A karyotype recognition method, device and electronic device based on fluorescence photographs

Abstract

The present invention discloses a karyotype recognition method, device and electronic device based on fluorescence photographs. The method includes respectively obtaining each panoramic fluorescence image of a target sample at different exposure levels based on bracketed exposure; comparing each panoramic fluorescence image and screening out abnormal panoramic fluorescence images with overexposure or underexposure; identifying the fluorescence performance information of each cell in the remaining panoramic fluorescence images to generate a karyotype recognition result. The present invention realizes image comparison and recognition of a pathological sample after fluorescence staining by means of bracketed exposure, thereby screening out panoramic fluorescence images with overexposure caused by strong positivity, ensuring the accuracy of the fluorescence performance information finally obtained based on the panoramic fluorescence images, and further ensuring the accuracy of the finally generated karyotype recognition result.

Description

Technical Field

[0001] This application relates to the technical field of karyotype recognition. Specifically, it relates to a method, device, and electronic device for karyotype recognition based on fluorescence photographs. Background Art

[0002] In the medical practice of autoimmune diseases, in order to accurately diagnose diseases, it is necessary to qualitatively and quantitatively analyze autoantibodies in patients' blood and identify the karyotype of autoantibodies. Currently, immunofluorescence is commonly used in clinical practice for identification: that is, after the specific binding of HEP-2 cells (containing specific antigens), the test serum (containing specific antibodies), and the fluorescently labeled antibody, a fluorescent image is obtained by stimulating the fluorescent label with the corresponding excitation light, and then a fluorescence photograph is obtained using an automatic photographing system, and the relevant determination of autoantibodies is completed by interpreting the characteristics of the fluorescence photograph.

[0003] The characteristics of the fluorescence photograph are mainly observed by observing the state of HEP-2 cells: whether there is fluorescence in HEP-2 cells (for qualitative analysis) and the intensity of the fluorescence signal (for quantitative analysis, expressed as the serum dilution factor or titer, judged from the intensity of the fluorescence photograph), the manifestation form of the fluorescence signal on the cell nucleus (the manifestation forms in the fluorescence photograph are vacuolar type and uniform full-coverage type), and whether there is fluorescence in the chromosomes of mitotic cells (the manifestation form of positive staining in the fluorescence photograph is uniform full-coverage type, and negative chromosomes have no fluorescence signal) are the main factors for judging the type of autoantibodies.

[0004] However, the current automatic photographing system for fluorescence photographs has the following two problems:

[0005] First, the exposure parameter settings of the camera are single, resulting in detail errors in the fluorescence photograph, which affects the determination of antibody karyotype and titer. Due to the huge differences in the autoantibody titers of different clinical serum samples and the uneven fluorescence signal intensities, the fluorescence photographs taken under a single parameter have the situation of under-exposure or over-exposure, resulting in errors in the details of the photographed HEP-2 cells. For example, when the fluorescence signal shows strong positivity, the automatic photographing is over-exposed, resulting in false positivity of negative chromosomes in the cell mitotic phase in the fluorescence photograph, thus affecting the determination of the autoantibody karyotype type. At the same time, over-exposure also increases the overall brightness of the fluorescence photograph, resulting in misjudgment of the autoantibody titer.

[0006] Second, the automatic photographing system has no panoramic photographing mode, and key information is covered when photographing cells in the chromosome mitotic phase. The fluorescence state of chromosomes in mitotic cells is a necessary identification index for autoantibody karyotype. However, the current automatic photographing method only randomly selects three local parts of the prepared specimens for photographing, which cannot ensure that the photographed photos contain mitotic chromosome cells, thus affecting the determination of autoantibody karyotype.

[0007] The above problems result in errors between the karyotype determination results obtained by automatically photographing fluorescence photos and the actual situation. Summary of the Invention

[0008] To solve the above problems, embodiments of the present application provide a karyotype recognition method, device, and electronic device based on fluorescence photos.

[0009] In a first aspect, embodiments of the present application provide a karyotype recognition method based on fluorescence photos, the method including:

[0010] Obtaining respective panoramic fluorescence images of a target sample at different exposure levels based on bracketing exposure;

[0011] Comparing the respective panoramic fluorescence images, and screening out abnormal panoramic fluorescence images with overexposure or underexposure;

[0012] Identifying the fluorescence performance information of each cell in the remaining panoramic fluorescence images, and generating a karyotype recognition result.

