Image flat field calibration method, device, equipment and storage medium

Abstract

Embodiments of the present application provide an image flat field calibration method, device, equipment and storage medium, and relate to the technical field of image processing. The method comprises the following steps: obtaining a channel image set corresponding to each channel under different channels by shooting a blank carrier by a target device; selecting a reference image corresponding to each channel from the channel image set corresponding to each channel; calculating a standard image corresponding to each channel according to the reference image of each channel; and performing flat field calibration on a to-be-processed image by using at least one standard image to obtain a calibration image. The whole process does not need to prepare an organization sample, the obtained flat field image can be used for the correction process of all immunofluorescence images of the same device, the time consumption of flat field calibration is reduced, and the processing efficiency of flat field calibration is improved. Meanwhile, the process of flat field calibration is optimized, so that the immunofluorescence image does not need to be subjected to organization background separation and morphological operation, and the influence of the separation result and noise on the flat field image is avoided.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to image flat field calibration methods, apparatus, devices and storage media. Background Technology

[0002] In biomedical research, immunofluorescence images are widely used for studying cells and tissues. However, due to the non-ideal imaging characteristics of microscope lenses, immunofluorescence images are often affected by flat-field distortion. To obtain accurate measurement and analysis results from the images, flat-field calibration is necessary.

[0003] In related techniques, a thresholding method is typically used to separate the sample region from the background region in an immunofluorescence image. Then, an image mask associated with the sample region is generated, and morphological operations are used to further remove the background region. Finally, an average image is calculated from the background-removed image. This method is used to calculate the average image for each of multiple samples, and the resulting average images are applied to a flat-field calibration sample set to determine which samples have the best average images. Finally, these average images are merged to form a flat-field image used to correct the entire sample group. However, this method requires multiple tissue samples and a corresponding flat-field calibration sample set, making the calibration process complex and time-consuming. Summary of the Invention

[0004] The main objective of this application is to propose an image flat field calibration method, apparatus, device, and storage medium to improve the calibration efficiency of flat field calibration.

[0005] To achieve the above objectives, a first aspect of this application proposes an image flat-field calibration method, comprising:

[0006] A set of channel images corresponding to different channels is obtained by capturing a blank slide using the target device. The set of channel images includes field-view images corresponding to multiple field-view angles. The blank slide does not include the sample area. A reference image corresponding to each channel is selected from the field-view images corresponding to the multiple field-view angles. A standard image corresponding to each channel is calculated based on the reference image of each channel. The image to be processed corresponding to the sample slice captured by the target device is obtained, and the image to be processed is flat-field calibrated using at least one standard image corresponding to a channel to obtain a calibration image.

[0007] In some embodiments of this disclosure, the imaging region of the target device includes a channel region and a background region, and the step of selecting a reference image corresponding to each channel from the field-view images corresponding to the plurality of field-view angles includes:

[0008] Based on the shooting angle of the field of view, the field of view that is aligned with the channel area is selected as the high-brightness field of view, and the brightness of the channel area is higher than the brightness of the background area;

[0009] Multiple field-view images corresponding to the bright field of view are selected from each of the channel image sets as the reference images for the corresponding channel.

[0010] In some embodiments of this disclosure, obtaining a set of channel images corresponding to different channels by capturing a blank wafer with a target device includes:

[0011] Acquire the field-of-view image of the blank slide in each channel at each field-of-view angle to obtain an initial image set;

[0012] Perform at least one shooting to obtain at least one initial image set corresponding to the number of shootings, and obtain the channel image set based on the initial image set.

[0013] In some embodiments of this disclosure, selecting a reference image corresponding to each channel from the set of channel images corresponding to each channel includes:

[0014] Select at least one field-of-view image corresponding to the highlighted field-of-view angle from each of the initial image sets;

[0015] The reference image for the corresponding channel is obtained from all selected field-of-view images in each initial image set.

[0016] In some embodiments of this disclosure, calculating the standard image corresponding to each channel based on the reference image of each channel includes:

[0017] Obtain the average image of the reference image corresponding to each channel;

[0018] A blur smoothing operation is performed based on the average image, the preset blur matrix, and the preset standard deviation to obtain the standard image corresponding to each channel.

[0019] In some embodiments of this disclosure, the step of performing flat-field calibration on the image to be processed using a standard image corresponding to at least one channel to obtain a calibration image includes:

[0020] Obtain the image to be processed corresponding to each of the channels in the image to be processed;

[0021] The standard image associated with the channel is used to perform flat-field calibration on the channel image to be processed, so as to obtain the calibration channel image corresponding to each channel;

[0022] The calibration image is obtained from all the calibration channel images.

[0023] In some embodiments of this disclosure, the step of performing flat-field calibration on the channel image to be processed using the standard image associated with the channel to obtain a calibration channel image corresponding to each channel includes:

[0024] Obtain the average pixel value of the standard image associated with the channel;

[0025] For each field of view, obtain the corresponding field of view image in the channel image to be processed, obtain the pixel value to be processed in the field of view image to be processed and the standard pixel value corresponding to the pixel value to be processed in the standard image;

[0026] The calibration parameter is obtained by the ratio of the average pixel value to the standard pixel value. The calibration parameter is multiplied by the pixel value to be processed to obtain the calibration field of view pixel value. The calibration field of view image corresponding to the field of view is obtained based on the calibration pixel value. The calibration channel image is obtained based on all the calibration field of view images.

[0027] To achieve the above objectives, a second aspect of this application provides an image flatness calibration apparatus, comprising:

[0028] Initial image acquisition module: used to capture blank slides with the target device to obtain channel image sets corresponding to different channels. The channel image sets include field angle images corresponding to multiple field angles. The blank slides do not include sample areas.

