Fluorescent slide image acquisition method and device based on automatic focusing and automatic exposure

Abstract

The invention provides a fluorescent slide image acquisition method and device based on automatic focusing and automatic exposure, and the method comprises the following steps: obtaining an initial image of a fluorescent slide, and obtaining optimized light source brightness and optimized light source exposure time based on the initial image, adjusting light source parameters by optimizing light source brightness and light source exposure time to obtain an optimized light source; at least one fluorescent channel is arranged, a clear image in each fluorescent channel is obtained under an optimized light source, and a plurality of first fluorescent images are obtained by continuously shooting the fluorescent slide from top to bottom in a preset route interval in each fluorescent channel; and selecting the first fluorescence image with the highest definition as a clear image, and integrating to obtain a fluorescence slide image. According to the scheme, the light source brightness and the exposure time are fixed, and the wavelength of each channel is dynamically adjusted by setting the fluorescent channels, so that automatic focusing exposure is fully automatically performed to obtain a clear image, and the consistency of each channel is ensured.

Description

Technical Field

[0001] The present application relates to the field of microscopic analysis technology, and in particular to a method and device for acquiring fluorescent slide images based on auto-focus and auto-exposure. Background Art

[0002] Fluorescence slide imaging is of key significance in many fields such as life science research and medical diagnosis, and its technological development has attracted much attention. In traditional fluorescence slide observation, there are many challenges. First of all, fluorescent slides often involve multiple staining channels, each channel is used to mark different cell structures or biological molecules to obtain multi-dimensional information. However, the manual adjustment of focus and exposure process is extremely cumbersome and inefficient. The operator needs to set the focus and exposure parameters for each staining channel separately, which is not only time-consuming and labor-intensive, but also difficult to ensure the consistency of operations between different channels.

[0003] Secondly, the subjectivity of manual operation leads to poor imaging consistency. Different operators have different experiences and judgment standards. Even for the same fluorescent slide, the acquired images may have significant differences in clarity and brightness. This instability seriously affects the reliability of the results, making subsequent observation and analysis of the images complicated and difficult, especially when conducting quantitative analysis or comparative studies of multiple groups of samples, the errors are large.

[0004] Furthermore, the brightness difference between different staining channels is a thorny issue. Since the fluorescent dyes corresponding to each staining channel have different characteristics, the wavelengths and intensities of the absorbed and emitted light are different, resulting in large differences in brightness between different channels. This phenomenon directly leads to uneven colors in the composite image, making it difficult to accurately present the true state of cells or tissues, greatly affecting the image contrast effect, and hindering researchers from accurately identifying and judging subtle structures and lesion characteristics. In addition, in clinical diagnosis scenarios, unstable image quality has brought great troubles to the work of medical staff. Inaccurate or inconsistent images may lead to misdiagnosis or missed diagnosis, delaying the diagnosis and treatment of the disease.

[0005] In summary, there is an urgent need for a fluorescent slide imaging technology that can automatically focus and expose while ensuring stable image quality and good consistency in each channel. Summary of the invention

[0006] The embodiments of the present application provide a method and device for acquiring fluorescent slide images based on automatic focus and automatic exposure. By fixing the brightness of the light source and the exposure time, the wavelength of each channel is dynamically adjusted by setting the fluorescent channel, so that automatic focus and exposure are fully automatically performed to acquire a clear image, and the consistency of each channel is ensured.

[0007] In a first aspect, an embodiment of the present application provides a method for acquiring a fluorescent slide image based on auto-focus and auto-exposure, the method comprising:

[0008] Acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source;

[0009] At least one fluorescent channel is set, and a clear image in each fluorescent channel is obtained under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image;

[0010] The clear images corresponding to each fluorescence channel are integrated to obtain the fluorescence slide image.

[0011] In a second aspect, an embodiment of the present application provides a fluorescent slide image acquisition device based on auto-focus and auto-exposure, comprising:

[0012] An acquisition module is used to acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source;

[0013] A selection module is used to set at least one fluorescent channel and obtain a clear image in each fluorescent channel under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image;

[0014] The fusion module is used to integrate the clear images corresponding to each fluorescent channel to obtain the fluorescent slide image.

