pixel in the fused image are mapped using the mapping formula to obtain a denoised grayscale image of the morphology. The denoised grayscale image is subjected to inverse grayscale conversion to obtain a denoised color image.

2. The cell morphology image noise reduction method according to claim 1, characterized in that, The grayscale conversion formulas for performing grayscale conversions on the morphology image and the amplitude image respectively are expressed as follows: Gray=(Red*0.3+Green*0.59+Blue*0.11); 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.

3. The cell morphology image noise reduction method according to claim 1, characterized in that, The morphology grayscale image and the amplitude grayscale image are fused to obtain a fused image, specifically including: The Laplacian pyramid image fusion algorithm is used to fuse the shape grayscale image and the amplitude grayscale image to obtain a fused image.

4. The cell morphology image noise reduction method according to claim 1, characterized in that, The pixel values ​​of each pixel in the non-noise region of the grayscale image are nonlinearly fitted with the pixel values ​​of the corresponding pixels in the fused image to obtain a mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image. Specifically, this includes: The first set of pixel values ​​is formed by the pixel values ​​of each pixel in the non-noise region of the grayscale image, and the second set of pixel values ​​is formed by the pixel values ​​of the corresponding pixels in the fused image. Based on the first set of pixel values ​​and the second set of pixel values, a 5-level polynomial regression model is used as the mapping relationship to fit the relationship, thereby obtaining the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image. The 5th-level 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 in the grayscale image of the shape, x represents the pixel value of a pixel in the fused image, ε is the random error, and a i Let be the i-th regression coefficient, where i∈[0,1,2,3,4,5].

5. The cell morphology image noise reduction method according to claim 4, characterized in that, Based on the first pixel value set and the second pixel value set, a 5-level polynomial regression model is used as the mapping relationship to fit the relationship, thereby obtaining the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image, specifically including: Based on the first set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the 5-level polynomial regression model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

6. The cell morphology image noise reduction method according to claim 5, characterized in that, Based on the first pixel value set and the second pixel value set, the least squares method is used to fit the 5-level polynomial regression model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image, specifically including: The 5th-level polynomial regression model is rewritten as a matrix form model, which is: Y = aX + ε; Where Y = [y1, y2, ..., y N ] T a = [a0, a1, ..., a N ] T X is a design matrix consisting of variables x and their powers, Y is the dependent variable vector, a is the coefficient vector, and y is the design matrix consisting of variables x and their powers. n x is the pixel value of the nth pixel sampling point in the grayscale image of the shape. n Let N be the pixel value of the nth pixel sampling point in the fused image, where 1 ≤ n ≤ N, and N is the number of pixel sampling points. Based on the first set of pixel values ​​and the second set of pixel values, the least squares method is used to fit the matrix-form model to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image.

7. A cell morphology image noise reduction device, characterized in that, The cell morphology image denoising device applies the cell morphology image denoising method according to any one of claims 1-6, and the cell morphology image denoising device comprises: The image acquisition module is used to acquire morphological and amplitude images of target cells generated by probe scanning in tapping mode atomic force microscopy. A grayscale conversion module is used to perform grayscale conversion on the morphology image and the amplitude image respectively to obtain a morphology grayscale image and an amplitude grayscale image; The image fusion module is used to fuse the shape grayscale image and the amplitude grayscale image to obtain a fused image; The mapping relationship determination module is used to perform nonlinear relationship fitting between the pixel values ​​of each pixel in the non-noise region of the grayscale image and the pixel values ​​of the corresponding pixel in the fused image to obtain the mapping relationship between the pixel values ​​in the grayscale image and the pixel values ​​in the fused image; the non-noise region is the region outside the cell nucleus; The denoised grayscale image determination module is used to map the pixel values ​​of each pixel in the fused image using the mapping relationship to obtain the denoised grayscale image. The denoised color morphology image determination module is used to perform inverse grayscale conversion on the denoised morphology grayscale image to obtain the denoised color morphology image.

8. A computer device, comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor executes the computer program to implement the cell morphology image noise reduction method according to 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 morphology image noise reduction method according to 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 morphology image noise reduction method according to any one of claims 1-6.

Images