[0029] Reference image selection module: used to select a reference image corresponding to each channel from the field-view images corresponding to multiple field-view angles, wherein the field-view angle of the reference image satisfies a preset brightness condition;

[0030] Standard image generation module: used to calculate the standard image corresponding to each channel based on the reference image of each channel;

[0031] Flat field calibration module: used to acquire the image to be processed corresponding to the sample slice captured by the target device, and to perform flat field calibration on the image to be processed using the standard image corresponding to at least one channel to obtain a calibration image.

[0032] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0033] To achieve the above objectives, a fourth aspect of the present application provides a storage medium that stores a computer program, which, when executed by a processor, implements the method described in the first aspect.

[0034] The image flattening calibration method, apparatus, device, and storage medium proposed in this application involve capturing blank slides with a target device to obtain channel image sets corresponding to different channels. Each channel image set includes field-angle images corresponding to multiple field-angles, while the blank slide does not include the sample area. A reference image is selected from the channel image set corresponding to each channel. A standard image corresponding to each channel is calculated based on the reference image. An image to be processed corresponding to a sample slice captured by the target device is obtained, and flattening calibration is performed on the image to be processed using at least one standard image corresponding to a channel to obtain a calibrated image. This application embodiment obtains a standard image indicating the brightness information of a microlens using a blank slide, and performs flattening calibration based on the non-uniform illumination information contained in the brightness distribution of the standard image. No tissue sample preparation is required, and the obtained flattened image can be used for the calibration process of all immunofluorescence images from the same device, reducing the time consumption of flattening calibration and improving the processing efficiency. Simultaneously, the flattening calibration process is optimized, eliminating the need for tissue background separation and morphological operations on the immunofluorescence image, thus avoiding the influence of separation results and noise on the flattened image. Attached Figure Description

[0035] Figure 1 This is a flowchart of the image flat field calibration method provided in the embodiments of this application.

[0036] Figure 2 This is a flowchart illustrating how a target device captures blank wafers to obtain initial image sets corresponding to different channels, as provided in an embodiment of this application.

[0037] Figure 3 This is a flowchart illustrating the selection of a portion of the field of view image as a reference image based on the field of view, as provided in an embodiment of this application.

[0038] Figure 4 This is a schematic diagram of the brightness changes of the field-angle image of the high-brightness field of view and the background field of view provided in the embodiments of this application.

[0039] Figure 5 This is a flowchart illustrating the selection of multiple field-view images corresponding to the flow channel region as reference images, as provided in the embodiments of this application.

[0040] Figure 6 This is a schematic diagram showing the brightness changes of different channels' field of view images provided in the embodiments of this application.

[0041] Figure 7This is a flowchart illustrating how a standard image corresponding to a channel is obtained from the average image of a reference image, as provided in an embodiment of this application.

[0042] Figure 8 This is a schematic diagram of the brightness change curve of the field-of-view image provided in the embodiments of this application.

[0043] Figure 9 This is a flowchart illustrating how a standard image is used to perform flat-field calibration on the image to be processed to obtain a calibration image, as provided in an embodiment of this application.

[0044] Figure 10 This is a flowchart illustrating how a standard image associated with a channel is used to perform flat-field calibration on a channel image to be processed, thereby obtaining a calibrated channel image, according to an embodiment of this application.

[0045] Figure 11 This is a schematic diagram comparing the field-of-view image to be processed and the calibrated field-of-view image provided in an embodiment of this application.

[0046] Figure 12 This is a comparative schematic diagram of the channel image to be processed and the calibration channel image provided in the embodiments of this application.

[0047] Figure 13 This is a structural block diagram of an image flat field calibration device provided in another embodiment of this application.

[0048] Figure 14 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0050] It should be noted that although functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0052] In biomedical research, immunofluorescence images are widely used for studying cells and tissues. However, due to the non-ideal imaging characteristics of microscope lenses, immunofluorescence images are often affected by field-planing distortion. For example, the microscopic images obtained from pathological sections using current microscopic equipment are a type of immunofluorescence image. However, microscopic equipment cannot directly capture a complete microscopic image; instead, it captures images at different field angles and then stitches them together. Each field angle may have uneven illumination, leading to more pronounced uneven illumination in the stitched result. Therefore, to obtain accurate measurement and analysis results from the images, field-planing calibration is necessary.

[0053] Traditional flat-field calibration techniques typically employ a thresholding method to separate the sample region from the background region in the acquired immunofluorescence image. An image mask associated with the sample region is then generated, and morphological operations are used to further remove the background region. An average image is then calculated from the background-removed image. This process is repeated for multiple samples, and the resulting average images are applied to the flat-field calibration sample set to determine which samples have the best average images. Finally, these average images are merged to form the flat-field image used to calibrate the entire sample group. Additionally, a dark-field image is sometimes captured during the flat-field calibration process, and both the flat-field and dark-field images are used in the immunofluorescence image flat-field calibration process. These methods have several drawbacks. First, significant differences exist between samples, making sample and background region separation difficult. Significant changes in morphological operation parameters can lead to poor accuracy in the flat-field image. Second, the calculation of the average image from the sample region is susceptible to noise. Finally, the entire process requires multiple tissue samples and a flat-field calibration sample set, resulting in a complex calibration procedure and high calibration time.

[0054] Based on this, embodiments of this application provide an image flattening calibration method, apparatus, device, and storage medium. A standard image indicating the brightness information of a microlens is obtained using a blank slide, and flattening calibration is performed based on the non-uniform illumination information contained in the brightness distribution of the standard image. No tissue sample preparation is required, and the obtained flattening image can be used for the calibration process of all immunofluorescence images from the same device, reducing the time consumption of flattening calibration and improving its processing efficiency. Simultaneously, the flattening calibration process is optimized so that tissue background separation and morphological operations on the immunofluorescence image are unnecessary, avoiding the influence of separation results and noise on the flattening image.