[0015] In a third aspect, an embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a fluorescent slide image acquisition method based on autofocus and autoexposure.

[0016] In a fourth aspect, an embodiment of the present application provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute a process, and the process includes a method for acquiring a fluorescent slide image based on autofocus and autoexposure.

[0017] The main contributions and innovations of the present invention are as follows:

[0018] The embodiment of the present application fixes the brightness of the light source and the exposure time of the light source, and uses a filter to dynamically obtain the excitation light of each channel, so that each channel can truly reflect the effective information in the slide; the embodiment of the present application uses an AI model to select the optimal light source parameters and clear images, reduce errors caused by human operation, and improve the consistency and reliability of experimental results; after fixing the brightness of the light source and the exposure time of the light source, the embodiment of the present application does not need to make a secondary adjustment to the light source, thereby ensuring the consistency of different staining channels and improving the texture and readability of the composite image.

[0019] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] 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:

[0021] Figure 1 is a flow chart of a method for acquiring a fluorescent slide image based on auto-focus and auto-exposure according to an embodiment of the present application;

[0022] Figure 2 is a schematic diagram of an initial image of a fluorescent glass slide according to an embodiment of the present application;

[0023] Figure 3 is a schematic diagram of a sample image according to an embodiment of the present application;

[0024] Figure 4 is a schematic diagram of a plurality of first fluorescent images taken by an objective lens moving from top to bottom within a route interval according to an embodiment of the present application;

[0025] Figure 5 is a schematic diagram of a marked first fluorescent image according to an embodiment of the present application;

[0026] Figure 6 is a structural block diagram of a fluorescent slide image acquisition device based on automatic focus and automatic exposure according to an embodiment of the present application;

[0027] Figure 7 It is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.

[0029] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.

[0030] Embodiment 1

[0031] The embodiment of the present application provides a method for acquiring a fluorescent slide image based on auto-focus and auto-exposure, which dynamically adjusts the wavelength of each channel by setting a fluorescent channel by fixing the brightness of the light source and the exposure time, thereby automatically performing auto-focus exposure to acquire a clear image and ensuring the consistency of each channel. Specifically, reference Figure 1 , the method comprising:

[0032] Acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source;

[0033] At least one fluorescent channel is set, and a clear image in each fluorescent channel is obtained under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image;

[0034] The clear images corresponding to each fluorescence channel are integrated to obtain the fluorescence slide image.

[0035] In some specific embodiments, the position information of the fluorescent glass slide is first obtained by pre-scanning with an objective lens, and then the fluorescent glass slide is photographed with default parameters to obtain an initial image of the fluorescent glass slide. The initial image of the fluorescent glass slide is as follows: Figure 2 shown.

[0036] Specifically, the objective lens used in this solution is a 2.5x objective lens.

[0037] In some embodiments, a pre-trained light source brightness and exposure time analysis model is used to analyze the initial image to obtain optimized light source brightness and optimized light source exposure time, wherein the light source brightness and exposure time analysis model is a CNN architecture.

[0038] Specifically, by determining the optimized light source brightness and the optimized light source exposure time, the brightness consistency of all subsequent different dyeing channels can be guaranteed, thereby improving the texture and readability of the composite image.

[0039] Furthermore, the light source brightness and exposure time analysis model is trained using images taken under different light source brightness and exposure time conditions as training samples, thereby ensuring that the training samples cover a wide range of scenes and lighting conditions and improving the activation ability of the model. The training method of the light source brightness and exposure time analysis model is as follows:

[0040] First, mark the light source brightness and exposure time of each training sample. The marking format is:

[0041] Image file path | light source brightness | exposure time

[0042] image1.jpg |300lux|50ms

[0043] image2.jpg |600lux|75ms

[0044] Then, a photometer is used to accurately measure the brightness of the light source in the scene, and a structured file is used to store all the information, including ISO, shutter speed, exposure time, scene light brightness, and all possible environmental variables. All sample images are then standardized. The standardization method includes: adjusting the size of the sample image to a specific size, using an interpolation method to process each sample image to ensure the quality of the sample image, converting the sample image to the HSV color space, and normalizing the pixel value of the sample image to between [0, 1].

