Cell image fusion method and device, computer equipment and storage medium

Abstract

The invention relates to a cell image fusion method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the gray conversion of N cell images shot in the same visual field, and obtaining a gray-scale map g; denoising each grey-scale map g to obtain a grey-scale map g2; subtracting the gray-scale map g from the corresponding gray-scale map g2 pixel by pixel and taking an absolute value to obtain an edge map gd; using a fast guiding filtering algorithm, taking the grey-scale map g2 as an input image, taking the corresponding edge map gd as a guiding image, and carrying out smoothing processing on the grey-scale map g2 to obtain a grey-scale map g3; pixel point-by-pixel comparison is carried out on the N grey-scale maps g3, the maximum value of each pixel point is taken, and an image max is obtained; subtracting the image max from each grey-scale map g3 pixel by pixel to obtain an area where a pixel point with a corresponding result of each grey-scale map g3 is located as an alternative area, wherein the result of the pixel point is less than or equal to 0; and the regions corresponding to the corresponding alternative regions in the cell image are merged to obtain a fused image, so that the cell morphology detection efficiency is effectively improved.

Description

Technical Field

[0001] The present application relates to the field of computer processing technology, and in particular to a cell image fusion method, device, computer equipment and storage medium. Background Art

[0002] Cell morphology examination is one of the key diagnostic methods in pathology and is often used to diagnose a variety of diseases, including leukemia, multiple myeloma, lymphoma, anemia, and pancytopenia. Traditional cell morphology examination is performed by doctors observing cell tissue slides under a microscope to obtain the morphology and number of each cell on the cell tissue as a basis for diagnosis. However, with the development of computer technology, intelligent cell morphology examination processes have replaced the traditional manual microscopic examination process. In the process of intelligent cell morphology examination, a scanning platform is required to automatically scan the cell tissue slides to obtain cell images. However, due to the incomplete leveling of the scanning platform, uneven thickness of the cell tissue, or impurities on the cell tissue slide, it is easy for the captured cell image to not have all the cells in the entire image in a clear state, which affects the efficiency of cell morphology examination.

[0003] In the prior art, during the automated photographing of cell tissue slides, it is easy for the captured cell images to not contain all cells in a clear state, which affects the efficiency of cell morphology testing. Currently, no effective solution has been proposed. Summary of the invention

[0004] Based on this, it is necessary to provide a cell image fusion method, device, computer equipment and storage medium to address the above technical problems, so as to solve the problem that in the process of automated shooting of cell tissue slides in related technologies, the captured cell images do not have all cells in the entire image in a clear state, thereby affecting the efficiency of cell morphology inspection.

[0005] In a first aspect, an embodiment of the present application provides a cell image fusion method, the method comprising the following steps:

[0006] Performing grayscale conversion on N cell images captured in the same field of view to obtain a grayscale image g corresponding to each of the cell images; wherein N is an integer greater than or equal to 2;

[0007] Denoising each of the grayscale images g respectively to obtain N grayscale images g2;

[0008] Subtract the grayscale image g from the corresponding grayscale image g2 pixel by pixel and take the absolute value to obtain N edge images gd;

[0009] Using a fast guided filtering algorithm, taking the grayscale image g2 as an input image and the corresponding edge image gd as a guide image, the grayscale image g2 is smoothed while retaining edge information to obtain N grayscale images g3;

[0010] Compare the N grayscale images g3 pixel by pixel, take the maximum value of each pixel, and obtain the image max;

[0011] Subtract the image max from each of the grayscale images g3 pixel by pixel, and obtain the area where the pixel points whose corresponding results of each of the grayscale images g3 are less than or equal to 0 are located as the candidate area;

[0012] The regions in each of the cell images corresponding to the candidate regions are merged to obtain a fused image.