[0013] Preferably, the obtaining respective panoramic fluorescence images of a target sample at different exposure levels based on bracketing exposure includes:

[0014] Determining an exposure adjustment parameter based on preset bracketing exposure information, and adjusting an initial exposure level according to the exposure adjustment parameter to obtain at least two exposure levels;

[0015] Respectively obtaining a panoramic fluorescence image of the target sample at each of the exposure levels.

[0016] Preferably, the obtaining a panoramic fluorescence image of the target sample includes:

[0017] Constructing a coordinate system based on the target sample, and generating a shooting route starting from the coordinate origin;

[0018] Controlling a camera to continuously collect and shoot images based on the shooting route, and stitching the respective shooting images to obtain a panoramic fluorescence image, the panoramic fluorescence image including all images of the target sample.

[0019] Preferably, the abnormal panoramic fluorescence images include a first abnormal panoramic fluorescence image and a second abnormal panoramic fluorescence image;

[0020] The comparing the respective panoramic fluorescence images, and screening out abnormal panoramic fluorescence images with overexposure or underexposure includes:

[0021] Determining a highlight area in each of the panoramic fluorescence images, the highlight area being an area composed of pixel points with a brightness value higher than a preset brightness value;

[0022] Compare each of the highlighted regions to determine an abnormal brightness region, where the abnormal brightness region is a brightness region with a matching ratio lower than a first preset ratio, and the matching ratio is the ratio of the presence of a matching region at the same position in all the other panoramic fluorescence images;

[0023] Determine the panoramic fluorescence image corresponding to the abnormal brightness region as the first abnormal panoramic fluorescence image, and screen out the first abnormal panoramic fluorescence image;

[0024] Determine the matching ratio of each of the highlighted regions in the remaining panoramic fluorescence images. When there is a matching ratio that is not a second preset ratio, determine the panoramic fluorescence image without the matching region corresponding to the matching ratio as the second abnormal panoramic fluorescence image, and screen out the second abnormal panoramic fluorescence image.

[0025] Preferably, the method of identifying the fluorescence performance information of each cell in the remaining panoramic fluorescence images to generate a karyotype recognition result includes:

[0026] Identify and divide each cell in the remaining panoramic fluorescence images based on a preset RGB value range, and obtain the fluorescence performance information of each cell, where the fluorescence performance information includes nuclear fluorescence performance information and chromosome fluorescence performance information;

[0027] Determine the first karyotype information corresponding to the cell based on the fluorescence performance information, and integrate each of the first karyotype information to generate a karyotype recognition result.

[0028] Preferably, the method further includes:

[0029] Determine target cells whose chromosome fluorescence performance information is characterized as a uniform full-coverage type or a no-fluorescence signal type;

[0030] Divide at least one recognition region in the panoramic fluorescence image based on the spatial distribution of each target cell, where the recognition region contains at least one of the target cells;

[0031] Enlarge the recognition region to make the size of the recognition region match that of the panoramic fluorescence image;

[0032] Determine the second karyotype information corresponding to each of the target cells in the recognition region, and compare the first karyotype information with the second karyotype information to generate verification result information.

[0033] Preferably, the method further includes:

[0034] Obtain a preset standard exposure adjustment parameter, and adjust the current exposure to the standard exposure based on the standard exposure adjustment parameter;

[0035] Obtain the titer judgment panoramic fluorescence image corresponding to the standard exposure, and identify the titer of the target sample based on the titer judgment panoramic fluorescence image.

[0036] In a second aspect, an embodiment of the present application provides a karyotype recognition device based on fluorescence photographs, and the device includes:

[0037] An acquisition module, configured to respectively acquire each panoramic fluorescence image of the target sample at different exposure levels based on bracketed exposure;

[0038] A comparison module, configured to compare each of the panoramic fluorescence images and screen out abnormal panoramic fluorescence images with overexposure or underexposure;

[0039] An identification module, configured to identify the fluorescence performance information of each cell in the remaining panoramic fluorescence images and generate a karyotype recognition result.

[0040] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of the method provided in the first aspect or any possible implementation manner of the first aspect are implemented.