[0055] This application provides an image flattening calibration method, apparatus, device, and storage medium, which are specifically described through the following embodiments. First, the image flattening calibration method in this application is described.

[0056] The image flattening calibration method provided in this application relates to the field of image processing technology. This method can be applied to a terminal, a server, or a computer program running on either the terminal or the server. For example, the computer program can be a native program or software module in an operating system; it can be a local application, i.e., a program that needs to be installed in the operating system to run, such as a client that supports image flattening calibration, i.e., a program that only needs to be downloaded to a browser environment to run; it can also be a small program that can be embedded in any APP. In short, the above-mentioned computer program can be any form of application, module, or plugin. The terminal communicates with the server via a network. The image flattening calibration method can be executed by the terminal or the server, or by the terminal and the server working together.

[0057] In some embodiments, the terminal may be an electronic device such as a smartphone, tablet, laptop, desktop computer, smartwatch, fluorescence microscope, or sequencer. The server may be a standalone server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks, and big data and artificial intelligence platforms; it may also be a service node in a blockchain system, where the service nodes form a peer-to-peer network. The terminal and server can connect via Bluetooth, Universal Serial Bus, or a network, and this embodiment does not impose any limitations on this connection.

[0058] The image flat field calibration method in the embodiments of this application is described below.

[0059] In one embodiment, the image flat-field calibration method of this application can be applied to the processing of tissue sample images, sequencing sample images, etc. For example, it can be used to correct immunofluorescence protein staining images of tissue samples. In the processing of tissue sample images, immunofluorescence staining and analysis are mainly performed using equipment such as an integrated immunofluorescence staining machine. By automating staining and fluorescence imaging on the same device, specific fluorescently labeled antibodies bind to proteins in the sample slices, and then the fluorescence signal is detected and analyzed using the imaging system of the corresponding instrument, thereby determining the expression and distribution of proteins in the tissue. Typically, such integrated immunofluorescence staining machines have high throughput, high sensitivity, and high resolution, enabling simultaneous processing of multiple tissue sample images and providing accurate and reliable detection results. Regarding the processing of sequencing sample images, it mainly covers the process of complementary pairing between nucleotide chains and free nucleotides, based on the characteristic that different free nucleotides emit light differently in different channels.

[0060] In one embodiment, reference is made to Figure 1 , Figure 1 This is an optional flowchart of the image flat-field calibration method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps 110 to 140. It is also understood that this embodiment... Figure 1 The order of steps 110 to 140 is not specifically limited. The order of steps can be adjusted or some steps can be reduced or added according to actual needs.

[0061] Step 110: Obtain the set of channel images corresponding to different channels by taking a blank film with the target device.

[0062] In one embodiment, the target device refers to a device capable of imaging sample sections, such as a fluorescence microscope or a sequencer. The target device performs four-channel fluorescence imaging of the sample section, illuminating the sample with light of a different wavelength in each channel to capture fluorescence signals from different staining sites. This allows for the acquisition of more comprehensive and multi-dimensional information, revealing the distribution, expression, and relationships of specific markers within the sample section. The DNA or RNA molecules in tissues contain four bases: adenine (A), thymine (T), cytosine (C), and guanine (G). Each base is visualized using a specific fluorescent dye. For example, different channels can be distinguished using four different wavelengths and corresponding receiving spectra. The principle is that different fluorescence bands capture the fluorescence emitted by different markers. Specifically, in the sequencing image, the wavelength range corresponding to A and T bases is 532 nm, while the wavelength range corresponding to C and G bases is 647 nm. Simultaneously, the receiving spectrum also has two corresponding bands. Based on this, the fluorescence signals can be separated into four channels—A, T, C, and G—through spectral splitting. These four channels correspond to the four channels: channel 1, channel 2, channel 3, and channel 4, respectively.

[0063] In one embodiment, a blank slide refers to a slide that does not contain the sample region. Samples typically include pathological tissue or nucleotide chains, which are placed on a slide to obtain a sample slide. During sequencing, the sample slide is analyzed. The blank slide in this embodiment can be considered a slide without the sample, or a blank sample slide. By imaging the blank slide through different channels, a set of channel images corresponding to each channel is obtained. Since the imaging is based on different field of view angles, each channel's set of channel images consists of field-angle images corresponding to multiple field of view angles. It is understood that the difference between the fluorescence image corresponding to the blank slide and the immunofluorescence image corresponding to the sample slide lies in the absence of sample region-related data on the blank slide.

[0064] Unlike related technologies that require acquiring dark-field images, which need to be captured under off or extremely low light conditions, increasing the number of times the light source is switched on and off, thus reducing the lifespan of the light source for fluorescence microscopy equipment. Furthermore, frequent switching between different lighting conditions can cause wear and tear on precision components such as camera sensors in the optical system, affecting their optical performance. Additionally, without strictly defined darkroom conditions, the obtained dark-field images may not achieve the expected performance, affecting the correction results. This application embodiment selects blank slides for imaging, eliminating the need for a dark-field environment setting; instead, imaging must be performed under normal lighting conditions. This allows for the capture of the illumination non-uniformity of the microscope light source and optical system during the imaging process, including light spots, shadows, or gradient effects. Since no additional dark-field image acquisition step is required, the entire image processing process of the image flattening calibration method in this application embodiment is simpler, and it also avoids the influence of the quality problems of the dark-field image itself on the correction results.