[0013] In some embodiments, merging the regions in each of the cell images corresponding to the candidate regions to obtain a fused image comprises the following steps:

[0014] For each of the grayscale images g3, assign a value of 255 to the pixels in the candidate area and a value of 0 to the pixels in the remaining areas, so as to obtain a binary image mask corresponding to each of the grayscale images g3;

[0015] Performing fuzzy processing on the binary image mask to obtain an image mask2 corresponding to each grayscale image g3;

[0016] Perform channel separation on each of the cell images, and obtain a red channel image r, a green channel image g, and a blue channel image b corresponding to each of the cell images;

[0017] Multiply the red channel image r, the green channel image g and the blue channel image b by the corresponding image mask2 pixel by pixel to obtain a red channel image r1, a green channel image g1 and a blue channel image b1 corresponding to each of the cell images;

[0018] Add all the red channel images r1 pixel by pixel to obtain a red channel image r2, add all the green channel images g1 pixel by pixel to obtain a green channel image g2, and add all the blue channel images b1 pixel by pixel to obtain a blue channel image b2;

[0019] The red channel image r2, the green channel image g2 and the blue channel image b2 are channel-merged to obtain a fused image.

[0020] In a second aspect, the present application further provides a cell image fusion device, the device comprising a conversion module, a denoising module, an edge map module, a filtering module, a value taking module, an alternative module and a merging module;

[0021] The conversion module is used to perform grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each of the cell images; wherein N is an integer greater than or equal to 2;

[0022] The denoising module is used to denoise each of the grayscale images g respectively to obtain N grayscale images g2;

[0023] The edge map module is used to subtract the grayscale map g from the corresponding grayscale map g2 pixel by pixel and take the absolute value to obtain N edge maps gd;

[0024] The filtering module is used to use a fast guided filtering algorithm to take the grayscale image g2 as an input image and the corresponding edge image gd as a guide image, and to smooth the grayscale image g2 while retaining edge information to obtain N grayscale images g3;

[0025] The value taking module is used to compare the N grayscale images g3 pixel by pixel, take the maximum value of each pixel, and obtain the image max;

[0026] The candidate module is used to subtract the image max from each of the grayscale images g3 pixel by pixel, and obtain the area where the pixel points whose corresponding results of each of the grayscale images g3 are less than or equal to 0 are located as the candidate area;

[0027] The merging module is used to merge the regions in each of the cell images corresponding to the candidate regions to obtain a fused image.

[0028] In a third aspect, a computer device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the method described in the first aspect when executing the computer program.

[0029] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0030] The above-mentioned cell image fusion method, device, computer equipment and storage medium perform grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2; perform denoising on each grayscale image g to obtain N grayscale images g2; subtract the grayscale image g from the corresponding grayscale image g2 pixel by pixel and take the absolute value to obtain N edge images gd; use a fast guided filtering algorithm to take the grayscale image g2 as the input image and the corresponding edge image gd as the guide image, and smooth the grayscale image g2 while retaining the edge information to obtain N grayscale images g3; perform pixel-by-pixel comparison on the N grayscale images g3, take the maximum value of each pixel to obtain image max; subtract image max from each grayscale image g3 pixel by pixel to obtain the area where the pixel corresponding to each grayscale image g3 is less than or equal to 0, as the candidate area; merge the area corresponding to the corresponding candidate area in each cell image to obtain a fused image. The present application extracts relatively clear areas of each image from N cell images taken in the same field of view, and merges all relatively clear areas of each image into the same image, thereby obtaining an image that contains the clearest areas of all cell images for subsequent cell morphology detection, thereby effectively improving the efficiency of cell morphology detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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:

[0032] Figure 1 This is an application scenario diagram of the cell image fusion method provided in an embodiment of the present application;

[0033] Figure 2 is a flow chart of a cell image fusion method provided according to an embodiment of the present application;

[0034] Figure 3 and Figure 4 is a schematic diagram of cell images captured in the same field of view in the cell image fusion method provided in an embodiment of the present application;

[0035] Figure 5 is a schematic diagram of an edge map in a cell image fusion method provided in an embodiment of the present application;

[0036] Figure 6 is a schematic diagram of image max in the cell image fusion method provided in an embodiment of the present application;

[0037] Figure 7 is a schematic diagram of a fused image in a cell image fusion method provided in an embodiment of the present application;

[0038] Figure 8 A schematic diagram of the structure of a cell image fusion device provided in an embodiment of the present application;

[0039] Fig. 9 A schematic diagram of the structure of a computer device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not intended to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0041] Obviously, the drawings described below are only some examples or embodiments of the present application. For ordinary technicians in this field, the present application can also be applied to other similar scenarios based on these drawings without creative work. In addition, it can also be understood that although the efforts made in this development process may be complicated and lengthy, for ordinary technicians in this field related to the content disclosed in this application, some changes in design, manufacturing or production based on the technical content disclosed in this application are just conventional technical means, and should not be understood as insufficient content disclosed in this application.