[0041] In a fourth aspect, an embodiment of 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 method provided in the first aspect or any possible implementation manner of the first aspect is implemented.

[0042] The beneficial effects of the present invention are as follows: 1. By bracketed exposure, image comparison and recognition are performed on the fluorescently stained sample, so as to screen out the panoramic fluorescence images with overexposure caused by strong positivity, ensure the accuracy of the fluorescence performance information finally obtained based on the panoramic fluorescence image, and further ensure the accuracy of the finally generated karyotype recognition result.

[0043] 2. By panoramic shooting to obtain fluorescence images, it is ensured that all cells on the sample can be observed and recognized, further improving the accuracy of karyotype recognition.

[0044] 3. The titer of the target sample is determined by the standard exposure, avoiding the influence of the bracketed exposure method on the judgment result of the sample titer. Description of the Drawings

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. 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.

[0046] Figure 1 A flowchart of a karyotype recognition method based on fluorescence photographs provided by an embodiment of the present application;

[0047] Figure 2 A structural schematic diagram of a karyotype recognition device based on fluorescence photographs provided by an embodiment of the present application;

[0048] Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0049] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application.

[0050] In the following description, the terms "first" and "second" are only for the purpose of description and cannot be construed as indicating or implying relative importance. The following description provides multiple embodiments of the present application. Different embodiments can be replaced or combined, so the present application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then the present application should also be considered to include embodiments containing all other possible combinations of A, B, C, and D, although such embodiments may not be explicitly described in the following content.

[0051] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes can be made to the functions and arrangements of the described elements without departing from the scope of the content of the present application. Each example can appropriately omit, substitute, or add various processes or components. For example, the described method can be executed in a different order from the described order, and various steps can be added, omitted, or combined. In addition, the features described in some examples can be combined into other examples.

[0052] See Figure 1 , Figure 1 is a flowchart of a karyotype recognition method based on fluorescence photographs provided by an embodiment of the present application. In the embodiment of the present application, the method includes:

[0053] S101. Obtain respective panoramic fluorescence images of a target sample at different exposure levels based on surround exposure.

[0054] The execution subject of the present application can be a controller of a terminal connected to a camera that takes pictures of a sample.

[0055] In the embodiments of the present application, under normal circumstances, in the fluorescence image captured by the camera, positive cell nuclei will be stained and presented as bright green fluorescence, positive chromosomes will be presented as bright green high-intensity fluorescence, and the rest will be presented as black because they are hardly stained. When the cell nucleus is positive, its manifestation in the fluorescence photo is of the vacuolar type and the uniform full-coverage type. If the cell nucleus is strongly positive of the vacuolar type, it may cause overexposure of the camera, and then the cell nucleus with an elliptical ring shape and a small internal vacuole will also be presented as white high-intensity, being misjudged as a positive chromosome. In addition, if the exposure of the camera is initially set too low for this reason, the fluorescence difference between the chromosome and the cell nucleus may not be obvious, making it difficult to distinguish the cell nucleus type. Therefore, the controller will adjust the exposure by means of bracketing exposure, and respectively obtain panoramic fluorescence images of the target sample taken at different exposure levels, so as to identify the overexposed position through comparison and judgment.

[0056] In an implementable manner, step S101 includes:

[0057] Determine the exposure adjustment parameter based on the preset bracketing exposure information, and adjust the initial exposure according to the exposure adjustment parameter to obtain at least two exposure levels;

[0058] Respectively, at each of the exposure levels, obtain the panoramic fluorescence image of the target sample.

[0059] In the embodiments of the present application, bracketing exposure forms 3 or 5 photos with different exposure amounts in the way of the middle exposure value, the reduced exposure value, and the increased exposure value. The user will preset the bracketing exposure information in the controller, and the exposure adjustment parameter is stored in the bracketing exposure information, that is, at what exposure interval to adjust the exposure. The camera is set to the initial exposure in the default state, so the controller will adjust the initial exposure according to the exposure adjustment parameter, and then obtain multiple exposure levels, and then respectively obtain the panoramic fluorescence images of the target sample according to these exposure levels.

[0060] In an implementable manner, the obtaining of the panoramic fluorescence image of the target sample includes:

[0061] Construct a coordinate system based on the target sample, and generate a shooting route starting from the coordinate origin;

[0062] Control the camera to continuously collect and shoot images based on the shooting route, and splice the shooting images to obtain a panoramic fluorescence image, and the panoramic fluorescence image includes all images of the target sample.