[0065] In one embodiment, to improve the accuracy of subsequent standard image selection, multiple rounds of shooting can be performed to acquire more image data. (Refer to...) Figure 2 , Figure 2 This is a flowchart illustrating how a target device captures a blank slide to obtain initial image sets corresponding to different channels, as provided in this application embodiment. The flowchart specifically includes the following steps:

[0066] Step 210: Obtain the field-of-view image of the blank slide in each channel at each field of view to obtain the initial image set.

[0067] In one embodiment, during a single shooting process, each channel of the blank wafer needs to be captured at each field of view, and the resulting field-of-view images are used as the initial image set. That is, one field of view corresponds to one field-of-view image. When shooting one channel, a field-of-view image is acquired from each field of view, and all the field-of-view images for that channel are aggregated to obtain the initial image set for that channel. For example, if there are a total of N field-of-views, and the current channel is the first channel, then the initial image set corresponding to the first channel during this shooting process contains N field-of-view images.

[0068] Step 220: Take at least one shot to obtain at least one initial image set corresponding to the number of shots, and obtain a channel image set based on the initial image set.

[0069] In one embodiment, multiple rounds of shooting can be performed, meaning the number of shots is greater than one. Each round yields an initial image set, and all initial image sets are then combined to obtain the total channel image set for that channel. For example, if the total number of shots is 5, then 5 rounds of shooting are performed on the blank slide. In each round, initial image sets corresponding to the four channels are obtained. For the first channel, five initial image sets are obtained, each containing N field-view images. The final channel image set for the blank slide corresponding to the first channel contains 5*N field-view images, with each field-view corresponding to 5 different field-view images.

[0070] Through the above process, a set of channel images corresponding to each channel of the blank wafer is obtained.

[0071] Step 120: Select the reference image corresponding to each channel from the field-view images corresponding to multiple field-view angles.

[0072] In one embodiment, the field of view of the reference image needs to meet a preset brightness condition. Figure 3 , Figure 3 This is a flowchart illustrating the selection of a portion of the field of view image as a reference image based on the field of view, provided in an embodiment of this application. The flowchart specifically includes the following steps:

[0073] Step 310: Select the field of view aligned with the flow channel area as the high-brightness field of view based on the shooting angle of the field of view.

[0074] In one embodiment, for a fluorescence microscopy device that captures immunofluorescence images of sample sections, the imaging region includes a flow channel region and a background region. The flow channel region refers to the path or channel through which liquid flows in the tissue sample, such as channels in cell culture media or microfluidic chips. The flow channel region is characterized by dynamic liquid flow within it; fluorescent dyes or labels may diffuse or accumulate in the flow channel, affecting the distribution and intensity of the fluorescence signal. The background region refers to the area surrounding the tissue sample, which typically does not contain structures or molecules of interest. In fluorescence imaging, the background region is an area without specific fluorescence signals. Therefore, the brightness of the flow channel region in the imaging result will be higher than that of the background region. In this case, the field of view in the target device can be distinguished according to its shooting position, with the field of view aligned with the flow channel region as the high-brightness field of view and the field of view aligned with the background region as the background field of view. Therefore, the preset brightness condition here refers to the selected field of view corresponding to the flow channel region, where the brightness of the flow channel region is higher than that of the background region.

[0075] Step 320: Select multiple field-view images corresponding to the highlight field of view from each channel image set as reference images for the corresponding channel.

[0076] In one embodiment, the field-of-view image can be distinguished based on the highlight field-of-view and the background field-of-view. (Refer to...) Figure 4 , Figure 4 This is a schematic diagram of the brightness changes of the field-angle image of the high-brightness field of view and the background field of view provided in the embodiments of this application. Figure 4 In the images obtained from the same pathological section using the same device, two bright field-of-view angles are selected, denoted as bright field-of-view angle G1 and bright field-of-view angle G2. Simultaneously, two background field-of-view angles are selected, denoted as background field-of-view angle B1 and background field-of-view angle B2. The diagrams illustrate the brightness variations in the same direction from different field-of-view angles. Unless otherwise explicitly illustrated in this embodiment, brightness is represented by grayscale values, resulting in brightness diagrams T1 (for bright field-of-view angle G1), T2 (for bright field-of-view angle G2), T3 (for background field-of-view angle B1), and T4 (for background field-of-view angle B2).

[0077] according to Figure 4 As shown in the diagram, firstly, the overall brightness of brightness maps T1 and T2 is higher than that of brightness maps T3 and T4. Secondly, the brightness distributions of brightness maps T1 and T2 are highly similar, as are the brightness distributions of brightness maps T3 and T4. Furthermore, brightness maps T3 and T4, as images corresponding to the background field of view, exhibit large curve fluctuation frequencies and significant noise. Finally, both the images corresponding to the bright and background field of view show a brightness distribution characteristic of being brighter in the center and darker around the edges.

[0078] Depend on Figure 4 The conclusion is that, regardless of the field of view, the image has a brightness distribution characteristic of being brighter in the center and darker around the edges. In addition, since the field of view image corresponding to the background field of view contains a lot of noise, this application embodiment selects multiple field of view images corresponding to the bright field of view as reference images.

[0079] In one embodiment, if the channel image set includes multiple initial image sets, then the reference image needs to be selected from each initial image set to ensure the breadth of data selection. (Refer to...) Figure 5 , Figure 5 This is a flowchart illustrating the selection of multiple field-view images corresponding to the flow channel region as reference images, provided in an embodiment of this application. The flowchart specifically includes the following steps:

[0080] Step 510: Select at least one field-of-view image corresponding to a highlight field-of-view angle from each initial image set.

[0081] Step 520: Obtain the reference image for the corresponding channel based on all selected field-of-view images in each initial image set.