[0045] The CNN architecture model is then used to extract features and train the sample images. When extracting features, the main features are the average brightness, standard deviation, color histogram, edge detection features, etc. of the sample images. The light source brightness and exposure time analysis model uses batch normalization and activation functions after each convolutional layer to improve the training effect. During training, the mean square error is used as the loss function to measure the square difference between the predicted value and the true value. All sample images are divided, following the principle of 70% for training, 15% for validation, and 15% for testing to ensure the representativeness of each subset. At the end of training, K-fold cross validation is used to further improve the robustness of the model and the evaluation accuracy.

[0046] For example, a schematic diagram of a sample image is shown as Figure 3 As shown, this scheme uses multiple fluorescence images with different brightness and exposure time as input into the model for training, so that the model can accurately capture the brightness and exposure time suitable for different images.

[0047] Specifically, the light source brightness and exposure time analysis model will first process the initial image into a 4D tensor consisting of batch size, image height, image width, and number of image channels, and then classify and analyze the 4D tensor to obtain the corresponding optimized light source brightness and optimized light source exposure time.

[0048] Specifically, this solution uses AI algorithms to intelligently analyze the brightness and exposure time of the light source, thereby reducing errors caused by human operation, improving the consistency and reliability of experimental results, and significantly improving image clarity and quality through precise autofocus and exposure adjustment, making it clearer to observe cell and tissue samples.

[0049] In some embodiments, a variety of different filters are provided, and the optimized light source is irradiated onto the fluorescent glass slide through the corresponding filters to form a fluorescent channel, and a clear image in each fluorescent channel is acquired by the camera.

[0050] Furthermore, each filter can only transmit light of the corresponding wavelength. Light of different wavelengths can excite the corresponding dyes in the fluorescent glass slide, and the camera can then obtain clear images corresponding to the different dyes.

[0051] Therefore, in practical applications, this scheme adjusts the filters used according to the different dyes used in the fluorescent slide to ensure that all fluorescent channels can completely cover all cells in the fluorescent slide. For example, when the fluorescent slide uses DAPI (4′,6-diamidino-2-phenylindole) dye, its excitation wavelength is 358nm, so a filter that can only transmit a wavelength of 358nm is set to form a fluorescent channel for observing the fluorescent slide. When the fluorescent slide uses FITC (fluorescein isothiocyanate) dye, its excitation wavelength is 494nm, so a filter that can only transmit a wavelength of 494nm is set to commemorate the fluorescent channel for observing the fluorescent slide.

[0052] Specifically, different filters are set to dynamically capture the excitation light of each channel, so that the clear image of each channel can truly reflect the effective information in the fluorescent slide.

[0053] In some specific embodiments, the maximum distance and the minimum distance between the objective lens and the fluorescent glass slide are set, the interval between the maximum distance and the minimum distance between the objective lens and the fluorescent glass slide is used as the route interval, the shooting time interval is set, the objective lens moves from top to bottom in the route interval, and continuously shoots at the shooting time interval to obtain multiple first fluorescent images. The schematic diagram of the multiple first fluorescent images shot by the objective lens moving from top to bottom in the route interval is as shown in FIG. Figure 4 As shown.

[0054] Specifically, this solution can greatly improve imaging efficiency and facilitate rapid processing of large-scale samples through automatic movement of the objective lens within the route interval and continuous image acquisition.

[0055] In some embodiments, a pre-trained region of interest determination model is first used to mark the region of interest in each first fluorescent image, and then a pre-trained image quality determination model is used to select the first fluorescent image with the highest clarity as the clear image.