[0063] In an embodiment of the present application, in order to ensure the accuracy of karyotype identification of the target sample, it is necessary to identify the fluorescence image corresponding to the entire target sample, rather than only randomly selecting local positions for identification. Therefore, the controller will construct a coordinate system according to the target sample, generate a shooting route in the coordinate system, and then generate a control instruction to control the camera to move according to the shooting route, and continuously collect the shooting images captured by the camera during the movement. Finally, by stitching the collected shooting images, a panoramic fluorescence image of the target sample can be obtained. And since the shooting route is constructed according to the coordinate system corresponding to the target sample, it is ensured that the collected shooting images cover all regions of the target sample.

[0064] S102. Compare the panoramic fluorescence images, and screen out abnormal panoramic fluorescence images with overexposure or underexposure.

[0065] In an embodiment of the present application, after the controller obtains each panoramic fluorescence image collected by the camera, by comparing the panoramic fluorescence images, it can determine abnormal panoramic fluorescence images with overexposed fluorescence or underexposure from the image recognition process of whether the white highlight positions in each panoramic fluorescence image are the same, and then screen them out to avoid errors in subsequent karyotype recognition.

[0066] In an implementable manner, the abnormal panoramic fluorescence images include a first abnormal panoramic fluorescence image and a second abnormal panoramic fluorescence image;

[0067] Step S102 includes:

[0068] Determine the high-brightness regions in each of the panoramic fluorescence images, where the high-brightness regions are regions composed of pixel points with brightness values higher than a preset brightness value;

[0069] Compare the high-brightness regions to determine an abnormal brightness region, where the abnormal brightness region is a brightness region with a matching ratio lower than a first preset ratio, and the matching ratio is the ratio of the existence of a matching region at the same position in all the other panoramic fluorescence images;

[0070] Determine the panoramic fluorescence image corresponding to the abnormal brightness region as the first abnormal panoramic fluorescence image, and screen out the first abnormal panoramic fluorescence image;

[0071] Determine the matching ratios of the high-brightness regions in the remaining panoramic fluorescence images. When there is a matching ratio that is not a second preset ratio, determine the panoramic fluorescence image without the matching region corresponding to the matching ratio as the second abnormal panoramic fluorescence image, and screen out the second abnormal panoramic fluorescence image.

[0072] In the embodiment of the present application, since the brightness represented by the positive chromosomes often far exceeds that of the positive cell nuclei, the controller first determines the high-brightness regions in the panoramic fluorescence image, and uses the high-brightness regions to represent the positive chromosome regions. For a certain high-brightness region, if this region is truly a positive chromosome, it will appear as bright green and highly bright regardless of the exposure level. However, if this region is an overexposed vacuolar cell nucleus, at a lower exposure level, its brightness value will not reach the preset brightness value, and thus the corresponding high-brightness region cannot be recognized in some panoramic fluorescence images. The controller will compare and identify each panoramic fluorescence image based on the above principle. As long as the matching ratio corresponding to a certain high-brightness region is lower than the first preset ratio (for example, twenty percent), it is considered that there is no bright green and high brightness at the same position in most of the remaining panoramic fluorescence images. The panoramic fluorescence image corresponding to this abnormal high-brightness region has an overexposure problem, and the controller will determine it as the first abnormal panoramic fluorescence image and screen it out.

[0073] In addition, there is also the situation of underexposure. Since the brightness value of the positions outside the cells in the panoramic fluorescence image is also relatively low, it is not possible to directly and automatically distinguish underexposed images well through the judgment of brightness values. Therefore, after screening out the overexposed images, the controller will confirm the matching ratio of each high-brightness region again. At this time, if there are no underexposed images, the matching ratio should be the second preset ratio (for example, 1). Therefore, when the matching ratio is not 1, the controller can directly determine which panoramic fluorescence images the matching regions covered by this matching ratio correspond to, and then determine the panoramic fluorescence images without the matching regions covered by this matching ratio as the second abnormal panoramic fluorescence images, that is, underexposed images, and screen them out, finally realizing the screening of overexposed and underexposed images.