[0082] In one embodiment, since each initial image set contains more than one bright field of view, it also includes more than one corresponding field of view image. To improve computational efficiency, at least one field of view image corresponding to a bright field of view is selected to participate in subsequent calculations. If multiple rounds of shooting are conducted, each round contains an initial image set; therefore, a portion of the field of view images corresponding to bright field of view are selected from each initial image set. A reference image is then obtained based on all selected field of view images.

[0083] For example, a total of 5 rounds of shooting are conducted, resulting in a total of 30 field-of-view images, of which 18 are high-brightness field-of-view images. For the first channel, there are 5 initial image sets, each containing 30 field-of-view images, including 18 images corresponding to high-brightness field-of-view images. Therefore, 10 images corresponding to high-brightness field-of-view images can be selected from each initial image set, resulting in a total of 50 field-of-view images as reference images. It is understood that the number of reference images selected in different initial image sets can be different or the same; this embodiment does not limit this.

[0084] Step 130: Calculate the standard image corresponding to each channel based on the reference image of each channel.

[0085] In one embodiment, reference is made to Figure 6 , Figure 6 This is a schematic diagram showing the brightness changes of different channels' field of view images provided in the embodiments of this application. Figure 6In this study, the same pathological slide was photographed twice using the same equipment. In each round, the field-of-view image corresponding to one high-brightness field-of-view angle of the first and second channels was selected, and the field-of-view images corresponding to one high-brightness field-of-view angle of each of the third and fourth channels were selected.

[0086] The brightness range of the two field-view images in the first channel is 4000 cd / m². 2 -6000cd / m 2 The brightness range of the two field-of-view images in the second channel is 10000 cd / m². 2 -15000cd / m 2 The brightness range of one field of view image in the third channel is 900 cd / m². 2 -1400cd / m 2 The brightness range of the fourth channel's field of view image is 350 cd / m². 2 -600cd / m 2 .from Figure 6 As can be seen, for the same channel, even in different shooting rounds, the brightness range and brightness distribution of its field of view image are basically the same. However, for different channels, the brightness range and brightness distribution of their field of view images are completely different.

[0087] Therefore, in this embodiment, for the same channel, reference images from different rounds can be averaged to obtain the standard image for that channel. Furthermore, for different channels, different standard images need to be generated separately. For any given channel, after obtaining the reference image, the standard image used for flat-field calibration can be calculated based on the reference image. (Refer to...) Figure 7 , Figure 7 This is a flowchart of obtaining the standard image corresponding to a channel from the average image of the reference image, provided in an embodiment of this application. The flowchart specifically includes the following steps:

[0088] Step 710: Obtain the average image of the reference image corresponding to each channel.

[0089] Step 720: Perform a blur smoothing operation based on the average image, the preset blur matrix, and the preset standard deviation to obtain the standard image corresponding to each channel.

[0090] In one embodiment, the average image of all reference images is first calculated, which can be obtained by averaging the pixel values ​​at each pixel location in the reference images. Next, the average image is smoothed by applying Gaussian blur. Specifically, in this embodiment, the Gaussian blur process involves selecting a Gaussian kernel to obtain a preset blur matrix. The size of the Gaussian kernel determines the degree of blur; a larger kernel results in a stronger blur effect, while a smaller kernel produces a slighter blur. Typically, the Gaussian kernel size is an odd-numbered matrix, such as 3x3, 5x5, or 7x7. Simultaneously, a preset standard deviation is selected to adjust the smoothness of the Gaussian filter. A larger preset standard deviation results in a smoother response from the Gaussian filter and better suppression of high-frequency noise in the average image. However, if the preset standard deviation is too large, it can lead to image blurring and loss of image detail. Therefore, this embodiment determines the size of the preset standard deviation based on actual conditions. For example, by pre-setting an image processing model, setting image samples, and predicting a suitable preset blur matrix and preset standard deviation.

[0091] After obtaining the preset blur matrix and preset standard deviation through the above process, they can be substituted into a Gaussian filter. For example, the Gaussian Blur function in the OpenCV library can perform Gaussian blur smoothing on the average image to obtain the corresponding standard image. In this way, the standard image corresponding to each channel can be obtained.

[0092] Step 140: Obtain the image to be processed corresponding to the sample slice captured by the target device, and perform flat field calibration on the image to be processed using the standard image corresponding to at least one channel to obtain the calibration image.

[0093] In one embodiment, for a certain sample slice, the image of the sample slice captured by the target device is acquired as the image to be processed. For the image to be processed, the standard image corresponding to each channel is used for illumination correction. This ensures that all fluorescence images captured by the target device, whether blank slides or sample slices, are analyzed under the same illumination conditions, thereby improving data consistency and increasing correction accuracy.

[0094] In one embodiment, reference is made to Figure 8 , Figure 8 This is a schematic diagram of the brightness change curve of the field-of-view image provided in the embodiments of this application. Figure 8 For four different sample slices, six rounds of shooting were performed. In each round, the field-of-view image corresponding to the same high-brightness field of view was selected from the first, second, third, and fourth channels. Therefore, in each round, each channel corresponds to four field-of-view images. The four field-of-view images corresponding to each channel in the same round were normalized, and their brightness variation curves from the upper left to the lower right corner were plotted. These brightness variation curves were then plotted on the same graph for brightness distribution comparison, resulting in... Figure 8 There are 6*4 comparison images in the middle.

[0095] from Figure 8 As can be seen, the brightness variation curves of different rounds within the same channel exhibit a generally consistent trend. Furthermore, the brightness variation curves of different sample slices within the same round of the same channel also largely overlap. This demonstrates that the uneven brightness distribution within a channel is consistent across different sample slices captured by the same target device. Therefore, for the same target device, after obtaining the standard image corresponding to each channel based on the blank slide, the standard image can be used to reflect the uneven illumination characteristics of the target device in the corresponding channel. This standard image can then be used to perform flat-field calibration on all images to be processed from the target device for the corresponding channel. In other words, this embodiment of the application combines the device itself to acquire and determine the standard image for each channel as the flat-field image, primarily used to correct the uneven illumination in other images, ensuring that each fluorescence microscopy image on the same device has consistent brightness and contrast across the entire field of view.