[0056] Specifically, this solution uses a region of interest judgment model to mark the region of interest in each first fluorescent image, which can provide more accurate quantitative data for cell information image proportion analysis and support researchers' in-depth analysis of samples.

[0057] Furthermore, the region of interest judgment model used in this scheme is the network architecture of Faster R-CNN. The marked first fluorescent image is as follows Figure 5 As shown, the training method of the region of interest judgment model is:

[0058] First, collect multiple fluorescence images marked with regions of interest as training samples, and divide the training samples into training set, validation set and test set. First, use the training set to train the region of interest judgment model. When the loss function during training meets the set conditions, use the validation set to verify the region of interest judgment model. Finally, use the test set to determine whether the output of the region of interest judgment model meets the requirements, thereby completing the training of the region of interest judgment model.

[0059] Furthermore, the image quality judgment model first uses the Laplace operator to calculate the clarity index of the image, then uses a convolutional neural network to extract features of the clarity index to obtain clarity features, and finally uses a CNN structure to perform clarity scoring on the clarity features, and selects the first fluorescent image with the highest clarity score as the clear image.

[0060] Specifically, in addition to the Laplace operator, this solution can also use Gaussian filtering, Laplace transform or variance method to calculate the image clarity.

[0061] Furthermore, the training method of the image quality judgment model used in this solution is as follows:

[0062] A data set containing images of different clarity is obtained, and the images in the data set are normalized in terms of image size and pixel value to obtain training samples. The training samples are used to train the image quality judgment model. During the training process, the mean square error is used as the loss function to judge the training results of the model.

[0063] In some specific embodiments, the image with the highest score is visualized for user convenience, and a clarity score threshold is set for each first fluorescent image, so that some automatically identified clear images are randomly selected for manual inspection to confirm the validity of the model.

[0064] Specifically, this solution realizes the automation of focus and exposure processes and standardizes experimental operations, which helps to improve the repeatability of experimental results. It is of great significance in scientific research and clinical applications. The user-friendly automation system allows even beginners to get started quickly without long-term training. This solution can be combined with more AI technologies and image processing algorithms in the future to continuously improve the overall performance and scope of application.

[0065] Embodiment 2

[0066] Based on the same idea, refer to Figure 6 The present application also proposes a fluorescent slide image acquisition device based on auto-focus and auto-exposure, comprising:

[0067] An acquisition module is used to acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source;

[0068] A selection module is used to set at least one fluorescent channel and obtain a clear image in each fluorescent channel under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image;

[0069] The fusion module is used to integrate the clear images corresponding to each fluorescent channel to obtain the fluorescent slide image.

[0070] Embodiment 3

[0071] This embodiment also provides an electronic device, referring to Figure 7 , comprises a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to execute the steps in any of the above method embodiments.

[0072] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0073] Among them, the memory 404 may include a large capacity memory 404 for data or instructions. By way of example and not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 404 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 404 may be inside or outside the data processing device. In a specific embodiment, the memory 404 is a non-volatile memory. In a specific embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (Static Random-Access Memory, abbreviated as SRAM) or a dynamic random access memory (Dynamic Random Access Memory, abbreviated as DRAM), wherein the DRAM can be a fast page mode dynamic random access memory 404 (Fast Page Mode Dynamic Random Access Memory, abbreviated as FPMDRAM), an extended data output dynamic random access memory (Extended Date Out Dynamic Random Access Memory, abbreviated as EDODRAM), a synchronous dynamic random access memory (Synchronous Dynamic Random-Access Memory, abbreviated as SDRAM), etc.

[0074] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .

[0075] The processor 402 reads and executes the computer program instructions stored in the memory 404 to implement any one of the fluorescent slide image acquisition methods based on automatic focus and automatic exposure in the above embodiments.

[0076] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .

[0077] The transmission device 406 can be used to receive or send data via a network. The specific examples of the above-mentioned network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0078] The input / output device 408 is used to input or output information. In this embodiment, the input information may be an initial image, optimized elimination, etc., and the output information may be a fluorescent slide image, etc.