[0074] S103. Identify the fluorescence performance information of each cell in the remaining panoramic fluorescence images, and generate a karyotype recognition result.

[0075] In the embodiment of the present application, after screening out the abnormal panoramic fluorescence images, the controller will identify the fluorescence performance information of each cell in the remaining panoramic fluorescence images considered to be normal, that is, confirm the category corresponding to the cell nucleus according to the fluorescence coverage rate in each cell, thereby judging the karyotype of the cell, and then generating a karyotype recognition result.

[0076] In an implementable manner, step S103 includes:

[0077] Based on a preset RGB value range, identify and divide each cell in the remaining panoramic fluorescence images, and obtain the fluorescence performance information of each cell. The fluorescence performance information includes nucleus fluorescence performance information and chromosome fluorescence performance information;

[0078] Determine the first karyotype information corresponding to the cell based on the fluorescence performance information, and integrate each piece of the first karyotype information to generate a karyotype recognition result.

[0079] In the embodiment of the present application, since the nucleus after fluorescence staining shows bright green fluorescence, the controller can identify the entire image according to the preset RGB value range, and then identify and divide each elliptical nucleus through the regional distribution of the bright green fluorescence, that is, divide each cell. After each cell is divided, the fluorescence performance information of each cell will be obtained, that is, determine the nucleus fluorescence performance information and chromosome fluorescence performance information according to whether the bright green fluorescence in the fluorescence region of the cell is fully covered, whether there is a white high-brightness region inside, etc., and combine the specific nucleus fluorescence performance information and chromosome fluorescence performance information to determine the first karyotype information corresponding to the cell. By integrating the first karyotype information corresponding to all cells, a karyotype recognition result can be generated.

[0080] In an implementable manner, the method further includes:

[0081] Determine target cells whose chromosome fluorescence performance information is characterized as uniformly fully covered type or no fluorescence signal type;

[0082] Based on the spatial distribution of each target cell, divide at least one recognition region in the panoramic fluorescence image, and the recognition region contains at least one of the target cells;

[0083] Enlarge the recognition region so that the size of the recognition region matches that of the panoramic fluorescence image;

[0084] Determine the second karyotype information corresponding to each target cell in the recognition region, and compare the first karyotype information with the second karyotype information to generate verification result information.

[0085] In the embodiment of the present application, since the recognition is based on the panoramic image in the foregoing process, the panoramic image may be large, making the relative size of each cell in the image small. It is possible that the vacuolar type is recognized as the fully covered type, and there may also be cases of incorrect chromosome recognition. Therefore, the controller will also mark the target cells according to the chromosome fluorescence performance information, divide several recognition regions in the panoramic fluorescence image based on the spatial distribution between the target cells, and enlarge the recognition regions, so as to re-identify and confirm the second core information for the enlarged recognition regions. By comparing the first karyotype information with the second karyotype information, the previously generated result can be verified to further judge the accuracy of the result.

[0086] Possibly, the dividing at least one recognition region in the panoramic fluorescence image based on the spatial distribution of each target cell, where the recognition region contains at least one of the target cells, includes:

[0087] Divide at least one recognition region in the panoramic fluorescence image, where the recognition region contains at least one of the target cells, the first distance between any two adjacent target cells is not greater than a first preset distance, and there is at least one second distance between a target cell in the recognition region and the region boundary that is not greater than a second preset distance.

[0088] In the embodiments of the present application, the sizes of the recognition regions can be different. They are divided according to the degree of closeness between the target cells, and adjacent and aggregated target cells are divided into the same recognition region to improve the verification efficiency.

[0089] In an implementable manner, the method further includes:

[0090] Obtain preset standard exposure adjustment parameters, and adjust the current exposure to the standard exposure based on the standard exposure adjustment parameters;

[0091] Obtain the titer judgment panoramic fluorescence image corresponding to the standard exposure, and identify the titer of the target sample based on the titer judgment panoramic fluorescence image.

[0092] In the embodiments of the present application, the identification process of the sample will also determine the titer of the sample, and the titer can specifically be judged by the brightness value. Therefore, different fluorescence photo brightnesses will reflect different sample titers. To avoid errors in the judgment results of the actual titer of the sample caused by the brightness between different exposure parameters, a unified standard exposure adjustment parameter will be preset, and the corresponding brightness will be used as the standard for titer judgment.