[0096] In one embodiment, reference is made to Figure 9 , Figure 9 This is a flowchart of a standard image used to perform flat-field calibration on the image to be processed to obtain a calibration image, provided in an embodiment of this application. The flowchart specifically includes the following steps:

[0097] Step 910: Obtain the image to be processed corresponding to each channel of the image to be processed.

[0098] Step 920: Use the standard image associated with the channel to perform flat field calibration on the image of the channel to be processed to obtain the calibration channel image corresponding to each channel.

[0099] Step 930: Obtain the calibration image based on all calibration channel images.

[0100] In one embodiment, the images of the image to be processed in different channels are first acquired. Then, a standard image associated with that channel is selected to perform flat-field calibration on the image of the channel to be processed, resulting in a calibration channel image corresponding to that channel. Flat-field calibration is performed on each channel in this manner to obtain a calibration channel image for each channel, which are then combined to obtain a calibration image.

[0101] For the flat-field calibration process of each channel, refer to Figure 10 , Figure 10 This is a flowchart illustrating how a standard image associated with channel correlation is used to perform flat-field calibration on an image of the channel to be processed, resulting in a calibrated channel image. The flowchart specifically includes the following steps:

[0102] Step 1010: Obtain the average pixel value of the standard image associated with the channel.

[0103] In one embodiment, for each pixel of the standard image, the corresponding standard pixel value F is obtained, and then the average value of all pixel values ​​is calculated to obtain the pixel average value F.mean. Here, the pixel value can be calculated using grayscale values ​​as an example.

[0104] Step 1020: For each field of view, obtain the corresponding field of view image in the image to be processed, obtain the pixel value to be processed in the image to be processed and the standard pixel value corresponding to the pixel value to be processed in the standard image.

[0105] In one embodiment, the channel image to be processed is composed of multiple field-of-view images corresponding to multiple field-of-view angles. Therefore, for each field-of-view angle, the pixel value of each pixel in its field-of-view image to be processed is obtained as the pixel value R to be processed.

[0106] Understandably, the standard image is calculated from the field-of-view image of the blank slide. Therefore, the standard image and the field-of-view channel image to be processed have the same image size, and the position of each pixel in the two images corresponds. After obtaining the pixel value R to be processed, the standard pixel value F can be obtained from the same position in the standard image based on the position of the pixel value to be processed.

[0107] Step 1030: Obtain the calibration parameters based on the ratio of the average pixel value to the standard pixel value. Multiply the calibration parameters and the pixel value to be processed to obtain the calibration field of view pixel value. Obtain the calibration field of view image corresponding to the field of view based on the calibration pixel value. Obtain the calibration channel image based on all calibration field of view images.

[0108] In one embodiment, the calibration parameters for the pixel value R to be processed are expressed as follows:

[0109]

[0110] Furthermore, the calibrated field of view pixel value C is expressed as:

[0111]

[0112] Since the standard pixel value F in the standard image satisfies the condition of being bright in the center, dark in the four corners, and free of impurities, according to the above formula, when the field of view image to be processed is corrected, the pixel values ​​of the pixels to be processed located in the four corners will be appropriately increased, while the pixel values ​​of the pixels to be processed located in the center will be appropriately decreased, making the final calibrated field of view image more uniform.

[0113] The calibration pixel value C for each pixel value R to be processed is calculated according to the above process, thus obtaining the calibration field-of-view image at that field of view. Then, the calibration channel image is obtained by stitching together the calibration field-of-view images corresponding to each field of view.

[0114] In one embodiment, reference is made to Figure 11 , Figure 11 This is a schematic diagram comparing the field-of-view image to be processed and the calibrated field-of-view image provided in an embodiment of this application. Figure 11 It can be seen that the center of the field-view image before flat field calibration is brighter and the edges are darker. The calibrated field-view image after flat field calibration has uniform brightness and better display effect.

[0115] In one embodiment, reference is made to Figure 12 , Figure 12 This is a comparative schematic diagram of the channel image to be processed and the calibration channel image provided in an embodiment of this application. Figure 12 As can be seen, the unprocessed channel image before flat-field calibration clearly shows stitching marks formed by splicing multiple unprocessed field-view images. Because the unprocessed field-view images are brighter in the center and darker around the edges, the spliced ​​unprocessed channel image shows quite obvious "grids". However, the calibration channel image obtained after flat-field calibration has less noticeable stitching marks because the calibration field-view image corresponding to each field-view is a uniformly bright image. The entire calibration channel image has more uniform color and better display effect.

[0116] This application embodiment uses the device itself to determine the flat-field image, which is used to eliminate illumination artifacts and correct uneven illumination in the image. All images captured by the same device in the corresponding channels can share a standard image as the flat-field image for correction. Therefore, no additional time is needed to calculate the flat-field image each time the image is processed, reducing time costs. Furthermore, calculating the flat-field image does not require preparing a lot of tissue sample-related data; only a set of blank slides needs to be captured, reducing operational complexity.