[0042] Reference to "embodiments" in this application means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0043] Unless otherwise defined, the technical terms or scientific terms involved in this application should be understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the" and the like involved in this application do not indicate a quantity limitation and may indicate the singular or plural. The terms "include", "comprise", "have" and any of their variations involved in this application are intended to cover non-exclusive inclusions; for example, a process, method, system, product or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units that are not listed, or may also include other steps or units inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there may be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the objects before and after are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0044] Figure 1 This is an application scenario diagram of the cell image fusion method provided by one embodiment of the present application. Figure 1As shown, data can be transmitted between the server 101 and the mobile terminal 102 through the network. The mobile terminal 102 is used to collect cell images and transmit the collected cell images to the server 101. After receiving N cell images taken in the same field of view, the server 101 performs grayscale conversion on the N cell images to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2; the server 101 denoises each grayscale image g to obtain N grayscale images g2; the server 101 subtracts the grayscale image g from the corresponding grayscale image g2 pixel by pixel and takes the absolute value to obtain N edge images gd; the server 101 uses a fast guided filtering algorithm to convert the grayscale image g 2 is an input image, and the corresponding edge image gd is used as a guide image. The grayscale image g2 is smoothed while retaining the edge information to obtain N grayscale images g3; the server 101 compares the N grayscale images g3 pixel by pixel, and takes the maximum value of each pixel to obtain the image max; the server 101 subtracts the image max from each grayscale image g3 pixel by pixel, and obtains the area where the pixel points of each grayscale image g3 corresponding to the result is less than or equal to 0 as the candidate area; the server 101 merges the area corresponding to the corresponding candidate area in each cell image to obtain the fused image. Among them, the server 101 can be implemented by an independent server or a server cluster composed of multiple servers, and the mobile terminal 102 can be any image acquisition device.

[0045] The present application embodiment provides a cell image fusion method, such as Figure 2 As shown, the method comprises the following steps:

[0046] Step S210, performing grayscale conversion on N cell images captured in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2;

[0047] Specifically, the number N of cell images taken in the same field of view can be determined according to actual conditions. Figure 3 and Figure 4 Schematic diagram of two cell images taken in the same field of view.

[0048] Step S220, denoising each grayscale image g respectively to obtain N grayscale images g2;

[0049] Specifically, a suitable template M can be created, and each grayscale image g can be denoised by Gaussian filtering or mean filtering. The specific formula is as follows:

[0050]

[0051] Among them, (x, y) is the current pixel, m is the template, a is the width of the template, and b is the height of the template.

[0052] Step S230, subtract the grayscale image g from the corresponding grayscale image g2 pixel by pixel and take the absolute value to obtain N edge images gd.

[0053] Specifically, Figure 5 Schematic diagram of one edge graph gd among N edge graphs gd.

[0054] Step S240, using a fast guided filtering algorithm, taking the grayscale image g2 as an input image and the corresponding edge image gd as a guided image, smoothing the grayscale image g2 while retaining edge information, to obtain N grayscale images g3.

[0055] Specifically, when using the fast guided filtering algorithm, a suitable local window size can be set to smooth the grayscale image g2 while retaining edge information to obtain N grayscale images g3.

[0056] Step S250, compare the N grayscale images g3 pixel by pixel, take the maximum value for each pixel, and obtain the image max.

[0057] Specifically, N grayscale images g3 are compared pixel by pixel, and the maximum value is taken for each pixel to obtain the schematic diagram of image max as shown in Figure 6 shown.

[0058] Step S260, subtract the image max from each grayscale image g3 pixel by pixel, and obtain the area where the pixel points of each grayscale image g3 whose corresponding result is less than or equal to 0 are located as the candidate area.

[0059] Step S270: merge the regions in each cell image that correspond to the corresponding candidate region to obtain a fused image.

[0060] Specifically, Figure 7 Schematic diagram of the fused image.

[0061] As one implementation manner, the above step S270 merges the regions in each cell image corresponding to the corresponding candidate region to obtain a fused image, including the following steps:

[0062] Step S271, for each grayscale image g3, assign 255 to the pixels in the candidate area and assign 0 to the pixels in the remaining areas, so as to obtain a binary image mask corresponding to each grayscale image g3.