[0093] Next, in conjunction with the attached Figure 2 , a karyotype recognition device based on fluorescence photos provided by the embodiments of the present application will be introduced in detail. It should be noted that the karyotype recognition device based on fluorescence photos shown in the attached Figure 2 is used to execute the method of the embodiments of the present application. For the convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the embodiments shown in the present application Figure 1 . Figure 1 shown in the embodiment.

[0094] Please refer to Figure 2 , Figure 2 is a schematic structural diagram of a karyotype recognition device based on fluorescence photos provided by the embodiments of the present application. As shown in Figure 2 , the device includes:

[0095] An acquisition module 201, configured to respectively acquire each panoramic fluorescence image of the target sample at different exposure levels based on bracketed exposure;

[0096] The comparison module 202 is used to compare each of the panoramic fluorescence images and screen out abnormal panoramic fluorescence images with overexposure or underexposure.

[0097] The recognition module 203 is used to recognize the fluorescence performance information of each cell in the remaining panoramic fluorescence images and generate a karyotype recognition result.

[0098] In an implementable manner, the acquisition module 201 includes:

[0099] An adjustment unit is used to determine exposure adjustment parameters based on preset bracketing exposure information and adjust the initial exposure according to the exposure adjustment parameters to obtain at least two exposures.

[0100] An acquisition unit is used to acquire panoramic fluorescence images of the target sample at each of the exposures.

[0101] In an implementable manner, the acquisition unit includes:

[0102] A construction component is used to construct a coordinate system based on the target sample and generate a shooting route starting from the coordinate origin.

[0103] A control component is used to control the camera to continuously acquire shooting images based on the shooting route and splice the shooting images to obtain a panoramic fluorescence image, which includes all images of the target sample.

[0104] In an implementable manner, the comparison module 202 includes:

[0105] A determination unit is used to determine the high-light regions in each of the panoramic fluorescence images, where the high-light region is a region composed of pixel points with a brightness value higher than a preset brightness value.

[0106] A comparison unit is used to compare each of the high-light regions to determine an abnormal brightness region, where the abnormal brightness region is a brightness region with a matching ratio lower than a first preset ratio, and the matching ratio is the ratio of the existence of a matching region at the same position in all the other panoramic fluorescence images.

[0107] A first screening unit is used to determine the panoramic fluorescence image corresponding to the abnormal brightness region as the first abnormal panoramic fluorescence image and screen out the first abnormal panoramic fluorescence image.

[0108] A second screening unit is used to determine the matching ratio of each of the high-light regions in the remaining panoramic fluorescence images. When there is a matching ratio that is not a second preset ratio, the panoramic fluorescence image without the matching region corresponding to the matching ratio is determined as the second abnormal panoramic fluorescence image and screened out.

[0109] In an implementable manner, the recognition module 203 includes:

[0110] A recognition unit, configured to recognize each cell in the remaining panoramic fluorescence image based on a preset RGB value range, and obtain fluorescence performance information of each cell, where the fluorescence performance information includes nuclear fluorescence performance information and chromosome fluorescence performance information;

[0111] A generation unit, configured to determine first karyotype information corresponding to the cell based on the fluorescence performance information, integrate the first karyotype information of each cell, and generate a karyotype recognition result.

[0112] In an implementable manner, the device further includes:

[0113] A first determination module, configured to determine target cells whose chromosome fluorescence performance information is characterized as a uniformly covered type or a no-fluorescence signal type;

[0114] A division module, configured to divide at least one recognition region in the panoramic fluorescence image based on the spatial distribution of each target cell, where the recognition region includes at least one of the target cells;

[0115] An amplification module, configured to amplify the recognition region so that the size of the recognition region matches the panoramic fluorescence image;

[0116] A second determination module, configured to determine second karyotype information corresponding to each target cell in the recognition region, and compare the first karyotype information with the second karyotype information to generate verification result information.

[0117] In an implementable manner, the division module includes:

[0118] A division unit, configured to divide at least one recognition region in the panoramic fluorescence image, where the recognition region includes at least one of the target cells, the first distance between any two adjacent target cells is not greater than a first preset distance, and the second distance between at least one target cell in the recognition region and the region boundary is not greater than a second preset distance.