[0117] The technical solution provided in this application involves obtaining a set of channel images corresponding to different channels by using a target device to capture blank slides. The set of channel images includes field-angle images corresponding to multiple field-angles, and the blank slide does not include the sample area. Then, a portion of the field-angle images whose brightness meets preset conditions is selected as reference images. Next, a standard image corresponding to each channel is obtained based on the average image of the reference images. Finally, the image to be processed corresponding to the sample slice captured by the target device is obtained, and the standard image is used to perform flat-field calibration on the image to be processed to obtain a calibration image. This application embodiment obtains a standard image indicating the brightness information of the microlens using a blank slide, and performs flat-field calibration based on the non-uniform illumination information contained in the brightness distribution of the standard image. No tissue sample preparation is required, and the obtained flat-field image can be used for the calibration process of all immunofluorescence images from the same device, reducing the time consumption of flat-field calibration and improving the processing efficiency. Simultaneously, the flat-field calibration process is optimized, eliminating the need for tissue background separation and morphological operations on the immunofluorescence image, thus avoiding the influence of separation results and noise on the flat-field image.

[0118] This application also provides an image flatness calibration device that can implement the above-described image flatness calibration method, referring to... Figure 13 The device includes:

[0119] Initial image acquisition module 1310: used to capture blank slides with the target device to obtain channel image sets corresponding to different channels. The channel image sets include field angle images corresponding to multiple field angles. The blank slides do not include sample areas.

[0120] Reference image selection module 1320: used to select the reference image corresponding to each channel from the field-view images corresponding to multiple field-view angles.

[0121] Standard image generation module 1330: used to calculate the standard image corresponding to each channel based on the reference image of each channel.

[0122] Flat field calibration module 1340: used to acquire the image to be processed corresponding to the sample slice captured by the target device, and to perform flat field calibration on the image to be processed using the standard image corresponding to at least one channel to obtain a calibration image.

[0123] In some embodiments of this application, the imaging area of ​​the target device includes a flow channel region and a background region, and the reference image selection module 1320 is used for:

[0124] A portion of the field of view image is selected as a reference image based on the field of view angle, including:

[0125] Based on the shooting angle of the field of view, the field of view that is aligned with the flow channel area is selected as the high brightness field of view, and the brightness of the flow channel area is higher than the brightness of the background area;

[0126] Select the field-view image corresponding to the highlight field of view from each channel image set as the reference image for the corresponding channel.

[0127] In some embodiments of this application, the initial image acquisition module 1310 is used for:

[0128] Acquire multiple field-view images of the blank slide under each channel at each field-view angle to obtain an initial image set;

[0129] Perform at least one shooting to obtain at least one initial image set corresponding to the number of shootings, and obtain a channel image set based on the initial image set.

[0130] In some embodiments of this application, the reference image selection module 1320 is further configured to:

[0131] Select at least one field-of-view image corresponding to a highlight field-of-view angle from each initial image set;

[0132] The reference image for the corresponding channel is obtained from all selected field-of-view images in each initial image set.

[0133] In some embodiments of this application, the standard image generation module 1330 is used for:

[0134] Obtain the average image of the reference image corresponding to each channel;

[0135] A blur smoothing operation is performed based on the average image, a preset blur matrix, and a preset standard deviation to obtain the standard image corresponding to each channel.

[0136] In some embodiments of this application, the flat field calibration module 1340 is used for:

[0137] Obtain the image to be processed corresponding to each channel of the image to be processed;

[0138] The standard image associated with the channel is used to perform flat field calibration on the image of the channel to be processed, so as to obtain the calibration channel image corresponding to each channel.

[0139] The calibration image is obtained from all calibration channel images.

[0140] In some embodiments of this application, the flat field calibration module 1340 is further used for:

[0141] Obtain the average pixel value of the standard image associated with the channels;

[0142] For each field of view, obtain the corresponding field of view image in the channel image to be processed, obtain the pixel value to be processed in the field of view image to be processed, and the standard pixel value corresponding to the pixel value to be processed in the standard image.

[0143] The calibration parameters are obtained by comparing the average pixel value with the standard pixel value. The calibration parameters are multiplied by the pixel value to be processed to obtain the calibration field of view pixel value. The calibration field of view image corresponding to the calibration pixel value is obtained based on the calibration pixel value. The calibration channel image is obtained based on all calibration field of view images.

[0144] The specific implementation of the image flat field calibration device in this embodiment is basically the same as the specific implementation of the image flat field calibration method described above, and will not be repeated here.

[0145] This application also provides an electronic device, including:

[0146] At least one memory;

[0147] At least one processor;

[0148] At least one program;

[0149] The program is stored in a memory, and the processor executes the at least one program to implement the image flat-field calibration method described above in this application. The electronic device can be a laptop computer, desktop computer, workbench, personal digital assistant, server, blade server, mainframe computer, sequencer, gene sequencing system, large-scale population genomics one-stop technology platform, laboratory automation system, sample preparation equipment, dispensing equipment, library production equipment, pipetting equipment, magnetic bead detection equipment, nucleic acid purification equipment, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The sequencer is used to determine the sequence of the genetic material of a sample. The sequencer can function in various ways and based on various technologies, including sequencing using labeled or unlabeled nucleotides via primer extension, such as sequencing-while-ligating or pyrosequencing, for example, using the Sanger dideoxy method, nanopores, or any sequencing method in the art. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the disclosure described and / or claimed herein.

[0150] Please see Figure 14 , Figure 14 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes:

[0151] The processor 1401 can be implemented using a general-purpose central processing unit (CPU), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application.

[0152] The memory 1402 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 1402 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 1402 and is called and executed by the processor 1401 to execute the image flat calibration method of the embodiments of this application.

[0153] The input / output interface 1403 is used to implement information input and output;

[0154] Communication interface 1404 is used to enable communication and interaction between this device and other devices. Communication can be achieved via wired means (e.g., USB, Ethernet cable) or wireless means (e.g., mobile network, Wi-Fi, Bluetooth).