[0063] Step S272, blurring the binary image mask to obtain an image mask2 corresponding to each grayscale image g3.

[0064] Step S273, performing channel separation on each cell image, and obtaining a red channel image r, a green channel image g, and a blue channel image b corresponding to each cell image.

[0065] Step S274, multiply the red channel image r, the green channel image g and the blue channel image b by the corresponding image mask2 pixel by pixel to obtain the red channel image r1, the green channel image g1 and the blue channel image b1 corresponding to each cell image.

[0066] Step S275, adding all red channel images r1 pixel by pixel to obtain red channel image r2, adding all green channel images g1 pixel by pixel to obtain green channel image g2, and adding all blue channel images b1 pixel by pixel to obtain blue channel image b2.

[0067] Step S276, merging the red channel image r2, the green channel image g2 and the blue channel image b2 to obtain a fused image.

[0068] Through the above steps S271 to S276, each channel of the red channel image, green channel image and blue channel image of the area corresponding to the corresponding candidate area in each cell image is multiplied by the corresponding ratio, and finally the corresponding channels of all cell images are added and the channels are merged to obtain an overall smooth and relatively clear fused image.

[0069] In the prior art, during the automated photographing of cell tissue slides, it is easy for the photographed cell images to not contain all cells in a clear state, thus affecting the efficiency of cell morphology inspection.

[0070] In order to solve the above problems, the present application provides a cell image fusion method, which performs grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2; denoises each grayscale image g to obtain N grayscale images g2; subtracts the grayscale image g from the corresponding grayscale image g2 pixel by pixel and takes the absolute value to obtain N edge images gd; uses a fast guided filtering algorithm to take the grayscale image g2 as the input image and the corresponding edge image gd as the guide image, and smoothes the grayscale image g2 while retaining the edge information to obtain N grayscale images g3; compares the N grayscale images g3 pixel by pixel, takes the maximum value of each pixel, and obtains the image max; subtracts the image max from each grayscale image g3 pixel by pixel, and obtains the area where the pixel points corresponding to the result of each grayscale image g3 are less than or equal to 0, as the candidate area; merges the areas corresponding to the corresponding candidate areas in each cell image to obtain the fused image. The present application extracts relatively clear areas of each image from N cell images taken in the same field of view, and merges all relatively clear areas of each image into the same image, thereby obtaining an image that contains the clearest areas of all cell images for subsequent cell morphology detection, thereby effectively improving the efficiency of cell morphology detection.

[0071] Figure 8 is a schematic diagram of a cell image fusion device according to an embodiment of the present invention. Figure 8 As shown, a cell image fusion device 30 is provided, the device includes a conversion module 31, a denoising module 32, an edge map module 33, a filtering module 34, a value module 35, an alternative module 36 and a merging module 37;

[0072] The conversion module 31 is used to perform grayscale conversion on N cell images captured in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2;

[0073] A denoising module 32, used for denoising each grayscale image g to obtain N grayscale images g2;

[0074] The edge map module 33 is used to subtract the grayscale map g from the corresponding grayscale map g2 pixel by pixel and take the absolute value to obtain N edge maps gd;

[0075] A filtering module 34 is used to use a fast guided filtering algorithm to take the grayscale image g2 as an input image and the corresponding edge image gd as a guide image, and to smooth the grayscale image g2 while retaining edge information, to obtain N grayscale images g3;

[0076] A value taking module 35 is used to compare the N grayscale images g3 pixel by pixel, take the maximum value of each pixel, and obtain an image max;

[0077] A candidate module 36 is used to subtract the image max from each grayscale image g3 pixel by pixel, and obtain the area where the pixel points corresponding to each grayscale image g3 are less than or equal to 0 as the candidate area;

[0078] The merging module 37 is used to merge the regions in each cell image that correspond to the corresponding candidate regions to obtain a fused image.