[0119] In an implementable manner, the device further includes:

[0120] An adjustment module, configured to obtain preset standard exposure adjustment parameters, and adjust the current exposure to the standard exposure based on the standard exposure adjustment parameters;

[0121] A titer recognition module, configured to obtain a titer judgment panoramic fluorescence image corresponding to the standard exposure, and recognize the titer of the target sample based on the titer judgment panoramic fluorescence image.

[0122] Those skilled in the art can clearly understand that the technical solutions of the embodiments of the present application can be realized by means of software and / or hardware. The "units" and "modules" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a Field-Programmable Gate Array (FPGA), an Integrated Circuit (IC), etc.

[0123] Each processing unit and / or module of the embodiments of the present application can be implemented by an analog circuit that implements the functions described in the embodiments of the present application, or can be implemented by software that executes the functions described in the embodiments of the present application.

[0124] See Figure 3 , which shows a schematic structural diagram of an electronic device involved in the embodiments of the present application. This electronic device can be used to implement Figure 1 the method in the shown embodiments. As Figure 3 shown, the electronic device 300 may include: at least one central processing unit 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0125] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0126] Among them, the user interface 303 may include a display screen (Display), a camera (Camera). Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0127] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0128] Among them, the central processing unit 301 may include one or more processing cores. The central processing unit 301 connects various parts within the entire electronic device 300 through various interfaces and circuits. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305, it performs various functions of the terminal 300 and processes data. Optionally, the central processing unit 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The central processing unit 301 may integrate a combination of one or several of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface, application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the central processing unit 301 and may be implemented separately by a single chip.

[0129] Among them, the memory 305 may include random access memory (RAM) and may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned central processing unit 301. As Figure 3 shown, the memory 305, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and program instructions.

[0130] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the central processing unit 301 can be used to call the karyotype recognition application program stored in the memory 305 and specifically perform the following operations:

[0131] Based on bracketed exposure, obtain respective panoramic fluorescence images of the target sample at different exposure levels;

[0132] Compare the respective panoramic fluorescence images, and screen out abnormal panoramic fluorescence images with overexposure or underexposure;

[0133] Identify the fluorescence performance information of each cell in the remaining panoramic fluorescence images, and generate a karyotype recognition result.

[0134] This application also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the steps of the above method are implemented. Among them, the computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical discs, DVDs, CD-ROMs, microdrives, and magneto-optical discs, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.

[0135] It should be noted that for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described action sequence, because according to this application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0136] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0137] In several embodiments provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces. The indirect couplings or communication connections of the devices or units can be electrical or other forms.

[0138] The unit described as a separation component may or may not be physically separated. The component shown as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0139] In addition, each functional unit in various embodiments of the present application can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned memory includes: USB flash drives, read-only memories (ROM), random access memories (RAM), mobile hard disks, magnetic disks or optical disks and other media that can store program codes.

[0141] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable memory, and the memory can include: flash drives, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks, etc.

[0142] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, all equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. After considering the specification and practicing the present disclosure, those skilled in the art will easily think of other embodiments of the present disclosure. The present application aims to cover any variations, uses or adaptations of the present disclosure, and these variations, uses or adaptations follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not described in the present disclosure. The specification and the embodiments are only regarded as exemplary, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A karyotype recognition method based on fluorescence photographs, characterized in that, The method includes: Obtaining respective panoramic fluorescence images of a target sample at different exposure levels based on bracketing exposure; Comparing the respective panoramic fluorescence images, and screening out abnormal panoramic fluorescence images with overexposure or underexposure; Identifying fluorescence performance information of each cell in the remaining panoramic fluorescence images, and generating a karyotype recognition result; Among them, the abnormal panoramic fluorescence images include a first abnormal panoramic fluorescence image and a second abnormal panoramic fluorescence image; The comparing the respective panoramic fluorescence images and screening out abnormal panoramic fluorescence images with overexposure or underexposure includes: Determining highlight regions in the respective panoramic fluorescence images, where the highlight regions are regions composed of pixel points with a brightness value higher than a preset brightness value; Comparing the respective highlight regions to determine abnormal brightness regions, where the abnormal brightness regions are brightness regions with a matching ratio lower than a first preset ratio, and the matching ratio is the ratio of the existence of a matching region at the same position in all the other panoramic fluorescence images; Determining the panoramic fluorescence image corresponding to the abnormal brightness region as the first abnormal panoramic fluorescence image, and screening out the first abnormal panoramic fluorescence image; Determining the matching ratio of each highlight region in the remaining respective panoramic fluorescence images, and when there is a matching ratio that is not a second preset ratio, determining the panoramic fluorescence image without the matching region corresponding to the matching ratio as the second abnormal panoramic fluorescence image, and screening out the second abnormal panoramic fluorescence image.