[0155] Bus 1405 transmits information between various components of the device (e.g., processor 1401, memory 1402, input / output interface 1403, and communication interface 1404);

[0156] The processor 1401, memory 1402, input / output interface 1403 and communication interface 1404 are connected to each other within the device via bus 1405.

[0157] This application embodiment also provides a storage medium that stores a computer program, which, when executed by a processor, implements the above-described image flat field calibration method.

[0158] Memory, as a non-transitory storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0159] The image flattening calibration method, apparatus, device, and storage medium proposed in this application obtain channel image sets corresponding to different channels by using a target device to capture blank slides. The channel image sets include multiple field-of-view images corresponding to different field-of-view angles, and the blank slides do not include the sample area. Then, a portion of the field-of-view images whose brightness meets preset conditions are selected as reference images. Next, a standard image corresponding to each channel is obtained based on the average image of the reference images. Finally, the image to be processed corresponding to the sample slice captured by the target device is obtained, and the standard image is used to perform flattening calibration on the image to be processed to obtain a calibrated image. This application embodiment obtains a standard image indicating the brightness information of the microlens using a blank slide, and performs flattening calibration based on the non-uniform illumination information contained in the brightness distribution of the standard image. No tissue sample preparation is required, and the obtained flattening image can be used for the calibration process of all immunofluorescence images from the same device, reducing the time consumption of flattening calibration and improving the processing efficiency. Simultaneously, the flattening calibration process is optimized so that tissue background separation and morphological operations on the immunofluorescence images are unnecessary, avoiding the influence of separation results and noise on the flattening image.

[0160] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0161] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0162] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0163] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0164] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0165] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0166] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0167] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0168] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0169] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0170] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. An image flat-field calibration method, characterized in that, include: By capturing blank slides with the target device, a set of channel images corresponding to different channels is obtained. The set of channel images includes field-view images corresponding to multiple field-view angles. The blank slides do not include sample areas. Select a reference image corresponding to each channel from the field-view images corresponding to multiple field-view angles; The standard image corresponding to each channel is calculated based on the reference image of each channel; The image to be processed corresponding to the sample slice captured by the target device is obtained, and the image to be processed is flat-field calibrated using a standard image corresponding to at least one channel to obtain a calibration image.

2. The image flat-field calibration method according to claim 1, characterized in that, The imaging area of ​​the target device includes a channel area and a background area. Selecting a reference image corresponding to each channel from the field-view images corresponding to multiple field-view angles includes: Based on the shooting angle of the field of view, the field of view that is aligned with the channel area is selected as the high-brightness field of view, and the brightness of the channel area is higher than the brightness of the background area; Multiple field-view images corresponding to the bright field of view are selected from each of the channel image sets as the reference images for the corresponding channel.

3. The image flatness calibration method according to claim 2, characterized in that, The process of obtaining a set of channel images corresponding to different channels by photographing a blank film using the target device includes: Acquire the field-of-view image of the blank slide in each channel at each field-of-view angle to obtain an initial image set; Perform at least one shooting to obtain at least one initial image set corresponding to the number of shootings, and obtain the channel image set based on the initial image set.

4. The image flatness calibration method according to claim 3, characterized in that, The step of selecting a reference image corresponding to each channel from the set of channel images corresponding to each channel includes: Select at least one field-of-view image corresponding to the highlighted field-of-view angle from each of the initial image sets; The reference image for the corresponding channel is obtained from all selected field-of-view images in each initial image set.

5. The image flatness calibration method according to claim 1, characterized in that, The step of calculating the standard image corresponding to each channel based on the reference image of each channel includes: Obtain the average image of the reference image corresponding to each channel; A blur smoothing operation is performed based on the average image, the preset blur matrix, and the preset standard deviation to obtain the standard image corresponding to each channel.

6. The image flatness calibration method according to claim 1, characterized in that, The step of performing flat-field calibration on the image to be processed using a standard image corresponding to at least one channel to obtain a calibration image includes: Obtain the image to be processed corresponding to each of the channels in the image to be processed; The standard image associated with the channel is used to perform flat-field calibration on the channel image to be processed, so as to obtain the calibration channel image corresponding to each channel; The calibration image is obtained from all the calibration channel images.

7. The image flat-field calibration method according to claim 6, characterized in that, The step of performing flat-field calibration on the channel image to be processed using the standard image associated with the channel to obtain a calibration channel image corresponding to each channel includes: Obtain the average pixel value of the standard image associated with the channel; For each field of view, obtain the corresponding field of view image in the channel image to be processed, obtain the pixel value to be processed in the field of view image to be processed and the standard pixel value corresponding to the pixel value to be processed in the standard image; The calibration parameter is obtained by the ratio of the average pixel value to the standard pixel value. The calibration parameter is multiplied by the pixel value to be processed to obtain the calibration field of view pixel value. The calibration field of view image corresponding to the field of view is obtained based on the calibration pixel value. The calibration channel image is obtained based on all the calibration field of view images.

8. An image flatness calibration device, characterized in that, include: Initial image acquisition module: used to capture blank slides with the target device to obtain channel image sets corresponding to different channels. The channel image sets include field angle images corresponding to multiple field angles. The blank slides do not include sample areas. Reference image selection module: used to select a reference image corresponding to each channel from the field-view images corresponding to multiple field-view angles; Standard image generation module: used to calculate the standard image corresponding to each channel based on the reference image of each channel; Flat field calibration module: used to acquire the image to be processed corresponding to the sample slice captured by the target device, and to perform flat field calibration on the image to be processed using the standard image corresponding to at least one channel to obtain a calibration image.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the image flat field calibration method according to any one of claims 1 to 7.

10. A storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the image flat field calibration method according to any one of claims 1 to 7.

Images