[0079] The above-mentioned cell image fusion device 30 performs grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2; denoises each grayscale image g to obtain N grayscale images g2; subtracts the grayscale image g from the corresponding grayscale image g2 pixel by pixel and takes the absolute value to obtain N edge images gd; uses a fast guided filtering algorithm to take the grayscale image g2 as the input image and the corresponding edge image gd as the guide image, and smoothes the grayscale image g2 while retaining the edge information to obtain N grayscale images g3; compares the N grayscale images g3 pixel by pixel, takes the maximum value of each pixel, and obtains the image max; subtracts the image max from each grayscale image g3 pixel by pixel, obtains the area where the pixel corresponding to each grayscale image g3 is less than or equal to 0, and uses it as the candidate area; merges the area corresponding to the corresponding candidate area in each cell image to obtain the fused image. The present application extracts relatively clear areas of each image from N cell images taken in the same field of view, and merges all relatively clear areas of each image into the same image, thereby obtaining an image that contains the clearest areas of all cell images for subsequent cell morphology detection, thereby effectively improving the efficiency of cell morphology detection.

[0080] In one embodiment, the merging module 37 is further used to assign 255 to the pixels in the candidate area and 0 to the pixels in the remaining areas for each grayscale image g3, so as to obtain a binary image mask corresponding to each grayscale image g3; blur the binary image mask to obtain an image mask2 corresponding to each grayscale image g3; perform channel separation on each cell image, and obtain a red channel image r, a green channel image g, and a blue channel image b corresponding to each cell image; multiply the red channel image r, the green channel image g, and the blue channel image b by the corresponding image mask2 pixel by pixel, respectively, to obtain a red channel image r1, a green channel image g1, and a blue channel image b1 corresponding to each cell image; add all the red channel images r1 pixel by pixel to obtain a red channel image r2, add all the green channel images g1 pixel by pixel to obtain a green channel image g2, and add all the blue channel images b1 pixel by pixel to obtain a blue channel image b2; perform channel merging on the red channel image r2, the green channel image g2, and the blue channel image b2 to obtain a fused image.

[0081] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. The above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0082] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. 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 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 a set of preset configuration information. The network 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, the above-mentioned cell image fusion method is implemented.

[0083] In one embodiment, a computer device is provided, which may be a terminal. The computer device includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. 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 and a computer program. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a cell image fusion method is implemented. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covered on the display screen, or a key, trackball, or touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0084] Those skilled in the art will understand that Fig. 9 The structure shown is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0085] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0086] Perform grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2;

[0087] De-noise each grayscale image g respectively to obtain N grayscale images g2;

[0088] Subtract the grayscale image g from the corresponding grayscale image g2 pixel by pixel and take the absolute value to obtain N edge images gd;

[0089] Use the fast guided filtering algorithm to take the grayscale image g2 as the input image and the corresponding edge image gd as the guide image, smooth the grayscale image g2 while retaining the edge information, and obtain N grayscale images g3;

[0090] Compare the N grayscale images g3 pixel by pixel, take the maximum value of each pixel, and get the image max;

[0091] Subtract the image max from each grayscale image g3 pixel by pixel, and obtain the area where the pixel points whose corresponding results of each grayscale image g3 are less than or equal to 0 are located as the candidate area;

[0092] The regions in each cell image corresponding to the corresponding candidate regions are merged to obtain a fused image.

[0093] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0094] For each grayscale image g3, assign 255 to the pixels in the candidate area and 0 to the pixels in the rest of the area, and obtain the binary image mask corresponding to each grayscale image g3;

[0095] Perform blur processing on the binary image mask to obtain the image mask2 corresponding to each grayscale image g3;

[0096] Each cell image is channel-separated, and each cell image corresponds to a red channel image r, a green channel image g, and a blue channel image b;

[0097] Multiply the red channel image r, the green channel image g, and the blue channel image b by the corresponding image mask2 pixel by pixel to obtain the red channel image r1, the green channel image g1, and the blue channel image b1 corresponding to each cell image;

[0098] Add all red channel images r1 pixel by pixel to obtain red channel image r2, add all green channel images g1 pixel by pixel to obtain green channel image g2, and add all blue channel images b1 pixel by pixel to obtain blue channel image b2;

[0099] The red channel image r2, the green channel image g2 and the blue channel image b2 are merged to obtain a fused image.