2. The method according to claim 1, wherein The obtaining respective panoramic fluorescence images of a target sample at different exposure levels based on bracketing exposure includes: Determining exposure adjustment parameters based on preset bracketing exposure information, and adjusting an initial exposure level according to the exposure adjustment parameters to obtain at least two exposure levels; Respectively obtaining panoramic fluorescence images of the target sample at each of the exposure levels.

3. The method according to claim 2, wherein The obtaining a panoramic fluorescence image of the target sample includes: Constructing a coordinate system based on the target sample, and generating a shooting route starting from the coordinate origin; Controlling a camera to continuously collect shooting images based on the shooting route, and stitching the respective shooting images to obtain a panoramic fluorescence image, where the panoramic fluorescence image includes all images of the target sample.

4. The method according to claim 1, wherein The identifying fluorescence performance information of each cell in the remaining panoramic fluorescence images and generating a karyotype recognition result includes: Identifying and dividing each cell in the remaining panoramic fluorescence images based on a preset RGB value range, and obtaining fluorescence performance information of each cell, where the fluorescence performance information includes nuclear fluorescence performance information and chromosome fluorescence performance information; Determining first karyotype information corresponding to the cell based on the fluorescence performance information, and integrating the respective first karyotype information to generate a karyotype recognition result.

5. The method according to claim 4, characterized in that, The method further includes: Determining target cells with chromosome fluorescence performance information characterized as uniformly fully covered type or no fluorescence signal type; Dividing at least one recognition region in the panoramic fluorescence image based on the spatial distribution of each target cell, where the recognition region includes at least one of the target cells; Magnifying the recognition region so that the size of the recognition region matches that of the panoramic fluorescence image; Determine the second karyotype information corresponding to each of the target cells in the identified area, and compare the first karyotype information with the second karyotype information to generate verification result information.

6. The method according to claim 1, characterized in that, The method further includes: Obtain a preset standard exposure adjustment parameter, and adjust the current exposure to the standard exposure based on the standard exposure adjustment parameter; Obtain the titer judgment panoramic fluorescence image corresponding to the standard exposure, and identify the titer of the target sample based on the titer judgment panoramic fluorescence image.

7. A karyotype recognition device based on fluorescence photographs, characterized in that, The device includes: An acquisition module, configured to respectively acquire each panoramic fluorescence image of the target sample at different exposure levels based on bracketed exposure; A comparison module, configured to compare each of the panoramic fluorescence images and screen out abnormal panoramic fluorescence images with overexposure or underexposure; An identification module, configured to identify the fluorescence performance information of each cell in the remaining panoramic fluorescence images to generate a karyotype identification result; Among them, the abnormal panoramic fluorescence image includes a first abnormal panoramic fluorescence image and a second abnormal panoramic fluorescence image; The comparison module includes: A determination unit, configured to determine the high-brightness area in each of the panoramic fluorescence images, where the high-brightness area is an area composed of pixel points with a brightness value higher than a preset brightness value; A comparison unit, configured to compare each of the high-brightness areas to determine an abnormal brightness area, where the abnormal brightness area is a brightness area with a matching ratio lower than a first preset ratio, and the matching ratio is the ratio of the existence of a matching area at the same position in all the other panoramic fluorescence images; A first screening unit, configured to determine the panoramic fluorescence image corresponding to the abnormal brightness area as the first abnormal panoramic fluorescence image and screen out the first abnormal panoramic fluorescence image; A second screening unit, configured to determine the matching ratio of each of the high-brightness areas in the remaining panoramic fluorescence images, and when there is a matching ratio that is not the second preset ratio, determine the panoramic fluorescence image without the matching area corresponding to the matching ratio as the second abnormal panoramic fluorescence image and screen out the second abnormal panoramic fluorescence image.

8. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1-6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1-6 are implemented.

Images