[0079] Optionally, in this embodiment, the processor 402 may be configured to perform the following steps through a computer program:

[0080] Acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source;

[0081] At least one fluorescent channel is set, and a clear image in each fluorescent channel is obtained under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image;

[0082] The clear images corresponding to each fluorescence channel are integrated to obtain the fluorescence slide image.

[0083] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0084] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software that may be executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.

[0085] Embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, at this point, it should be noted that, for example, Figure 7 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or storage blocks implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and data variants thereof, CDs, etc. Physical media are non-transitory media.

[0086] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for acquiring a fluorescent slide image based on auto-focus and auto-exposure, characterized in that: The following steps are involved: Acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source; At least one fluorescent channel is set, and a clear image in each fluorescent channel is obtained under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image; The clear images corresponding to each fluorescence channel are integrated to obtain the fluorescence slide image.

2. The method for acquiring fluorescent slide images based on automatic focus and automatic exposure according to claim 1, characterized in that: First, the position information of the fluorescent glass slide is obtained by pre-scanning with the objective lens, and then the fluorescent glass slide is photographed with default parameters to obtain the initial image of the fluorescent glass slide.

3. The method for acquiring fluorescent slide images based on automatic focus and automatic exposure according to claim 1, characterized in that: The initial image is analyzed using a pre-trained light source brightness and exposure time analysis model to obtain optimized light source brightness and optimized light source exposure time, wherein the light source brightness and exposure time analysis model is a CNN architecture.

4. The method for acquiring fluorescent slide images based on automatic focus and automatic exposure according to claim 1, characterized in that: A variety of different filters are set, and the optimized light source is irradiated onto the fluorescent glass slide through the corresponding filters to form a fluorescent channel, and the camera obtains a clear image in each fluorescent channel.

5. The method for acquiring fluorescent slide images based on automatic focus and automatic exposure according to claim 1, characterized in that: The maximum distance and the minimum distance between the objective lens and the fluorescent glass slide are set, the interval between the maximum distance and the minimum distance between the objective lens and the fluorescent glass slide is used as the route interval, the shooting time interval is set, the objective lens moves from top to bottom in the route interval, and continuously shoots at the shooting time interval to obtain multiple first fluorescent images.

6. The method for acquiring fluorescent slide images based on automatic focus and automatic exposure according to claim 1, characterized in that: First, the region of interest in each first fluorescent image is marked using a pre-trained region of interest judgment model, and then the pre-trained image quality judgment model is used to select the first fluorescent image with the highest clarity as a clear image.

7. The method for acquiring fluorescent slide images based on automatic focus and automatic exposure according to claim 6, characterized in that: The image quality judgment model first uses the Laplace operator to calculate the clarity index of the image, then uses a convolutional neural network to extract features of the clarity index to obtain clarity features, and finally uses a CNN structure to perform clarity scoring on the clarity features, and selects the first fluorescent image with the highest clarity score as the clear image.

8. A fluorescent slide image acquisition device based on auto-focus and auto-exposure, characterized in that: include: An acquisition module is used to acquire an initial image of the fluorescent glass slide, and acquire an optimized light source brightness and an optimized light source exposure time based on the initial image, so as to adjust the light source parameters by optimizing the light source brightness and the optimized light source exposure time to obtain an optimized light source; A selection module is used to set at least one fluorescent channel and obtain a clear image in each fluorescent channel under an optimized light source, wherein in each fluorescent channel, a fluorescent glass slide is continuously photographed from top to bottom in a preset route interval to obtain multiple first fluorescent images, and the first fluorescent image with the highest clarity is selected as the clear image; The fusion module is used to integrate the clear images corresponding to each fluorescence channel to obtain the fluorescence slide image.

9. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for acquiring a fluorescent slide image based on automatic focus and automatic exposure according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores a computer program, wherein the computer program includes a program code for controlling a process to execute a process, wherein the process includes a method for acquiring a fluorescent slide image based on automatic focus and automatic exposure according to any one of claims 1 to 7.

Images