[0100] The above-mentioned storage medium performs grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each cell image; wherein N is an integer greater than or equal to 2; denoises each grayscale image g to obtain N grayscale images g2; subtracts the grayscale image g from the corresponding grayscale image g2 pixel by pixel and takes the absolute value to obtain N edge images gd; uses a fast guided filtering algorithm to take the grayscale image g2 as the input image and the corresponding edge image gd as the guide image, and smoothes the grayscale image g2 while retaining the edge information to obtain N grayscale images g3; compares the N grayscale images g3 pixel by pixel, takes the maximum value of each pixel, and obtains the image max; subtracts the image max from each grayscale image g3 pixel by pixel, obtains the area where the pixel corresponding to each grayscale image g3 is less than or equal to 0, and uses it as the candidate area; merges the area corresponding to the corresponding candidate area in each cell image to obtain a fused image. The present application extracts relatively clear areas of each image from N cell images taken in the same field of view, and merges all relatively clear areas of each image into the same image, thereby obtaining an image that contains the clearest areas of all cell images for subsequent cell morphology detection, thereby effectively improving the efficiency of cell morphology detection.

[0101] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. All other embodiments obtained by ordinary technicians in this field without creative work according to the embodiments provided in this application are within the protection scope of this application.

[0102] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0103] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0104] 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 patent protection. 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 scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A cell image fusion method, characterized in that: The method comprises the following steps: Performing grayscale conversion on N cell images captured in the same field of view to obtain a grayscale image g corresponding to each of the cell images; wherein N is an integer greater than or equal to 2; Denoising each of the grayscale images g respectively to obtain N grayscale images g2; Subtract the grayscale image g from the corresponding grayscale image g2 pixel by pixel and take the absolute value to obtain N edge images gd; Using a fast guided filtering algorithm, taking the grayscale image g2 as an input image and the corresponding edge image gd as a guide image, the grayscale image g2 is smoothed while retaining edge information to obtain N grayscale images g3; Compare the N grayscale images g3 pixel by pixel, take the maximum value of each pixel, and obtain the image max; Subtract the image max from each of the grayscale images g3 pixel by pixel, and obtain the area where the pixel points whose corresponding results of each of the grayscale images g3 are less than or equal to 0 are located as the candidate area; The regions in each of the cell images corresponding to the candidate regions are merged to obtain a fused image.

2. The image fusion method according to claim 1, characterized in that: The step of merging the regions in each of the cell images corresponding to the candidate regions to obtain a fused image comprises the following steps: For each of the grayscale images g3, assign a value of 255 to the pixels in the candidate area and a value of 0 to the pixels in the remaining areas, so as to obtain a binary image mask corresponding to each of the grayscale images g3; Performing fuzzy processing on the binary image mask to obtain an image mask2 corresponding to each grayscale image g3; Perform channel separation on each of the cell images, and obtain a red channel image r, a green channel image g, and a blue channel image b corresponding to each of the cell images; Multiply the red channel image r, the green channel image g and the blue channel image b by the corresponding image mask2 pixel by pixel to obtain a red channel image r1, a green channel image g1 and a blue channel image b1 corresponding to each of the cell images; Add all the red channel images r1 pixel by pixel to obtain a red channel image r2, add all the green channel images g1 pixel by pixel to obtain a green channel image g2, and add all the blue channel images b1 pixel by pixel to obtain a blue channel image b2; The red channel image r2, the green channel image g2 and the blue channel image b2 are channel-merged to obtain a fused image.

3. A cell image fusion device, characterized in that: The device includes a conversion module, a denoising module, an edge map module, a filtering module, a value taking module, an alternative module and a merging module; The conversion module is used to perform grayscale conversion on N cell images taken in the same field of view to obtain a grayscale image g corresponding to each of the cell images; wherein N is an integer greater than or equal to 2; The denoising module is used to denoise each of the grayscale images g respectively to obtain N grayscale images g2; The edge map module is used to subtract the grayscale map g from the corresponding grayscale map g2 pixel by pixel and take the absolute value to obtain N edge maps gd; The filtering module is used to use a fast guided filtering algorithm to take the grayscale image g2 as an input image and the corresponding edge image gd as a guide image, and to smooth the grayscale image g2 while retaining edge information to obtain N grayscale images g3; The value taking module is used to compare the N grayscale images g3 pixel by pixel, take the maximum value of each pixel, and obtain the image max; The candidate module is used to subtract the image max from each of the grayscale images g3 pixel by pixel, and obtain the area where the pixel points whose corresponding results of each of the grayscale images g3 are less than or equal to 0 are located as the candidate area; The merging module is used to merge the regions in each of the cell images corresponding to the candidate regions to obtain a fused image.

4. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to claim 1 or 2 are implemented.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to claim 1 or 2 are implemented.

Images